Summary of the invention
In view of this, present disclose provides sleep state analysis method and devices, intelligent wearable device, to solve correlation
Deficiency in technology.
According to the first aspect of the embodiments of the present disclosure, a kind of sleep state analysis method is provided, is set for intelligently wearable
It is standby, which comprises
Physiological characteristic data value when user's daily routines is acquired, the physiological characteristic data value is included at least for characterizing
The body of severe degree when user's daily routines moves data value and the heart rate for when characterizing user's daily routines becomes
The heart rate value of change;
The sleep period of the user is determined according to the physiological characteristic data value.
Optionally, physiological characteristic data value when acquisition user's daily routines, comprising:
Institute when user's daily routines is acquired by acceleration transducer, gyro sensor or magnetic induction sensor
The body stated in physiological characteristic data value moves data value;
Physiological characteristic number when user's daily routines is acquired by EGC sensor or photoelectricity heart rate sensor
According to the heart rate value in value.
Optionally, the sleep period that the user is determined according to the physiological characteristic data value, comprising:
The physiological characteristic data value is pre-processed;
According to the pretreated physiological characteristic data value, the sleep period of the user is determined.
It is optionally, described that the physiological characteristic data value is pre-processed, comprising:
Median filter process or mean filter processing are carried out to the physiological characteristic data value.
It is optionally, described that the sleep period of the user is determined according to the pretreated physiological characteristic data value,
Include:
Pass through the pretreated physiological characteristic data value according to corresponding with each preset time period, determines each institute
State interval belonging to preset time period is stated, the state interval includes characterizing dormant sleep interval and the awake shape of characterization
The awake section of state;
If multiple awake sections and target sleep interval are adjacent, the sleep interval of the target sleep interval is risen
Time point beginning is determined as the sleep starting point of the user;
If multiple sleep intervals and target are regained consciousness, section is adjacent, and the awake section in the awake section of the target is risen
Time point beginning is determined as the sleep termination point of the user;
Period between the sleep starting point and sleep termination point is determined as the sleep period.
Optionally, the basis is corresponding with each preset time period passes through the pretreated physiological characteristic data
Value, determines state interval belonging to each preset time period, comprising:
To moving data value by the pretreated body in the preset time period and the heart rate value counts,
It respectively obtains body and moves data statistics value and heart rate statistical value;
The body is moved into data statistics value and moves preset value lower than the first body, and the heart rate statistical value is lower than the first preset value
The preset time period belonging to state interval be determined as the sleep interval;
The body is moved into data statistics value and moves preset value not less than first body, and the heart rate statistical value is not less than institute
It states state interval belonging to the preset time period of the second preset value and is determined as the awake section.
Optionally, after the sleep period that the user is determined according to the physiological characteristic data value, the side
Method further include:
It is analyzed according to sleep state of the physiological characteristic data value to the user in the sleep period, really
Determine sleep state analysis result;
Wherein, the sleep state analysis result includes that the user is in deep sleep state in the sleep period
The sound sleep period and sound sleep duration, shallowly sleeping the period and shallowly sleep duration and in rapid-eye-movement sleep in sleeping state
The rapid eye movement period of state and in rapid eye movement duration at least one of.
Optionally, it is described according to the physiological characteristic data value to the sleep state of the user in the sleep period
It is analyzed, determines that sleep state analyzes result, comprising:
According to the physiological characteristic data value, when determining that the user is described default each of in the sleep period
Between the corresponding sleep state of section;
The accumulation duration for calculating the corresponding preset time period of the identical sleep state obtains the sleep state point
Analyse result.
Optionally, described according to the physiological characteristic data value, determine that the user is every in the sleep period
The corresponding sleep state of a preset time period, comprising:
If the heart rate value in the preset time period is above the first heart rate threshold, determine the user described
The sleep state in preset time period is the rapid-eye-movement sleep state;
If the heart rate value in the preset time period is below the second heart rate threshold, and in the preset time period
The body move data value lower than the second body move preset value, determine the sleep shape of the user in the preset time period
State is the deep sleep state;
If the sleep state in the preset time period is not belonging to the rapid-eye-movement sleep state and is not belonging to
The deep sleep state determines that the sleep state of the user in the preset time period is the sleeping state.
