CN114073513A - Detection method and device for getting up at night during sleep and intelligent wearable equipment - Google Patents

Detection method and device for getting up at night during sleep and intelligent wearable equipment Download PDF

Info

Publication number
CN114073513A
CN114073513A CN202010796610.2A CN202010796610A CN114073513A CN 114073513 A CN114073513 A CN 114073513A CN 202010796610 A CN202010796610 A CN 202010796610A CN 114073513 A CN114073513 A CN 114073513A
Authority
CN
China
Prior art keywords
time point
activity
activity amount
preset threshold
determining
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.)
Withdrawn
Application number
CN202010796610.2A
Other languages
Chinese (zh)
Inventor
赵明喜
汪孔桥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Huami Health Technology Co Ltd
Original Assignee
Anhui Huami Health Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui Huami Health Technology Co Ltd filed Critical Anhui Huami Health Technology Co Ltd
Priority to CN202010796610.2A priority Critical patent/CN114073513A/en
Publication of CN114073513A publication Critical patent/CN114073513A/en
Withdrawn legal-status Critical Current

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
    • A61B5/103—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
    • A61B5/48—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

Abstract

The invention provides a detection method and a detection device for rising night in sleep and intelligent wearable equipment, wherein the detection method comprises the following steps: acquiring the activity amount generated in the sleeping process of a user; calculating the duration of the activity amount of the user when the activity amount is greater than a first preset threshold; and when the duration of the activity amount is greater than a second preset threshold value, determining that the user is up to night. According to the invention, through a new activity measurement method, additional storage overhead is not required to be added, and the overnight activity of the user in sleep can be efficiently and accurately detected, so that better user experience is brought.

