CN115137308A - Method for improving accuracy of in-out sleep detection in sleep algorithm of intelligent wearable device - Google Patents
Method for improving accuracy of in-out sleep detection in sleep algorithm of intelligent wearable device Download PDFInfo
- Publication number
- CN115137308A CN115137308A CN202210756042.2A CN202210756042A CN115137308A CN 115137308 A CN115137308 A CN 115137308A CN 202210756042 A CN202210756042 A CN 202210756042A CN 115137308 A CN115137308 A CN 115137308A
- Authority
- CN
- China
- Prior art keywords
- sleep
- state
- user
- heart rate
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/681—Wristwatch-type devices
-
- 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
- A61B5/7221—Determining signal validity, reliability or 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
- A61B5/7235—Details of waveform analysis
-
- 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
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
Abstract
The invention discloses a method for improving the accuracy of sleep entrance and exit detection in a sleep algorithm of intelligent wearable equipment, which comprises the following steps: the method comprises the steps of obtaining corresponding initial acceleration signals and initial heart rate signals through an acceleration sensor and a heart rate sensor, obtaining acceleration signals S1 and heart rate signals S2 after signal processing, obtaining corresponding signal characteristics through analysis processing of the acceleration signals S1 and the heart rate signals S2, preliminarily judging whether the state of a user is in a sleeping state or out of the sleeping state according to a sleep algorithm of the intelligent device, introducing parameters of the using state of a mobile phone when the in-sleeping state and out-sleeping state of the user are detected in the sleep algorithm, improving the accuracy of the intelligent device on in-sleeping and-out time detection, adjusting the in-sleeping and-out time in the sleep algorithm according to feedback of the state of the mobile phone, updating model parameters in the sleep algorithm according to the signal characteristics of the acceleration signals S1 and the heart rate signals S2 in the current state, and finally achieving the purpose of higher accuracy of in-sleeping and-out detection.
Description
The technical field is as follows:
the invention relates to the technical field of intelligent wearable equipment, in particular to a method for improving the accuracy of in-and-out sleep detection in a sleep algorithm of the intelligent wearable equipment.
Background art:
along with the development of intelligence wearing equipment, intelligent wrist-watch, intelligent bracelet obtain quick development. The intelligent wearable devices integrate a plurality of sensors, can be used for recording relevant data such as exercise and sleep in daily life of a user, and can also detect body function information of the user.
The mode that is arranged in intelligent wearing equipment to be used for detecting user sleep information at present mainly is through detecting body index parameters such as user's rhythm of the heart to and user's physical activity parameter, judge user's the state of sleeping in and out of cominging in and going out. See patent application No.: the invention patent application 201810721118.1 in China discloses a detection system and a detection method for detecting the sleep state of a user, and adopts the following technical scheme: a detection system and a detection method for detecting the sleep state of a user comprise a wearable intelligent monitoring device, a data acquisition module and a data processing module, wherein the wearable intelligent monitoring device is used for monitoring the heart rate, the blood oxygen and the body movement data of the user; the server is in communication connection with the wearable intelligent monitoring device and used for receiving and storing the heart rate, blood oxygen and body movement data monitored by the wearable intelligent monitoring device, and the server comprises an analysis module which is used for analyzing the sleep state of the user. The wearable intelligent monitoring equipment is used for acquiring heart rate, blood oxygen and body movement parameters in real time in the sleeping process, the acquired data are transmitted to the server end in real time to be analyzed and judged in the sleeping state, and the analyzing and judging method is used for analyzing by combining the heart rate and the blood oxygen data on the basis of the body movement data and judging the real sleeping state of a user.
According to the invention patent application, currently, for the intelligent wearable device, in the sleep algorithm, the method for judging the sleep state of the user is to collect various different parameters (as in the invention patent, heart rate, blood oxygen and body movement data are used as judgment bases for improving the accuracy of sleep detection), determine a corresponding judgment threshold according to the change of the parameters of the user in the sleep state, and when the parameters are in the judgment threshold, the intelligent wearable device judges that the user is in the sleep state, otherwise, the intelligent wearable device judges that the user is in the non-sleep state.