Optionally, after the physiological characteristic data value in acquisition user's daily routines, the method also includes:
After the physiological characteristic data value is inputted preset model, model training is carried out;
Sleep model is established according to model training result;
User sleep state locating for each preset time period is marked out by the sleep model.
According to the second aspect of an embodiment of the present disclosure, a kind of sleep state analytical equipment is provided, is set for intelligently wearable
Standby, described device includes:
Data acquisition module, for acquiring physiological characteristic data value when user's daily routines, the physiological characteristic data
The body of severe degree when value is included at least for characterizing user's daily routines moves data value and for characterizing the user
The heart rate value of changes in heart rate when daily routines;
Sleep period determining module, for determining the sleeping time of the user according to the physiological characteristic data value
Section.
Optionally, the data acquisition module includes:
First acquisition submodule, for acquiring institute by acceleration transducer, gyro sensor or magnetic induction sensor
The body in physiological characteristic data value when stating user's daily routines moves data value;
Second acquisition submodule, for acquiring user's daily routines by EGC sensor or photoelectricity heart rate sensor
When the physiological characteristic data value in the heart rate value.
Optionally, the sleep period determining module includes:
Submodule is pre-processed, for pre-processing to the physiological characteristic data value;
Sleep period determines submodule, for determining the use according to the pretreated physiological characteristic data value
The sleep period at family.
Optionally, the pretreatment submodule includes:
Filter processing unit, for carrying out median filter process or mean filter processing to the physiological characteristic data value.
Optionally, the sleep period determines that submodule includes:
State interval determination unit, for passing through the pretreated physiology according to corresponding with each preset time period
Characteristic data value determines that state interval belonging to each preset time period, the state interval include characterization sleep state
Sleep interval and characterization waking state awake section;
Starting point determination unit of sleeping will be described if adjacent for multiple awake sections and target sleep interval
The sleep interval start time point of target sleep interval is determined as the sleep starting point of the user;
Sleep termination point determination unit will be described if adjacent for multiple sleep intervals and the awake section of target
The awake section start time point in the awake section of target is determined as the sleep termination point of the user;
Sleep period determination unit, for by it is described sleep starting point and sleep termination point between period it is true
It is set to the sleep period.
Optionally, the state interval unit includes:
Subelement is counted, for moving data value and described by the pretreated body in the preset time period
Heart rate value is counted, and is respectively obtained body and is moved data statistics value and heart rate statistical value;
First state section determines subelement, moves preset value lower than the first body for the body to be moved data statistics value, and
State interval belonging to the preset time period of the heart rate statistical value lower than the first preset value is determined as the sleep interval;
Second state interval determines subelement, dynamic not less than first body default for the body to be moved data statistics value
Value, and state interval belonging to the preset time period of the heart rate statistical value not less than second preset value is determined as institute
State awake section.
Optionally, described device further include:
Sleep state analyzes result determining module, is used for according to the physiological characteristic data value in the sleep period
The sleep state of the user is analyzed, and determines that sleep state analyzes result;
Wherein, the sleep state analysis result includes that the user is in deep sleep state in the sleep period
The sound sleep period and sound sleep duration, shallowly sleeping the period and shallowly sleep duration and in rapid-eye-movement sleep in sleeping state
The rapid eye movement period of state and in rapid eye movement duration at least one of.
Optionally, the sleep state analysis result determining module includes:
Sleep state determines submodule, for determining the user in the sleep according to the physiological characteristic data value
The corresponding sleep state of the preset time period each of in period;
Computational submodule is obtained for calculating the accumulation duration of the corresponding preset time period of the identical sleep state
Result is analyzed to the sleep state.
Optionally, the sleep state determines that submodule includes:
First sleep state determination unit, if the heart rate value in the preset time period is above first heart
Rate threshold value determines that the sleep state of the user in the preset time period is the rapid-eye-movement sleep state;
Second sleep state determination unit, if the heart rate value in the preset time period is below second heart
Rate threshold value, and the body in the preset time period moves data value and moves preset value lower than the second body, determines the user in institute
Stating the sleep state in preset time period is the deep sleep state;
Third sleep state determination unit, if be not belonging to for the sleep state in the preset time period described
Rapid-eye-movement sleep state and be not belonging to the deep sleep state, determine the user in the preset time period described in sleep
Dormancy state is the sleeping state.