Description

Detection method and device for getting up at night during sleep and intelligent wearable equipment
Technical Field
The invention relates to the technical field of sleep detection, in particular to a sleep-midnight detection method/device and intelligent wearable equipment.
Background
The sleep detection is an important function of the wearable device, the sleep night detection is an important subtask, and the existing night detection is basically based on an acceleration sensor. The acceleration sensor can measure X, Y, Z acceleration values in three directions respectively, the value of the X direction represents horizontal movement, the value of the Y direction represents vertical movement, the value of the Z direction represents the spatial vertical direction, the sky direction is positive, the earth direction is negative, the acceleration sensor finally transmits the related acceleration values to the operating system, and the operating system judges whether the user is at night according to the change of the acceleration values.
Since the sampling rate of the acceleration sensor is generally set to 25Hz in consideration of the balance of power consumption and performance, even with such a low sampling rate, the wearable device may not hold all of the raw sampling data. Data is typically stored in units of minutes, and the size of data stored per minute is also very limited, typically between 16 and 24 bytes. When the wearable device and the mobile phone are connected, the data of the minutes are uploaded to the mobile phone end, and then the mobile phone end performs sleep analysis on the data, wherein important analysis items comprise time points of going in and out of sleep and night activities in sleep.
Whereas in the current solution there are many false positives for the detection of overnight activity, fragmented activity is linked together due to time granularity on the order of minutes, such as two hand lifts or turns, but if the intervening interval is less than one minute, this will be considered continuous activity. One existing solution is to reduce the length of the unit time, i.e. to the order of minutes to seconds, such as 30 seconds. This reduces false positives, but does not substantially eliminate them, and increases storage overhead.
Disclosure of Invention
Objects of the invention
The invention aims to provide a method and a device for detecting the night in sleep and intelligent wearable equipment.
(II) technical scheme
To solve the above problem, according to an aspect of the present invention, there is provided a method for detecting nighttime in sleep, comprising: acquiring the activity amount generated in the sleeping process of a user; calculating the duration of the activity amount of the user when the activity amount is greater than a first preset threshold; and when the duration of the activity amount is greater than a second preset threshold, determining that the user is up to night.
Further, calculating the duration of the activity amount of the user from the acquired activity amount includes: determining a time point for starting to generate the activity amount as an activity starting time point; determining a time point at which the sleep data is again generated after the start time point as an activity end time point; the duration time is calculated from the activity start time point and the activity end time point of the activity amount.
Further, the step of determining the amount of activity to begin generating includes: when the activity amount is larger than a first preset threshold value, determining that the activity amount starts to be generated; or when the activity amount is larger than a first preset threshold and at least a preset first time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount being greater than the first preset threshold value is the first time point.
Further, the step of determining an activity end time point includes: when the activity amount is smaller than a first preset threshold value, determining an activity ending time point; or when the activity amount is smaller than a first preset threshold value and at least a preset second time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount smaller than the first preset threshold value is a second time point.
Further, the step of determining that the user is up to night comprises: acquiring a time gap of the duration of adjacent activity amounts; when the time gap is smaller than a third preset threshold, combining the duration of the adjacent activity amount into a time period; when the time period is greater than a second preset threshold value, determining that the user is staying at night; the third preset threshold is used for determining whether the adjacent activity amount is continuous, and the second preset threshold is used for determining whether the continuous adjacent activity amount is overnight.
Further, acquiring the activity amount generated in the sleeping process of the user through an acceleration sensor; and performing a weighted average algorithm on historical data acquired by the acceleration sensor to obtain a first preset threshold, a second preset threshold and a third preset threshold.
According to another aspect of the invention, there is provided a detection apparatus for waking up during sleep, comprising: the device comprises a data acquisition module, a first processing module and a second processing module; the data acquisition module is used for acquiring activity generated in the sleeping process of a user and sending the activity to the first processing module; the first processing module is used for judging whether the received activity amount is greater than a first preset threshold value, calculating the duration time of the activity amount of the user when the activity amount is greater than the first preset threshold value, and sending the duration time to the second processing module; the second processing module judges whether the user gets up to night or not based on the duration of the activity amount, and determines that the user gets up to night when the duration is larger than a second preset threshold.
Further, the first processing module comprises: a first determination unit configured to determine a time point at which generation of the activity amount starts as an activity start time point; a second determination unit for determining a time point at which the sleep data is again generated after the start time point as an activity end time point; and a calculation unit that calculates the duration time from the activity start time point and the activity end time point of the activity amount.
