CN109568760A - Sleep environment adjusting method and system - Google Patents
Sleep environment adjusting method and system Download PDFInfo
- Publication number
- CN109568760A CN109568760A CN201710912360.2A CN201710912360A CN109568760A CN 109568760 A CN109568760 A CN 109568760A CN 201710912360 A CN201710912360 A CN 201710912360A CN 109568760 A CN109568760 A CN 109568760A
- Authority
- CN
- China
- Prior art keywords
- sleep
- model
- environment
- environmental parameter
- user
- 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.)
- Granted
Links
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
- 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
Abstract
The invention discloses a sleep environment adjusting method and system, which are used for improving the accuracy of sleep adjustment. The sleep environment adjusting method comprises the following steps: acquiring at least one physical sign parameter in a preset time period when a user sleeps, wherein the physical sign parameter at least comprises one or any combination of a bioelectricity signal characteristic parameter and a human body limb activity characteristic parameter; determining a personal sleep environment adjusting model matched with a user from the crowd sleep environment adjusting model; analyzing the obtained physical sign parameters through the determined personal sleep environment adjusting model, and determining at least one environmental parameter to be adjusted; and informing at least one household environment device in the sleeping environment of the user of the at least one environment parameter, so that the at least one household environment device operates according to the at least one environment parameter.
Description
Technical field
The present invention relates to assisting sleep technical field, in particular to a kind of sleep environment adjusting method and system.
Background technique
Sleep is the essential physiological activity of human body, and good sleep is to maintain a primary condition of health.
But due to operating pressure is big, daily life system is irregular etc., the sleep quality for resulting in most people is not good enough, therefore, needs
It to assist people to sleep by other means, people is helped to improve sleep quality.
Currently, mainly the sleep quality of people is improved by changing the environment of people's sleep, for example, passing through sleeping lamp
Illumination appropriate is provided to increase the generation of melatonin in body, to adjust sleep quality.Alternatively, suitable by providing
Alpha's wave frequency section sleeping music is incremented by since people carry out sleeping state in 8Hz to 13Hz with the gradient of 0.5Hz
Frequency range emits Alpha's wave frequency section sleeping music to adjust sleep.But since the difference of age bracket, difference of constitution etc. cause
Everyone enters sleep stage to the sensitivity difference of environment, improves the sleep quality of people by changing environment, for
Sleep quality may be improved for somebody, and instead may be reduction sleep quality for somebody, or even is influenced
To sleep.
As it can be seen that current sleeping method can not adapt to different users, this results in that different users can not be adapted to, and adjusts
That sleeps is accurately poor.
Summary of the invention
The embodiment of the present invention provides a kind of sleep environment adjusting method and system, for improving the accuracy for adjusting sleep.
In a first aspect, one embodiment of the invention provides a kind of sleep environment adjusting method, the sleep environment adjusting side
Method includes:
At least one physical sign parameters of user in the preset time period in sleep are obtained, the physical sign parameters include at least
One of bioelectrical signals characteristic parameter, human body limb active characteristics parameter or any combination;
The determining personal sleep environment to match with the user in model, which is adjusted, from crowd's sleep environment adjusts model;
Model is adjusted by determining personal sleep environment to analyze the physical sign parameters of acquisition, determination to be adjusted to
A few environmental parameter;
At least one described environmental parameter is notified at least one the domestic environment equipment being located in user's sleep environment,
So that at least one described domestic environment equipment is run according at least one described environmental parameter;
Wherein, it is to be carried out by deep learning network at least one environmental parameter that the personal sleep environment, which adjusts model,
The relational model of environmental parameter collection and physical sign parameters that the layer-by-layer training of supervised learning obtains;Crowd's sleep environment is adjusted
Model includes that the sleep environment of at least a kind of user adjusts model, and the sleep environment of every class user adjusts the corresponding sleep of model
Environment adjusts model.
Optionally, the determining personal sleep environment to match with the user in model is adjusted from crowd's sleep environment to adjust
Model, comprising:
Determine the user type of the user;
It is adjusted from the crowd's sleep environment pre-established and searches sleep environment tune corresponding with the user type in model
Save model;
The sleep environment of lookup is adjusted into model and is determined as the personal sleep environment to match with the user adjusting model.
Optionally, the method also includes:
Determine that crowd's sleep environment adjusts the sleep environment being correspondingly arranged in model with the user type and adjusts mould
Type;
Judge whether the personal sleep regulation model of the user is an advantage over the sleep environment adjusting model of the setting;
If so, it is that the personal sleep environment adjusts model that the sleep environment of the setting, which is adjusted model modification,;
Otherwise, then the sleep environment for retaining the setting adjusts model.
Optionally, the physical sign parameters of acquisition are analyzed by determining personal sleep environment adjusting model, is determined
Before at least one to be adjusted environmental parameter, further includes:
Determine that sleep quality scores according at least one physical sign parameters of acquisition;
Model is adjusted by determining personal sleep environment to analyze the physical sign parameters of acquisition, determination to be adjusted to
A few environmental parameter, comprising:
It adjusts model by determining personal sleep environment to analyze determining sleep quality, determination will be adjusted
At least one environmental parameter.
Optionally, determine that sleep quality scores according at least one physical sign parameters of acquisition, comprising:
According to value changing rule of at least one the described physical sign parameters in the preset time period, when will be described default
Between section be divided at least two sleep stages;Wherein, the preset time period is the sleep stage corresponding period of standard;
Respectively according to corresponding at least one sign ginseng of each sleep stage at least two sleep stage
The accounting of several values and each sleep stage in the preset time period calculates the user when described default
Between sleep quality scoring in section.
Optionally, it adjusts model by determining personal sleep environment to analyze the sleep quality of acquisition, really
Surely at least one to be adjusted environmental parameter, comprising:
It is pushed away, is obtained and the sleep matter by the way that sleep quality scoring of the personal sleep environment adjusting model to acquisition is counter
The corresponding environmental parameter collection of amount scoring;
The environmental parameter collection of acquisition is determined as at least one to be adjusted environmental parameter.
Optionally, by determining personal sleep environment adjust model to the sleep quality of acquisition score physical sign parameters into
Row is analyzed, before determination at least one to be adjusted environmental parameter, the method also includes:
For the user, establish at least one environmental parameter of environment where when the user is in sleep state with it is right
The functional relationship model between sleep quality scoring answered;Wherein, the input of the functional relationship model be it is described at least one
Environmental parameter exports as sleep quality scoring;
The functional relationship model is successively trained by least one preset sample environment parameter, until described
The value of sleep quality scoring reaches established standards, adjusts model to obtain the sleep environment of the user;
Wherein, during being trained each time to the functional relationship model, by the preceding sleep matter once exported
Amount scoring is as the training supervision factor training functional relationship model.
Optionally, the functional relationship model is carried out based on supervised learning by least one sample environment parameter
Successively training obtains the sleep environment and adjusts model, comprising:
Each time to the functional relationship model carry out supervised learning training during, by it is preceding once export sleep
Dormancy quality score is as the training supervision factor training functional relationship model;
At least one described environmental parameter and a quality of human sleeping scoring are established into incidence relation, obtain the sleep environment
Adjust model.
Optionally, the functional relationship model is being carried out based on supervised learning by least one sample environment parameter
Layer-by-layer training, obtain before the sleep environment adjusts model, the method also includes:
Calculate the related coefficient between each environmental parameter and the same environmental parameter;
The environmental parameter that the related coefficient is greater than preset threshold is removed, is dropped with adjusting model to the sleep environment
Dimension processing.
Optionally, the method also includes:
Determine whether the corresponding sleep quality scoring of at least one environmental parameter currently obtained is higher than last acquisition
The corresponding sleep quality scoring of at least one environmental parameter;
If so, replacing described last at least one environment obtained to join at least one environmental parameter currently obtained
Number becomes at least one optimal environmental parameter;
Otherwise, then retain described last at least one environmental parameter obtained.
Second aspect, one embodiment of the invention provide a kind of sleep environment regulating system, the system comprises:
Environmental parameter acquisition adjusts unit, sleep quality assessment unit, data processing unit and gateway;Wherein,
Environmental parameter acquisition adjusts unit and is used for: acquiring at least one environmental parameter, and by the environmental parameter of acquisition
It is sent to the gateway;
The sleep quality assessment unit is used for: at least one sign of acquisition user in the preset time period in sleep
At least one described physical sign parameters are sent to the gateway by parameter;Wherein, the physical sign parameters include at least bioelectrical signals
One of characteristic parameter, human body limb active characteristics parameter or any combination;
The gateway is used for: received at least one environmental parameter is sent to at least one described physical sign parameters
The data processing unit;
The data processing unit is used for: at least one the described physical sign parameters for the user that the gateway is sent are received, and
The determining personal sleep environment to match with the user in model is adjusted from crowd's sleep environment and adjusts model, by determining
Personal sleep environment adjusts model and analyzes the physical sign parameters of acquisition, determination at least one to be adjusted environmental parameter, and
At least one to be adjusted environmental parameter is notified at least one the domestic environment equipment being located in user's sleep environment,
So that at least one described domestic environment equipment is run according at least one described environmental parameter;
Wherein, the data processing unit is also used to: in advance by deep learning network at least one environmental parameter into
The relational model of environmental parameter collection and sleep quality scoring that the layer-by-layer training of row supervised learning obtains;Crowd's sleep ring
Border adjusts the sleep environment that model includes at least a kind of user and adjusts model, and the sleep environment of every class user adjusts model corresponding one
A sleep environment adjusts model.
Optionally, the data processing unit is specifically used for:
At least one to be adjusted environmental parameter is notified to the gateway;
The gateway is also used to: received at least one to be adjusted environmental parameter is notified to positioned at user
At least one domestic environment equipment in sleep environment.
Optionally, the sleep quality assessment unit is specifically used for:
According to value changing rule of at least one the described physical sign parameters in the preset time period, when will be described default
Between section be divided at least two sleep stages;Wherein, the preset time period is the sleep stage corresponding period of standard;
Respectively according to corresponding at least one sign ginseng of each sleep stage at least two sleep stage
The accounting of several values and each sleep stage in the preset time period calculates the user when described default
Between sleep quality scoring in section.