By taking various parameters such as heart rate, blood oxygen and body movement data as judgment bases, the accuracy of judging the sleep state is improved, but certain defects still exist. Mainly embodied in the following aspects:
most people usually do small activities for a long time in bed before sleeping, such as lying to read books, reading mobile phones, etc.; after waking up, small activities such as reading books, reading a mobile phone, etc. are performed in bed for a long time. At this time, the activity of the human body is very small, the parameters such as the heart rate are not significantly changed, which easily causes the wearable devices such as smartband and watch to make mistakes when detecting the sleep state of the user, for example, the user is mistakenly considered to be asleep (the user actually still looks at the mobile phone in bed) through the existing algorithm, or the user is mistakenly considered to be still asleep (the user actually wakes up to look at the mobile phone) through the existing algorithm.
On the other hand, along with the development of smart phones, various smart devices are all interconnected with the mobile phones when in use, and the interconnection between the smart devices and the mobile phones can be realized through APP.
In conclusion, the inventor provides the following technical scheme aiming at the defects existing in the sleep algorithm of the intelligent wearable devices such as the current intelligent watch, the current bracelet and the like.
The invention content is as follows:
the invention aims to overcome the defects of the prior art and provides a method for improving the accuracy of in-and-out sleep detection in a sleep algorithm of intelligent wearable equipment.
In order to solve the technical problems, the invention adopts the following technical scheme: a method for improving the accuracy of in-and-out sleep detection in a sleep algorithm of intelligent wearable equipment comprises the following steps: acceleration sensor and rhythm of the heart sensor through integrated at intelligent wearing equipment, acquire corresponding initial acceleration signal and initial rhythm of the heart signal, through acquire acceleration signal S1 and rhythm of the heart signal S2 after to signal processing, obtain corresponding signal characteristic through the analysis processes to acceleration signal S1 and rhythm of the heart signal S2, and according to smart machine sleep algorithm, tentatively judge the state of user for falling asleep state or going out asleep state, introduce the mobile phone state as the parameter in the method, judge the user for getting into the state of falling asleep when the step, user' S mobile phone state is for not playing the cell-phone, then judge and be: the user enters a sleeping state, and then enters a sleeping in and out detection output state; when the user is judged to enter the sleep state at first and the mobile phone playing state of the user is the mobile phone playing state, the judgment is that: the user does not enter the sleeping state, and then enters the in-and-out sleeping detection updating state; when the user is initially judged to enter the out-of-sleep state, and if the user plays the mobile phone, the state is that the user plays the mobile phone, the judgment is that: the user enters a sleep-out state, and then enters a sleep-in and sleep-out detection output state; when the user is judged not to fall asleep and the user is in a mobile phone playing state in the initial judgment, the judgment is that: the user enters a sleeping-out state, and then enters a sleeping-in/out detection output state and a sleeping-in/out detection updating state; through the judgment result, when the user enters the in-and-out sleeping detection output state, the judgment result is directly output; when the user enters the in-and-out sleep detection updating state, the signal characteristics of the acceleration signal S1 and the heart rate signal S2 in the corresponding states are updated according to the model parameters of the sleep algorithm of the intelligent device, and the accuracy of in-and-out sleep detection is continuously improved through continuous updating of the model parameters.
Further, in the above technical solution, the method for acquiring the acceleration signal S1 includes: acquiring triaxial acceleration data xACC, yACC and zACC of an acceleration sensor, then carrying out vector synthesis operation on triaxial acceleration signals to obtain synthesized acceleration signals, carrying out filtering and denoising processing on the synthesized acceleration signals to obtain acceleration signals S1, and then calculating the fluctuation signal characteristics of the signals in a set time window.
Further, in the above technical solution, in the method for acquiring an acceleration signal S1, performing vector synthesis on a triaxial acceleration signal is: and (3) re-squaring the sum of squares of the three-axis acceleration signals, wherein the corresponding calculation formula is as follows:
synthesis ofAfter the acceleration signal is subjected to filtering and denoising processing, the maximum value and the minimum value in a set window are found, and the fluctuation signal characteristic of the synthesized acceleration signal is calculated according to the difference between the maximum value and the minimum value.
Further, in the above technical solution, the method for acquiring the heart rate signal S2 includes: the method comprises the steps of collecting heart rate wave signals of a heart rate sensor, then carrying out filtering and denoising processing on the collected heart rate wave signals to obtain heart rate signals S2, and then extracting waveform signal characteristics of heart rate and heart rate variability.