Further, the first processing module further comprises: the first processing unit is used for determining to start generating the activity amount when the activity amount is larger than a first preset threshold value; or when the activity amount is larger than a first preset threshold and at least a preset first time point exists before the current time point, determining that the activity amount is generated from the current time point; the time point corresponding to the activity amount being greater than the first preset threshold value is a first time point; the second processing unit is used for determining an activity ending time point when the activity amount is smaller than a first preset threshold; or when the activity amount is smaller than a first preset threshold value and at least a preset second time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount smaller than the first preset threshold value is a second time point.
Further, the second processing module comprises: an acquisition subunit configured to acquire a time gap of durations of adjacent activity amounts; a merging unit, configured to merge the durations of the adjacent activity amounts into a time period when the time gap is smaller than a third preset threshold; and the detection determining unit is used for determining that the user is up night when the time period is greater than a second preset threshold.
Further, the data acquisition module comprises: the acceleration sensor is used for acquiring the activity amount generated in the sleeping process of the user; and the threshold determining unit is used for performing a weighted average algorithm on the historical data acquired by the acceleration sensor to obtain a first preset threshold, a second preset threshold and a third preset threshold.
According to another aspect of the present invention, the present invention provides a smart wearable device, including the above-explained detection apparatus for waking up during sleep, further including: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to: acquiring the activity amount generated in the sleeping process of a user; calculating the duration of the activity amount of the user when the activity amount is greater than a first preset threshold; and when the duration of the activity amount is greater than a second preset threshold, determining that the user is up to night.
(III) advantageous effects
The technical scheme of the invention has the following beneficial technical effects:
the sleep-starting activity in sleep can be efficiently and accurately detected, so that better user experience is brought.
Drawings
FIG. 1 is a flow chart of a method for detecting nighttime sleep provided by the present invention;
FIG. 2 is a flowchart of step S2 in the method for detecting nighttime in sleep according to the present invention;
FIG. 3 is a flowchart of step S3 in the method for detecting nighttime in sleep according to the present invention;
FIG. 4 is a flowchart of an embodiment of step S2 of the method for detecting an overnight-in-sleep event provided by the present invention;
FIG. 5 is a flowchart of an embodiment of step S3 of the method for detecting an overnight-in-sleep event provided by the present invention;
fig. 6 is a block diagram of a detection device for waking up during sleep according to the present invention.
Reference numerals:
1-a data acquisition module; 2-a first processing module; 3-a second processing module; 101-an acquisition subunit; 102-determining a threshold unit; 201-a first determination unit; 202-a second determination unit; 203-a calculation unit; 301-an acquisition subunit; 302-a merging unit; 303-a detection determination unit; s1, S2, S3, S21, S22, S23, S31, S32, S33-steps.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The present invention will be described in detail below with reference to the accompanying drawings and examples.
Fig. 1 is a flowchart of a method for detecting nighttime in sleep provided by the present invention.
The invention provides a detection method for rising night in sleep, which comprises the following steps:
s1: acquiring the activity amount generated in the sleeping process of a user;
s2: calculating the duration of the activity amount of the user when the activity amount is greater than a first preset threshold;
s3: and when the duration of the activity amount is greater than a second preset threshold, determining that the user is up to night.
Specifically, in step S1, the activity amount generated during the sleep process of the user is obtained through the three-axis acceleration sensor, the three-axis acceleration sensor pre-installed on the intelligent wearable device is firstly adopted to collect acceleration data generated in the x, y, and z three direction axes during the sleep process of the user in real time, the difference of the three-axis acceleration on the time axis is calculated, the change amount of the acceleration data, namely the distance degree, is represented by the difference, and the activity amount generated during the sleep process of the user can be obtained by calculating the difference of the three-axis acceleration on the time axis according to the correlation.
Wherein the activity FiComprises the following steps: an accumulated or maximum value of activity per unit time.
The duration of activity T is: single frame activity F greater than first preset thresholdiDuration of (i.e. amount of single frame activity F)iTime to start to generate to single frame activityFiThe time of the end.
The night activities are as follows: if the amount of activity in sleep FiContinuously exceeds a first preset threshold value and activity FiIs greater than a second preset threshold, is defined as an overnight activity.
The first preset threshold and the second preset threshold are obtained by statistics according to historical data acquired by the triaxial acceleration sensor, and specifically, a weighted average algorithm is adopted to calculate the average value of the historical data so as to ensure that the obtained data conforms to all users.
In one embodiment, the activity F is obtained using a three-axis acceleration sensor based on minute-scale dataiWhen the sampling rate is 25hz, there are 60 × 25 data points in a minute, and the activity F is presentiThe calculation is carried out according to the following formula:
∑i＝1 sqrt(xi 2+yi 2+zi 2) (1)
or
MAXi(sqrt(xi 2+yi 2+zi 2)) (2)
In the above formulas (1) and (2), i ranges from 1 to 60 × 25; x, y, z are differences of the accelerations of the three directional axes on the time axis (generally, differences of 1-5 orders, and the change amount of the acceleration, that is, the moving distance degree, is expressed by the difference); sqrt (x)i 2+yi 2+zi 2) For a single frame activity Fi. The frame refers to one data point, and when the sampling rate is 25hz, there are 25 data frames per second.
Thus, in one embodiment, step S1 includes:
s11: differences x, y, z of accelerations of three directional axes of a current frame i (i >0) on a time axis are received.
S12: substituting x, y and z into formula (1) or (2) to calculate the activity F of the current framei。
Fig. 2 is a flowchart of step S2 in the method for detecting nighttime sleep provided by the present invention, please refer to fig. 2, in an embodiment, step S2 includes:
s21: determining a time point for starting to generate the activity amount as an activity starting time point;
s22: determining a time point at which the sleep data is again generated after the start time point as an activity end time point;
s23: the duration time is calculated from the activity start time point and the activity end time point of the activity amount.
Optionally, in step S21, the step of determining the start of generation of the activity amount includes: when the activity amount is greater than a first preset threshold, it is determined that the activity amount starts to be generated.
The first preset threshold is used for judging whether the activity of the user occurs in the sleeping process. Therefore, when the user has an activity amount at a time point during the sleep and the activity amount is greater than the first preset threshold, the time point is taken as an activity start time point.
Optionally, in step S21, the step of determining the start of generation of the activity amount includes: when the activity amount is larger than a first preset threshold value and at least a preset first time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount being greater than the first preset threshold value is the first time point.
Specifically, to prevent accidental errors from occurring in the data, it is determined whether the activity amount at a time point is greater than a first preset threshold, and at the same time, it is determined whether the activity amount at a first preset time point before the time point is also greater than the first preset threshold.
In this step, the activity amount at each time point is calculated only once, and the calculated activity amounts are stored in one buffer. And when the comparison with the first preset threshold value is needed, calling the activity of the buffer area.
Optionally, in step S22, the step of determining the activity end time point includes: and when the activity amount is less than a first preset threshold value, determining an activity ending time point.
Specifically, step S21 has determined that the user is in an active state, and step S22 is to determine whether the user ends the activity and to determine a time point at which the activity is ended.
When it is detected that the activity amount of the user is smaller than the first preset threshold, it is indicated that the user is already asleep at the time point, i.e., the user has recovered from the active state to the sleep state, and thus the time point is taken as an activity end time point.
Optionally, in step S22, the step of determining the activity end time point includes: when the activity amount is smaller than a first preset threshold value and at least a preset second time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount smaller than the first preset threshold value is a second time point.
Specifically, to prevent accidental errors from occurring in the data, it is determined whether the activity level at a time point is less than a first preset threshold, and at the same time, it is determined whether the activity level at a second time point that is a preset time point before the time point is also less than the first preset threshold.
In this step, the activity amount at each time point is calculated only once, and the calculated activity amounts are stored in one buffer. And when the comparison with the first preset threshold value is needed, calling the activity of the buffer area.
Specifically, step S23 is for calculating a duration of the amount of activity, the duration of the amount of activity being used to characterize a time interval during which the user is active while sleeping. The duration of the activity amount is equal to the activity end time point-the activity start time point.
Fig. 3 is a flowchart of step S3 in the method for detecting nighttime sleep provided by the present invention, please refer to fig. 3, in an embodiment, step S3 includes:
s31: acquiring a time gap of the duration of adjacent activity amounts;
s32: when the time gap is smaller than a third preset threshold, combining the duration of the adjacent activity amount into a time period;
s33: when the time period is greater than a second preset threshold value, determining that the user is staying at night;
the third preset threshold is used for determining whether the adjacent activity amount is continuous, and the second preset threshold is used for determining whether the continuous adjacent activity amount is overnight.
Specifically, a time interval of the durations of a series of activity amounts is first acquired, and if the duration interval of adjacent activity amounts is shorter, it is indicated that the adjacent activity amounts are continuous, so the third preset threshold is used to determine whether the adjacent activity amounts are continuous.
And the third preset threshold is obtained by statistics according to historical data acquired by the triaxial acceleration sensor, and specifically, the average value of the historical data is calculated by adopting a weighted average algorithm so as to ensure that the obtained data conforms to all users.
If the adjacent activity amounts are continuous, combining the adjacent activity amounts into a time period; if the time period is longer, the longer the activity duration is, and the user is in the night at the moment, so that the second preset threshold is used for judging whether the duration of the time period meets the condition that the user is in the night.
In the following, a detailed description is given by way of specific examples, fig. 4 is a flowchart of an example of step S2 of the detection method for waking up during sleep provided by the present invention, fig. 5 is a flowchart of an example of step S3 of the detection method for waking up during sleep provided by the present invention, please see fig. 4 and fig. 5.
Example (b):
the method comprises the following steps: firstly, acquiring the activity F generated in the sleeping process of a user at the current time point through an acceleration sensori。
Step two: judging the activity F at the current time pointiIs greater than a first preset threshold δ, and there are at least α first time points of activity quantity F before the current time pointiIs also greater than the first preset threshold δ; if so, marking the current time point as an activity starting time point.
If not, directly carrying out the next step.
Step three: judging the activity F of the current time pointiIs smaller than a first preset threshold δ, and there are at least α second time points of activity quantity F before the current time pointiWhether all values of (A) are less than a first preset threshold valueδ; if the current time point is smaller than the activity end time point, marking the current time point as the activity end time point, and showing that the user is in a sleep state at the moment.
And if not, detecting the activity amount of the next time point.