Optionally, the data processing unit is in advance carrying out at least one environmental parameter by deep learning network
The relational model of environmental parameter collection and sleep quality scoring that the layer-by-layer training of supervised learning obtains, comprising:
For the user, establish at least one environmental parameter of environment where when the user is in sleep state with it is right
The functional relationship model between sleep quality scoring answered;Wherein, the input of the functional relationship model be it is described at least one
Environmental parameter exports as sleep quality scoring;
The functional relationship model is successively trained by least one preset sample environment parameter, until described
The value of sleep quality scoring reaches established standards, adjusts model to obtain the sleep environment of the user;
Wherein, during being trained each time to the functional relationship model, by the preceding sleep matter once exported
Amount scoring is as the training supervision factor training functional relationship model.
Optionally, the data processing unit is specifically used for:
Each time to the functional relationship model carry out supervised learning training during, by it is preceding once export sleep
Dormancy quality score is as the training supervision factor training functional relationship model;
At least one described environmental parameter and a quality of human sleeping scoring are established into incidence relation, obtain the sleep environment
Adjust model.
Optionally, the data processing unit by least one sample environment parameter to the functional relationship model into
Layer-by-layer training of the row based on supervised learning is also used to before obtaining the sleep environment adjusting model:
Calculate the related coefficient between each environmental parameter and the same environmental parameter;
The environmental parameter that the related coefficient is greater than preset threshold is removed, is dropped with adjusting model to the sleep environment
Dimension processing.
Optionally, the data processing unit is also used to:
Determine whether the corresponding sleep quality scoring of at least one environmental parameter currently obtained is higher than last acquisition
The corresponding sleep quality scoring of at least one environmental parameter;
If so, replacing described last at least one environment obtained to join at least one environmental parameter currently obtained
Number becomes at least one optimal environmental parameter;
Otherwise, then retain described last at least one environmental parameter obtained.
Optionally, the data processing unit is specifically used for:
Determine the user type of the user;
It is adjusted from the crowd's sleep environment pre-established and searches sleep environment tune corresponding with the user type in model
Save model;
The sleep environment of lookup is adjusted into model and is determined as the personal sleep environment to match with the user adjusting model.
Optionally, the data processing unit is also used to:
Determine that crowd's sleep environment adjusts the sleep environment being correspondingly arranged in model with the user type and adjusts mould
Type;
Judge whether the personal sleep regulation model of the user is an advantage over the sleep environment adjusting model of the setting;
If so, it is that the personal sleep environment adjusts model that the sleep environment of the setting, which is adjusted model modification,;
Otherwise, then the sleep environment for retaining the setting adjusts model.
The third aspect, one embodiment of the invention provide a kind of sleep environment adjustment equipment, and the sleep environment adjusting is set
It is standby to include:
At least one processor, and
The memory being connect at least one described processor;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, described at least one
The instruction that device is stored by executing the memory is managed, method described in first aspect and/or second aspect is executed.
Fourth aspect, one embodiment of the invention provide a kind of computer readable storage medium, comprising:
The computer-readable recording medium storage has computer instruction, when the computer instruction is run on computers
When, so that computer executes method described in first aspect and/or second aspect.
The sleep environment of the adjustable user of the embodiment of the present invention is adjusted with the sleep quality to user.To user's
When sleep environment is adjusted, determine that the sleep quality of user scores by characteristic parameter of the user in sleep, then by a
People's sleep environment adjust model, i.e., environmental parameter collection and sleep quality scoring relational model to the sleep quality of user score into
Row analysis, determines the environmental parameter of suitable user's sleep, is suitble to user's so as to build by control domestic environment equipment
Sleep environment, to adjust the sleep quality of user.Rather than just by general sleeping method, whether which is used in this way
Family is applicable in different users, can carry out the adjusting of sleep environment to the user for the personal characteristics of the user, improve
Adjust the accuracy of sleep.
Detailed description of the invention
Fig. 1 is the flow diagram of sleep environment adjusting method provided in an embodiment of the present invention;
Fig. 2 is the structural schematic diagram of sleep environment regulating system provided in an embodiment of the present invention
Fig. 3 is that EEG/ body provided in an embodiment of the present invention moves-normal age gold sleep stage data and curves schematic diagram;
Fig. 4 is that ECG/ body provided in an embodiment of the present invention moves-normal age gold sleep stage data and curves schematic diagram;
Fig. 5 establishes structural schematic diagram for sleep environment adjusting model;
Fig. 6 is a kind of structural schematic diagram of sleep environment regulating system provided in an embodiment of the present invention;
Fig. 7 is a kind of structural schematic diagram of sleep environment adjustment equipment provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
Current sleep environment adjusting method is changed by control domestic environment equipment, such as light irradiation apparatus, air-conditioning etc.
The sleep environment of user, to improve the sleep quality of user.But due to the difference of age bracket, difference of constitution etc. cause it is each
People enters that sleep stage is different to the sensitivity of environment, improved by current sleep environment adjusting method sleep matter
Amount, may improve sleep quality for somebody, and instead may be reduction sleep quality for somebody, very
It sleeps to influencing.
In consideration of it, determining the use according to the physical sign parameters of individual subscriber in the technical solution that the embodiment of the present invention proposes
The sleep quality at family scores, that is, the user sleep quality fine or not degree, then model is adjusted by personal sleep environment
At least one environmental parameter for the sleep for being suitble to the user is determined to score according to the sleep quality of the user, to pass through control
Domestic environment changes the sleep environment of the user.Rather than just by general sleeping method, whether which user in this way,
The adjusting that can carry out sleep environment to the user for the personal characteristics of the user, improves the accuracy for adjusting sleep.
Sleep environment adjusting method provided in an embodiment of the present invention can be applied to the electronic equipment with computing capability, example
Such as PC, server etc., for the type of electronic equipment, the embodiment of the present invention is with no restriction.Hereinafter, the present invention is implemented
The method for building up that the sleep environment adjusting method and sleep environment that example provides adjust model is uniformly applied to electronic equipment.
Domestic environment equipment at least may include in the intelligent appliances equipment such as air-conditioning, sleeping lamp, humidifier, air purifier
It is one or more.
Technical solution provided in an embodiment of the present invention is introduced below with reference to each attached drawing of specification.
Referring to Figure 1, the embodiment of the invention provides a kind of sleep environment adjusting method, which can be by sleeping
Dormancy environment adjustment system is realized.The process of the adjusting method is described as follows.
S101: obtaining at least one physical sign parameters of user in the preset time period in sleep, and physical sign parameters at least wrap
Include one of bioelectrical signals characteristic parameter, human body limb active characteristics parameter or any combination;
S102: the determining personal sleep environment to match with user in model is adjusted from crowd's sleep environment and adjusts model;
S103: model is adjusted by determining personal sleep environment, the physical sign parameters of acquisition is analyzed, determination will adjust
At least one environmental parameter of section;
S104: at least one environmental parameter is notified to set at least one domestic environment being located in user's sleep environment
It is standby, so that at least one domestic environment equipment is run according at least one described environmental parameter.
In the embodiment of the present invention, it is to be joined by deep learning network at least one environment that personal sleep environment, which adjusts model,
The relational model of environmental parameter collection and sleep quality scoring that the layer-by-layer training that number carries out supervised learning obtains.Crowd's sleep ring
Border adjusts the sleep environment that model includes at least a kind of user and adjusts model, and the sleep environment of every class user adjusts model corresponding one
A sleep environment adjusts model.
In the specific implementation process, Fig. 2 is referred to, Fig. 2 is sleep environment regulating system provided in an embodiment of the present invention
Structural schematic diagram.It is adjusted as shown in Fig. 2, the embodiment of the present invention can establish personal sleep environment by data processing unit in advance
Model.When establishing, in possible embodiment, data processing unit can be directed to user, when establishing user and being in sleep state
Functional relationship model between at least one environmental parameter of place environment and the scoring of corresponding sleep quality, wherein function closes
The input for being model is at least one environmental parameter, is exported as sleep quality scoring.Pass through at least one preset sample ring again
Border parameter successively trains functional relationship model, until the value of sleep quality scoring reaches established standards, to obtain use
The sleep environment at family adjusts model, wherein during being trained each time to functional relationship model, by preceding primary output
Sleep quality scoring as training supervision the factor training functional relationship model.
The embodiment of the present invention can acquire adjusting unit by environmental parameter as shown in Figure 2 and can acquire at user in advance
At least one environmental parameter of environment where when sleep state, such as temperature, humidity, intensity of illumination, noise, carbon dioxide are dense
Degree etc..Meanwhile the embodiment of the present invention can be used for by sleep quality assessment unit as shown in Figure 2: acquisition user is sleeping
When preset time period at least one physical sign parameters, and determine according at least one physical sign parameters of acquisition the sleep of user
Quality score, and the scoring of the sleep quality of at least user of a physical sign parameters and determination is sent to gateway.Gateway will receive
At least one physical sign parameters and determination user sleep quality scoring be transmitted to data processing unit.Wherein, physical sign parameters
Including at least one of bioelectrical signals characteristic parameter, human body limb active characteristics parameter or any combination.
At least one environmental parameter, at least one physical sign parameters and the determination that data processing unit can be sent according to gateway
The sleep quality scoring of user establish personal sleep environment and adjust model.
Lower mask body introduces how the embodiment of the present invention establishes personal sleep environment adjusting model.
In the embodiment of the present invention, sleep quality assessment unit may include sign acquisition module, such as wearable device.This
Inventive embodiments can acquire physical sign parameters when user's sleep by wearable device, such as lead hypnotic instrument by medical grade more
At least one bioelectrical signals for acquiring user, to obtain bioelectrical signals characteristic parameter.It is logical due to obtaining bioelectrical signals
It is often to lead hypnotic instrument by medical grade to realize, however, this just needs user to wear medical grade leads hypnotic instrument more, this can be to user more
Sleep interfere, in daily life without operability.For this purpose, the embodiment of the present invention can be wearable by health care grade
Sleep health care settings, such as it is worn on the Intelligent monitoring device at a certain position of body, such as Intelligent bracelet, smartwatch, intelligence
Can belt etc., using the body movement of 3-axis acceleration sensor measurement human body, for example, human body wrist movement, human body turn over it is dynamic
The method of work judges the sleep state of user.Usual user falls asleep under waking state, and the number of human action has bright
Significant difference is different, as long as therefore measure human action number difference size, can judge that user is awake or sleep shape
State.
But user, when being in sleep state, if sleep quality is bad, the body of user moves the number of movement
May be more, then judging that the sleep state of user is obviously less accurate only according to body movement.Therefore, in the embodiment of the present invention
Electronic equipment can be acquired including bioelectrical signals characteristic parameter and human body limb active characteristics parameter, by bioelectrical signals feature
Parameter and human body limb active characteristics parameter are associated analysis, further determine that the sleep state of user, and raising judges user
Dormant accuracy.