Optionally, described device further include:
Model training module carries out model training after the physiological characteristic data value is inputted preset model;
Sleep model building module, for establishing sleep model according to model training result;
Labeling module, for by the sleep model mark out the user locating for each preset time period described in
Sleep state.
According to the third aspect of an embodiment of the present disclosure, a kind of intelligent wearable device is provided, comprising:
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to executing sleep state analysis method described in above-mentioned first aspect.
By above technical scheme as it can be seen that intelligent wearable device can physiological characteristic when collecting user's daily routines
It after data, analyzes it, so that it is determined that the sleep period of the user out.By the above process, user only needs to wear
Wear intelligent wearable device, so that it may determine the sleep state analysis as a result, real-time by the intelligent wearable device
Height, realizes easy, and availability is high, improves that intelligent wearable device is intelligentized simultaneously, and the user experience is improved.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
It is only to be not intended to be limiting the disclosure merely for for the purpose of describing particular embodiments in the term that the disclosure uses.
The "an" of the singular used in disclosure and the accompanying claims book, " described " and "the" are also intended to including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the disclosure
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where disclosure range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
The method provided in the embodiment of the present disclosure can be used for intelligent wearable device, including but not limited to Intelligent bracelet,
Smartwatch, smart bracelet, intelligent ring, intelligent necklace, intelligent foot chain, intelligent leather belt etc., as shown in Figure 1, Fig. 1 is according to one
A kind of sleep state analysis method shown in exemplary embodiment, comprising the following steps:
In a step 101, physiological characteristic data value when user's daily routines is acquired.
In the embodiment of the present disclosure, optionally, the physiological characteristic data value includes at least daily for characterizing the user
The body of severe degree when movable moves data value and the heart rate value for changes in heart rate when characterizing user's daily routines.
In this step, the intelligence wearable device can pass through acceleration transducer, gyro sensor or magnetic induction
Sensor acquires the body according to predeterminated frequency and moves data value.Meanwhile the intelligent wearable device can pass through electrocardio sensing
Device or photoelectricity heart rate sensor are also according to the predeterminated frequency acquisition heart rate value.
In a step 102, the sleep period of the user is determined according to the physiological characteristic data value.
Optionally, step 102 is as shown in Fig. 2, Fig. 2 is another sleep shown on the basis of embodiment shown in Fig. 1
State analysis method flow chart may include:
In step 102-1, the physiological characteristic data value is pre-processed.
In this step, in order to reduce influence of noise and data fluctuations, the intelligence wearable device can be according to related skill
Art carries out median filter process to the collected physiological characteristic data or mean filter is handled.If after filtering processing
The physiological characteristic data value in further include exceptional data point, such as heart rate value is more than the data point of normal cardiac rate value range,
It is also the same to need to filter out, so that it is guaranteed that the sleep state precision of analysis of the user.
In step 102-2, according to the pretreated physiological characteristic data value, the sleeping time of the user is determined
Section.
Optionally, step 102-2 is as shown in figure 3, Fig. 3 is that the another kind shown on the basis of embodiment shown in Fig. 2 is slept
Dormancy state analysis method flow chart may include:
In step 102-21, pass through the pretreated physiological characteristic number according to corresponding with each preset time period
According to value, state interval belonging to each preset time period is determined.
Optionally, the state interval includes the awake area for characterizing dormant sleep interval and characterizing waking state
Between.
In this step, data value and described first can be moved by the pretreated body in the preset time period
Heart rate value is counted, and is respectively obtained body and is moved data statistics value and heart rate statistical value.
It wherein, can be to the described default of selection in order to ensure the sleep state precision of analysis of the user
The physiological characteristic data value in period is overlapped processing, that is, deletes and be located at the of foremost in the preset time period
It is pre- to increase the adjacent first object after the preset time period for the physiological characteristic data value of one target preset time period
If the physiological characteristic data value of period, the obtained physiological characteristic data value is determined as first preset time
The corresponding physiological characteristic data value of section.Wherein, the first object preset time period is preparatory for the superposition processing
The period less than the preset time period duration of setting.
