CN109498001A - Sleep quality appraisal procedure and device - Google Patents
Sleep quality appraisal procedure and device Download PDFInfo
- Publication number
- CN109498001A CN109498001A CN201811594779.9A CN201811594779A CN109498001A CN 109498001 A CN109498001 A CN 109498001A CN 201811594779 A CN201811594779 A CN 201811594779A CN 109498001 A CN109498001 A CN 109498001A
- Authority
- CN
- China
- Prior art keywords
- period
- eeg signals
- feature
- body movement
- 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
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4815—Sleep quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Anesthesiology (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention provides sleep quality appraisal procedure and device, wherein method includes: the first EEG signals and the first body movement signal for obtaining user in first time period;The first time period is divided into multiple periods using preset duration as the time span of a cycle, determines corresponding first EEG signals of each period and the first body movement signal respectively;Corresponding first, second brain electrical feature of each period is determined to the first, second feature extraction of each period corresponding first EEG signals progress respectively;It carries out third feature to each period corresponding first body movement signal respectively and extracts to determine that corresponding first body of each period moves feature;Feature, which is moved, according to each period corresponding first, second brain electrical feature, the first body generates eigenmatrix;Sleep Quality Index value of the user in the first time period is determined according to the eigenmatrix.The accuracy of user's sleep quality assessment can be improved in the technical solution.
Description
Technical field
The present invention relates to sleep quality evaluation areas more particularly to sleep quality appraisal procedure and devices.
Background technique
The quality of sleep quality has vital influence to human body health, some physiology in acquisition user's sleep
Signal, which carries out analysis, can be used for assessing sleep quality.
Existing sleep quality appraisal procedure is general are as follows: body movement signal when acquisition user's sleep, one signal of every acquisition
With regard to carrying out a hard decision, to judge sleep state that user is presently in.Since one signal of every acquisition is judged as once, and
Collected signal, which is easy to be interfered, leads to error in judgement, and the data reliability counted in this way is poor, can not accurate evaluation user
Sleep quality, therefore, existing sleep quality appraisal procedure be unable to satisfy user want accurately understand oneself sleep quality shape
The demand of condition.
Summary of the invention
The embodiment of the present invention provides sleep quality appraisal procedure and device, solves sleep quality and assesses not accurate enough ask
Topic.
In a first aspect, providing sleep quality appraisal procedure, comprising:
First EEG signals and first body movement signal of the user in first time period are obtained, the first time period is institute
State user's sleep procedure corresponding period;
The first time period is divided into multiple periods using preset duration as the time span of a cycle, is determined respectively
Each period corresponding first EEG signals and the first body movement signal in the multiple period;
It carries out fisrt feature to each period corresponding first EEG signals respectively and extracts to determine each period
Corresponding first brain electrical feature, the first brain electrical feature are used to indicate the sleep situation of change of the user;
It carries out second feature to each period corresponding first EEG signals respectively and extracts to determine each period
Corresponding second brain electrical feature, the second brain electrical feature are used to indicate the brain active degree of the user;
It carries out third feature to each period corresponding first body movement signal respectively and extracts to determine each period
Corresponding first body moves feature, and first body moves the motion conditions that feature is used to indicate the user;
Feature, which is moved, according to each period corresponding first brain electrical feature, the second brain electrical feature, the first body generates feature
Matrix, the eigenmatrix are used to indicate the sleep quality situation of the user, and the eigenmatrix is the matrix of 3*N, and N is institute
State the quantity in period;
Sleep Quality Index value of the user in the first time period is determined according to the eigenmatrix.
In the embodiment of the present invention, it is divided by the EEG signals in the user's sleep procedure that will acquire with body movement signal
The multiple time spans identical period, and feature extraction is carried out to the EEG signals in each period and obtains each period corresponding the
One brain electrical feature, the second brain electrical feature carry out feature extraction to the body movement signal in each period and obtain each period corresponding the
The dynamic feature of one, generates eigenmatrix according to corresponding three features of each period, is met by searching in eigenmatrix
The period of condition obtains three parameters relevant to Sleep Quality Index value, carries out user is calculated to three parameters and sleep
Dormancy Quality index value determines the sleep quality situation of user according to Sleep Quality Index value.By to corresponding brain of each period
Feature extraction three obtained feature reflects the sleep situation of change of user to electrical feature respectively, user sleeps with body dynamic feature progress
The motion conditions in brain active degree and user's sleep procedure during dormancy, due to from multiple dimensional analysis user's
Sleep quality improves the accuracy of user's sleep quality assessment.
With reference to first aspect, in one possible implementation, it is described obtain user in first time period first
EEG signals and the first body movement signal, comprising: acquire second EEG signals and of the user in the first time period
Two body movement signals, second body movement signal include the acceleration degree series on X, Y, Z axis direction;By filter to described second
EEG signals are filtered, and obtain first EEG signals;Acceleration degree series on the X, Y, Z axis direction close and are added
Conjunction body movement signal is calculated in speed;The corresponding conjunction body movement signal of body movement signal will be closed to target each in the conjunction body movement signal
Set carries out the signal that average value processing obtains and is determined as first body movement signal, and the fit dynamic signal set includes the mesh
Preceding A conjunction body movement signal, the target that mark closes body movement signal close body movement signal and the target closes rear B of body movement signal
Body movement signal is closed, A, B are positive integer, and the sum of A, B and 1 are of the conjunction body movement signal in the fit dynamic signal set
Number.By being filtered to collected EEG signals and carrying out total speed calculating and mean value to collected body movement signal
Processing eliminates the noise in EEG signals and body movement signal, has obtained the first EEG signals and the first body movement signal.
With reference to first aspect, in one possible implementation, described respectively to each period corresponding first
EEG signals carry out fisrt feature extraction and determine corresponding first brain electrical feature of each period, comprising: according to described each
Period corresponding first EEG signals determine that corresponding low frequency EEG signals of each period are corresponding with each period
High frequency EEG signals, the low frequency EEG signals are the EEG signals lower than first frequency threshold value, and the high frequency EEG signals are
Higher than the EEG signals of first frequency threshold value;Calculate corresponding first sample entropy of each period and each period pair
The the second sample entropy answered, the first sample entropy are the sample entropy of the high frequency EEG signals, second Sample Entropy
Value is the sample entropy of the low frequency EEG signals;By each period corresponding first sample entropy and each period
The ratio of corresponding second sample entropy is determined as corresponding first brain electrical feature of each period.By to each period pair
The first EEG signals answered carry out fisrt feature extraction, have obtained corresponding first brain electrical feature.
With reference to first aspect, in one possible implementation, described according to each period corresponding first brain
Electric signal determines corresponding low frequency EEG signals of each period high frequency EEG signals corresponding with each period, packet
It includes: each period corresponding first EEG signals being carried out by the low-pass filter that cutoff frequency is first frequency threshold value
Filtering obtains corresponding low frequency EEG signals of each period, and is the high-pass filtering of first frequency threshold value by cutoff frequency
Device is filtered to obtain corresponding high frequency EEG signals of each period to each period corresponding first EEG signals,
Alternatively, by low-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first EEG signals into
Row filtering obtains corresponding low frequency EEG signals of each period, and passes through the corresponding first brain electricity of each period
Signal subtracts the corresponding low frequency EEG signals of each period, obtains corresponding high frequency brain telecommunications of each period
Number, alternatively, by high-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first brain telecommunications
It number is filtered to obtain corresponding high frequency EEG signals of each period, and passes through each period corresponding described first
EEG signals subtract the corresponding high frequency EEG signals of each period, obtain corresponding low frequency brain electricity of each period
Signal.The first EEG signals are filtered by filter, have obtained corresponding high frequency EEG signals of each period and low frequency
EEG signals eliminate the noise in EEG signals.
With reference to first aspect, in one possible implementation, described respectively to each period corresponding first
EEG signals carry out second feature extraction and determine corresponding second brain electrical feature of each period, comprising: pass through bandpass filtering
Device is filtered to obtain corresponding third EEG signals of each period to each period corresponding first EEG signals,
First cutoff frequency of the bandpass filter is second frequency threshold value, and the second cutoff frequency of the bandpass filter is third
Frequency threshold, the second frequency threshold value are less than the third frequency threshold;Determine corresponding tritencepehalon electricity of each period
The corresponding energy value of signal;The ratio of corresponding energy value of each period and the first energy value is determined as each period pair
The the second brain electrical feature answered, first energy value are the corresponding energy value of a cycle in each period.By right
The first EEG signals in each period are filtered, and are made energy calculation to filtered third EEG signals, have obtained
Two brain electrical features.