It can also include sleep point that sleep environment in the embodiment of the present invention, which adjusts the sleep quality assessment unit in model,
Analysing module can will acquire when sleep analysis module determines sleep quality scoring by least one characteristic parameter of user
At least one bioelectrical signals analyzed, to obtain at least one bioelectrical signals characteristic parameter.Such as will acquire
At least one EEG signals carry out Wavelet transformation and carry out wavelet transformation, Hilbert-Huang transform and singular value decomposition acquisition brain telecommunications
Number Wavelet Entropy, Hilbert Huang entropy and singular value first principal component, that is, the maximum value in singular spectrum is denoted as respectively
Feature vector P1、P2、P3, that is, characteristic parameter, thus obtain EEG signals of the user in sleep procedure time domain,
The various features parameter of frequency domain.
For another example the electrocardiosignal that will acquire extracts heart rate variability (heart rate variability, HRV) spy
Sign calculates the frequency spectrum entropy of very low frequencies (VLF), low frequency (LF) and high frequency (HF), and the FRACTAL DIMENSION of HRV is calculated by wavelet transformation
Degree, is denoted as feature vector P respectively4、P5、P6、P7, that is, characteristic parameter, thus obtain the heart of the user in sleep procedure
Electric signal is in time domain, the various features parameter of frequency domain.
For another example the electronic equipment in the embodiment of the present invention can pass through for human body limb active characteristics parameter
Acceleration transducer acquires three-dimensional acceleration, three-dimensional magnetic field, three-dimensional angular velocity etc., calculates three-dimensional acceleration, three-dimensional magnetic field, three-dimensional
The geometric mean of angular speed obtains human body limb active characteristics parameter.
After electronic equipment in the embodiment of the present invention obtains at least one physical sign parameters, if at least one to acquisition
Physical sign parameters are analyzed, it is clear that data volume be it is very big, which adds the burdens of electronic equipment.And at least one body
Sign parameter has certain plyability and correlation each other, therefore can use the data of acceleration transducer acquisition, and
Judge human motion type using median filtering, layering judge human body whether stationary motion, motive position, type, classification samples
Judge main feature, and then judge the features such as sleep such as turn over, push, getting up, to reduce calculation amount, mitigates the negative of electronic equipment
Load.
In possible embodiment, the condition for setting human motion can set three, wherein first condition can be
The range value of acceleration transducer synthesis, if range value is in preset threshold range, human body remains static, no
Then, human body is kept in motion.
Wherein, shown in the range value such as formula (1) of acceleration transducer synthesis:
The minimum value of preset threshold range can be thamin=8m/s, maximum value can be thamax=11m/s.
Second condition can be the local variance of acceleration transducer output, if local variance is lower than preset threshold
Value, then determine that the part of the human body is static, otherwise the body part movement of human body.
Wherein, shown in the local variance such as formula (2) of acceleration transducer synthesis:
In formula (2),The output average value that amplitude is synthesized for section acceleration transducer thus, can pass through public affairs
Formula (3) is illustrated:
In formula (2) and formula (3), s is half window number of samples, and usually defining its value is that 15 preset threshold values can be with
Are as follows: thσa=0.5m/s2。
Third condition can be angular-rate sensor output angular velocity synthesis amplitude, is lower than preset threshold value, then determines
It is static for the body part, otherwise determine that the body part moves.
Shown in the synthesis amplitude such as formula (4) of angular-rate sensor output:
Preset threshold value can be with are as follows: thwmax=50/s.
In above three condition, if first condition judges human body for stationary state, without second condition, Article 3
The judgement of part.If second condition is judged as the judgement that the body part is static, without third condition.
It, can when differentiating to judging that human body can be sampled calculating by formula (5) for the physical sign parameters of motion state
Can be bigger than normal due to wherein some status criteria difference, another status criteria difference is less than normal, just offsets, cause it is no abnormal, therefore
Random sampling verifying is carried out again.
In formula (5), a, b, c are respectively three directional acceleration/magnitude of angular velocities of user, and N is frequency in sampling.
After judging human body for the sampling of the physical sign parameters of motion state, sign characteristic parameter can be further extracted, it can be with
The principal component of physical sign parameters is analyzed, determines weight coefficient shared by each principal component respectively convenient for extracting emphasis feature.
The information content that each principal component includes have have few, can will include the more principal component of information content as emphasis feature, for
It can give up including the less principal component of information content.
It can be assumed for instance that original motion vector group is (F1, F2...Fm), m is less than 9.Then principal component and original vector group
Relationship can be illustrated by following formula:
Wherein, P is three directional accelerations, magnetic field, angular speed.Original vector F1It is most to contain information content, there is maximum
Variance, referred to as first principal component, F2,...,FmSuccessively successively decrease, referred to as Second principal component,, m principal component.Therefore it is main at
The process of analysis can regard determining weight coefficient a asik(i=1, m;K=1,9) process.
Then emphasis feature is extracted, n times observation is carried out to 9 three directional accelerations, magnetic field, angular speed variables first,
Obtained observation data can be used following matrix to indicate:
Wherein, PbhH-th of feature that (i.e. b-th of sample) is observed for the b times, to initial data Pn*9It is standardized place
It manages, the element in matrix subtracts the mean value of column, then divided by the standard deviation of column, so that the mean value of each variable is 0,
Variance is 1, obtains matrix Pn*9 *。
It then can be in the hope of the covariance matrix C of matrixn*9, Pn*9 *In can calculate association side between two variables between wantonly two column
Difference, so that it may obtain covariance matrix C9*9。
To covariance matrix C9*9Characteristic root decomposition is carried out, characteristic root matrix A is obtained9*9And feature vector U9*9。
C9*9=U9*9∧9*9U9*9′
Wherein feature vector U9*9As the reference axis of principal component, new vector space is constituted,
Wherein the size of characteristic root λ r (r=1,2,9) represents the information content that r-th of principal component contains.U9*9' be
U9*9Transposed matrix, can be in the hope of initial data Pn*9Projection in new vector space, i.e. principal component vector group Fn*9: Fn*9=
Pn*9U9*9.Then accumulation contribution rate is sought.The characteristic root size of each principal component represents its number for containing information content.Seek preceding k (k
=1,9) the accumulation contribution rate of a principal component, following formula:
Wherein λiIt is to find out ith feature root.
Preset accumulation contribution rate is selected, d principal component F before makingn*dPattern-recognition is carried out as new data.If accumulative
When contribution rate is to 50% or more, using than supreme people's court, the feature value vector of highest contribution rate is left, as fixed work samples
Collection, otherwise gives up.
For example, experiment is using 2000 sample above as a result, obtaining 9 principal components altogether.The tribute of first principal component F1
Offering the contribution rate that the contribution rate that rate is 58%, F2 is 33%, F3 is 22%, and the contribution rate of F4, F5, F6, F7, F8 in total is 5%
(8 principal component contributor rates come to 100%), the accumulation contribution rate of first three principal component (F1, F2, F3) is to 96%, also
It is to say that first three principal component has contained the information of principal component 96%, then these three principal components is selected to be divided as characteristic parameter
Analysis is pattern-recognition, and the dimension of eigenmatrix is reduced while guaranteeing information content, also just reduces calculation amount, mitigates electronics
The burden of equipment.
Similarly, at least one corresponding feature of brain wave (Electroencephalogram, EEG) signal of acquisition
Parameter and at least one HRV characteristic parameter can calculate the correlation of the two.In possible embodiment, electronic equipment can be with
It calculates the coherence factor of EEG signal delta frequency range and HRV parameter: power spectral density point is carried out to EEG signal and HRV signal
Analysis, and be normalized, then EEG signal delta frequency range and HRV signal LF, HF are calculated separately using coherent function
Coherence factor is denoted as feature vector P respectively8、P9。
Sleep analysis module can also calculate the coherence factor of EEG signal delta frequency range Yu HRV signal LF, HF: interception one
EEG, HRV signal of a sleep period 30s, is pre-processed, including becomes reference, down-sampled, denoising and interference, pretreatment
EEG signal afterwards is denoted as x, and HRV signal is denoted as y.The power spectral density and the two of EEG, HRV are calculated using Welch algorithm
Cross-spectral density is denoted as P respectively as shown in formula (6), formula (7), formula (8) respectivelyxx(f1)、Pyy(f2)、Pxy
(f1f2)。
In formula (6) and formula (7), U is normalization factor, and d2 (n) is Gauss function, which is is divided by L
Number of segment, the length that M is every section.Xi (n) is the i-th segment data of x (EEG signal), and yi (n) is the i-th segment data of y (HRV signal),
J is empty unit.
The coherence factor of EEG signal delta frequency range Yu HRV signal LF, HF is calculated separately by coherent function, such as by such as
Lower formula is realized:
Then the f of EEG signal is calculated1In delta frequency range [0.5,4], HRV signal f2In LF [0.05,0.15] range
Average coherence coefficient, as the coherence factor of EEG signal delta frequency range and HRV signal LF, then calculate f1In delta frequency range
[0.5,4], f2It is following public as the related coefficient of delta frequency range and HF in the average coherence coefficient of HF [0.15,0.4] range
Shown in formula:
Wherein, n f1In [0.5,4], f2The Coh in [0.05,0.15] rangexy(f1f2) points, m f1[0.5,
4],f2The Coh in [0.15,0.4] rangexy(f1f2) points.
It is assumed that EEG signals x is f1 in frequency component, heart rate variability signals y is in the component amplitude that frequency component is at f2
The standardization mean value of product, value interval are [0,1], reflect the degree of correlation of 2 signals.Coherence spectrum shows closer to 1
2 signals are more related.Coherence factor is 1, show it is highly relevant between 2 signals, and a signal be another signal times
Number, coherence factor 0 show that 2 signals are completely irrelevant.The embodiment of the present invention can choose the high characteristic parameter of related coefficient
It determines that sleep quality scores, reduces calculation amount in this way, alleviate the burden of sleep analysis module.
Sleep analysis module in the embodiment of the present invention can for user personal characteristics to the sleep quality of user into
Row is adjusted.