For example, every time to preset time period when a length of 10 milliseconds (ms) body move data value and be overlapped processing, described the
The duration of one target preset time period is less than the duration of the preset time period, is 2ms.In 1ms to the described pre- of 10ms
If the period corresponding body moves in data value, the body for deleting 1ms to 2ms moves data value, by 11ms to the
The body of 12ms, which moves data value, increases to the dynamic data of the corresponding body of the preset time period of the 1ms to 10ms
In value.Finally, it is 3ms to 12ms's that the corresponding body of the preset time period of 1ms to 10ms, which moves data value,
The body moves data value.
Similarly, the heart rate value can also be handled using same superposition processing method.
By above-mentioned superposition processing, can be generated to avoid the wearable device when acquiring the physiological characteristic data value
Time delay, it is ensured that physiological characteristic data acquisition accuracy.Furthermore it is also possible to make the corresponding institute of the adjacent preset time period
It is stronger to state relevance between physiological characteristic data value, available more precisely sleep state analyzes result.
In the embodiment of the present disclosure, data value and the heart rate value are moved according to the relevant technologies to the body Jing Guo superposition processing
It is counted, the available body moves data statistics value and the heart rate statistical value.
Wherein, it may include that the body moves the body moving-target mean value of data value, body moving-target that the body, which moves data statistics value,
First body moment value of the first body moving-target mean value of variance, the body moving-target mean value and target preset time period, Yi Jisuo
It states in the second body moment value of the first body moving-target variance of body moving-target variance and the second target preset time period extremely
One item missing, when the second target preset time period is described default for first before or after presently described preset time period
Between section.
Similarly, the heart rate statistical value may include the heart rate goal mean value, heart rate goal variance, institute of the heart rate value
State the first heart rate goal mean value of heart rate goal mean value and the target preset time period the first heart rate difference and the heart
At least one of in second heart rate difference of the first heart rate goal variance of rate target variance and the target preset time period.
In the embodiment of the present disclosure, if the body, which moves data statistics value, moves preset value lower than the first body, and the heart rate is united
Evaluation is lower than the first preset value, then state interval belonging to the preset time period is determined as the sleep interval.If institute
It states body and moves data statistics value not less than the dynamic preset value of first body, and the heart rate statistical value is default not less than described second
Value, then be determined as the awake section for state interval belonging to the preset time period.
In step 102-22, if multiple awake sections and target sleep interval are adjacent, the target is slept
The sleep interval start time point in section is determined as the sleep starting point of the user.
In this step, if adjacent with a certain sleep interval in multiple awake sections, which is
For the target sleep interval.It can determine that the user switchs to sleep state by waking state, then by target sleep area
Between sleep interval start time point be determined as the sleep starting point of the user.
In step 102-23, if multiple sleep intervals and target are regained consciousness, section is adjacent, and the target is regained consciousness
The awake section start time point in section is determined as the sleep termination point of the user.
In this step, if adjacent with a certain awake section in multiple sleep intervals, which is
For the awake section of the target.It can determine that the user switchs to waking state by sleep state, then by the awake area of the target
Between awake section start time point be determined as the sleep termination point of the user.
In step 102-24, the period between the sleep starting point and sleep termination point is determined as described
Sleep period.
In this step, the period between the sleep starting point and sleep termination point is exactly the sleeping time
Section.
In the embodiment of the present disclosure, based on the physiological characteristic number for including at least the body dynamic data value and the heart rate value
The sleep period of the user is determined according to value, user only needs to wear intelligent wearable device, so that it may by described
Intelligent wearable device is analyzed to determine the sleep state as a result, real-time is high, and realization is easy, and availability is high, improves intelligence
Energy wearable device is intelligentized simultaneously, and the user experience is improved.
Further, the above-mentioned sleep state analysis method that the embodiment of the present disclosure provides, as shown in figure 4, Fig. 4 is in Fig. 1
Another sleep state analysis method flow chart shown on the basis of illustrated embodiment can also include:
In step 103, according to the physiological characteristic data value to the sleep shape of the user in the sleep period
State is analyzed, and determines that sleep state analyzes result.