With reference to first aspect, in one possible implementation, described respectively to each period corresponding first
Body movement signal carries out third feature extraction and determines that corresponding first body of each period moves feature, comprising: calculates separately described
The standard deviation of each period corresponding first body movement signal;The quantity of each period corresponding third body movement signal is determined
Move feature for each period corresponding first body, the third body movement signal be absolute value be greater than G times of standard deviation body it is dynamic
Signal, G are the positive integer less than or equal to 3.By calculating the standard deviation of the first body movement signal in each period and comparing
The absolute value of first body movement signal and the relationship of standard deviation have obtained first body of the user within each period and have moved feature.
With reference to first aspect, in one possible implementation, described that the user is determined according to the eigenmatrix
Sleep Quality Index value in the first time period, comprising: the first parameter, the second parameter are determined according to the eigenmatrix
With third parameter, first parameter, the second parameter and third parameter are the parameter for determining Sleep Quality Index value;According to
First parameter, second parameter, the third parameter and sleep quality assessment formula calculate the sleep quality and refer to
Numerical value, the sleep quality assessment formula areWherein, S is the sleep matter
Volume index value, H1For first parameter, H2For second parameter, H3For the third parameter.
It is with reference to first aspect, in one possible implementation, described that first parameter is determined according to the eigenmatrix,
It include: that sequence valve of the period 1 in the first time period is determined according to the eigenmatrix, the period 1 is institute
The first brain electrical feature is stated less than the first sleep threshold and the second brain electrical feature less than the first alive threshold a cycle;
The inverse of difference is determined as the first parameter, the difference is the difference of the sequence valve and 1 in the first time period.
It is with reference to first aspect, in one possible implementation, described that second parameter is determined according to the eigenmatrix,
It include: the quantity that second round is determined according to the eigenmatrix, the second round is the first brain electrical feature less than the
One sleep threshold and first body move period of the feature less than the first movement threshold;By the quantity of the second round and N
Ratio is determined as second parameter.
It is with reference to first aspect, in one possible implementation, described that third parameter is determined according to the eigenmatrix,
It include: the quantity that the period 3 is determined according to the eigenmatrix, the period 3 is the first brain electrical feature less than the
Two sleep thresholds and first body move period of the feature less than the second movement threshold, and second sleep threshold is less than described the
One sleep threshold, second movement threshold are less than first movement threshold;By the quantity of the period 3 and described the
The ratio of the quantity of two cycles is determined as the third parameter.
Second aspect provides a kind of sleep quality assessment device, comprising: signal acquisition module, for obtaining user the
The first EEG signals and the first body movement signal in one period, the first time period are that user's sleep procedure is corresponding
Period;
Period division module, for being divided into the first time period using preset duration as the time span of a cycle
Multiple periods determine corresponding first EEG signals of each period and the first body movement signal respectively;
Fisrt feature extraction module, for carrying out fisrt feature to each period corresponding first EEG signals respectively
It extracts and determines that corresponding first brain electrical feature of each period, the first brain electrical feature are used to indicate the sleep of the user
Situation of change;
Second feature extraction module, for carrying out second feature to each period corresponding first EEG signals respectively
It extracts and determines that corresponding second brain electrical feature of each period, the second brain electrical feature are used to indicate the brain of the user
Active degree;
Third feature extraction module, for carrying out third feature to each period corresponding first body movement signal respectively
It extracts and determines that corresponding first body of each period moves feature, first body moves the movement that feature is used to indicate the user
Situation;
Matrix generation module, for according to each period corresponding first brain electrical feature, the second brain electrical feature, first
Body moves feature and generates eigenmatrix, and the eigenmatrix is used to indicate the sleep quality situation of the user, the eigenmatrix
For the matrix of 3*N, N is the quantity in the period;
Index determining module, for determining sleep of the user in the first time period according to the eigenmatrix
Quality index value.
The third aspect provides a kind of sleep quality assessment device, including processor, memory and input/output interface,
The processor, memory and input/output interface are connected with each other, wherein the input/output interface is for inputting or exporting number
According to the memory is for storing program code, and the processor is for calling said program code, to execute above-mentioned first party
The method in face.
Fourth aspect provides a kind of computer storage medium, and the computer storage medium is stored with computer program, institute
Stating computer program includes program instruction, and described program instructs when being executed by a processor, the method for executing above-mentioned first aspect.
In the embodiment of the present invention, it is divided by the EEG signals in the user's sleep procedure that will acquire with body movement signal
The multiple time spans identical period, and feature extraction is carried out to the EEG signals in each period and obtains each period corresponding the
One brain electrical feature, the second brain electrical feature carry out feature extraction to the body movement signal in each period and obtain each period corresponding the
The dynamic feature of one, generates eigenmatrix according to corresponding three features of each period, is met by searching in eigenmatrix
The period of condition obtains three parameters relevant to Sleep Quality Index value, carries out user is calculated to three parameters and sleep
Dormancy Quality index value determines the sleep quality situation of user according to Sleep Quality Index value.By to corresponding brain of each period
Feature extraction three obtained feature reflects the sleep situation of change of user to electrical feature respectively, user sleeps with body dynamic feature progress
The motion conditions in brain active degree and user's sleep procedure during dormancy, due to from multiple dimensional analysis user's
Sleep quality improves the accuracy of user's sleep quality assessment.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow diagram of sleep quality appraisal procedure provided in an embodiment of the present invention;
Fig. 2 a is the schematic diagram of first EEG signals provided in an embodiment of the present invention;
Fig. 2 b be it is provided in an embodiment of the present invention it is a kind of filtered by low-pass filter after obtain showing for low frequency EEG signals
It is intended to;
Fig. 2 c is provided in an embodiment of the present invention a kind of by obtaining showing for high frequency EEG signals after high pass filter filters
It is intended to;
Fig. 3 a is the schematic diagram of another the first EEG signals provided in an embodiment of the present invention;
Fig. 3 b is provided in an embodiment of the present invention a kind of by obtaining showing for third EEG signals after band-pass filter
It is intended to;
Fig. 4 is the flow diagram of another sleep quality appraisal procedure provided in an embodiment of the present invention;
Fig. 5 is a kind of composed structure schematic diagram of sleep quality assessment device provided in an embodiment of the present invention;
Fig. 6 is the composed structure schematic diagram of another sleep quality assessment device provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
Technical solution of the present invention is suitable for being acquired the EEG signals user's sleep procedure with body movement signal, root
Processing analysis is carried out according to collected EEG signals and body movement signal and obtains user's sleep quality index value, so that it is determined that user sleeps
The scene of dormancy quality.
It is a kind of flow diagram of sleep quality appraisal procedure provided in an embodiment of the present invention referring to Fig. 1, Fig. 1, such as schemes
It is shown, this method comprises:
S101, obtaining first EEG signals and first body movement signal, first time period of the user in first time period is
User's sleep procedure corresponding period.
In the embodiment of the present invention, the first EEG signals can be determined by following steps:
One, the EEG signals in user's sleep procedure can be sampled by the first sample rate, obtains the second brain electricity
Signal.Here, the first sample rate can be 500 hertz (Hz, the basic unit of frequency), or the number such as 50Hz, 100Hz
Value.
Two, the second EEG signals can be filtered by the filter of first frequency range, obtains the first brain telecommunications
Number.Specifically, filter can be FIR bandpass filter, and first frequency may range from 0.3-35Hz, first frequency range
It can be the ranges such as 0.5-40Hz.
In the embodiment of the present invention, the first body movement signal can be determined by following steps:
One, second body movement signal of the acquisition user in first time period.
The body movement signal in user's sleep procedure can be sampled by the second sample rate, the second body movement signal includes
Acceleration degree series on X, Y, Z axis direction.In the specific implementation, the second body of user can be acquired by 3-axis acceleration sensor
Dynamic signal, is acquired the acceleration on the X, Y, Z axis direction in user's sleep procedure by 3-axis acceleration sensor
To corresponding acceleration degree series.Second sample rate can be 50Hz, and the second sample rate may be the numerical value such as 30Hz, 40Hz.
Two, resultant acceleration is carried out to the acceleration degree series on X, Y, Z axis direction and conjunction body movement signal is calculated.
Here, the formula that resultant acceleration calculates can be with are as follows:Wherein, BMiIt is dynamic for zoarium
Signal value, Xi、Yi、ZiFor three acceleration in three axis directions of acceleration transducer, i is the ordinal number of each sequence.
For example, 3-axis acceleration sensor acquires 3 acceleration, X1、Y1、Z1Respectively 1,0,1, X2、Y2、Z2Respectively
0,1,1, X3、Y3、Z3Respectively 0,0,1, thenBM3=1.