Under normal conditions, the sleep state of people can be divided into the awakening phase, the NREM sleep phase (and be divided into sleep 1,2,
3,4 phase), the rapid-eye-movement sleep phase.The embodiment of the present invention can be by detecting the sleep state of user, and is worked as according to what is detected
Preceding sleep state determines the quality of the sleep quality of user, further to improve user according to the quality of sleep quality
Sleep quality.In the embodiment of the present invention, the fine or not degree of the sleep quality of user can be identified by sleep quality scoring.
Currently, standard of comparison current for the sleep stage of people is the normal age gold sleep stage obtained.Without the same year
Sleep state of the people of age section in section at the same time is deviated.Therefore, the data processing unit in the embodiment of the present invention
It can be with the Sleep architecture of ex ante analysis normal population, that is, sleep stage.In conjunction at least one environmental parameter, at least of acquisition
A kind of physical sign parameters and the scoring of the sleep quality of determination re-start division to sleep analysis.
Available 28000 experiment samples of data processing unit in possible embodiment, in the embodiment of the present invention
Data, and obtain percentage shared by sleep each stage and age correlations initial value is as shown in table 1.
Table 1
Sleep stage and age correlations are shown in table 1.S1, S2, S3, S4, S (3+4), SW, SR respectively represent sleep 1
Phase, 2 phases, 3 phases, 4 phases, lucid interval, rapid eye movement phase correspond to the standard percentage rate of age bracket.
Data processing unit in the embodiment of the present invention can be according to the physical sign parameters of at least one after screening, that is, drop
Dimension treated the value changing rule of at least one physical sign parameters within a preset period of time, preset time period is divided at least
Two sleep stages, such as it is divided into S1, S2, S3, S4, S (3+4), SW, SR.In possible embodiment, data processing unit
After extracting at least one physical sign parameters, SVM can be used, physical sign parameters are identified, carries out sleep mode automatically by stages.For example, choosing
Take 1000 groups of at least one physical sign parameters to be trained, and with sleep stage be output, by training respectively obtain based on EEG,
Then the sleep mode automatically of HRV and its coherence prediction model by stages carry out sleep mode automatically by stages, respectively obtain " EEG/ body is dynamic-
Normal age gold sleep stage " and " ECG/ body moves-normal age gold sleep stage ".Wherein, EEG/ body moves-normal year
Age gold sleep stage is as shown in figure 3, Fig. 3 is that EEG/ body moves-normal age gold sleep stage data and curves schematic diagram.
ECG/ body is dynamic-normal age gold sleep stage as shown in figure 4, Fig. 4 be ECG/ body it is dynamic-normal age gold sleep stage number
According to curve synoptic diagram.
After data processing unit carries out sleep mode automatically by stages, it can be slept respectively according to each at least two sleep stages
It sleeps the accounting of the value of at least one corresponding physical sign parameters and each sleep stage within a preset period of time by stages, meter
Calculate the sleep quality scoring of user within a preset period of time.Specific calculate can be realized according to formula (9).
In formula (9), S1i、S2i、S3i、S4i、S(3+4)i、SWi、SRiThe characteristic parameter used for user's i-th.Formula
(9) value for the X being calculated in is smaller, indicates that sleep deviation normal value is smaller, sleep quality is better.
Data processing unit in the embodiment of the present invention has determined the sleep quality scoring of user, so that it may know the user
Sleep quality it is whether preferable, with according to the sleep quality score the determination user's local environment to be adjusted at least one environment
Parameter, to inform at least one the domestic environment equipment being located in user's sleep environment, so that at least one domestic environment equipment
It is run according at least one environmental parameter, to reach the suitable environment of user's sleep, realizes the sleep quality for adjusting user.
Data processing unit in the embodiment of the present invention can adjust sleep of the model to acquisition by personal sleep environment
Quality score is analyzed, determination at least one to be adjusted environmental parameter.Wherein, it is to pass through that personal sleep environment, which adjusts model,
Deep learning network carries out the environmental parameter collection and sleep that the layer-by-layer training of supervised learning obtains at least one environmental parameter
The relational model of quality score.Deep learning network can run on data processing unit above-mentioned, be also possible to have calculating
On any electronic equipment of ability, based on the characteristic of deep learning network, deep learning network is in continuous training process, meeting
It is continuously updated the deep learning network model of itself.That is, in the embodiment of the present invention, by deep learning network to extremely
The layer-by-layer training that a few environmental parameter carries out supervised learning updates the process of deep learning network model, is by least
The process of one environmental parameter training deep learning network, the deep learning network model completed by least one environmental training
It is people's sleep environment adjusting model in the embodiment of the present invention.
Data processing unit can be directed to user, establish at least one environment of place environment when user is in sleep state
Functional relationship model between parameter and the scoring of corresponding sleep quality, wherein the input of functional relationship model is at least one
Environmental parameter exports as sleep quality scoring.Again by least one preset sample environment parameter to functional relationship model into
Row successively training, until the value of sleep quality scoring reaches established standards, to obtain the sleep environment adjusting model of user,
In, during being trained each time to functional relationship model, by the preceding sleep quality scoring once exported as training
Supervise factor training functional relationship model.
In the embodiment of the present invention, data processing unit can obtain at least one of place environment when user is in sleep state
A environmental parameter, such as temperature, humidity, intensity of illumination, noise, gas concentration lwevel etc., and sleeping according to aforementioned determining user
The method of dormancy quality score determines the sleep quality scoring of corresponding user, to establish place ring when user is in sleep state
Functional relationship model between at least one environmental parameter in border and the scoring of corresponding sleep quality, wherein functional relationship model
Input be at least one environmental parameter, export for sleep quality scoring, as shown in figure 5, Fig. 5 be the sleep environment adjust model
Structural schematic diagram.The input of input layer can be at least one environmental parameter in Fig. 5, for example, temperature, humidity, intensity of illumination,
Noise, gas concentration lwevel etc., output can be sleep quality scoring.
Since the sleep environment that at least one environmental parameter of environment where user is built at this time for a user may be used
It can not be the best sleep environment of user, therefore, at least one preset sample environment can be passed through in the embodiment of the present invention
Parameter successively trains functional relationship model, until the value of sleep quality scoring reaches established standards, to obtain user
Sleep environment adjust model, wherein during being trained each time to functional relationship model, once exported preceding
Sleep quality scoring is as training supervision factor training functional relationship model.In order to make it easy to understand, below with wherein primary training
The process of functional relationship model is illustrated:
At least one environmental parameter can be acquired first, some environmental parameters are deposited each other at least one environmental parameter
It is larger in relevance, for example temperature is in a certain range, humidity is in respective range, the sleep quality of possible corresponding user
It scores all higher, then the relevance of the two environmental parameters is bigger, therefore, a certain range of temperature can represent one
Determine the humidity in range.If all regarding at least one environmental parameter of acquisition as sample environment parameter, data processing
For the calculation amount of unit with regard to larger, arithmetic speed is just lower, reduces computational efficiency.
In consideration of it, after the embodiment of the present invention acquires at least one environmental parameter, each environmental parameter and same can be calculated
Related coefficient between one environmental parameter rejects the environmental parameter that related coefficient is greater than preset threshold, that is, will be to sleeping
The lesser environmental parameter of the weighing factor of dormancy quality score is rejected, and it is larger only to retain the weighing factor to score sleep quality
At least one environmental parameter as at least one preset sample environment parameter, to reduce the calculation amount of data processing unit,
Mitigate the burden of data processing unit.
Environment where when being then in sleep state to user by least one preset sample environment parameter is at least
Functional relationship model between one environmental parameter and the scoring of corresponding sleep quality carries out supervised learning and successively trains, each
Layer can all export sleep quality scoring.Each time to functional relationship model carry out supervised learning training during, will before
The sleep quality scoring once exported is as training supervision factor training functional relationship model, that is, by last environmental parameter
The model formed is inputted, i.e., the environmental parameter that history is most preferably slept compares, if current obtained sleep quality scoring is low
In the sleep quality scoring of last time output, then functional relationship model output is 0, it is otherwise 1.It, can be always in training
Training reaches established standards, such as 1 until the value that sleep quality scores, then it is assumed that at least one sample environment inputted at this time
It is the suitable environment parameter of user's sleep, then at least one sample environment parameter of input and a quality of human sleeping can be commented
Divide and establish incidence relation, obtains sleep environment and adjust model.
To be input to forward-propagating direction of the direction as signal of output, in the training process, each neuron of network, i.e., often
The weight and threshold values of one layer of input remain unchanged, each layer of neuron only under the influence of one layer of neuron output and input shape
State, if not obtaining desired output valve in output end, network is the back-propagation process for being transferred to error signal.Error signal
Successively passback carries out backpropagation by output end, adjusts model to correct sleep environment.In this communication process, network is each
The weight and threshold values of neuron are adjusted according to certain rules by error feedback.Two stage alternate cycles of training and amendment
It carries out, every training is completed once, to be modified with genetic algorithm, adjusts model to obtain preferably sleep environment.
After establishing personal sleep environment adjusting model in the embodiment of the present invention, it can be adjusted by personal sleep environment
Model analyzes the sleep quality of acquisition, with determination at least one to be adjusted environmental parameter.Since individual sleeps
Environment adjusts at least one ring that model is place environment when being in sleep state to initial user by sample environment parameter
Functional relationship model between border parameter and the scoring of corresponding sleep quality carries out what supervised learning successively training obtained, then
Personal sleep environment adjusts the corresponding relationship that model is substantially exactly environmental parameter collection and sleep quality scoring.Its input is environment
Parameter set, output are sleep quality scorings, and therefore, the data processing unit in the embodiment of the present invention can pass through individual's sleep ring
Border adjusting model is counter to the sleep quality scoring of acquisition to be pushed away, and environmental parameter collection corresponding with sleep quality scoring is obtained, will
The environmental parameter collection of acquisition is determined as at least one to be adjusted environmental parameter.
After data processing unit in the embodiment of the present invention has determined at least one to be adjusted environmental parameter, Ke Yitong
Gateway is crossed to notify at least one environmental parameter at least one the domestic environment equipment, such as sleeping being located in user's sleep environment
Lamp, air-conditioning or humidifier etc. are suitble to so that at least one domestic environment equipment is run according at least one environmental parameter with building
The suitable environment of user's sleep, to improve the sleep quality of user.Wherein, gateway can be understood as logical by near radio
News mode (WIFI, zigbee module, bluetooth module, 433 wireless communication modules, 315 wireless communication modules) is set with domestic environment
Standby Lian Yuke is communicated with domestic environment equipment.On the other hand it can be set by the modes such as 3G, 4G, GPRS, optical fiber and electronics
Standby connection is communicated.Intelligent gateway can be set-top box, Intelligent flat, intelligent sound box etc..In possible embodiment, gateway
After receiving at least one environmental parameter, the control module that can be sent in sleep environment acquisition adjusting unit passes through control
At least one domestic environment equipment in module user sleep environment.