Wherein, optionally, the sleep state analysis result includes that the user is in deep in the sleep period
Dormant sound sleep period and sound sleep duration, shallowly sleeping the period and shallowly sleep duration and in quick in sleeping state
The rapid eye movement period of REM sleep state and in rapid eye movement duration at least one of.
Step 103 is as shown in figure 5, Fig. 5 is another sleep state analysis shown on the basis of the embodiment shown in fig. 4
Method flow diagram may include:
In step 103-1, according to the physiological characteristic data value, determine the user in the sleep period
The corresponding sleep state of each preset time period.
The sleep state includes deep sleep state, sleeping state or rapid-eye-movement sleep state.
In the embodiment of the present disclosure, number can be marked by stages for marking the dormant data according to currently existing
According to determining the sleep state in different ways.If the data obtained by stages labeled data number not
More than preset number, i.e., labeled data is less by stages for the described data, then can determine the sleep state using unsupervised mode.
If the number of the data obtained labeled data by stages is more than the preset number, i.e., the described data mark by stages
It is more to infuse data, then can use has monitor mode to determine the sleep state.It is described below respectively.
First way, unsupervised mode.
It is possible, firstly, to determine the first heart rate threshold and the second heart rate threshold according to above-mentioned heart rate statistical value.Optionally, may be used
The corresponding terminating point heart rate value of the sleep termination point is determined as first heart rate threshold, by the sleep starting point pair
The starting point heart rate value answered is determined as second heart rate threshold.
If the heart rate value in the preset time period is above first heart rate threshold, it is determined that the user
The sleep state in the preset time period is the rapid-eye-movement sleep state, as shown in Figure 6.
If the heart rate value in the preset time period is below the second heart rate threshold, and in the preset time period
The body move data value lower than the second body move preset value, determine the sleep shape of the user in the preset time period
State is the deep sleep state, also shown in FIG. 6.
It is the institute for being not belonging to the rapid-eye-movement sleep state and being not belonging to the deep sleep state again by the sleep state
The sleep state for stating preset time period is determined as the sleeping state, also shown in FIG. 6.
The second way has monitor mode.
Step 101 can be acquired to the physiological characteristic data value input preset model, the preset model can be hidden
Containing Markov model, support vector machines, maximum entropy model, perceptron etc., to carry out model training according to the relevant technologies.Root
Sleep model is established according to model training result.It is possible to further be based on existing data labeled data by stages, to described
User's sleep state locating for each preset time period is labeled.It is marked out using there is monitor mode that can also synchronize
The user is in waking state in some described preset time period.
By taking hidden Markov model as an example, in model training stage, statistical value and heart rate system are moved based on the body
Evaluation counts the transition probability and hair between each sleep state on the basis of the existing data labeled data by stages
Penetrate probability.
Wherein, the transition probability is when Markov chain is made of m state, from any one state, warp
Cross any primary transfer, necessarily out present condition 1,2 ..., one in m, the transfer between this state is known as transition probability.
In the hidden Markov model include hidden state and aobvious state, such as user a some friend b daily according to weather
{ raining, become a fine day } determines one of the activity { park is taken a walk, shopping, clean rooms } on the same day, and user a daily can only be in social activity
The information for seeing friend b hair on website be ", my day before yesterday park is taken a walk, shopping yesterday, today clean rooms!", then using
This three days weather of the site information inference friend b that family a can be sent out according to friend b.Wherein, aobvious state is the work of friend b
Dynamic state, hidden state is state of weather.The emission probability is to be showed in the hidden Markov model by hidden state
To show shape probability of state.
Wherein, the feature templates that hidden Markov model uses may include: second before presently described preset time period
The body of a preset time period moves statistical value and the heart rate statistical value, first institute before presently described preset time period
The body for stating preset time period moves statistical value and the heart rate statistical value, the dynamic statistics of the body of presently described preset time period
The body of value and the heart rate statistical value, preset time period described in presently described preset time period the latter moves statistical value and institute
Heart rate statistical value is stated, the body of second preset time period moves statistical value and the heart after presently described preset time period
Rate statistical value and the combination of these statistical values etc..In decoding stage, Viterbi decoding algorithm can be used and obtain output mark
Sequence.To be labeled to user sleep state locating for each preset time period.