Three, target each in pairing body movement signal is closed into the corresponding fit dynamic signal set of body movement signal and carries out average value processing
Obtained signal is determined as the first body movement signal.Here, fit dynamic signal set includes the preceding A zoarium that target closes body movement signal
Dynamic signal, target close body movement signal and target closes the rear B conjunction body movement signal of body movement signal, and A, B are positive integer, and A, B
It is the fit number for moving the conjunction body movement signal in signal set with the sum of 1.
Specifically, the formula of average value processing can be with are as follows:Wherein, BMiFor the first body movement signal value, A
+ B+1 is to close the total number of body movement signal, BM in fit dynamic signal setjFor each fit dynamic letter in fit dynamic signal set
Number, i+B is the rear B conjunction body movement signal that target closes body movement signal, and i-A is the preceding A conjunction body movement signal that target closes body movement signal.
For example, having 4 conjunction body movement signals, the respectively dynamic letter of target zoarium in the dynamic signal set of zoarium when A is 1, B is 2
Number first 1 close body movement signal, target closes rear 2 conjunctions body movement signal that body movement signal and target close body movement signal, then
First time period is divided into multiple periods using preset duration as the time span of a cycle by S102, true respectively
Each period corresponding first EEG signals and the first body movement signal in fixed multiple periods.
Here, since the EEG signals in 30s are relatively stable, thus preset duration can be 30s, then a cycle when
Between length be 30s, first time period is divided into multiple 30s, corresponding first EEG signals of each 30s are then that the period is corresponding
The first EEG signals, corresponding first body movement signal of each 30s is then the period corresponding first body movement signal.For example, the
One period was 30min, then first time period was divided into 60 periods using 30s as the time span of a cycle, first
The 30s corresponding period is a cycle, and second 30s corresponding period is second period ... ..., and the 60th 30s is corresponding
Period be the 60th period.Corresponding first EEG signals of first 30s are then the corresponding first brain telecommunications of a cycle
Number, corresponding first body movement signal of first 30s is then corresponding first body movement signal ... ... of a cycle, the 60th 30s
Corresponding first EEG signals are then the 60th period corresponding first EEG signals, the dynamic letter of corresponding first body of the 60th 30s
It number is then the 60th period corresponding first body movement signal.
S103, the first EEG signals corresponding to each period carry out fisrt feature extraction and determine that each period is corresponding respectively
The first brain electrical feature, the first brain electrical feature is used to indicate the sleep situation of change of user.
In the embodiment of the present invention, the can be carried out by corresponding to each period the first EEG signals of following steps
One feature extraction:
One, corresponding low frequency EEG signals of each period high frequency EEG signals corresponding with each period are obtained.Here, may be used
By obtaining corresponding low frequency EEG signals of each period high frequency EEG signals corresponding with each period in a manner of following three kinds.
First way is the low-pass filter corresponding to each period first of first frequency threshold value by cutoff frequency
EEG signals are filtered to obtain corresponding low frequency EEG signals of each period, and are first frequency threshold value by cutoff frequency
High-pass filter the first EEG signals corresponding to each period are filtered to obtain corresponding high frequency EEG signals of each period.
Here, low frequency EEG signals are the EEG signals lower than first frequency threshold value, and high frequency EEG signals are higher than first frequency threshold value
EEG signals.First frequency threshold value can be the frequency of 8Hz, or the numerical value such as 3Hz, 5Hz, 10Hz.
As shown in Figure 2 a, Fig. 2 a is a first EEG signals schematic diagram provided in an embodiment of the present invention, in figure, abscissa
For frequency, ordinate is amplitude (unit: dB), and the frequency of the first EEG signals is 0.3-30Hz.It is 8Hz's by cutoff frequency
Low-pass filter is filtered the first EEG signals in Fig. 2 a to obtain low frequency EEG signals as shown in Figure 2 b, and frequency is
0.3-8Hz.The first EEG signals in Fig. 2 a are filtered to obtain in Fig. 2 c by the high-pass filter that cutoff frequency is 8Hz
High frequency EEG signals, frequency 8-30Hz.
The second way is the low-pass filter corresponding to each period first of first frequency threshold value by cutoff frequency
EEG signals are filtered to obtain corresponding low frequency EEG signals of each period, and pass through corresponding first brain telecommunications of each period
Number corresponding low frequency EEG signals of each period are subtracted, obtains corresponding high frequency EEG signals of each period.
As shown in Figure 2 a, the frequency of the first EEG signals is 0.3-30Hz, the low pass for being 8Hz by cutoff frequency in Fig. 2 a
Filter is filtered to obtain the low frequency EEG signals in Fig. 2 b to the first EEG signals in Fig. 2 a, and frequency 0.3-8Hz leads to
The first EEG signals crossed in Fig. 2 a subtract the low frequency EEG signals, obtain corresponding high frequency EEG signals, frequency 8-30Hz.
The third mode is the high-pass filter corresponding to each period first of first frequency threshold value by cutoff frequency
EEG signals are filtered to obtain corresponding high frequency EEG signals of each period, and pass through corresponding first brain telecommunications of each period
Number corresponding high frequency EEG signals of each period are subtracted, obtains corresponding low frequency EEG signals of each period.
As shown in Figure 2 a, the frequency of the first EEG signals is 0.3-30Hz, the high pass for being 8Hz by cutoff frequency in Fig. 2 a
Filter is filtered to obtain the high frequency EEG signals in Fig. 2 c to the first EEG signals in Fig. 2 a, and frequency 8-30Hz leads to
The first EEG signals crossed in Fig. 2 a subtract the high frequency EEG signals, obtain corresponding low frequency EEG signals, frequency 0.3-
8Hz。
Two, each period corresponding first sample entropy and corresponding second sample entropy of each period are calculated.Here,
One sample entropy is the sample entropy of high frequency EEG signals, and the second sample entropy is the sample entropy of low frequency EEG signals.
Sample Entropy is by generating the probability size of new model in metric signal come measure time sequence complexity, new model
The probability of generation is bigger, and the complexity of sequence is bigger, i.e., EEG signals randomness is bigger, complexity is higher, and (i.e. user sleeps
Dormancy degree is shallower), then sample entropy is bigger;Conversely, EEG signals are more regular (i.e. the sleep degree of user is deeper), sample entropy
It is smaller.
For time series { q (t) }=q (1), the q (2) being made of T data ..., q (T), the calculation method of Sample Entropy
It is as follows:
(1) sequence vector that an array dimension is w, Qw (1) ..., Qw (T-w+1), wherein Qw (u)={ q are formed by serial number
(u),q(u+1),…,q(u+w-1)},1≤u≤T-w+1.These vectors represent the value of the w continuous q since u point.
(2) the distance between definition vector Qw (u) and Qw (v) d [Qw (u), Qw (v)] are maximum poor in the two corresponding element
The absolute value of value.That is:
D [Qw (u), Qw (v)]=maxK=0 ..., w-1(|q(u+k)-q(v+k)|)
(3) v (1≤v≤T-w, v of r is less than or equal to for given Qw (u), statistics the distance between Qw (u) and Qw (v)
≠ u) number, and be denoted as Cu.For 1≤v≤T-w, define:
(4) C is defined(w)(r) are as follows:
(5) increase dimension to w+1, calculate Qw+1 (u) and Qw+1 (v) (1≤v≤T-w, v ≠ u) distance less than or equal to r's
Number, as Eu。Is defined as:
(6) E is defined(w)(r) are as follows:
C(w)(r) it is probability that two sequences match w point at similar tolerance r, and E(w)It (r) is two sequences match w+
The probability of 1 point.Sample Entropy is defined as:It, can when T is finite value
To be estimated with following formula:Here, T is the time span and sample rate in period
Product.
Finally, first sample entropy and the second sample entropy can be obtained by the above method.
Three, corresponding first sample entropy of each period (the sample entropy of high frequency EEG signals) is corresponding with each period
The ratio of the second sample entropy (the sample entropy of low frequency EEG signals) be determined as corresponding first brain electrical feature of each period
F1.For example, obtaining first sample entropy by above-mentioned Sample Entropy calculation method is the 0.6, second Sample Entropy by taking a cycle as an example
When value is 0.3, then the period corresponding first brain electrical feature
S104, the first EEG signals corresponding to each period carry out second feature extraction and determine that each period is corresponding respectively
The second brain electrical feature, the second brain electrical feature is used to indicate the brain active degree of user.