It, can be true after data processing unit in the embodiment of the present invention has determined at least one to be adjusted environmental parameter
Whether the corresponding sleep quality scoring of at least one environmental parameter obtained before settled is higher than last at least one ring obtained
The corresponding sleep quality scoring of border parameter, if the corresponding sleep quality scoring of at least one environmental parameter currently obtained is higher than
The corresponding sleep quality scoring of at least one environmental parameter that last time obtains, then at least one environment that will can currently obtain
Parameter replaces last at least one environmental parameter obtained to become at least one optimal environmental parameter, otherwise, then retains
At least one environmental parameter once obtained adjusts model to optimize personal sleep environment.
Further, the embodiment of the present invention can establish crowd's sleep environment and adjust model, and crowd's sleep environment adjusts mould
Type may include the sleep environment model of N class user.N class can be understood as classifying according to the age, it is understood that for by
According to the classification etc. that personal sign feature carries out, the embodiment of the present invention to this with no restriction.In possible embodiment, the present invention is real
Applying example can be according to input value judgement by sample data input SVM classifier training with initial registration individual's N class sample data
Which kind of (1, N) is, if exceeding (1, N) range, then new registration classification N+1 class, then updates classifier again.Wherein, sample
Notebook data can be each physical sign parameters of at least one physical sign parameters of acquisition after screening and standard deviation taken to obtain.Data
Characteristic value is more, with the data instance that acceleration acquires, there is tri- direction character values of a, b, c, when it is compared with model library, leads to
It crosses formula (10) and standard deviation is taken to it,It is characterized crowd's mean value of value.N is sample size, first trains classifier, then
Sample is identified with classifier.
In this way, obtained crowd's sleep environment, which adjusts the sleep environment that model may include at least a kind of user, adjusts mould
Type, the sleep environment of every class user adjust the corresponding sleep environment of model and adjust model.The crowd's sleep environment being initially obtained
It may not be optimal model that the sleep environment for adjusting the every class user for including in model, which adjusts model,.Therefore the embodiment of the present invention
Obtain user personal sleep environment adjust model after, can determine the user type of the user, and with the user type pair
The sleep environment that should be arranged adjusts model.In possible embodiment, can from crowd's sleep environment adjust model in search with
The corresponding sleep environment of user type adjusts model.
After the embodiment of the present invention has determined that user type adjusts model with the sleep environment being correspondingly arranged, it can be determined that user
Personal sleep regulation model whether be an advantage over setting sleep environment adjust model, that is, crowd's sleep environment adjust model
In the initial sleep environment of certain class user adjust model.If the personal sleep regulation model of user is better than the sleep ring of setting
Border adjusts model, then the sleep environment of setting is adjusted model modification is that personal sleep environment adjusts model, otherwise, retains setting
Sleep environment adjust model.
In possible embodiment, personal sleep environment, which adjusts model, can also be used as crowd's sleep environment adjusting model
The sleep environment of corresponding certain class crowd adjusts a new input factor of model, corrects whole crowd with SVM heredity and corresponds to certain
Class crowd's sleep environment adjusts model, and the sleep environment for certain class user that the sleep environment for corresponding to crowd adjusts model adjusts mould
Type constantly clearly refines.It can be that SVM classifier draws sample by SVM classifier fitness function during specific reality
Divide accuracy, with the increase of sample size, if accuracy is higher than history best model, which replaces original best mould
Type, to obtain optimal crowd's sleep environment as the increase model adaptation of sample size is continued to optimize perfect and adjust model.
Wherein, SVM classifier fitness function may include f (xi)=min (1-g (xi)),
After the embodiment of the present invention establishes crowd's sleep environment adjusting model, crowd's sleep environment can be adjusted into model
As assessment strategy, on its basis, forms personal sleep environment and sleep quality carries out deep learning association analysis, formation
People's sleep environment adjusts model.On the one hand the model influences the parameter setting of the intelligent appliance of personal sleep environment, into new one
In the training study of wheel, with the increase of data volume, constantly adaptive perfect personal sleep environment adjusts model.On the other hand make
For in whole crowd, the new input factor of one of corresponding certain class crowd corrects whole crowd and corresponds to certain class crowd's sleep environment tune
Save model.
The embodiment of the present invention adjusts the sleep environment of the adjustable user of model by the personal sleep environment established, with right
The sleep quality of user is adjusted.It is true by characteristic parameter of the user in sleep when the sleep environment to user is adjusted
Determine the sleep quality scoring of user, then model, i.e. environmental parameter collection and sleep quality scoring are adjusted by personal sleep environment
Relational model analyzes the sleep quality of user, the environmental parameter of suitable user's sleep is determined, so as to pass through
It controls domestic environment equipment and builds the sleep environment for being suitble to user, to adjust the sleep quality of user.Rather than just by logical
Sleeping method, so whether which user, that is, be applicable in different users, can be directed to the personal characteristics pair of the user
The user carries out the adjusting of sleep environment, improves the accuracy for adjusting sleep.
When data processing unit in the embodiment of the present invention establishes personal sleep environment adjusting model, at least one is acquired
After environmental parameter, at least one environmental parameter further progress of acquisition can be rejected, retain component environment parameter as sample
This environmental parameter trains functional relationship model, reduces the calculation amount of data processing unit, alleviates data processing unit
Burden.
To sum up, as shown in fig. 6, Fig. 6 establishes schematic diagram for sleep environment provided in an embodiment of the present invention adjusting model.It is first
The first embodiment of the present invention can obtain at least one environmental parameter and at least one physical sign parameters, and at least one environment is combined to join
Several and at least one physical sign parameters assess sleep quality.Wherein, in possible embodiment, first according at least one
Physical sign parameters combine the sleep stage repartitioned to carry out analysis and obtain sleep quality scoring, join in conjunction at least one environment
Number, it is understood that pre-processed for environmental parameter collection, such as dimension-reduction treatment etc., then carry out supervised learning, obtained personal
Sleep environment adjusts model.After obtaining multiple personal sleep environments adjusting models, it can establish crowd's sleep environment and adjust mould
Type, that is, multiple sleep environments adjusting model is classified, such as is classified according to the type of user, it can in every one kind
Model is adjusted to retain the optimal sleep environment that an optimal personal sleep environment adjusts model as this kind of user.It is using
When crowd's sleep environment adjusts model, the type of user can be first determined, in the determining personal sleep ring to match with the user
Border adjusts model, and the sleep environment of user is adjusted to adjust model by determining personal sleep environment.
The embodiment of the present invention can establish crowd's sleep environment and adjust model, and adjust model not by personal sleep environment
The sleep environment that disconnected optimization crowd sleep environment adjusts certain class crowd in model adjusts model, can be obtained by inhomogeneity people in this way
The best sleep environment of group adjusts model.In the sleep quality for needing to adjust user, it can first determine that user belongs in crowd
Which kind of, and then adjusting of the model realization to the sleep environment of user is adjusted according to the best sleep environment of such crowd.This
Sample can use corresponding sleep environment to adjust the adjusting that model carries out sleep environment, adaptability for different everyone
It is relatively strong.
System provided in an embodiment of the present invention is introduced with reference to the accompanying drawing.
Fig. 2 is referred to, based on the same inventive concept, one embodiment of the invention provides a kind of sleep environment regulating system,
The sleep environment regulating system includes: that environmental parameter acquisition adjusts unit, sleep quality assessment unit, data processing unit and net
It closes.
Wherein, environmental parameter acquisition adjusts unit for acquiring at least one environmental parameter, and by the environmental parameter of acquisition
It is sent to gateway.Sleep quality assessment unit is used to acquire at least one sign ginseng of the user in the preset time period in sleep
Number, at least will be sent to gateway by a physical sign parameters, wherein physical sign parameters include at least bioelectrical signals characteristic parameter, human body
One of limb activity characteristic parameter or any combination.Gateway is used for received at least one environmental parameter and at least one
Physical sign parameters are sent to data processing unit.Data processing unit is used to receive at least one sign ginseng of the user of gateway transmission
Number, and adjust the determining personal sleep environment to match with user in model from crowd's sleep environment and adjust model, pass through determination
Personal sleep environment adjust model the physical sign parameters of acquisition are analyzed, determination at least one to be adjusted environmental parameter,
And at least one environmental parameter that will be adjusted notifies to make at least one the domestic environment equipment being located in user's sleep environment
At least one domestic environment equipment is obtained to run according at least one environmental parameter.
Wherein, data processing unit is also used to carry out prison at least one environmental parameter by deep learning network in advance
The relational model of environmental parameter collection and sleep quality scoring that the layer-by-layer training that educational inspector practises obtains;Crowd's sleep environment adjusts model
Sleep environment including at least a kind of user adjusts model, and the sleep environment of every class user adjusts the corresponding sleep environment of model
Adjust model.
Optionally, data processing unit is specifically used for:
At least one environmental parameter that will be adjusted is notified to gateway;
Gateway is also used to: received at least one to be adjusted environmental parameter is notified in user's sleep environment
At least one domestic environment equipment.
Optionally, sleep quality assessment unit is specifically used for:
According to the value changing rule of at least one physical sign parameters within a preset period of time, by preset time period be divided into
Few two sleep stages;Wherein, preset time period is the sleep stage corresponding period of standard;
Respectively according to the value of at least one corresponding physical sign parameters of each sleep stage at least two sleep stages,
And the accounting of each sleep stage within a preset period of time, calculate the sleep quality scoring of user within a preset period of time.
Optionally, data processing unit is for having carried out prison at least one environmental parameter by deep learning network in advance
The relational model of environmental parameter collection and sleep quality scoring that the layer-by-layer training that educational inspector practises obtains, comprising:
For user, at least one environmental parameter of environment where when user is in sleep state and corresponding sleep are established
Functional relationship model between quality score;Wherein, the input of functional relationship model is at least one environmental parameter, is exported to sleep
Dormancy quality score;
Functional relationship model is successively trained by least one preset sample environment parameter, until sleep quality
The value of scoring reaches established standards, adjusts model to obtain the sleep environment of user;
Wherein, during being trained each time to functional relationship model, the preceding sleep quality once exported is commented
It is allocated as training supervision factor training functional relationship model.