Step three: the duration of the activity amount is calculated, and the duration of the activity amount is the activity ending time point-the activity starting time point.
Step four: detecting activity amounts at a plurality of time points to obtain a series of ordered activity amount duration times, and judging whether time gaps of the adjacent activity amount duration times are smaller than a third preset threshold value tau, if so, combining the adjacent activity amount duration times into a time period Ti。
Step five: judging the time period T obtained in the step fouriIf the duration is greater than a second preset threshold beta, if so, determining that the user is in the night, and the time period T isiThe user's overnight time while sleeping.
Fig. 6 is a block diagram of a detection device for overnight sleep provided by the present invention, please refer to fig. 6.
The invention also provides a device for detecting the night in sleep, which comprises: the device comprises a data acquisition module 1, a first processing module 2 and a second processing module 3. The data acquisition module 1 is used for acquiring activity generated in the sleeping process of a user and sending the activity to the first processing module 2; the first processing module 2 is configured to determine whether the received activity amount is greater than a first preset threshold, calculate a duration of the activity amount of the user when the activity amount is greater than the first preset threshold, and send the duration to the second processing module 3; the second processing module judges whether the user gets up to night or not based on the duration of the activity amount, and determines that the user gets up to night when the duration is larger than a second preset threshold.
In one embodiment, the data acquisition module 1 includes: an acquisition sub-unit 101 and a threshold determination unit 102. The acquisition subunit 101 is an acceleration sensor, and is configured to detect an activity amount generated during a sleep process of a user, and send the activity amount to the first processing module 2; the threshold determining unit 102 is configured to perform a weighted average algorithm on historical data acquired by the acceleration sensor to obtain a first preset threshold, a second preset threshold, and a third preset threshold, and send the first preset threshold, the second preset threshold, and the third preset threshold to the first processing module 2.
In an embodiment, the first processing module 2 comprises: a first determining unit 201, a second determining unit 202 and a calculating unit 203. The first determination unit 201 is configured to determine a time point at which generation of the activity amount is started as an activity start time point; the second determining unit 202 is configured to determine a time point at which the sleep data is again generated after the start time point as an activity end time point; the calculation unit 203 is configured to calculate the duration time according to the activity start time point and the activity end time point of the activity amount.
The first processing module 2 further comprises: a first processing unit and a second processing unit. The first processing unit is used for determining to start generating the activity amount when the activity amount is larger than a first preset threshold value; or when the activity amount is larger than a first preset threshold and at least a preset first time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount being greater than the first preset threshold value is the first time point. The second processing unit is used for determining an activity ending time point when the activity amount is smaller than a first preset threshold; or when the activity amount is smaller than a first preset threshold value and at least a preset second time point exists before the current time point, determining that the activity amount is generated from the current time point; and the time point corresponding to the activity amount smaller than the first preset threshold value is a second time point.
In an embodiment, the second processing module 3 comprises: an acquisition sub-unit 301, a merging unit 302, and a detection determination unit 303. The acquisition subunit 301 is configured to acquire a time gap of durations of adjacent activity amounts; the merging unit 302 is configured to merge the durations of the adjacent activity amounts into a time period when the time gap is smaller than a third preset threshold; the detection determining unit 303 is configured to determine that the user is up night when the time period is greater than a second preset threshold.
The invention also provides an intelligent wearable device, which comprises the detection device for waking up in sleep, and further comprises: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to: acquiring the activity amount generated in the sleeping process of a user; calculating the duration of the activity amount of the user when the activity amount is greater than a first preset threshold; and when the duration is greater than a second preset threshold, determining that the user is up to night.
The invention aims to protect a detection method and a device for rising night in sleep and intelligent wearable equipment, wherein the detection method for rising night in sleep comprises the following steps: acquiring the activity amount generated in the sleeping process of a user; calculating the duration of the activity amount of the user when the activity amount is greater than a first preset threshold; and when the duration is greater than a second preset threshold, determining that the user is up to night. The detection device for getting up in sleep comprises: the device comprises a data acquisition module, a first processing module and a second processing module; the data acquisition module is used for acquiring activity generated in the sleeping process of a user and sending the activity to the first processing module; the first processing module is used for judging whether the received activity amount is greater than a first preset threshold value, calculating the duration time of the activity amount of the user when the activity amount is greater than the first preset threshold value, and sending the duration time to the second processing module; the second processing module judges whether the user gets up to night or not based on the duration of the activity amount, and determines that the user gets up to night when the duration is larger than a second preset threshold. The intelligent wearable device comprises the detection device for getting up to night in sleep. Therefore, the method and the device for detecting the night in sleep and the intelligent wearable device can efficiently and accurately detect the night activity of the user in sleep by a new activity measurement method without adding extra storage overhead, thereby bringing better user experience.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.