In the embodiment of the present invention, the can be carried out by corresponding to each period the first EEG signals of following steps
Two feature extractions:
One, it is filtered to obtain each period correspondence by bandpass filter the first EEG signals corresponding to each period
Third EEG signals.Here, the first cutoff frequency of bandpass filter be second frequency threshold value, second section of bandpass filter
Only frequency is third frequency threshold, and second frequency threshold value is less than third frequency threshold, and third EEG signals are then greater than the second frequency
Rate threshold value and the signal for being less than third frequency threshold.Here, second frequency threshold value can be 8Hz, and third frequency threshold can be
12Hz。
As shown in Figure 3a, Fig. 3 a is a first EEG signals schematic diagram provided in an embodiment of the present invention, in figure, abscissa
For frequency, ordinate is amplitude, and the frequency of the first EEG signals is 1-18Hz.It is 8Hz and second section by the first cutoff frequency
Only frequency is that the bandpass filter of 12Hz is filtered the first EEG signals in Fig. 3 a, and obtained third EEG signals are as schemed
Shown in 3b, the frequency of the third EEG signals is 8-12Hz.
Two, the corresponding energy value of corresponding third EEG signals of each period is determined.Energy balane formula are as follows:Wherein, P is energy value, EEGiFor by the first sample rate to the first EEG signals in each period into
The corresponding value of each third EEG signals that row sampling obtains, L (EEG) are the third EEG signals sampled in each period
Quantity.Here, if the first sample rate of selection is 500Hz, period 30s, then L (EEG) is 30*500=15000, i.e. in 30s
The first EEG signals in each period are sampled to obtain 15000 third EEG signals,For to being adopted in 30s
Square summation for the corresponding value of 15000 third EEG signals that sample obtains.
Citing is to be illustrated energy value calculation formula.For example, when the sample rate of selection is 3Hz, the period is 2s, L
It (EEG) is 2*3=6,
Three, corresponding energy value of each period and the ratio of the first energy value are determined as corresponding second brain of each period
Electrical feature F2.Here, the first energy value is the corresponding energy value of a cycle in each period, then a cycle is corresponding
Second brain electrical feature F2 is equal to 1, and here, a cycle is then first 30s corresponding period in first time period.Example
Such as, the corresponding energy value of a cycle is 0.8, the corresponding energy value of second period is 0.4, third period corresponding energy
Magnitude is 0.2, then the corresponding second brain electrical feature of a cycleThe corresponding second brain electricity of second period is special
SignThird period corresponding second brain electrical feature
S105, the first body movement signal corresponding to each period carries out third feature extraction and determines that each period is corresponding respectively
The first body move feature, the first body moves feature and is used to indicate the motion conditions of user.
In the embodiment of the present invention, the can be carried out by corresponding to each period the first body movement signal of following steps
Three feature extractions:
One, the standard deviation of corresponding first body movement signal of each period is calculated separately.It is corresponding to calculate separately each period
The corresponding value of the first body movement signal standard deviation, obtain the standard of the corresponding value of corresponding first body movement signal of each period
Difference.
Two, the quantity of corresponding third body movement signal of each period is determined as corresponding first body of each period and moves feature
F3.Here, third body movement signal is the body movement signal that absolute value is greater than G times of standard deviation, and G is the positive integer less than or equal to 3, example
Such as, G can be equivalent for 1,2,3.
By taking a cycle as an example, the standard deviation of corresponding each first body movement signal of a cycle is calculated, it will be in the period
The first body movement signal that absolute value is greater than G times of standard deviation in each first body movement signal sets 1, sets 1 the first body movement signal representative
User's body is in the state of movement in the first body movement signal corresponding period, as user sleeps in turn or other changes
The state of appearance;Absolute value in first body movement signal each in the period is less than or equal to the first body movement signal of G times of standard deviation
0 is set, 0 the first body movement signal is set and represents user's body in the first body movement signal corresponding period and be in the shape not moved
State.Corresponding first body of a cycle move feature F3 be then set 1 the first body movement signal quantity.
For example, working as the first body movement signal that absolute value in corresponding first body movement signal of a cycle is greater than 3 times of standard deviations
Quantity be 100, and absolute value is less than or equal to the dynamic letter of the first body of 3 times of standard deviations in the period corresponding first body movement signal
Number quantity be 1400, then the quantity of 1 the first body movement signal built in the period be 100, set the quantity of 0 the first body movement signal
It is 1400, then it is 100 that the period corresponding first body, which moves feature F3,.
S106 moves feature according to corresponding first brain electrical feature of each period, the second brain electrical feature, the first body and generates feature
Matrix, eigenmatrix are used to indicate the sleep quality situation of user, and eigenmatrix is the matrix of 3*N, and N is the quantity in period.
Specifically, due to the corresponding first brain electrical feature of each period, the corresponding second brain electrical feature of each period,
Each period, corresponding first body moved feature, then eigenmatrix is the matrix of 3*N, when N is the quantity, i.e. user the first in period
Between period in section quantity.For example, the corresponding F1 of a cycle is 0.8, F2 0.5, F3 100 when N is 2, second
Period corresponding F1 is 0.3, F2 0.5, F3 50, then eigenmatrix are as follows:
S107 determines Sleep Quality Index value of the user in first time period according to eigenmatrix.
In the embodiment of the present invention, Sleep Quality Index value of the user in first time period is determined according to eigenmatrix, is slept
Dormancy Quality index value is bigger, and the sleep quality for representing user in first time period is better.Determine user according to eigenmatrix
The concrete mode of Sleep Quality Index value in one period refers to the corresponding embodiment of Fig. 4, does not do excessive description herein.
In the embodiment of the present invention, it is divided by the EEG signals in the user's sleep procedure that will acquire with body movement signal
The multiple time spans identical period, and feature extraction is carried out to the EEG signals in each period and obtains each period corresponding the
One brain electrical feature, the second brain electrical feature carry out feature extraction to the body movement signal in each period and obtain each period corresponding the
The dynamic feature of one, generates eigenmatrix according to corresponding three features of each period, is met by searching in eigenmatrix
The period of condition obtains three parameters relevant to Sleep Quality Index value, carries out user is calculated to three parameters and sleep
Dormancy Quality index value determines the sleep quality situation of user according to Sleep Quality Index value.By to corresponding brain of each period
Feature extraction three obtained feature reflects the sleep situation of change of user to electrical feature respectively, user sleeps with body dynamic feature progress
The motion conditions in brain active degree and user's sleep procedure during dormancy, due to from multiple dimensional analysis user's
Sleep quality improves the accuracy of user's sleep quality assessment.
In one possible implementation, determine that sleep quality of the user in first time period refers to according to eigenmatrix
The specific steps of numerical value are as shown in figure 4, Fig. 4 is a kind of process signal of sleep quality appraisal procedure provided in an embodiment of the present invention
Figure, as shown, this method comprises:
S201 determines sequence valve of the period 1 in first time period according to eigenmatrix, and the period 1 is the first brain
Electrical feature less than the first sleep threshold and the second brain electrical feature less than the first alive threshold a cycle.
Here, the period 1 is to meet the first brain electrical feature F1 for the first time less than the first sleep threshold and the second brain electrical feature
Period of the F2 less than the first alive threshold.Sequence valve of the period 1 in first time period is N1, then N1 is the period 1
Sequence of the corresponding 30s in multiple 30s in first time period.For example, the 5th period in first time period is corresponding
First brain electrical feature F1 is less than the first sleep threshold and the second brain electrical feature F2 is less than the first alive threshold, and in first time period
Preceding 4 periods be all unsatisfactory for the first brain electrical feature F1 less than the first sleep threshold and the second brain electrical feature F2 is active less than first
Threshold value, then sequence valve of the period 1 in first time period is 5, i.e. N1=5.
Here, the first sleep threshold can be the positive number less than or equal to 1, such as the arbitrary values such as 0.1,0.3,0.8.First
Alive threshold can be the positive number less than or equal to 1, such as the arbitrary values such as 0.2,0.5,0.8.
The inverse of difference is determined as the first parameter by S202, and difference is sequence valve of the period 1 in first time period
And 1 difference.
First parameter is the inverse of the difference of the sequence valve N1 and 1 in first time period, i.e.,For example, when first
When sequence valve N1 of the period in first time period is 5, the first parameterHere, the first parameter is user
Drowsy state in first time period, the corresponding numerical value of the first parameter is bigger, and the time for representing user's sleep is more early.
S203 determines the quantity of second round according to eigenmatrix, and second round is that the first brain electrical feature is slept less than first
Dormancy threshold value and the first body move period of the feature less than the first movement threshold.
Here, second round is the first brain electrical feature F1 less than the first sleep threshold and the first body moves feature F3 less than first
The period of movement threshold, the quantity of second round are N2.Here, the first movement threshold is according to the sample rate time corresponding with the period
Length determines, for example, then first moving when the sample rate of the first body movement signal is 50Hz, period corresponding time span is 30s
Threshold value can be any one integer in 0-1500, such as can be the arbitrary values such as 100,200.
The ratio of the quantity of second round and N is determined as the second parameter by S204.