Any one in through the above way, the sleep shape of the obtained user in the sleep period
State example is as shown in Figure 7.
In step 103-2, the accumulation duration of the corresponding preset time period of the identical sleep state is calculated, is obtained
The sleep state analyzes result.
In this step, the duration of the corresponding preset time period of all deep sleep states can be added up,
Obtain the sound sleep duration.Similarly, the duration of the corresponding preset time period of all sleeping states is carried out tired
Add, obtain it is described shallowly sleep duration, the duration of the corresponding preset time period of all rapid-eye-movement sleep states is carried out
It is cumulative, obtain the rapid eye movement duration.
In the embodiment of the present disclosure, the finally obtained sleep state analysis result may include that the user is in described
Sound sleep period when deep sleep state, including sound sleep start time point and sound sleep terminate time point.Similarly, described shallowly when sleeping
Between section include shallowly sleep start time point and shallowly sleep terminate time point, the rapid eye movement period includes rapid eye movement initial time
Point and rapid eye movement terminate time point.Each sleep state can occur repeatedly.
In the embodiment of the present disclosure, above-mentioned sleep state analysis result is sent preparatory binding by the intelligence wearable device
Intelligent electronic device, the intelligent electronic device can be any intelligence in smart phone, intelligent computer or smart home
Energy electronic equipment etc..It is shown by the intelligent electronic device, so that the user learns the sleep state analysis result.
In above-described embodiment, intelligent wearable device can physiological characteristic data when collecting user's daily routines
Afterwards, it analyzes it, so that it is determined that the sleep period of the user out, further, to institute in the sleep period
The sleep state for stating user is analyzed, and the sleep state analysis result of the user is obtained.Wherein, the sleep state analysis
It as a result include sound sleep period and sound sleep duration of the user in the sleep period in deep sleep state, in shallow
It is dormant shallowly to sleep the period and shallowly sleep duration and rapid eye movement period and quick eye in rapid-eye-movement sleep state
At least one of in dynamic duration.By the above process, user only needs to wear intelligent wearable device, so that it may by the intelligence
Wearable device is analyzed to determine the sleep state as a result, real-time is high, and realization is easy, and availability is high, and improving intelligence can
Wearable device is intelligentized simultaneously, and the user experience is improved.
Corresponding with preceding method embodiment, the disclosure additionally provides the embodiment of device.
As shown in figure 8, Fig. 8 is a kind of disclosure sleep state analytical equipment frame shown according to an exemplary embodiment
Figure, comprising:
Data acquisition module 210, for acquiring physiological characteristic data value when user's daily routines, the physiological characteristic number
The body of severe degree when including at least according to value for characterizing user's daily routines moves data value and for characterizing the use
The heart rate value of changes in heart rate when the daily routines of family;
Sleep period determining module 220, when for determining the sleep of the user according to the physiological characteristic data value
Between section.
Optionally, the data acquisition module includes:
First acquisition submodule, for acquiring institute by acceleration transducer, gyro sensor or magnetic induction sensor
The body in physiological characteristic data value when stating user's daily routines moves data value;
Second acquisition submodule, for acquiring user's daily routines by EGC sensor or photoelectricity heart rate sensor
When the physiological characteristic data value in the heart rate value.
Optionally, the sleep period determining module includes:
Submodule is pre-processed, for pre-processing to the physiological characteristic data value;
Sleep period determines submodule, for determining the use according to the pretreated physiological characteristic data value
The sleep period at family.
Optionally, the pretreatment submodule includes:
Filter processing unit, for carrying out median filter process or mean filter processing to the physiological characteristic data value.
Optionally, the sleep period determines that submodule includes:
State interval determination unit, for passing through the pretreated physiology according to corresponding with each preset time period
Characteristic data value determines that state interval belonging to each preset time period, the state interval include characterization sleep state
Sleep interval and characterization waking state awake section;
Starting point determination unit of sleeping will be described if adjacent for multiple awake sections and target sleep interval
The sleep interval start time point of target sleep interval is determined as the sleep starting point of the user;
Sleep termination point determination unit will be described if adjacent for multiple sleep intervals and the awake section of target
The awake section start time point in the awake section of target is determined as the sleep termination point of the user;
Sleep period determination unit, for by it is described sleep starting point and sleep termination point between period it is true
It is set to the sleep period.