Claims (12)

1. A method for detecting nighttime in sleep, comprising:
acquiring the activity amount generated in the sleeping process of a user;
calculating a duration of the activity amount of the user when the activity amount is greater than a first preset threshold;
and when the duration of the activity amount is greater than a second preset threshold, determining that the user is up to night.
2. The detection method according to claim 1, wherein the calculating a duration of the activity amount of the user from the acquired activity amount comprises:
determining a time point at which the generation of the activity amount is started as the activity start time point;
determining a time point at which sleep data is again generated after the start time point as the activity end time point;
calculating the duration time according to the activity starting time point and the activity ending time point of the activity amount.
3. The detection method according to claim 2, wherein the step of determining the onset of the generation of the activity amount comprises:
when the activity amount is larger than a first preset threshold value, determining to start generating the activity amount; or
When the activity amount is larger than a first preset threshold value and at least a preset first time point exists before a current time point, determining that the activity amount is generated from the current time point;
and the time point corresponding to the activity amount larger than the first preset threshold value is a first time point.
4. The detection method according to claim 2 or 3, wherein the step of determining the activity end time point comprises:
when the activity amount is smaller than a first preset threshold value, determining an activity ending time point; or
When the activity amount is smaller than a first preset threshold value and at least a preset second time point exists before a current time point, determining that the activity amount is generated from the beginning of the current time point;
and the time point corresponding to the activity amount smaller than the first preset threshold value is a second time point.
5. The detection method according to claim 4, wherein the step of determining that the user is up to night comprises:
obtaining a time gap adjacent to the duration of the activity measure;
when the time gap is smaller than a third preset threshold, combining the durations of the adjacent activity amounts into a time period;
when the time period is greater than a second preset threshold value, determining that the user is staying at night;
the third preset threshold is used for determining whether the adjacent activity amount is continuous, and the second preset threshold is used for determining whether the continuous adjacent activity amount is overnight.
6. The detection method according to claim 5,
acquiring activity amount generated in the sleeping process of a user through an acceleration sensor;
and performing a weighted average algorithm on historical data acquired by the acceleration sensor to obtain the first preset threshold, the second preset threshold and the third preset threshold.
7. A sleep overnight detection device, comprising: the device comprises a data acquisition module, a first processing module and a second processing module;
the data acquisition module is used for acquiring activity generated in the sleeping process of a user and sending the activity to the first processing module;
the first processing module is used for judging whether the received activity amount is greater than a first preset threshold value, calculating the duration time of the activity amount of the user when the activity amount is greater than the first preset threshold value, and sending the duration time to the second processing module;
and the second processing module judges whether the user gets up to night or not based on the duration of the activity amount, and determines that the user gets up to night when the duration is greater than a second preset threshold.
8. The detection apparatus according to claim 6,
the first processing module comprises:
a first determination unit configured to determine a time point at which generation of the activity amount is started as the activity start time point;
a second determination unit for determining a time point at which sleep data is again generated after the start time point as the activity end time point;
and the calculating unit calculates the duration according to the activity starting time point and the activity ending time point of the activity amount.
9. The detection apparatus according to claim 8,
the first processing module further comprises:
the first processing unit is used for determining to start generating the activity amount when the activity amount is larger than a first preset threshold value; or when the activity amount is larger than a first preset threshold and at least a preset first time point exists before a current time point, determining that the activity amount is generated from the current time point; the time point corresponding to the activity amount larger than the first preset threshold is a first time point;
the second processing unit is used for determining the activity ending time point when the activity amount is smaller than a first preset threshold; or when the activity amount is smaller than a first preset threshold value and at least a preset second time point exists before the current time point, determining that the activity amount is generated from the beginning of the current time point; and the time point corresponding to the activity amount smaller than the first preset threshold value is a second time point.
10. The detection apparatus according to claim 9,
the second processing module comprises:
an acquisition subunit configured to acquire a time gap adjacent to a duration of the activity amount;
a merging unit, configured to merge the durations of the adjacent activity amounts into a time period when the time gap is smaller than a third preset threshold;
and the detection determining unit is used for determining that the user is up to night when the time period is greater than a second preset threshold value.
11. The detection apparatus according to claim 10,
the data acquisition module comprises:
the acquisition subunit is an acceleration sensor and is used for acquiring the activity generated in the sleeping process of the user;
and the threshold determining unit is used for performing a weighted average algorithm on the historical data acquired by the acceleration sensor to obtain the first preset threshold, the second preset threshold and the third preset threshold.
12. A smart wearable device comprising the sleep overnight detection apparatus of any of claims 6-11, further comprising: a processor and a memory for storing processor-executable instructions;
wherein the processor is configured to:
acquiring the activity amount generated in the sleeping process of a user;
calculating a duration of the activity amount of the user when the activity amount is greater than a first preset threshold;
and when the duration of the activity amount is greater than a second preset threshold, determining that the user is up to night.
CN202010796610.2A 2020-08-10 2020-08-10 Detection method and device for getting up at night during sleep and intelligent wearable equipment Withdrawn CN114073513A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010796610.2A CN114073513A (en) 2020-08-10 2020-08-10 Detection method and device for getting up at night during sleep and intelligent wearable equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010796610.2A CN114073513A (en) 2020-08-10 2020-08-10 Detection method and device for getting up at night during sleep and intelligent wearable equipment