It here, is the quantity in the period in user's first time period according to step S106 N.Then the second parameterFor example, when meeting the first brain electrical feature F1 less than the first sleep threshold and the first body in the period in first time period
Dynamic feature F3 is 500 less than the amount of cycles of the first movement threshold, when the quantity in the period in first time period is 1000, thenSecond parameter is Sleep efficiency of the user in first time period, i.e. the corresponding numerical value of the second parameter is got over
It is higher to represent user's Sleep efficiency greatly.
S205 determines the quantity of period 3 according to eigenmatrix, and the period 3 is that the first brain electrical feature is slept less than second
Dormancy threshold value and the first body move period of the feature less than the second movement threshold, and the second sleep threshold is less than the first sleep threshold, and second
Movement threshold is less than the first movement threshold.
Here, the period 3 is the first brain electrical feature F1 less than the second sleep threshold and the first body moves feature F3 less than second
The period of movement threshold.The quantity of period 3 is N3.Second sleep threshold can be the positive number less than or equal to 1, such as
0.1, the arbitrary values such as 0.3,0.8.Second movement threshold is determined according to sample rate time span corresponding with the period, for example, first
The sample rate of body movement signal is 50Hz, period corresponding time span is 30s, then the second movement threshold can be in 0-1500
Any one integer, such as can be the arbitrary values such as 50,100,200.Second sleep threshold is less than the first sleep threshold, the second fortune
Threshold value is moved less than the first movement threshold.
The ratio of the quantity of period 3 and the quantity of second round is determined as third parameter by S206.
Third parameterFor example, when meeting the first brain electrical feature F1 less than second in the period in first time period
It is 400 that sleep threshold and the first body, which move feature F3 less than the quantity in the period of the second movement threshold, meets the first brain electrical feature F1
Less than the first sleep threshold and the first body is when to move feature F3 less than the amount of cycles of the first movement threshold be 800, thenThird parameter is deep sleep ratio of the user in first time period, the i.e. corresponding numerical value of third parameter
It is bigger that represent user's deep sleep time longer.
Above-mentioned the step of determining the first parameter, the second parameter and third parameter according to eigenmatrix, can execute side by side,
It can first carry out and the first parameter is determined according to eigenmatrix or first carries out according to the second parameter of eigenmatrix or first carries out
The step of determining third parameter according to eigenmatrix is not defined this sequentially in the embodiment of the present invention.
S207 assesses formula calculating sleep quality according to the first parameter, the second parameter, third parameter and sleep quality and refers to
Numerical value.
Here, sleep quality assessment formula isWherein, S is sleep matter
Volume index value, H1For the first parameter, H2For the second parameter, H3For third parameter.Here, Sleep Quality Index value is oneself of 1-100
So number, Sleep Quality Index value is bigger, and the sleep quality for representing user in first time period is better.
In the embodiment of the present invention, it is divided by the EEG signals in the user's sleep procedure that will acquire with body movement signal
The multiple time spans identical period, and feature extraction is carried out to the EEG signals in each period and obtains each period corresponding the
One brain electrical feature, the second brain electrical feature carry out feature extraction to the body movement signal in each period and obtain each period corresponding the
The dynamic feature of one, generates eigenmatrix according to corresponding three features of each period, is met by searching in eigenmatrix
The period of condition obtains three parameters relevant to Sleep Quality Index value, carries out user is calculated to three parameters and sleep
Dormancy Quality index value determines the sleep quality situation of user according to Sleep Quality Index value.By to corresponding brain of each period
Feature extraction three obtained feature reflects the sleep situation of change of user to electrical feature respectively, user sleeps with body dynamic feature progress
The motion conditions in brain active degree and user's sleep procedure during dormancy, due to from multiple dimensional analysis user's
Sleep quality improves the accuracy of user's sleep quality assessment.
The method of inventive embodiments is described above, the device of inventive embodiments is described below.
It is a kind of composed structure schematic diagram of sleep quality assessment device provided in an embodiment of the present invention referring to Fig. 5, Fig. 5,
The device 30 includes:
Signal acquisition module 301, for obtaining the dynamic letter of first EEG signals and first body of the user in first time period
Number, the first time period is user's sleep procedure corresponding period;
Period division module 302, for drawing the first time period using preset duration as the time span of a cycle
It is divided into multiple periods, determines corresponding first EEG signals of each period and the first body movement signal respectively;
Fisrt feature extraction module 303, for carrying out first to each period corresponding first EEG signals respectively
Feature extraction determines that corresponding first brain electrical feature of each period, the first brain electrical feature are used to indicate the sleep of user
Situation of change;
Second feature extraction module 304, for carrying out second to each period corresponding first EEG signals respectively
Feature extraction determines that corresponding second brain electrical feature of each period, the second brain electrical feature are used to indicate the brain of user
Active degree;
Third feature extraction module 305, for carrying out third to each period corresponding first body movement signal respectively
Feature extraction determines that corresponding first body of each period moves feature, and first body moves the movement that feature is used to indicate user
Situation;
Matrix generation module 306, for according to each period corresponding first brain electrical feature, the second brain electrical feature,
First body moves feature and generates eigenmatrix, and the eigenmatrix is used to indicate the sleep quality situation of user, the eigenmatrix
For the matrix of 3*N, N is the quantity in the period;
Index determining module 307, for determining the user in the first time period according to the eigenmatrix
Sleep Quality Index value.
In a kind of possible design, the signal acquisition module 301 is specifically used for:
Acquire second EEG signals and second body movement signal of the user in the first time period, second body
Dynamic signal includes the acceleration degree series on X, Y, Z axis direction;
Second EEG signals are filtered by filter, obtain first EEG signals;
Resultant acceleration is carried out to the acceleration degree series on the X, Y, Z axis direction, conjunction body movement signal is calculated;
The corresponding fit dynamic signal set of body movement signal will be closed to target each in the conjunction body movement signal to carry out at mean value
It manages obtained signal and is determined as first body movement signal, the fit dynamic signal set includes that the target closes body movement signal
First A is closed the rear B conjunction body movement signal that body movement signal, target conjunction body movement signal and the target close body movement signal, A, B
It is positive integer, and the sum of A, B and 1 are the number of the conjunction body movement signal in the fit dynamic signal set.
In a kind of possible design, the fisrt feature extraction module 303 is specifically used for:
Corresponding low frequency EEG signals of each period are determined according to each period corresponding first EEG signals
High frequency EEG signals corresponding with each period, the low frequency EEG signals are the brain telecommunications lower than first frequency threshold value
Number, the high frequency EEG signals are the EEG signals higher than first frequency threshold value;
Calculate corresponding first sample entropy of each period and corresponding second sample entropy of each period, institute
The sample entropy that first sample entropy is the high frequency EEG signals is stated, the second sample entropy is the low frequency EEG signals
Sample entropy;
By the ratio of each the period corresponding first sample entropy and corresponding second sample entropy of each period
Value is determined as corresponding first brain electrical feature of each period.
In a kind of possible design, the fisrt feature extraction module 303 is specifically used for:
By low-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first brain telecommunications
It number is filtered to obtain corresponding low frequency EEG signals of each period, and is the height of first frequency threshold value by cutoff frequency
Bandpass filter is filtered to obtain corresponding high frequency brain of each period to each period corresponding first EEG signals
Electric signal, alternatively,
By low-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first brain telecommunications
It number is filtered to obtain corresponding low frequency EEG signals of each period, and passes through each period corresponding described first
EEG signals subtract the corresponding low frequency EEG signals of each period, obtain corresponding high frequency brain electricity of each period
Signal, alternatively,
By high-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first brain telecommunications
It number is filtered to obtain corresponding high frequency EEG signals of each period, and passes through each period corresponding described first
EEG signals subtract the corresponding high frequency EEG signals of each period, obtain corresponding low frequency brain electricity of each period
Signal.
In a kind of possible design, the second feature extraction module 304 is specifically used for:
Each period corresponding first EEG signals are filtered to obtain each week by bandpass filter
Phase corresponding third EEG signals, the first cutoff frequency of the bandpass filter are second frequency threshold value, the bandpass filtering
Second cutoff frequency of device is third frequency threshold, and the second frequency threshold value is less than the third frequency threshold;
Determine the corresponding energy value of corresponding third EEG signals of each period;
Corresponding energy value of each period is determined as each period corresponding second with the ratio of the first energy value
Brain electrical feature, first energy value are the corresponding energy value of a cycle in each period.
In a kind of possible design, the third feature extraction module 305 is specifically used for:
Calculate separately the standard deviation of corresponding first body movement signal of each period;
By each period, the quantity of corresponding third body movement signal is determined as corresponding first body of each period
Dynamic feature, the third body movement signal are the body movement signal that absolute value is greater than G times of standard deviation, and G is just whole less than or equal to 3
Number.
In a kind of possible design, the index determining module 307 is specifically used for:
The first parameter, the second parameter and third parameter, first parameter, the second parameter are determined according to the eigenmatrix
With the parameter that third parameter is for determining Sleep Quality Index value;
Formula, which is assessed, according to first parameter, second parameter, the third parameter and sleep quality calculates institute
Sleep Quality Index value is stated, the sleep quality assessment formula is Wherein, S
For the Sleep Quality Index value, H1For first parameter, H2For second parameter, H3For the third parameter.
In a kind of possible design, the index determining module 307 is specifically used for:
Sequence valve of the period 1 in the first time period is determined according to the eigenmatrix, and the period 1 is
The first brain electrical feature less than the first sleep threshold and the second brain electrical feature less than the first alive threshold the first week
Phase;
The inverse of difference is determined as the first parameter, the difference is the difference of the sequence valve and 1 in the first time period.
In a kind of possible design, the index determining module 307 is specifically used for:
The quantity of second round is determined according to the eigenmatrix, the second round is that the first brain electrical feature is less than
First sleep threshold and first body move period of the feature less than the first movement threshold;
The ratio of the quantity of the second round and N is determined as second parameter.
In a kind of possible design, the index determining module 307 is specifically used for:
The quantity of period 3 is determined according to the eigenmatrix, the period 3 is that the first brain electrical feature is less than
Second sleep threshold and first body move period of the feature less than the second movement threshold, and second sleep threshold is less than described
First sleep threshold, second movement threshold are less than first movement threshold;
The ratio of the quantity of the period 3 and the quantity of the second round is determined as the third parameter.
It should be noted that unmentioned content can be found in the description of embodiment of the method in the corresponding embodiment of Fig. 5, here
It repeats no more.
In the embodiment of the present invention, it is divided by the EEG signals in the user's sleep procedure that will acquire with body movement signal
The multiple time spans identical period, and feature extraction is carried out to the EEG signals in each period and obtains each period corresponding the
One brain electrical feature, the second brain electrical feature carry out feature extraction to the body movement signal in each period and obtain each period corresponding the
The dynamic feature of one, generates eigenmatrix according to corresponding three features of each period, is met by searching in eigenmatrix
The period of condition obtains three parameters relevant to Sleep Quality Index value, carries out user is calculated to three parameters and sleep
Dormancy Quality index value determines the sleep quality situation of user according to Sleep Quality Index value.By to corresponding brain of each period
Feature extraction three obtained feature reflects the sleep situation of change of user to electrical feature respectively, user sleeps with body dynamic feature progress
The motion conditions in brain active degree and user's sleep procedure during dormancy, due to from multiple dimensional analysis user's
Sleep quality improves the accuracy of user's sleep quality assessment.
It is a kind of composed structure schematic diagram of sleep quality assessment device provided in an embodiment of the present invention referring to Fig. 6, Fig. 6,
The device includes processor 401, memory 402 and input/output interface 403.Processor 401 is connected to memory 402 and defeated
Enter output interface 403, such as processor 401 can be connected to memory 402 and input/output interface 403 by bus.
Processor 401 is configured as that the device of the sleep quality assessment is supported to execute sleep quality described in Fig. 1, Fig. 4
Corresponding function in the method for assessment.The processor 401 can be central processing unit (central processing unit,
CPU), network processing unit (network processor, NP), hardware chip or any combination thereof.Above-mentioned hardware chip can be with
It is specific integrated circuit (application specific integrated circuit, ASIC), programmable logic device
(programmable logic device, PLD) or combinations thereof.Above-mentioned PLD can be Complex Programmable Logic Devices
(complex programmable logic device, CPLD), field programmable gate array (field-
Programmable gate array, FPGA), Universal Array Logic (generic array logic, GAL) or its any group
It closes.
402 memory of memory is for storing program code etc..Memory 402 may include volatile memory
(volatile memory, VM), such as random access memory (random access memory, RAM);Memory 402
It may include nonvolatile memory (non-volatile memory, NVM), such as read-only memory (read-only
Memory, ROM), flash memory (flash memory), hard disk (hard disk drive, HDD) or solid state hard disk
(solid-state drive, SSD);Memory 402 can also include the combination of the memory of mentioned kind.
The input/output interface 403 is for input or output data.
Processor 401 can call said program code to execute following operation:
First EEG signals and first body movement signal of the user in first time period are obtained, the first time period is to use
The family sleep procedure corresponding period;
The first time period is divided into multiple periods using preset duration as the time span of a cycle, is determined respectively
Each period corresponding first EEG signals and the first body movement signal in the multiple period;
It carries out fisrt feature to each period corresponding first EEG signals respectively and extracts to determine each period
Corresponding first brain electrical feature, the first brain electrical feature are used to indicate the sleep situation of change of the user;
It carries out second feature to each period corresponding first EEG signals respectively and extracts to determine each period
Corresponding second brain electrical feature, the second brain electrical feature are used to indicate the brain active degree of the user;
It carries out third feature to each period corresponding first body movement signal respectively and extracts to determine each period
Corresponding first body moves feature, and first body moves the motion conditions that feature is used to indicate the user;
Feature, which is moved, according to each period corresponding first brain electrical feature, the second brain electrical feature, the first body generates feature
Matrix, the eigenmatrix are used to indicate the sleep quality situation of the user, and the eigenmatrix is the matrix of 3*N, and N is institute
State the quantity in period;
Sleep Quality Index value of the user in the first time period is determined according to the eigenmatrix.It needs
It is bright, the realization of each operation can also correspond to referring to Fig.1, the corresponding description of embodiment of the method shown in Fig. 4;The processing
Device 401 can also cooperate other operations executed in above method embodiment with input/output interface 403.
The embodiment of the present invention also provides a kind of computer storage medium, and the computer storage medium is stored with computer journey
Sequence, the computer program include program instruction, and described program instruction executes the computer such as
Method described in previous embodiment, the computer can assess a part of device for sleep quality mentioned above.Such as
For above-mentioned processor 401.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (13)
1. a kind of sleep quality appraisal procedure characterized by comprising
First EEG signals and first body movement signal of the user in first time period are obtained, the first time period is the use
The family sleep procedure corresponding period;
The first time period is divided into multiple periods using preset duration as the time span of a cycle, respectively determine described in
Each period corresponding first EEG signals and the first body movement signal in multiple periods;
It carries out fisrt feature to each period corresponding first EEG signals respectively and extracts to determine that each period is corresponding
The first brain electrical feature, the first brain electrical feature is used to indicate the sleep situation of change of the user;
It carries out second feature to each period corresponding first EEG signals respectively and extracts to determine that each period is corresponding
The second brain electrical feature, the second brain electrical feature is used to indicate the brain active degree of the user;
It carries out third feature to each period corresponding first body movement signal respectively and extracts to determine that each period is corresponding
The first body move feature, first body moves feature and is used to indicate the motion conditions of the user;
Feature, which is moved, according to each period corresponding first brain electrical feature, the second brain electrical feature, the first body generates eigenmatrix,
The eigenmatrix is used to indicate the sleep quality situation of the user, and the eigenmatrix is the matrix of 3*N, and N is the week
The quantity of phase;
Sleep Quality Index value of the user in the first time period is determined according to the eigenmatrix.
2. the method according to claim 1, wherein the first brain electricity for obtaining user in first time period
Signal and the first body movement signal, comprising:
Acquire second EEG signals and second body movement signal of the user in the first time period, the dynamic letter of second body
Number include X, Y, Z axis direction on acceleration degree series;
Second EEG signals are filtered by filter, obtain first EEG signals;
Resultant acceleration is carried out to the acceleration degree series on the X, Y, Z axis direction, conjunction body movement signal is calculated;
The corresponding fit dynamic signal set progress average value processing of body movement signal will be closed to target each in the conjunction body movement signal to obtain
To signal be determined as first body movement signal, the fit dynamic signal set includes the preceding A that the target closes body movement signal
A rear B conjunction body movement signal closed body movement signal, target conjunction body movement signal and the target and close body movement signal, A, B are equal
For positive integer, and the sum of A, B and 1 are the number of the conjunction body movement signal in the fit dynamic signal set.
3. the method according to claim 1, wherein described respectively to each period corresponding first brain electricity
Signal carries out fisrt feature extraction and determines corresponding first brain electrical feature of each period, comprising:
Corresponding low frequency EEG signals of each period and institute are determined according to each period corresponding first EEG signals
Corresponding high frequency EEG signals of each period are stated, the low frequency EEG signals are the EEG signals lower than first frequency threshold value, institute
Stating high frequency EEG signals is the EEG signals higher than the first frequency threshold value;
Calculate corresponding first sample entropy of each period and corresponding second sample entropy of each period, described
One sample entropy is the sample entropy of the high frequency EEG signals, and the second sample entropy is the sample of the low frequency EEG signals
This entropy;
The ratio of each period corresponding first sample entropy the second sample entropy corresponding with each period is true
It is set to corresponding first brain electrical feature of each period.
4. according to the method described in claim 3, it is characterized in that, described according to each period corresponding first brain telecommunications
Number determine each period corresponding low frequency EEG signals high frequency EEG signals corresponding with each period, comprising:
By low-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first EEG signals into
Row filtering obtains corresponding low frequency EEG signals of each period, and is filtered by the high pass that cutoff frequency is first frequency threshold value
Wave device is filtered to obtain corresponding high frequency brain telecommunications of each period to each period corresponding first EEG signals
Number, alternatively,
By low-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first EEG signals into
Row filtering obtains corresponding low frequency EEG signals of each period, and passes through the corresponding first brain electricity of each period
Signal subtracts the corresponding low frequency EEG signals of each period, obtains corresponding high frequency brain telecommunications of each period
Number, alternatively,
By high-pass filter that cutoff frequency is first frequency threshold value to each period corresponding first EEG signals into
Row filtering obtains corresponding high frequency EEG signals of each period, and passes through the corresponding first brain electricity of each period
Signal subtracts the corresponding high frequency EEG signals of each period, obtains corresponding low frequency brain telecommunications of each period
Number.
5. the method according to claim 1, wherein described respectively to each period corresponding first brain electricity
Signal carries out second feature extraction and determines corresponding second brain electrical feature of each period, comprising:
Each period corresponding first EEG signals are filtered to obtain each period pair by bandpass filter
The third EEG signals answered, the first cutoff frequency of the bandpass filter are second frequency threshold value, the bandpass filter
Second cutoff frequency is third frequency threshold, and the second frequency threshold value is less than the third frequency threshold;
Determine the corresponding energy value of corresponding third EEG signals of each period;
The corresponding energy value of each period is determined as each period corresponding second with the ratio of the first energy value
Brain electrical feature, first energy value are the corresponding energy value of a cycle in each period.
6. the method according to claim 1, wherein described dynamic to each period corresponding first body respectively
Signal carries out third feature extraction and determines that corresponding first body of each period moves feature, comprising:
Calculate separately the standard deviation of corresponding first body movement signal of each period;
The quantity of each period corresponding third body movement signal is determined as the dynamic spy of corresponding first body of each period
Sign, the third body movement signal are the body movement signal that absolute value is greater than G times of standard deviation, and G is the positive integer less than or equal to 3.
7. the method according to claim 1, wherein described determine the user in institute according to the eigenmatrix
State the Sleep Quality Index value in first time period, comprising:
The first parameter, the second parameter and third parameter are determined according to the eigenmatrix, first parameter, the second parameter and the
Three parameters are the parameter for determining Sleep Quality Index value;
It is slept according to the assessment formula calculating of first parameter, second parameter, the third parameter and sleep quality
Dormancy Quality index value, the sleep quality assessment formula are Wherein, S is institute
State Sleep Quality Index value, H1For first parameter, H2For second parameter, H3For the third parameter.
8. being wrapped the method according to the description of claim 7 is characterized in that described determine the first parameter according to the eigenmatrix
It includes:
Sequence valve of the period 1 in the first time period is determined according to the eigenmatrix, and the period 1 is described
First brain electrical feature less than the first sleep threshold and the second brain electrical feature less than the first alive threshold a cycle;
The inverse of difference is determined as the first parameter, the difference is the difference of the sequence valve and 1 in the first time period.
9. being wrapped the method according to the description of claim 7 is characterized in that described determine the second parameter according to the eigenmatrix
It includes:
The quantity of second round is determined according to the eigenmatrix, the second round is the first brain electrical feature less than first
Sleep threshold and first body move period of the feature less than the first movement threshold;
The ratio of the quantity of the second round and N is determined as second parameter.
10. being wrapped the method according to the description of claim 7 is characterized in that described determine third parameter according to the eigenmatrix
It includes:
The quantity of period 3 is determined according to the eigenmatrix, the period 3 is the first brain electrical feature less than second
Sleep threshold and first body move period of the feature less than the second movement threshold, and second sleep threshold is less than described first
Sleep threshold, second movement threshold are less than first movement threshold;
The ratio of the quantity of the period 3 and the quantity of the second round is determined as the third parameter.
11. a kind of sleep quality assesses device characterized by comprising
Signal acquisition module, it is described for obtaining first EEG signals and first body movement signal of the user in first time period
First time period is user's sleep procedure corresponding period;
Period division module, it is multiple for being divided into the first time period using preset duration as the time span of a cycle
Period determines each period corresponding first EEG signals and the first body movement signal in the multiple period respectively;
Fisrt feature extraction module, for carrying out fisrt feature extraction to each period corresponding first EEG signals respectively
Determine that corresponding first brain electrical feature of each period, the first brain electrical feature are used to indicate the sleep variation of the user
Situation;
Second feature extraction module, for carrying out second feature extraction to each period corresponding first EEG signals respectively
Determine that corresponding second brain electrical feature of each period, the brain that the second brain electrical feature is used to indicate the user are active
Degree;
Third feature extraction module, for carrying out third feature extraction to each period corresponding first body movement signal respectively
Determine that corresponding first body of each period moves feature, first body moves the movement feelings that feature is used to indicate the user
Condition;
Matrix generation module, for dynamic according to each period corresponding first brain electrical feature, the second brain electrical feature, the first body
Feature generates eigenmatrix, and the eigenmatrix is used to indicate the sleep quality situation of the user, and the eigenmatrix is 3*N
Matrix, N be the period quantity;
Index determining module, for determining sleep quality of the user in the first time period according to the eigenmatrix
Index value.
12. a kind of sleep quality assesses device, which is characterized in that described including processor, memory and input/output interface
Processor, memory and input/output interface are connected with each other, wherein and the input/output interface is used to input or output data,
The memory executes such as claim 1-10 for calling said program code for storing program code, the processor
Described in any item methods.
13. a kind of computer storage medium, which is characterized in that the computer storage medium is stored with computer program, described
Computer program includes program instruction, and described program is instructed when being executed by a processor, executed such as any one of claim 1-10
The method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811594779.9A CN109498001B (en) | 2018-12-25 | 2018-12-25 | Sleep quality evaluation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811594779.9A CN109498001B (en) | 2018-12-25 | 2018-12-25 | Sleep quality evaluation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109498001A true CN109498001A (en) | 2019-03-22 |
CN109498001B CN109498001B (en) | 2021-08-31 |
Family
ID=65755083
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811594779.9A Active CN109498001B (en) | 2018-12-25 | 2018-12-25 | Sleep quality evaluation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109498001B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111870250A (en) * | 2020-07-14 | 2020-11-03 | 深圳数联天下智能科技有限公司 | User state monitoring method and device, computing equipment and computer storage medium |
CN113367657A (en) * | 2020-03-10 | 2021-09-10 | 中国科学院脑科学与智能技术卓越创新中心 | Sleep quality evaluation method, device, equipment and storage medium based on high-frequency electroencephalogram |
CN114010206A (en) * | 2022-01-05 | 2022-02-08 | 深圳市心流科技有限公司 | Sleep plan customizing method, system and terminal based on electroencephalogram signals |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006008743A2 (en) * | 2004-07-21 | 2006-01-26 | Widemed Ltd. | Sleep quality indicators |
CN101236083A (en) * | 2008-03-06 | 2008-08-06 | 浙江大学 | Fast switching optical fibre gyroscope active and static data output method |
US20090292215A1 (en) * | 2003-05-15 | 2009-11-26 | Widemed Ltd | Sleep quality indicators |
US20110301487A1 (en) * | 2008-11-28 | 2011-12-08 | The University Of Queensland | Method and apparatus for determining sleep states |
US20120323085A1 (en) * | 2011-06-09 | 2012-12-20 | Takeda Haruto | Information processing device, information processing method, and information processing program |
CN103750820A (en) * | 2013-12-26 | 2014-04-30 | 沈阳熙康阿尔卑斯科技有限公司 | Method and device for monitoring sleep quality |
CN103961091A (en) * | 2014-04-15 | 2014-08-06 | 杭州电子科技大学 | Motor imagery electroencephalogram signal characteristic extracting method based on dual-tree complex wavelet sample entropy |
CN204358913U (en) * | 2014-12-13 | 2015-05-27 | 深圳市易特科信息技术有限公司 | For improving automatic temperature-regulator and the system of sleep quality |
US9202008B1 (en) * | 2007-06-08 | 2015-12-01 | Cleveland Medical Devices Inc. | Method and device for sleep analysis |
CN105496363A (en) * | 2015-12-15 | 2016-04-20 | 浙江神灯生物科技有限公司 | Method for classifying sleep stages on basis of sleep EGG (electroencephalogram) signal detection |
CN106175754A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Waking state detection device in sleep state analysis |
CN106175698A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Sleep cycle detection device in sleep state analysis |
WO2017067010A1 (en) * | 2015-10-24 | 2017-04-27 | 深圳市迈迪加科技发展有限公司 | Sleep evaluation display method and apparatus, and evaluation device |
CN106618560A (en) * | 2016-12-23 | 2017-05-10 | 北京怡和嘉业医疗科技股份有限公司 | Method and device for processing brain wave signals |
CN106682406A (en) * | 2016-12-12 | 2017-05-17 | 西北工业大学 | Sleep state monitoring method based on GM-GP algorithm |
CN107811635A (en) * | 2016-09-12 | 2018-03-20 | 深圳先进技术研究院 | A kind of health status sorting technique and device based on physiology signal |
CN107874750A (en) * | 2017-11-28 | 2018-04-06 | 华南理工大学 | Pulse frequency variability and the psychological pressure monitoring method and device of sleep quality fusion |
CN108201435A (en) * | 2017-12-06 | 2018-06-26 | 深圳和而泰数据资源与云技术有限公司 | Sleep stage determines method, relevant device and computer-readable medium |
WO2018154136A1 (en) * | 2017-02-27 | 2018-08-30 | Polar Electro Oy | Measuring and estimating sleep quality |
-
2018
- 2018-12-25 CN CN201811594779.9A patent/CN109498001B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090292215A1 (en) * | 2003-05-15 | 2009-11-26 | Widemed Ltd | Sleep quality indicators |
WO2006008743A2 (en) * | 2004-07-21 | 2006-01-26 | Widemed Ltd. | Sleep quality indicators |
US9202008B1 (en) * | 2007-06-08 | 2015-12-01 | Cleveland Medical Devices Inc. | Method and device for sleep analysis |
CN101236083A (en) * | 2008-03-06 | 2008-08-06 | 浙江大学 | Fast switching optical fibre gyroscope active and static data output method |
US20110301487A1 (en) * | 2008-11-28 | 2011-12-08 | The University Of Queensland | Method and apparatus for determining sleep states |
US20120323085A1 (en) * | 2011-06-09 | 2012-12-20 | Takeda Haruto | Information processing device, information processing method, and information processing program |
CN103750820A (en) * | 2013-12-26 | 2014-04-30 | 沈阳熙康阿尔卑斯科技有限公司 | Method and device for monitoring sleep quality |
CN103961091A (en) * | 2014-04-15 | 2014-08-06 | 杭州电子科技大学 | Motor imagery electroencephalogram signal characteristic extracting method based on dual-tree complex wavelet sample entropy |
CN204358913U (en) * | 2014-12-13 | 2015-05-27 | 深圳市易特科信息技术有限公司 | For improving automatic temperature-regulator and the system of sleep quality |
WO2017067010A1 (en) * | 2015-10-24 | 2017-04-27 | 深圳市迈迪加科技发展有限公司 | Sleep evaluation display method and apparatus, and evaluation device |
CN105496363A (en) * | 2015-12-15 | 2016-04-20 | 浙江神灯生物科技有限公司 | Method for classifying sleep stages on basis of sleep EGG (electroencephalogram) signal detection |
CN107811635A (en) * | 2016-09-12 | 2018-03-20 | 深圳先进技术研究院 | A kind of health status sorting technique and device based on physiology signal |
CN106175698A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Sleep cycle detection device in sleep state analysis |
CN106175754A (en) * | 2016-09-21 | 2016-12-07 | 广州视源电子科技股份有限公司 | Waking state detection device in sleep state analysis |
CN106682406A (en) * | 2016-12-12 | 2017-05-17 | 西北工业大学 | Sleep state monitoring method based on GM-GP algorithm |
CN106618560A (en) * | 2016-12-23 | 2017-05-10 | 北京怡和嘉业医疗科技股份有限公司 | Method and device for processing brain wave signals |
WO2018154136A1 (en) * | 2017-02-27 | 2018-08-30 | Polar Electro Oy | Measuring and estimating sleep quality |
CN107874750A (en) * | 2017-11-28 | 2018-04-06 | 华南理工大学 | Pulse frequency variability and the psychological pressure monitoring method and device of sleep quality fusion |
CN108201435A (en) * | 2017-12-06 | 2018-06-26 | 深圳和而泰数据资源与云技术有限公司 | Sleep stage determines method, relevant device and computer-readable medium |
Non-Patent Citations (2)
Title |
---|
李昕,孙小棋,蔡仁娟,范梦頔,侯永捷: "严肃游戏训练对脑功能状态改善作用研究", 《中国生物医学工程学报》 * |
郭全红 著: "《睡眠解析》", 30 June 2018 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113367657A (en) * | 2020-03-10 | 2021-09-10 | 中国科学院脑科学与智能技术卓越创新中心 | Sleep quality evaluation method, device, equipment and storage medium based on high-frequency electroencephalogram |
WO2021180028A1 (en) * | 2020-03-10 | 2021-09-16 | 中国科学院脑科学与智能技术卓越创新中心 | Method, apparatus and device for evaluating sleep quality on basis of high-frequency electroencephalography, and storage medium |
CN111870250A (en) * | 2020-07-14 | 2020-11-03 | 深圳数联天下智能科技有限公司 | User state monitoring method and device, computing equipment and computer storage medium |
CN114010206A (en) * | 2022-01-05 | 2022-02-08 | 深圳市心流科技有限公司 | Sleep plan customizing method, system and terminal based on electroencephalogram signals |
Also Published As
Publication number | Publication date |
---|---|
CN109498001B (en) | 2021-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109498001A (en) | Sleep quality appraisal procedure and device | |
Abdelhalim et al. | Phase-synchronization early epileptic seizure detector VLSI architecture | |
Beebe et al. | Charge injection limits of activated iridium oxide electrodes with 0.2 ms pulses in bicarbonate buffered saline (neurological stimulation application) | |
Zhang et al. | VLSI friendly ECG QRS complex detector for body sensor networks | |
WO2013145731A9 (en) | Pulse detection device, electronic apparatus, and program | |
JP4952162B2 (en) | Data processing apparatus, data processing method, and data processing program | |
CN104546007B (en) | Anti-interference processing method and device for fetal movement detection | |
CN107303177A (en) | Method and system for detecting T wave and P wave of electrocardiogram | |
CN106667439A (en) | Noise reducing method and device of electrocardiosignal | |
CN105852850A (en) | Method and related device for extracting respiratory signals from ECG (electrocardiogram) signals | |
CN108992054A (en) | A kind of pulse signal peak point detection method and device | |
CN106227355A (en) | A kind of Intelligent bracelet of the bright screen that realizes raising one's hand | |
Singh et al. | Design of digital IIR filter for noise reduction in ECG signal | |
CN106419865A (en) | Sleep apnea syndrome determining method based on vibration sensor | |
Yang et al. | Removal of pulse waveform baseline drift using cubic spline interpolation | |
CN116964963A (en) | Signal processing circuit and device | |
CN106529425A (en) | R-wave extraction method and system for ECG signals | |
Tripathi et al. | Study of various data compression techniques used in lossless compression of ECG signals | |
JP6010979B2 (en) | Pulsation detection device, electronic device and program | |
KR20120045526A (en) | Apparatus and method for eliminating noise | |
CN116369888A (en) | Non-contact heart rate variability data acquisition method and device | |
JP2014135987A (en) | Sensor terminal for acquiring signal including quasi-periodic delimiter pulse, and signal acquisition method | |
CN108694337A (en) | Sensing system and method for sensing | |
CN113499064A (en) | Wi-Fi perception human body tumbling detection method and system in bathroom scene | |
JP2013208312A (en) | Signal analyzer, electronic equipment and program |
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 | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: 518000 Guangdong science and technology innovation and Research Institute, Shenzhen, Shenzhen, Nanshan District No. 6, science and technology innovation and Research Institute, Shenzhen, D 10, 1004, 10 Patentee after: Shenzhen Hetai intelligent home appliance controller Co.,Ltd. Address before: 518000 Guangdong science and technology innovation and Research Institute, Shenzhen, Shenzhen, Nanshan District No. 6, science and technology innovation and Research Institute, Shenzhen, D 10, 1004, 10 Patentee before: SHENZHEN H&T DATA RESOURCES AND CLOUD TECHNOLOGY Ltd. |