Further, in the above technical solution, the method for acquiring the waveform signal characteristics of the heart rate and the heart rate variability comprises: and detecting effective valley/peak points of the heart rate wave signal S2 subjected to filtering and denoising by using a valley/peak detection algorithm, and calculating to obtain the waveform signal characteristics of the heart rate and the heart rate variability according to the valley/peak positions detected in a set time window and by combining the sampling rate.
Further, in the above technical scheme, the intelligent wearable device is an intelligent watch or an intelligent bracelet with sleep monitoring.
The invention utilizes the interconnection system between the existing intelligent wearable device and the mobile phone, and introduces the parameters of the use state of the mobile phone when detecting the in-and-out sleep state of the user in a sleep algorithm, thereby improving the accuracy of the detection of the in-and-out sleep time by the intelligent device.
Description of the drawings:
FIG. 1 is a flow chart of a sleep algorithm in the present invention;
FIGS. 2a-2d are schematic diagrams illustrating the determination of the in-and-out-of-sleep state in the sleep algorithm of the present invention;
fig. 3 is a signal diagram of the acceleration signal S1 in an exemplary embodiment of the present invention.
The specific implementation mode is as follows:
the invention is further illustrated below with reference to specific embodiments and the accompanying drawings.
The invention relates to a method for improving the accuracy of sleep-in and sleep-out detection in a sleep algorithm of intelligent wearable equipment. The sleep monitoring module is generally provided in the electronic equipment, the sleep algorithm adopted by the sleep monitoring module is basically the same as the current common algorithm, corresponding original acceleration signals and original heart rate signals are obtained through an acceleration sensor and a heart rate sensor which are integrated on the intelligent wearable equipment, the acceleration signals S1 and the heart rate signals S2 are obtained after the signals are processed, corresponding signal characteristics are obtained through the analysis of the acceleration signals S1 and the heart rate signals S2, and the state of a user is preliminarily judged to be in a sleeping state or out of sleeping state according to set model parameters.
The invention further optimizes the sleep algorithm, thereby further improving the accuracy of the in-and-out sleep detection in the algorithm. In brief, the invention introduces the state of the mobile phone as a parameter in the existing sleep algorithm, and can further confirm whether the user is in the sleep or out-of-sleep state by identifying the state of the mobile phone. Specifically, the detection of the user falling asleep and falling asleep includes the following four situations.
1. When the user is judged to be in the sleep state in the initial step and the mobile phone state of the user is not playing the mobile phone, the judgment is that: the user enters a sleep state;
2. when the user is judged to enter the sleep state at first and the mobile phone playing state of the user is the mobile phone playing state, the judgment is that: the user does not enter a sleep state;
3. when the user is judged to enter the sleeping state at first step and the mobile phone playing state of the user is the mobile phone playing state, the judgment is that: the user enters a sleep state;
4. when the user is judged not to fall asleep at the beginning, and the user plays the mobile phone, the judgment is that: the user enters a sleep state;
for the cases 1 and 3, finally judging that the user enters the sleep-in state and the sleep-out state, directly entering the sleep-in and sleep-out detection output state next step, outputting the sleep-in state or the sleep-out state of the user to the intelligent device processing unit, and recording the sleep data of the user by the intelligent device. Namely, through the detection and judgment, when the user enters the in-and-out sleeping detection output state, the judgment result is directly output.
For the case of the type 2, although it is preliminarily determined that the user enters the sleep state according to the sleep algorithm, it is determined that the user does not actually enter the sleep state by correcting the mobile phone state of the user; in the case of the 4 th case, although it is not preliminarily determined that the user has entered the out-of-sleep state according to the sleep algorithm, it is determined that the user has actually entered the out-of-sleep state by correcting the state of the mobile phone of the user.
When the user enters the in-and-out sleep detection updating state, the signal characteristics of the acceleration signal S1 and the heart rate signal S2 in the corresponding states are updated, and the model parameters set in the sleep algorithm are updated, so that the accuracy of in-and-out sleep detection is continuously improved through continuous updating of the model parameters.