Publications (1)

Publication Number Publication Date
CN114073513A true CN114073513A (en) 2022-02-22

Family

ID=80279543

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010796610.2A Withdrawn CN114073513A (en) 2020-08-10 2020-08-10 Detection method and device for getting up at night during sleep and intelligent wearable equipment

Country Status (1)

Country Link
CN (1) CN114073513A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005124858A (en) * 2003-10-24 2005-05-19 Yamatake Corp Action state judgment apparatus, watching supporting system, and method for action state judgment
JP2010264193A (en) * 2009-05-18 2010-11-25 Paramount Bed Co Ltd Sleeping condition decision instrument, program, and sleeping condition decision system
CN104952210A (en) * 2015-05-15 2015-09-30 南京邮电大学 Fatigue driving state detecting system and method based on decision-making level data integration
CN107184217A (en) * 2017-07-06 2017-09-22 深圳市新元素医疗技术开发有限公司 A kind of circadian rhythm analysis method
CN108430309A (en) * 2016-11-30 2018-08-21 华为技术有限公司 A kind of sleep monitor method, apparatus and terminal

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005124858A (en) * 2003-10-24 2005-05-19 Yamatake Corp Action state judgment apparatus, watching supporting system, and method for action state judgment
JP2010264193A (en) * 2009-05-18 2010-11-25 Paramount Bed Co Ltd Sleeping condition decision instrument, program, and sleeping condition decision system
CN104952210A (en) * 2015-05-15 2015-09-30 南京邮电大学 Fatigue driving state detecting system and method based on decision-making level data integration
CN108430309A (en) * 2016-11-30 2018-08-21 华为技术有限公司 A kind of sleep monitor method, apparatus and terminal
CN107184217A (en) * 2017-07-06 2017-09-22 深圳市新元素医疗技术开发有限公司 A kind of circadian rhythm analysis method

Similar Documents

Publication Publication Date Title
CN108076218B (en) Charging reminding method and mobile terminal
US8560229B1 (en) Sensor based activity detection
CN102973276B (en) Device for preventing myopia and cervical spondylosis
US20220163348A1 (en) Positioning method and electronic device
US20110077865A1 (en) Fall detection system
US20220246015A1 (en) Fall detection method and apparatus, and wearable device
US20130285813A1 (en) Portable electronic apparatus, and falling prediction method
CN106510720B (en) User state prompting method and device
CN109581437B (en) Wearable device and positioning method and device thereof
CN104406603A (en) Step-counting method based on acceleration sensor and device thereof
CN107608855B (en) Reminding method and mobile terminal
CN104834896A (en) Method and terminal for information acquisition
CN103492884A (en) Low average velocity pedestrial motion identification
JP5382719B2 (en) Behavior and condition monitoring method and program
CN212089543U (en) Posture detection equipment and necklace
US20180199876A1 (en) User Health Monitoring Method, Monitoring Device, and Monitoring Terminal
CN107638165B (en) Sleep detection method and device
CN111148166B (en) Network optimization method based on wearable device and wearable device
JP2009163538A (en) Fall determination system, fall determination method, and fall determination program
CN114073513A (en) Detection method and device for getting up at night during sleep and intelligent wearable equipment
CN111637975A (en) Wrist temperature measuring method and device, wearable device and storage medium
US9820223B2 (en) Method and system for managing a location detector
JP5522338B2 (en) Situation judging device, situation judging system, method and program thereof
CN111084624A (en) Body posture detection method and device and necklace
CN114926959A (en) Self-power-generation old man falling alarm device and falling judgment method thereof

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20220222