Optionally, data processing unit is specifically used for:
During carrying out supervised learning training to functional relationship model each time, by the preceding sleep matter once exported
Amount scoring is as training supervision factor training functional relationship model;
At least one environmental parameter and a quality of human sleeping scoring are established into incidence relation, sleep environment is obtained and adjusts mould
Type.
Optionally, data processing unit is carrying out being based on having by least one sample environment parameter to functional relationship model
The layer-by-layer training of supervised learning is also used to before obtaining sleep environment adjusting model:
Calculate the related coefficient between each environmental parameter and the same environmental parameter;
The environmental parameter that related coefficient is greater than preset threshold is removed, carries out dimension-reduction treatment to adjust model to sleep environment.
Optionally, data processing unit is also used to:
Determine whether the corresponding sleep quality scoring of at least one environmental parameter currently obtained is higher than last acquisition
The corresponding sleep quality scoring of at least one environmental parameter;
If so, by least one environmental parameter currently obtained replace last at least one environmental parameter obtained at
For at least one optimal environmental parameter;
Otherwise, then retain at least one environmental parameter of last acquisition.
Optionally, data processing unit is specifically used for:
Determine the user type of user;
It is adjusted from the crowd's sleep environment pre-established and searches sleep environment adjusting mould corresponding with user type in model
Type;
The sleep environment of lookup is adjusted into model and is determined as the personal sleep environment to match with user adjusting model.
Optionally, data processing unit is also used to:
Determine that crowd's sleep environment adjusts the sleep environment being correspondingly arranged in model with user type and adjusts model;
Judge whether the personal sleep regulation model of user is an advantage over the sleep environment adjusting model of setting;
If so, it is that personal sleep environment adjusts model that the sleep environment of setting, which is adjusted model modification,;
Otherwise, then the sleep environment for retaining setting adjusts model.
The equipment can be used for executing method provided by embodiment shown in FIG. 1, therefore, for each function of the equipment
The function etc. that module can be realized can refer to the description of embodiment shown in FIG. 1, seldom repeat.
Fig. 7 is referred to, one embodiment of the invention additionally provides a kind of computer equipment, which includes: at least
One processor 701, and the memory 702 being connect at least one processor 701.Wherein, be stored with can quilt for memory 702
The instruction that at least one described processor 701 executes, the instruction that at least one processor 701 is stored by executing memory 702,
Execute such as Fig. 1 and/or method shown in Fig. 2.
In the specific implementation process, each processor 801 specifically can be central processing unit, application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC) can be one or more and hold for controlling program
Capable integrated circuit can be use site programmable gate array (Field Programmable Gate Array, FPGA) and open
The hardware circuit of hair, can be baseband processor.
Memory 802 may include read-only memory (Read Only Memory, ROM), random access memory
(Random Access Memory, RAM) and magnetic disk storage, required data when being run for storage processor 701.Storage
The quantity of device 702 is one or more.Wherein, memory 702 is shown together in Fig. 7, but it is understood that memory 702
It is not essential functional module, therefore shown in dotted line in Fig. 7.
Based on the same inventive concept, the embodiment of the present invention provides a kind of computer readable storage medium, this is computer-readable
Storage medium is stored with computer instruction, when computer instruction is run on computers, so that computer executes as shown in Figure 1
Method.
In the specific implementation process, computer readable storage medium includes: general serial bus USB
(Universal Serial Bus flash drive, USB), mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The storage medium of code.
It is apparent to those skilled in the art that for convenience and simplicity of description, only with above-mentioned each function
The division progress of module can according to need and for example, in practical application by above-mentioned function distribution by different function moulds
Block is completed, i.e., the internal structure of device is divided into different functional modules, to complete all or part of function described above
Energy.The specific work process of the system, apparatus, and unit of foregoing description, can be with reference to corresponding in preceding method embodiment
Journey, details are not described herein.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the module or unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the application
The all or part of the steps of embodiment the method.And storage medium above-mentioned includes: general serial bus USB
(Universal Serial Bus flash disk), mobile hard disk, read-only memory (Read-Only Memory, ROM),
Random access memory (Random Access Memory, RAM), magnetic or disk etc. be various to can store program code
Medium.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (21)
1. a kind of sleep environment adjusting method characterized by comprising
At least one physical sign parameters of user in the preset time period in sleep are obtained, the physical sign parameters include at least biology
One of signal characteristics parameter, human body limb active characteristics parameter or any combination;
The determining personal sleep environment to match with the user in model, which is adjusted, from crowd's sleep environment adjusts model;
Model is adjusted by determining personal sleep environment to analyze the physical sign parameters of acquisition, determination to be adjusted at least one
A environmental parameter;
At least one described environmental parameter is notified at least one the domestic environment equipment being located in user's sleep environment, so that
At least one described domestic environment equipment is run according at least one described environmental parameter;
Wherein, it is to have carried out prison at least one environmental parameter by deep learning network that the personal sleep environment, which adjusts model,
The relational model of environmental parameter collection and physical sign parameters that the layer-by-layer training that educational inspector practises obtains;Crowd's sleep environment adjusts model
Sleep environment including at least a kind of user adjusts model, and the sleep environment of every class user adjusts the corresponding sleep environment of model
Adjust model.
2. the method as described in claim 1, which is characterized in that adjust the determining and user in model from crowd's sleep environment
The personal sleep environment to match adjusts model, comprising:
Determine the user type of the user;
It is adjusted from the crowd's sleep environment pre-established and searches sleep environment adjusting mould corresponding with the user type in model
Type;
The sleep environment of lookup is adjusted into model and is determined as the personal sleep environment to match with the user adjusting model.
3. method according to claim 2, which is characterized in that the method also includes:
Determine that crowd's sleep environment adjusts the sleep environment being correspondingly arranged in model with the user type and adjusts model;
Judge whether the personal sleep regulation model of the user is an advantage over the sleep environment adjusting model of the setting;
If so, it is that the personal sleep environment adjusts model that the sleep environment of the setting, which is adjusted model modification,;
Otherwise, then the sleep environment for retaining the setting adjusts model.
4. the method as described in claim 1, which is characterized in that adjusting model to acquisition by determining personal sleep environment
Physical sign parameters analyzed, before determination at least one to be adjusted environmental parameter, further includes:
Determine that sleep quality scores according at least one physical sign parameters of acquisition;
Model is adjusted by determining personal sleep environment to analyze the physical sign parameters of acquisition, determination to be adjusted at least one
A environmental parameter, comprising:
Model is adjusted by determining personal sleep environment to analyze determining sleep quality, determination to be adjusted to
A few environmental parameter.
5. method as claimed in claim 4, which is characterized in that determine sleep quality according at least one physical sign parameters of acquisition
Scoring, comprising:
According to value changing rule of at least one the described physical sign parameters in the preset time period, by the preset time period
It is divided at least two sleep stages;Wherein, the preset time period is the sleep stage corresponding period of standard;
Respectively according to corresponding at least one physical sign parameters of each sleep stage at least two sleep stage
The accounting of value and each sleep stage in the preset time period calculates the user in the preset time period
Interior sleep quality scoring.
6. method as claimed in claim 5, which is characterized in that adjust model to acquisition by determining personal sleep environment
Sleep quality is analyzed, determination at least one to be adjusted environmental parameter, comprising:
It is pushed away by the way that sleep quality scoring of the personal sleep environment adjusting model to acquisition is counter, acquisition is commented with the sleep quality
Divide corresponding environmental parameter collection;
The environmental parameter collection of acquisition is determined as at least one to be adjusted environmental parameter.
7. method as claimed in claim 6, which is characterized in that adjusting model to acquisition by determining personal sleep environment
Sleep quality scoring physical sign parameters analyzed, before determination at least one to be adjusted environmental parameter, the method is also wrapped
It includes:
For the user, establish at least one environmental parameter of environment where when the user is in sleep state with it is corresponding
Functional relationship model between sleep quality scoring;Wherein, the input of the functional relationship model is at least one described environment
Parameter exports as sleep quality scoring;
The functional relationship model is successively trained by least one preset sample environment parameter, until the sleep
The value of quality score reaches established standards, adjusts model to obtain the sleep environment of the user;
Wherein, during being trained each time to the functional relationship model, the preceding sleep quality once exported is commented
It is allocated as the training supervision factor training functional relationship model.
8. the method for claim 7, which is characterized in that by least one sample environment parameter to the functional relation
Model carries out the layer-by-layer training based on supervised learning, obtains the sleep environment and adjusts model, comprising:
During carrying out supervised learning training to the functional relationship model each time, by the preceding sleep matter once exported
Amount scoring is as the training supervision factor training functional relationship model;
At least one described environmental parameter and a quality of human sleeping scoring are established into incidence relation, the sleep environment is obtained and adjusts
Model.
9. method according to claim 8, which is characterized in that closed by least one sample environment parameter to the function
It is that model carries out the layer-by-layer training based on supervised learning, before obtaining the sleep environment adjusting model, the method is also wrapped
It includes:
Calculate the related coefficient between each environmental parameter and the same environmental parameter;
The environmental parameter that the related coefficient is greater than preset threshold is removed, is carried out at dimensionality reduction with adjusting model to the sleep environment
Reason.
10. the method for claim 7, which is characterized in that the method also includes:
Determine whether the corresponding sleep quality scoring of at least one environmental parameter currently obtained is higher than last obtain at least
The corresponding sleep quality scoring of one environmental parameter;
If so, by least one environmental parameter currently obtained replace described last at least one environmental parameter obtained at
For at least one optimal environmental parameter;
Otherwise, then retain described last at least one environmental parameter obtained.