Because the invention introduces the state parameter of the mobile phone, the misjudgment in the sleep algorithm can be corrected through the state parameter of the mobile phone, and the signal characteristics of the acceleration signal S1 and the heart rate signal S2 corresponding to the continuous updating calculation are continuously updated and learned through the continuous updating model, so that the result obtained by the sleep algorithm can be more and more accurate. And finally, after the state parameters of the mobile phone are not introduced, the algorithm can be learned according to continuous updating, and a more accurate result is obtained.
Referring to fig. 1, the method for acquiring the acceleration signal S1 in the sleep algorithm of the present invention includes:
first, the raw acceleration (gsensor) signal is acquired. The original acceleration sensor comprises acceleration data xACC, yACC and zACC of three axes of X/Y/Z.
And then, carrying out vector synthesis operation on the triaxial acceleration signals to obtain a synthesized acceleration signal. The vector synthesis operation of the triaxial acceleration signal is as follows: and performing quadratic sum re-evolution on the triaxial acceleration signals, wherein the corresponding calculation formula is as follows:
then, the synthesized acceleration signal is subjected to signal processing, and feature extraction is performed. In this step, the signal processing mainly includes: the acceleration signal S1 is obtained through filtering and denoising processing. A low-pass filtering of 3Hz (adjustable to the actual situation) is usually carried out to obtain the processed acceleration signal S1. The characteristic extraction is to calculate the fluctuation signal characteristic of the signal in the set window length and extract the fluctuation signal characteristic. The method comprises the following steps: after the synthesized acceleration signal is subjected to filtering and denoising processing, the maximum value and the minimum value in a set window are found, and the fluctuation signal characteristic of the synthesized acceleration signal is calculated according to the difference between the maximum value and the minimum value. The composite acceleration signal fluctuation signal characteristic is used as a parameter in a sleep algorithm, and can be generally judged as a sleeping state when the signal characteristic is within a certain threshold range, and can be judged as a sleeping state when the signal characteristic is within another threshold range. In order to increase the accuracy, when the continuous composite acceleration signal fluctuation signal characteristics are all within the set threshold value range, corresponding judgment is made.
Referring to fig. 1, the method for acquiring the heart rate signal S2 in the sleep algorithm of the present invention includes:
firstly, an original heart rate wave (ppg) signal of a heart rate sensor is collected, and most of the existing heart rate sensors adopt a photoelectric volume pulse wave sensor which detects a human pulse signal through an optical signal so as to obtain a heart rate signal of a user.
Then, the collected heart rate wave signals are filtered and denoised, low-pass filtering of 3Hz (which can be adjusted according to actual conditions) is usually carried out to remove clutter, the pulse wave signal part in the signals is highlighted to obtain heart rate signals S2,
then, the waveform signal characteristics of the heart rate and the heart rate variability are extracted. In this step, the method for acquiring the heart rate and the waveform signal characteristics of the heart rate variability comprises the following steps: and detecting effective valley (peak) value points of the heart rate wave signal S2 subjected to filtering and denoising by using a valley (peak) value detection algorithm, and calculating the waveform signal characteristics of the heart rate and the heart rate variability according to the valley (peak) positions detected in the set window width and by combining the sampling rate. For example, the effective peak positions of the detection signals in the unit time T are respectively T1, T2 \8230 \ 8230, and when the corresponding effective peaks are detected at the time points, the heart rate of the user and the waveform signal characteristics of the heart rate change can be obtained according to the detection frequency. The heart rate and the waveform signal characteristics of the heart rate variability are used as another parameter in the sleep algorithm, and when the waveform signal characteristics are within a certain threshold value range, the sleep state can be judged. When the signal characteristic is within another threshold range, the sleep state can be judged. In order to increase accuracy, when the continuous signal characteristics are all within the set threshold value range, corresponding judgment is made.
As shown in fig. 1, the synthesized acceleration signal fluctuation signal characteristics and the waveform signal characteristics of the heart rate and the heart rate variability obtained by the algorithm are input into the algorithm in-and-out sleep detection module to preliminarily judge the sleep state of the user, and when the two signal characteristics are the same, a preliminary sleep state judgment result is obtained. And inputting the preliminary judgment result and the parameters of the mobile phone playing state detected by the mobile phone into the comprehensive in-and-out sleep detection module together to carry out the final sleep state judgment.
As shown in fig. 2a-2d, the detection of the user falling asleep and falling asleep by the in-and-out-of-sleep detection module, in combination with the foregoing, finally includes the following four situations.