Optionally, the state interval unit includes:
Subelement is counted, for moving data value and described by the pretreated body in the preset time period
Heart rate value is counted, and is respectively obtained body and is moved data statistics value and heart rate statistical value;
First state section determines subelement, moves preset value lower than the first body for the body to be moved data statistics value, and
State interval belonging to the preset time period of the heart rate statistical value lower than the first preset value is determined as the sleep interval;
Second state interval determines subelement, dynamic not less than first body default for the body to be moved data statistics value
Value, and state interval belonging to the preset time period of the heart rate statistical value not less than second preset value is determined as institute
State awake section.
As shown in figure 9, Fig. 9 is the disclosure another sleep state analytical equipment frame shown according to an exemplary embodiment
Figure, the embodiment is on the basis of aforementioned embodiment illustrated in fig. 8, described device further include:
Sleep state analyzes result determining module 230, is used for according to the physiological characteristic data value to the sleeping time
The sleep state of the user is analyzed in section, determines that sleep state analyzes result;
Wherein, the sleep state analysis result includes that the user is in deep sleep state in the sleep period
The sound sleep period and sound sleep duration, shallowly sleeping the period and shallowly sleep duration and in rapid-eye-movement sleep in sleeping state
The rapid eye movement period of state and in rapid eye movement duration at least one of.
Optionally, the sleep state analysis result determining module includes:
Sleep state determines submodule, for determining the user in the sleep according to the physiological characteristic data value
The corresponding sleep state of the preset time period each of in period;
Computational submodule is obtained for calculating the accumulation duration of the corresponding preset time period of the identical sleep state
Result is analyzed to the sleep state.
Optionally, the sleep state determines that submodule includes:
First sleep state determination unit, if the heart rate value in the preset time period is above first heart
Rate threshold value determines that the sleep state of the user in the preset time period is the rapid-eye-movement sleep state;
Second sleep state determination unit, if the heart rate value in the preset time period is below second heart
Rate threshold value, and the body in the preset time period moves data value and moves preset value lower than the second body, determines the user in institute
Stating the sleep state in preset time period is the deep sleep state;
Third sleep state determination unit, if be not belonging to for the sleep state in the preset time period described
Rapid-eye-movement sleep state and be not belonging to the deep sleep state, determine the user in the preset time period described in sleep
Dormancy state is the sleeping state.
As shown in Figure 10, Figure 10 is the disclosure another sleep state analytical equipment shown according to an exemplary embodiment
Block diagram, the embodiment is on the basis of aforementioned embodiment illustrated in fig. 8, described device further include:
Model training module 240 carries out model training after the physiological characteristic data value is inputted preset model;
Sleep model building module 250, for establishing sleep model according to model training result;
Labeling module 260, for marking out the user locating for each preset time period by the sleep model
The sleep state.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein being used as separate part description
Unit may or may not be physically separated, component shown as a unit may or may not be
Physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to the actual needs
Some or all of the modules therein is selected to realize the purpose of disclosure scheme.Those of ordinary skill in the art are not paying wound
In the case that the property made is worked, it can understand and implement.
Correspondingly, the disclosure also provides a kind of intelligent wearable device, comprising:
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to executing sleep state analysis method described in any of the above embodiments.
The disclosure also proposed shown in Figure 11 according to the intelligent wearable device of the exemplary embodiment of the application
Schematic configuration diagram.As shown in figure 11, in hardware view, which includes that processor, internal bus, network connect
Mouth, memory and nonvolatile memory, are also possible that hardware required for other business certainly.Processor is from non-volatile
It reads corresponding computer program in memory then to run into memory, which can execute above-mentioned sleep state point
Analysis method.Certainly, other than software realization mode, the application is not precluded other implementations, for example, logical device or
Mode of software and hardware combining etc., that is to say, that the executing subject of following process flow is not limited to each logic unit,
It can be hardware or logical device.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the application
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follows the general principle of the application and including the undocumented common knowledge in the art of the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are by following
Claim is pointed out.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all essences in the disclosure
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of disclosure protection.