11. a kind of sleep environment regulating system characterized by comprising environmental parameter acquisition adjusts unit, sleep quality assessment
Unit, data processing unit and gateway;Wherein,
The environmental parameter acquisition adjusts unit and is used for: acquiring at least one environmental parameter, and the environmental parameter of acquisition is sent
To the gateway;
The sleep quality assessment unit is used for: at least one sign ginseng of the acquisition user in the preset time period in sleep
At least one described physical sign parameters are sent to the gateway by number;Wherein, it is special to include at least bioelectrical signals for the physical sign parameters
Levy one of parameter, human body limb active characteristics parameter or any combination;
The gateway is used for: received at least one environmental parameter and at least one described physical sign parameters being sent to described
Data processing unit;
The data processing unit is used for: receiving at least one the described physical sign parameters for the user that the gateway is sent, and from people
Group's sleep environment adjusts the determining personal sleep environment to match with the user in model and adjusts model, passes through determining individual
Sleep environment adjusts model and analyzes the physical sign parameters of acquisition, determination at least one to be adjusted environmental parameter, and by institute
At least one to be adjusted environmental parameter is stated to notify at least one the domestic environment equipment being located in user's sleep environment, so that
At least one described domestic environment equipment is run according at least one described environmental parameter;
Wherein, the data processing unit is also used to: being had in advance by deep learning network at least one environmental parameter
The relational model of environmental parameter collection and sleep quality scoring that the layer-by-layer training of supervised learning obtains;Crowd's sleep environment tune
Section model includes that the sleep environment of at least a kind of user adjusts model, and the sleep environment of every class user adjusts corresponding one, model and sleeps
Dormancy environment adjusts model.
12. system as claimed in claim 11, which is characterized in that the data processing unit is specifically used for:
At least one to be adjusted environmental parameter is notified to the gateway;
The gateway is also used to: received at least one to be adjusted environmental parameter is notified to sleep to positioned at user
At least one domestic environment equipment in environment.
13. system as claimed in claim 11, which is characterized in that the sleep quality assessment unit is specifically used for:
According to value changing rule of at least one the described physical sign parameters in the preset time period, by the preset time period
It is divided at least two sleep stages;Wherein, the preset time period is the sleep stage corresponding period of standard;
Respectively according to corresponding at least one physical sign parameters of each sleep stage at least two sleep stage
The accounting of value and each sleep stage in the preset time period calculates the user in the preset time period
Interior sleep quality scoring.
14. system as claimed in claim 12, which is characterized in that the data processing unit for passing through deep learning in advance
The environmental parameter collection and sleep quality that the layer-by-layer training that network carries out supervised learning at least one environmental parameter obtains score
Relational model, comprising:
For the user, establish at least one environmental parameter of environment where when the user is in sleep state with it is corresponding
Functional relationship model between sleep quality scoring;Wherein, the input of the functional relationship model is at least one described environment
Parameter exports as sleep quality scoring;
The functional relationship model is successively trained by least one preset sample environment parameter, until the sleep
The value of quality score reaches established standards, adjusts model to obtain the sleep environment of the user;
Wherein, during being trained each time to the functional relationship model, the preceding sleep quality once exported is commented
It is allocated as the training supervision factor training functional relationship model.
15. system as claimed in claim 14, which is characterized in that the data processing unit is specifically used for:
During carrying out supervised learning training to the functional relationship model each time, by the preceding sleep matter once exported
Amount scoring is as the training supervision factor training functional relationship model;
At least one described environmental parameter and a quality of human sleeping scoring are established into incidence relation, the sleep environment is obtained and adjusts
Model.
16. system as claimed in claim 14, which is characterized in that the data processing unit is passing through at least one sample ring
Border parameter carries out the layer-by-layer training based on supervised learning to the functional relationship model, obtains the sleep environment and adjusts model
Before, it is also used to:
Calculate the related coefficient between each environmental parameter and the same environmental parameter;
The environmental parameter that the related coefficient is greater than preset threshold is removed, is carried out at dimensionality reduction with adjusting model to the sleep environment
Reason.
17. system as claimed in claim 14, which is characterized in that the data processing unit is also used to:
Determine whether the corresponding sleep quality scoring of at least one environmental parameter currently obtained is higher than last obtain at least
The corresponding sleep quality scoring of one environmental parameter;
If so, by least one environmental parameter currently obtained replace described last at least one environmental parameter obtained at
For at least one optimal environmental parameter;
Otherwise, then retain described last at least one environmental parameter obtained.
18. system as claimed in claim 14, which is characterized in that the data processing unit is specifically used for:
Determine the user type of the user;
It is adjusted from the crowd's sleep environment pre-established and searches sleep environment adjusting mould corresponding with the user type in model
Type;
The sleep environment of lookup is adjusted into model and is determined as the personal sleep environment to match with the user adjusting model.
19. system as claimed in claim 14, which is characterized in that the data processing unit is also used to:
Determine that crowd's sleep environment adjusts the sleep environment being correspondingly arranged in model with the user type and adjusts model;
Judge whether the personal sleep regulation model of the user is an advantage over the sleep environment adjusting model of the setting;
If so, it is that the personal sleep environment adjusts model that the sleep environment of the setting, which is adjusted model modification,;
Otherwise, then the sleep environment for retaining the setting adjusts model.
20. a kind of sleep environment adjustment equipment, which is characterized in that the equipment includes:
At least one processor, and
The memory being connect at least one described processor;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, at least one described processor
By executing the instruction of the memory storage, such as method of any of claims 1-10 is executed.
21. a kind of computer readable storage medium, it is characterised in that:
The computer-readable recording medium storage has computer instruction, when the computer instruction is run on computers,
So that computer executes such as method of any of claims 1-10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710912360.2A CN109568760B (en) | 2017-09-29 | 2017-09-29 | Sleep environment adjusting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710912360.2A CN109568760B (en) | 2017-09-29 | 2017-09-29 | Sleep environment adjusting method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109568760A true CN109568760A (en) | 2019-04-05 |
CN109568760B CN109568760B (en) | 2022-05-13 |
Family
ID=65919195
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710912360.2A Active CN109568760B (en) | 2017-09-29 | 2017-09-29 | Sleep environment adjusting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109568760B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110974195A (en) * | 2019-12-05 | 2020-04-10 | 珠海格力电器股份有限公司 | Method, device and storage medium for adjusting sleep environment |
CN110989735A (en) * | 2019-11-12 | 2020-04-10 | 珠海格力电器股份有限公司 | Self-adaptive adjustment method and device for sleep environment and electronic equipment |
CN111077925A (en) * | 2019-10-31 | 2020-04-28 | 珠海格力电器股份有限公司 | Control method and device of illumination adjusting equipment, electronic equipment and storage medium |
CN111887830A (en) * | 2020-09-10 | 2020-11-06 | 贵州省人民医院 | Sleep monitoring method, device, equipment and readable storage medium |
CN112206395A (en) * | 2020-09-11 | 2021-01-12 | 深圳数联天下智能科技有限公司 | Setting method and device of linkage scene |
CN112353401A (en) * | 2020-10-19 | 2021-02-12 | 燕山大学 | Staged regulation and control method based on physiological state evaluation |
CN112451834A (en) * | 2020-11-24 | 2021-03-09 | 珠海格力电器股份有限公司 | Sleep quality management method, device, system and storage medium |
CN112545853A (en) * | 2020-11-17 | 2021-03-26 | 未来穿戴技术有限公司 | Massage pulse output method, massage device, electronic device, and storage medium |
CN112674755A (en) * | 2020-12-09 | 2021-04-20 | 珠海格力电器股份有限公司 | Sleep detection system, method and storage medium |
CN113268098A (en) * | 2021-06-23 | 2021-08-17 | 上海市建筑科学研究院有限公司 | Indoor environment regulation and control method and system |
CN113679339A (en) * | 2020-05-19 | 2021-11-23 | 安徽华米健康科技有限公司 | Sleep monitoring method, device, system and storage medium |
CN114053551A (en) * | 2022-01-13 | 2022-02-18 | 深圳市心流科技有限公司 | Electroencephalogram signal-based auxiliary sleep-in method and device, terminal and storage medium |
CN114995563A (en) * | 2022-08-03 | 2022-09-02 | 利亚德光电股份有限公司 | State demand self-matching environment state display method, system, medium and equipment |
CN115120837A (en) * | 2022-06-27 | 2022-09-30 | 慕思健康睡眠股份有限公司 | Sleep environment adjusting method, system, device and medium based on deep learning |
CN115137315A (en) * | 2022-09-06 | 2022-10-04 | 深圳市心流科技有限公司 | Sleep environment scoring method, device, terminal and storage medium |
CN115496105A (en) * | 2022-09-28 | 2022-12-20 | 广东省新黄埔中医药联合创新研究院 | Sleep prediction model training method, sleep condition prediction method and related device |
CN115865670A (en) * | 2023-02-27 | 2023-03-28 | 灵长智能科技(杭州)有限公司 | Method and device for adjusting concurrency performance of WEB security gateway based on kernel tuning |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007044201A (en) * | 2005-08-09 | 2007-02-22 | Sekisui House Ltd | Sleep environment adjusting system and method |