1. The detection of the algorithm in-out sleep detection module is in a sleep state, the state of the mobile phone of the user is not playing the mobile phone, and the final judgment of the comprehensive in-out sleep detection module is as follows: and (5) falling asleep.
2. The detection of the algorithm in-out sleep detection module is in-sleep state, the state of the user mobile phone is in playing the mobile phone, and the final judgment of the comprehensive in-out sleep detection module is as follows: and if the user does not fall asleep, entering an algorithm out-of-sleep detection parameter updating module and caching the current data.
3. The detection of the algorithm in-out sleep detection module is in-out sleep state, the state of the user mobile phone is in playing the mobile phone, and the final judgment of the comprehensive in-out sleep detection module is as follows: go out to sleep.
4. If the algorithm out-of-sleep detection module does not detect that the user is in the out-of-sleep state and the user mobile phone state is playing the mobile phone, the comprehensive out-of-sleep detection module finally judges that: go out of sleep, buffer the current data.
And when the user is finally judged to enter the sleeping state and the sleeping out state, the user directly enters the sleeping in and sleeping out detection output state next step, the sleeping in or sleeping out state of the user is output to the intelligent equipment processing unit, and the intelligent equipment records the sleeping data of the user. Namely, through the detection and judgment, when the user enters the in-and-out sleeping detection output state, the judgment result is directly output.
When the sleep in and out detection parameter updating state of the algorithm is entered, the signal characteristics of the acceleration signal S1 and the heart rate signal S2 in the corresponding states are updated, and the model parameters set in the sleep algorithm are updated. The method comprises the steps of extracting the wave characteristics of a synthetic acceleration signal and the waveform signal characteristics of the heart rate and the heart rate variability from buffer data, combining the buffered label data, carrying out online retraining on the data, and updating model parameters.
Fig. 3 is a signal diagram of the acceleration signal S1 in an exemplary embodiment of the present invention. Wherein t1 is the time for playing the mobile phone when the user lies on the bed; t2 is the real time to fall asleep; t3 is the sleep-in time detected by the model after the sleep algorithm sleep-in detection module updates the parameters; and t4 is the preliminary sleep-in time detected before the sleep algorithm sleep-in detection module updates the parameters.
Therefore, by adopting a general sleep algorithm, the early-judged falling-asleep time t4 is advanced from the real falling-asleep time t2 by a longer time, and after the sleep algorithm after the parameters are continuously updated, the detected falling-asleep time is finally judged to be t3, so that the accuracy of the initial-judged falling-asleep time t2 is greatly improved relative to the accuracy of the initial-judged falling-asleep time t 4.
It should be understood that the above description is only exemplary of the present invention, and is not intended to limit the scope of the present invention, which is defined by the appended claims.
Claims (7)
1. A method for improving the accuracy of in-and-out sleep detection in a sleep algorithm of intelligent wearable equipment comprises the following steps: through integrated acceleration sensor and the rhythm of the heart sensor at intelligent wearing equipment, acquire corresponding original acceleration signal and original rhythm of the heart signal, through acquire acceleration signal S1 and rhythm of the heart signal S2 after to signal processing, obtain corresponding signal characteristic through the analytic processing to acceleration signal S1 and rhythm of the heart signal S2 to according to smart machine sleep algorithm, tentatively judge user' S state for falling asleep state or the state of falling asleep, its characterized in that:
the method introduces the state of the mobile phone as a parameter,
when the user is judged to be in the sleep state in the initial step and the mobile phone state of the user is not playing the mobile phone, the judgment is that: the user enters a sleeping state, and then enters a sleeping in and out detection output state;
when the user is judged to enter the sleep state at first and the mobile phone playing state of the user is the mobile phone playing state, the judgment is that: if the user does not enter the sleep state, the user enters the sleep in and out detection updating state;
when the user is judged to enter the sleep state in the initial step and the mobile phone playing state of the user is the mobile phone playing state, the judgment is that: the user enters a sleep-out state, and then enters a sleep-in and sleep-out detection output state;
when the user is judged not to fall asleep at the beginning, and the user plays the mobile phone, the judgment is that: the user enters a sleeping-out state, and then enters a sleeping-in/out detection output state and a sleeping-in/out detection updating state;
outputting a judgment result when the user enters a sleep in and out detection output state according to the judgment result; when the user enters the in-and-out sleep detection updating state, the signal characteristics of the acceleration signal S1 and the heart rate signal S2 in the corresponding states are updated according to the model parameters of the sleep algorithm of the intelligent device, and the accuracy of in-and-out sleep detection is continuously improved through continuous updating of the model parameters.
2. The method for improving the accuracy of the out-of-sleep detection in the sleep algorithm of the intelligent wearable device as claimed in claim 1, wherein the method comprises the following steps: the method for acquiring the acceleration signal S1 comprises the following steps: acquiring triaxial acceleration data xACC, yACC and zACC of an acceleration sensor, then carrying out vector synthesis operation on triaxial acceleration signals to obtain synthesized acceleration signals, carrying out filtering and denoising processing on the synthesized acceleration signals to obtain acceleration signals S1, and then calculating the fluctuation signal characteristics of the signals in a set time window.
3. The method for improving the accuracy of the out-of-sleep detection in the sleep algorithm of the intelligent wearable device according to claim 2, wherein the method comprises the following steps: in the method for acquiring the acceleration signal S1, the vector synthesis operation performed on the three-axis acceleration signal is: and (3) re-squaring the sum of squares of the three-axis acceleration signals, wherein the corresponding calculation formula is as follows:
4. the method for improving the accuracy of the out-of-sleep detection in the sleep algorithm of the intelligent wearable device according to claim 2, wherein the method comprises the following steps: and after filtering and denoising the synthesized acceleration signal, finding out the maximum value and the minimum value in a set window, and calculating the fluctuation signal characteristic of the synthesized acceleration signal according to the difference between the maximum value and the minimum value.
5. The method for improving the accuracy of the detection of going out of sleep in the sleep algorithm of the intelligent wearable device as claimed in claim 1, wherein: the method for acquiring the heart rate signal S2 comprises the following steps: the method comprises the steps of collecting heart rate wave signals of a heart rate sensor, then carrying out filtering and denoising processing on the collected heart rate wave signals to obtain heart rate signals S2, and then extracting waveform signal characteristics of heart rate and heart rate variability.
6. The method for improving the accuracy of the out-of-sleep detection in the sleep algorithm of the intelligent wearable device according to claim 5, characterized in that: the method for acquiring the waveform signal characteristics of the heart rate and the heart rate variability comprises the following steps: and detecting effective valley/peak points of the heart rate wave signal S2 subjected to filtering and denoising by using a valley/peak detection algorithm, and calculating to obtain the waveform signal characteristics of the heart rate and the heart rate variability according to the detected valley/peak positions in a set time window and in combination with the sampling rate.
7. The method for improving the accuracy of in-and-out sleep detection in the sleep algorithm of the intelligent wearable device according to any one of claims 1 to 6, wherein the method comprises the following steps: the intelligent wearable device comprises an intelligent watch and an intelligent bracelet, wherein the intelligent watch and the intelligent bracelet are provided with sleep monitoring functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210756042.2A CN115137308A (en) | 2022-06-29 | 2022-06-29 | Method for improving accuracy of in-out sleep detection in sleep algorithm of intelligent wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210756042.2A CN115137308A (en) | 2022-06-29 | 2022-06-29 | Method for improving accuracy of in-out sleep detection in sleep algorithm of intelligent wearable device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115137308A true CN115137308A (en) | 2022-10-04 |
Family
ID=83410286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210756042.2A Pending CN115137308A (en) | 2022-06-29 | 2022-06-29 | Method for improving accuracy of in-out sleep detection in sleep algorithm of intelligent wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115137308A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023217137A1 (en) * | 2022-05-09 | 2023-11-16 | 维沃移动通信有限公司 | Sleep data calibration method and electronic device |
| CN117370769A (en) * | 2023-12-08 | 2024-01-09 | 深圳市光速时代科技有限公司 | Intelligent wearable device data processing method suitable for sleep environment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050177051A1 (en) * | 2003-04-23 | 2005-08-11 | Quiescent, Inc. | Apparatus and method for monitoring heart rate variability |
| JP2016059736A (en) * | 2014-09-22 | 2016-04-25 | 株式会社東芝 | Biological information measurement apparatus and program |
| CN109091150A (en) * | 2017-11-29 | 2018-12-28 | 惠州市德赛工业研究院有限公司 | Recognition methods, sleep quality appraisal procedure and the intelligent wearable device that body of sleeping moves |
| CN112401838A (en) * | 2020-11-16 | 2021-02-26 | 上海创功通讯技术有限公司 | Method for detecting sleep state of wearable device and wearable device |
| CN114343587A (en) * | 2020-09-29 | 2022-04-15 | Oppo广东移动通信有限公司 | Sleep monitoring method and device, electronic equipment and computer readable medium |
-
2022
- 2022-06-29 CN CN202210756042.2A patent/CN115137308A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050177051A1 (en) * | 2003-04-23 | 2005-08-11 | Quiescent, Inc. | Apparatus and method for monitoring heart rate variability |
| JP2016059736A (en) * | 2014-09-22 | 2016-04-25 | 株式会社東芝 | Biological information measurement apparatus and program |
| CN109091150A (en) * | 2017-11-29 | 2018-12-28 | 惠州市德赛工业研究院有限公司 | Recognition methods, sleep quality appraisal procedure and the intelligent wearable device that body of sleeping moves |
| CN114343587A (en) * | 2020-09-29 | 2022-04-15 | Oppo广东移动通信有限公司 | Sleep monitoring method and device, electronic equipment and computer readable medium |
| CN112401838A (en) * | 2020-11-16 | 2021-02-26 | 上海创功通讯技术有限公司 | Method for detecting sleep state of wearable device and wearable device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023217137A1 (en) * | 2022-05-09 | 2023-11-16 | 维沃移动通信有限公司 | Sleep data calibration method and electronic device |
| CN117370769A (en) * | 2023-12-08 | 2024-01-09 | 深圳市光速时代科技有限公司 | Intelligent wearable device data processing method suitable for sleep environment |
| CN117370769B (en) * | 2023-12-08 | 2024-02-23 | 深圳市光速时代科技有限公司 | Intelligent wearable device data processing method suitable for sleep environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115137308A (en) | Method for improving accuracy of in-out sleep detection in sleep algorithm of intelligent wearable device | |
| CN104545844B (en) | Multi-parameter sleep monitoring and intelligent diagnosis system based on 4G mobile communication technology and application method of multi-parameter sleep monitoring and intelligent diagnosis system | |
| CN110664390B (en) | Heart rate monitoring system and method based on wrist strap type PPG and deep learning | |
| CN106919958B (en) | Human body finger action recognition method based on smart watch | |
| CN107106085A (en) | Apparatus and method for sleep monitor | |
| CN106228200A (en) | A kind of action identification method not relying on action message collecting device | |
| CN110850988B (en) | Anti-interference wrist-lifting screen-lighting method | |
| CN108392211A (en) | A kind of fatigue detection method based on Multi-information acquisition | |
| CN110123314A (en) | Judge that brain is absorbed in the method for relaxation state based on EEG signals | |
| CN105595996A (en) | Driving fatigue electroencephalogram monitoring method based on electrooculogram and electroencephalogram comprehensive determination | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN109840480B (en) | Interaction method and interaction system of smart watch | |
| CN112057066A (en) | Heart rate detection method, wearable device and computer storage medium | |
| CN112099624B (en) | Multimode diamond-shaped frame type capacitive sensing gesture recognition system | |
| CN113288095A (en) | Sleep health management method and system for calculating sleep cycle based on physical activity and heart rate information | |
| CN112043280A (en) | Dangerous driving behavior detection method and system based on smart phone gait recognition | |
| CN112294264A (en) | Sleep staging method based on BCG and blood oxygen saturation rate | |
| CN108992040A (en) | A kind of sleep quality state monitoring method and device | |
| CN115089179A (en) | Psychological emotion insights analysis method and system | |
| CN107765890A (en) | A kind of write content detection system and method based on acceleration transducer | |
| CN117272155A (en) | Intelligent watch-based driver road anger disease detection method | |
| CN116616708A (en) | Vital sign data processing method and system based on intelligent wearable device | |
| CN116115198A (en) | Low-power consumption snore automatic recording method and device based on physiological sign | |
| CN115770028A (en) | Blood pressure detection method, system, device and storage medium | |
| CN110710954A (en) | Method for detecting sleep quality through sound collection |
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 |