US20090264715A1 (en) * | 2003-12-31 | 2009-10-22 | Raphael Auphan | Sleep and Environment Control Method and System |
CN102626538A (en) * | 2012-03-30 | 2012-08-08 | 北京品驰医疗设备有限公司 | Sleep detection-based integrated closed loop deep brain stimulator |
WO2013054712A1 (en) * | 2011-10-14 | 2013-04-18 | 株式会社タニタ | Sleep assessment system and sleep assessment apparatus |
CN104110786A (en) * | 2013-12-30 | 2014-10-22 | 广东美的制冷设备有限公司 | Intelligent air conditioner, sleep control device thereof and sleep control method for intelligent air conditioner |
CN104243247A (en) * | 2013-06-21 | 2014-12-24 | 广州杰赛科技股份有限公司 | Intelligent household appliance control device based on cloud |
CN104848473A (en) * | 2015-04-23 | 2015-08-19 | 广东美的制冷设备有限公司 | Air conditioner control method, device and system based on wearable device |
CN105890117A (en) * | 2016-04-28 | 2016-08-24 | 北京小米移动软件有限公司 | Method and device for controlling air conditioner and server |
US20160292584A1 (en) * | 2015-03-31 | 2016-10-06 | Microsoft Technology Licensing, Llc | Inferring User Sleep Patterns |
CN106123206A (en) * | 2016-06-17 | 2016-11-16 | 美的集团股份有限公司 | A kind of method and system adjusting ambient heat |
CN106175697A (en) * | 2016-09-18 | 2016-12-07 | 广州视源电子科技股份有限公司 | Sleep state detection method and device |
US20160361515A1 (en) * | 2015-06-11 | 2016-12-15 | Samsung Electronics Co., Ltd. | Method and apparatus for controlling temperature adjustment device |
CN205827291U (en) * | 2016-05-18 | 2016-12-21 | 复旦大学附属上海市第五人民医院 | A kind of patient sleeps assesses dip stick |
JP2017000211A (en) * | 2015-06-04 | 2017-01-05 | パナソニックIpマネジメント株式会社 | Sleep environment control system |
WO2017010794A1 (en) * | 2015-07-13 | 2017-01-19 | 삼성전자 주식회사 | Control method and apparatus for managing sleep environment |
CN106618486A (en) * | 2016-09-21 | 2017-05-10 | 广州视源电子科技股份有限公司 | Sleep state recognition method and system in intelligent assistant sleep |
JP2017113454A (en) * | 2015-12-25 | 2017-06-29 | トヨタホーム株式会社 | Sleep support device |
CN106913313A (en) * | 2015-12-28 | 2017-07-04 | 中国移动通信集团公司 | A kind of sleep monitor method and system |
-
2017
- 2017-09-29 CN CN201710912360.2A patent/CN109568760B/en active Active
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090264715A1 (en) * | 2003-12-31 | 2009-10-22 | Raphael Auphan | Sleep and Environment Control Method and System |
JP2007044201A (en) * | 2005-08-09 | 2007-02-22 | Sekisui House Ltd | Sleep environment adjusting system and method |
WO2013054712A1 (en) * | 2011-10-14 | 2013-04-18 | 株式会社タニタ | Sleep assessment system and sleep assessment apparatus |
CN102626538A (en) * | 2012-03-30 | 2012-08-08 | 北京品驰医疗设备有限公司 | Sleep detection-based integrated closed loop deep brain stimulator |
CN104243247A (en) * | 2013-06-21 | 2014-12-24 | 广州杰赛科技股份有限公司 | Intelligent household appliance control device based on cloud |
CN104110786A (en) * | 2013-12-30 | 2014-10-22 | 广东美的制冷设备有限公司 | Intelligent air conditioner, sleep control device thereof and sleep control method for intelligent air conditioner |
US20160292584A1 (en) * | 2015-03-31 | 2016-10-06 | Microsoft Technology Licensing, Llc | Inferring User Sleep Patterns |
CN104848473A (en) * | 2015-04-23 | 2015-08-19 | 广东美的制冷设备有限公司 | Air conditioner control method, device and system based on wearable device |
JP2017000211A (en) * | 2015-06-04 | 2017-01-05 | パナソニックIpマネジメント株式会社 | Sleep environment control system |
US20160361515A1 (en) * | 2015-06-11 | 2016-12-15 | Samsung Electronics Co., Ltd. | Method and apparatus for controlling temperature adjustment device |
WO2017010794A1 (en) * | 2015-07-13 | 2017-01-19 | 삼성전자 주식회사 | Control method and apparatus for managing sleep environment |
JP2017113454A (en) * | 2015-12-25 | 2017-06-29 | トヨタホーム株式会社 | Sleep support device |
CN106913313A (en) * | 2015-12-28 | 2017-07-04 | 中国移动通信集团公司 | A kind of sleep monitor method and system |
CN105890117A (en) * | 2016-04-28 | 2016-08-24 | 北京小米移动软件有限公司 | Method and device for controlling air conditioner and server |
CN205827291U (en) * | 2016-05-18 | 2016-12-21 | 复旦大学附属上海市第五人民医院 | A kind of patient sleeps assesses dip stick |
CN106123206A (en) * | 2016-06-17 | 2016-11-16 | 美的集团股份有限公司 | A kind of method and system adjusting ambient heat |
CN106175697A (en) * | 2016-09-18 | 2016-12-07 | 广州视源电子科技股份有限公司 | Sleep state detection method and device |
CN106618486A (en) * | 2016-09-21 | 2017-05-10 | 广州视源电子科技股份有限公司 | Sleep state recognition method and system in intelligent assistant sleep |
Non-Patent Citations (2)
Title |
---|
黄俊杰 等: "睡眠环境调节系统的血氧饱和度与心率信号采集环节研制", 《微型电脑应用》 * |
黄耀梁 等: "结合睡眠状态检测的睡眠环境智能调节系统", 《中国自动化学会中南六省(区)2010年第28届年会 论文集》 * |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111077925A (en) * | 2019-10-31 | 2020-04-28 | 珠海格力电器股份有限公司 | Control method and device of illumination adjusting equipment, electronic equipment and storage medium |
CN110989735A (en) * | 2019-11-12 | 2020-04-10 | 珠海格力电器股份有限公司 | Self-adaptive adjustment method and device for sleep environment and electronic equipment |
CN110974195A (en) * | 2019-12-05 | 2020-04-10 | 珠海格力电器股份有限公司 | Method, device and storage medium for adjusting sleep environment |
CN113679339A (en) * | 2020-05-19 | 2021-11-23 | 安徽华米健康科技有限公司 | Sleep monitoring method, device, system and storage medium |
CN111887830A (en) * | 2020-09-10 | 2020-11-06 | 贵州省人民医院 | Sleep monitoring method, device, equipment and readable storage medium |
CN111887830B (en) * | 2020-09-10 | 2023-03-10 | 贵州省人民医院 | Sleep monitoring method, device, equipment and readable storage medium |
CN112206395A (en) * | 2020-09-11 | 2021-01-12 | 深圳数联天下智能科技有限公司 | Setting method and device of linkage scene |
CN112206395B (en) * | 2020-09-11 | 2022-07-15 | 深圳数联天下智能科技有限公司 | Setting method and device of linkage scene |
CN112353401A (en) * | 2020-10-19 | 2021-02-12 | 燕山大学 | Staged regulation and control method based on physiological state evaluation |
CN112353401B (en) * | 2020-10-19 | 2022-04-19 | 燕山大学 | Staged regulation and control method based on physiological state evaluation |
CN112545853A (en) * | 2020-11-17 | 2021-03-26 | 未来穿戴技术有限公司 | Massage pulse output method, massage device, electronic device, and storage medium |
CN112451834B (en) * | 2020-11-24 | 2022-03-04 | 珠海格力电器股份有限公司 | Sleep quality management method, device, system and storage medium |
CN112451834A (en) * | 2020-11-24 | 2021-03-09 | 珠海格力电器股份有限公司 | Sleep quality management method, device, system and storage medium |
CN112674755A (en) * | 2020-12-09 | 2021-04-20 | 珠海格力电器股份有限公司 | Sleep detection system, method and storage medium |
CN113268098B (en) * | 2021-06-23 | 2022-09-23 | 上海市建筑科学研究院有限公司 | Indoor environment regulation and control method and system |
CN113268098A (en) * | 2021-06-23 | 2021-08-17 | 上海市建筑科学研究院有限公司 | Indoor environment regulation and control method and system |
CN114053551B (en) * | 2022-01-13 | 2022-05-17 | 深圳市心流科技有限公司 | Electroencephalogram signal-based auxiliary sleep-helping method and device, terminal and storage medium |
CN114053551A (en) * | 2022-01-13 | 2022-02-18 | 深圳市心流科技有限公司 | Electroencephalogram signal-based auxiliary sleep-in method and device, terminal and storage medium |
CN115120837A (en) * | 2022-06-27 | 2022-09-30 | 慕思健康睡眠股份有限公司 | Sleep environment adjusting method, system, device and medium based on deep learning |
CN114995563A (en) * | 2022-08-03 | 2022-09-02 | 利亚德光电股份有限公司 | State demand self-matching environment state display method, system, medium and equipment |
CN115137315A (en) * | 2022-09-06 | 2022-10-04 | 深圳市心流科技有限公司 | Sleep environment scoring method, device, terminal and storage medium |
CN115496105A (en) * | 2022-09-28 | 2022-12-20 | 广东省新黄埔中医药联合创新研究院 | Sleep prediction model training method, sleep condition prediction method and related device |
CN115496105B (en) * | 2022-09-28 | 2023-10-24 | 广东省新黄埔中医药联合创新研究院 | Sleep prediction model training method, sleep condition prediction method and related devices |
CN115865670A (en) * | 2023-02-27 | 2023-03-28 | 灵长智能科技(杭州)有限公司 | Method and device for adjusting concurrency performance of WEB security gateway based on kernel tuning |
CN115865670B (en) * | 2023-02-27 | 2023-06-16 | 灵长智能科技(杭州)有限公司 | Method and device for adjusting concurrency performance of WEB security gateway based on kernel tuning |
Also Published As
Publication number | Publication date |
---|---|
CN109568760B (en) | 2022-05-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109568760A (en) | Sleep environment adjusting method and system | |
Peker | An efficient sleep scoring system based on EEG signal using complex-valued machine learning algorithms | |
CN112656427B (en) | Electroencephalogram emotion recognition method based on dimension model | |
He et al. | Strengthen EEG-based emotion recognition using firefly integrated optimization algorithm | |
CN108742517A (en) | One kind is based on the mono- lead brain electrosleep of Stacking method by stages automatically | |
WO2017193497A1 (en) | Fusion model-based intellectualized health management server and system, and control method therefor | |
CN110897639A (en) | Electroencephalogram sleep staging method based on deep convolutional neural network | |
Cheng et al. | A motor imagery EEG feature extraction method based on energy principal component analysis and deep belief networks | |
CN110706816A (en) | Method and equipment for regulating sleep environment based on artificial intelligence | |
CN109260566A (en) | Enhance sleep technology using shadow casting technique | |
CN106599057A (en) | Music rhythm control terminal and method adaptive to user emotion | |
Sezer et al. | Employment and comparison of different artificial neural networks for epilepsy diagnosis from EEG signals | |
Xie et al. | Electroencephalogram emotion recognition based on a stacking classification model | |
Zhang et al. | Competition convolutional neural network for sleep stage classification | |
CN113448438A (en) | Control system and method based on sleep perception | |
CN112353401B (en) | Staged regulation and control method based on physiological state evaluation | |
CN107233653A (en) | Decompression method is loosened based on brain wave context aware and cloud platform storage technology | |
KR20080107961A (en) | User adaptative pattern clinical diagnosis/medical system and method using brain waves and the sense infomation treatment techniques | |
Khare et al. | Classification of mental states from rational dilation wavelet transform and bagged tree classifier using EEG signals | |
CN110473631A (en) | Intelligent sleep monitoring method and system based on real world research | |
Chitti et al. | EEG signal feature selection algorithm and support vector machine model in patient's fatigue recognition | |
Cen et al. | Deep learning method for sleep stage classification | |
Zhang et al. | EEG-based odor recognition using channel-frequency convolutional neural network | |
Hazra et al. | On effective cognitive state classification using novel feature extraction strategies | |
Dabas et al. | A Step Closer to Becoming Symbiotic with AI through EEG: A Review of Recent BCI Technology |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |