CN116649917B - Sleep quality monitoring method and device and wearable equipment - Google Patents

Abstract

The application discloses a sleep quality monitoring method, a sleep quality monitoring device and wearable equipment, wherein the sleep quality monitoring method comprises the following steps: calculating to obtain first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window; determining a deep sleep time alternative interval and a deep sleep ending time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval; and determining a time point when the target subject enters the deep sleep based on the distribution state of the first PPG signal quality data in the deep sleep time alternative interval, and determining a time point when the target subject ends the deep sleep based on the distribution state of the first PPG signal quality data in the deep sleep end time alternative interval. The method utilizes the characteristic of poor motion disturbance resistance of PPG signal quality, and has higher sensitivity and accuracy on the judgment result of the deep sleep time.

Description

Sleep quality monitoring method and device and wearable equipment

Technical Field

The application relates to the technical field of health monitoring, in particular to a sleep quality monitoring method. The application also relates to a sleep quality monitoring device and a wearable device.

Background

Conventional deep sleep recognition algorithms often use accelerometer (accounter, abbreviated as acc) and gyroscope (gyroscillo) data, and the principle is as follows: when a user enters a deep sleep state, the body of the user usually keeps a resting state, whether the body of the user is in the resting state can be determined by detecting vibration in the acc, gyro and other data, and if the body of the user is continuously in the resting state, the user can be inferred to enter the deep sleep state.

However, the above manner has the following drawbacks:

accelerometer or gyroscope can cause misjudgment in deep sleep due to mechanical noise and data drift problems of its sensor.

Disclosure of Invention

The invention provides a sleep quality monitoring method and device and wearable equipment, and aims to solve the problems in the prior art.

To solve or improve the above technical problems to a certain extent, according to an aspect of the present invention, there is provided a sleep quality monitoring method, including:

sliding window is carried out on the PPG signal quality of a target object in a sleep state based on preset first characteristic windows, first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window is obtained through calculation, the first PPG signal quality data represent PPG signal quality to be higher than a first quality threshold, and the second PPG signal quality data represent PPG signal quality to be lower than the first quality threshold;

Determining a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval;

determining a time point when the target subject enters deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep time candidate interval, and determining a time point when the target subject ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep end time candidate interval.

In some embodiments, the method further comprises:

and determining a time interval between a time point when the target object enters deep sleep and a time point when the target object finishes deep sleep as a deep sleep time interval of the target object, and determining a time length corresponding to the first PPG signal quality data in the deep sleep time interval as a deep sleep time length of the target object.

In some embodiments, the determining, from each preset first time interval, a deep sleep time alternative interval and a deep sleep end time alternative interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval includes:

determining the first target time interval as a deep sleep time alternative interval in response to the proportion of the first PPG signal quality data in a first target time interval in each preset first time interval being higher than a first proportion threshold or the proportion of the second PPG signal quality data being lower than a second proportion threshold; and determining the second target time interval as a deep sleep ending time alternative interval in response to the proportion of the first PPG signal quality data in a second target time interval in each preset first time interval being lower than a third proportion threshold or the proportion of the second PPG signal quality data being higher than a fourth proportion threshold, wherein the first proportion threshold is not smaller than the second proportion threshold and the third proportion threshold is not larger than the fourth proportion threshold.

In some embodiments, the determining a point in time at which the target subject enters deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep onset time interval comprises:

determining a time point when the first PPG signal quality data starts to be stably distributed in the deep sleep time alternative interval as a time point when the target subject enters deep sleep; or, in response to the first PPG signal quality data remaining stably distributed from the starting position of the deep sleep onset time alternative interval, determining a point in time at which the first PPG signal quality data starts to be stably distributed in a previous time interval of the deep sleep onset time alternative interval as a point in time at which the target subject enters deep sleep;

the determining, based on the distribution state of the second PPG signal quality data in the deep sleep time alternative interval, a time point at which the target subject enters deep sleep includes:

determining a starting time point of continuous zero distribution of the second PPG signal quality data in the deep sleep time alternative interval as a time point of the target object entering deep sleep; or, in response to the second PPG signal quality data maintaining a zero distribution from a starting position of the deep sleep onset time alternative interval, determining a starting time point of the second PPG signal quality data continuing the zero distribution in a previous time interval of the deep sleep onset time alternative interval as a time point of the target subject entering deep sleep.

In some embodiments, the determining a point in time at which the target subject ends deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep end time candidate interval comprises:

determining a time point of the first PPG signal quality data beginning discrete distribution in the deep sleep ending time alternative interval as a time point of ending deep sleep of the target subject; or, in response to the first PPG signal quality data remaining discretely distributed from a starting position of the deep sleep end time alternative interval, determining a point in time at which the first PPG signal quality data starts discretely distributed in a previous time interval of the deep sleep end time alternative interval as a point in time at which the target subject ends deep sleep;

determining a point in time at which the target subject ends deep sleep based on a distribution state of the second PPG signal quality data in the deep sleep end time candidate interval, comprising:

determining a time point at which the second PPG signal quality data starts to appear in the deep sleep end time alternative interval as a time point at which the target subject ends deep sleep; or in response to the starting position of the deep sleep ending time alternative interval being the second PPG signal quality data, determining a time point at which the second PPG signal quality data starts to appear in a previous time interval of the deep sleep ending time alternative interval as a time point at which the target subject ends deep sleep.

In some embodiments, before the calculating obtains the first PPG signal quality data or the second PPG signal quality data corresponding to each first feature window, the method further comprises:

sliding window is carried out on the PPG signal quality of the target object based on preset second characteristic windows, third PPG signal quality data or fourth PPG signal quality data corresponding to each second characteristic window is obtained through calculation, the third PPG signal quality data represents that the PPG signal quality is higher than a second quality threshold, the second PPG signal quality data represents that the PPG signal quality is lower than the second quality threshold, and the second quality threshold is smaller than the first quality threshold;

and determining an alternative sleep time interval from each preset second time interval based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, and determining a sleep time point of the target object based on the distribution state of the third PPG signal quality data or the distribution state of the fourth PPG signal quality data in the alternative sleep time interval.

In some embodiments, the determining, based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, an alternative sleep time interval from the preset second time interval includes:

And determining the third target time interval as an alternative sleep time interval in response to the proportion of the third PPG signal quality data in the third target time interval in each preset second time interval being higher than a fifth proportion threshold or the proportion of the fourth PPG signal quality data being lower than a sixth proportion threshold, wherein the fifth proportion threshold is not smaller than the sixth proportion threshold.

In some embodiments, the determining a point in time of falling asleep of the target subject based on the distribution state of the third PPG signal quality data in the alternative falling asleep time interval comprises:

determining a point in time at which the third PPG signal quality data starts to be steadily distributed in the alternative sleep-on time interval as a sleep-on time point of the target subject; or, in response to the third PPG signal quality data remaining steadily distributed from the starting position of the alternative sleep-on time interval, determining a point in time at which the third PPG signal quality data starts steadily distributed in the last time interval of the alternative sleep-on time interval as a sleep-on time point of the target subject;

the determining a sleep time point of the target subject based on a distribution state of the fourth PPG signal quality data in the alternative sleep time interval comprises:

Determining a starting time point of the fourth PPG signal quality data continuous zero distribution in the alternative sleep time interval as a sleep time point of the target subject; or, in response to the fourth PPG signal quality data maintaining a zero distribution from a starting position of the alternative sleep-on time interval, determining a starting time point of the fourth PPG signal quality data continuing zero distribution in a last time interval of the alternative sleep-on time interval as a sleep-on time point of the target subject.

According to another aspect of the present invention, there is provided a sleep quality monitoring apparatus, the apparatus comprising:

the system comprises a PPG signal quality data obtaining unit, a first quality control unit and a second quality control unit, wherein the PPG signal quality obtaining unit is used for sliding window on the PPG signal quality of a target object in a sleep state based on a preset first characteristic window, calculating and obtaining first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window, the first PPG signal quality data represents that the PPG signal quality is higher than a first quality threshold, and the second PPG signal quality data represents that the PPG signal quality is lower than the first quality threshold;

an alternative interval determining unit, configured to determine a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on a proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval;

A deep sleep time point determining unit, configured to determine a time point when the target subject enters deep sleep based on a distribution state of the first PPG signal quality data or a distribution state of the second PPG signal quality data in the deep sleep time candidate interval, and determine a time point when the target subject ends deep sleep based on a distribution state of the first PPG signal quality data or a distribution state of the second PPG signal quality data in the deep sleep end time candidate interval.

According to another aspect of the invention, a wearable device is provided, which may perform the method as described above.

Compared with the prior art, the invention has the following advantages:

according to the sleep quality monitoring method provided by the invention, the PPG signal quality of a target object in a sleep state is subjected to sliding window based on a preset first characteristic window, first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window are obtained through calculation, the first PPG signal quality data represents that the PPG signal quality is higher than a first quality threshold, and the second PPG signal quality data represents that the PPG signal quality is lower than the first quality threshold; determining a deep sleep time alternative interval and a deep sleep ending time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval; the method comprises the steps of determining a time point when a target subject enters deep sleep based on the distribution state of first PPG signal quality data or the distribution state of second PPG signal quality data in a deep sleep time alternative interval, and determining a time point when the target subject ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in a deep sleep end time alternative interval. The method utilizes the characteristic that the PPG signal quality has poor motion disturbance resistance (namely, the waveform of PPG original data is very easy to be destroyed in the active state of a user), determines a time alternative interval for deep sleep and a time alternative interval for deep sleep ending through the proportion of the PPG signal quality, and further accurately determines the time point of a target object entering deep sleep and the time point for ending deep sleep based on the distribution state of the PPG signal quality data. Compared with the traditional deep sleep monitoring mode, the method has higher sensitivity and accuracy on the judgment result of the deep sleep time, is less influenced by other actions in the sleep process, has lower false alarm rate, and avoids the problem of false judgment of the judgment result of the deep sleep time caused by the mechanical noise and data drift problem of the sensor of the accelerometer or gyroscope.

Drawings

FIG. 1 is a flow chart of a sleep quality monitoring method according to an embodiment of the present application;

FIG. 2 is a block diagram of a sleep quality monitoring apparatus according to an embodiment of the present application;

fig. 3 is a schematic logic structure diagram of a wearable device according to an embodiment of the present application;

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may be embodied in many other forms than those herein described, and those skilled in the art will readily appreciate that the present application may be similarly embodied without departing from the spirit or essential characteristics thereof, and therefore the present application is not limited to the specific embodiments disclosed below.

Aiming at a deep sleep monitoring scene, the application provides a sleep quality monitoring method, a sleep quality monitoring device corresponding to the method and a wearable device for improving the sensitivity and accuracy of a deep sleep monitoring result. The following provides examples to describe the above methods, apparatuses, and wearable devices in detail.

An embodiment of the present application provides a sleep quality monitoring method, where an application body of the method may be a computing device application for monitoring a deep sleep condition of a user, where the computing device application may be running on an intelligent wearable device or a network platform server for performing deep sleep monitoring. Fig. 1 is a flowchart of a sleep quality monitoring method according to the present embodiment, and the sleep quality monitoring method according to the present embodiment is described in detail below with reference to fig. 1. The embodiments referred to in the following description are intended to illustrate the method principles and not to limit the practical use.

As shown in fig. 1, the sleep quality monitoring method provided in this embodiment includes the following steps:

s101, sliding windows are carried out on the PPG signal quality of a target object in a sleep state based on preset first characteristic windows, and first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window are obtained through calculation.

The method comprises the steps of carrying out sliding window on the PPG signal quality of a target object in a sleep state based on preset first characteristic windows, calculating and obtaining first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window, wherein the first PPG signal quality data represents that the PPG signal quality is higher than a first quality threshold, and the second PPG signal quality data represents that the PPG signal quality is lower than the first quality threshold. The method comprises the steps of carrying out sliding window on the PPG signal quality of a target object with a window width of a preset time length, calculating PPG signal quality data in each characteristic window, marking the PPG signal quality of a certain characteristic window as first PPG signal quality data when the PPG signal quality of the certain characteristic window is higher than a preset first quality threshold value, and marking the PPG signal quality of the certain characteristic window as second PPG signal quality data when the PPG signal quality of the certain characteristic window is lower than the preset quality threshold value. The PPG signal (photoplethysmogram) is similar to the ECG signal, can be obtained by a non-invasive means (such as measurement by a finger), can reflect the abundant microcirculation physiological information of a human body, has the unique physiological characteristics of the human body, is difficult to copy and imitate, and has higher safety. The PPG signal quality is obtained by calculation and characterizes the stability of the PPG signal (stability of the PPG signal waveform), which is poor in the user's awake state and good in the user's sleep or resting state. The PPG signal quality may be the proportion of the normal waveform with a smooth rule in the original waveform diagram corresponding to the window width (e.g. 1 minute) of the preset feature window. PPG photoplethysmography is a non-invasive method for measuring blood volume changes of a tissue micro-vascular bed, which is generally used for measuring heart rate and blood oxygen level, but has poor anti-motion disturbance capability due to its measurement principle being continuous blood volume changes, i.e. when the user is in a motion state, the corresponding PPG signal quality is poor, and when the user is in a rest state, the corresponding PPG signal quality is better, so that by utilizing the characteristic that the PPG signal quality has poor anti-motion disturbance capability (i.e. PPG raw data waveform is very easily destroyed in a user's motion state), the user can be effectively distinguished from being in a rest state or a motion state by identifying the PPG signal quality.

S102, determining a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval.

After the first PPG signal quality data or the second PPG signal quality data corresponding to each first feature window are obtained through calculation in the step, the step is used for determining a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval, wherein the deep sleep time alternative interval refers to a time interval when a target object is at least partially in a deep sleep state and possibly contains a time point when the target object enters deep sleep, and the deep sleep end time alternative interval refers to a time interval when the target object is at least partially not in the deep sleep state and possibly contains a time point when the target object ends deep sleep.

The above process of determining the deep sleep time alternative interval and the deep sleep end time alternative interval may specifically refer to: determining the first target time interval as a deep sleep time alternative interval in response to the proportion of the first PPG signal quality data in the first target time interval in each preset first time interval being higher than a first proportion threshold or the proportion of the second PPG signal quality data being lower than a second proportion threshold; and determining the second target time interval as a deep sleep ending time alternative interval in response to the proportion of the first PPG signal quality data in the second target time interval in each preset first time interval being lower than a third proportion threshold or the proportion of the second PPG signal quality data being higher than a fourth proportion threshold, wherein the first proportion threshold is not smaller than the second proportion threshold, and the third proportion threshold is not larger than the fourth proportion threshold.

S103, determining a time point when the target object enters deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep time alternative interval, and determining a time point when the target object ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep end time alternative interval.

After determining the interval of the time alternative for deep sleep and the interval of the time alternative for deep sleep, the method is used for further determining the time point when the target object enters deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the interval of the time alternative for deep sleep, and further determining the time point when the target object ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the interval of the time alternative for deep sleep.

Specifically, the determining, based on the distribution state of the first PPG signal quality data in the deep sleep time candidate interval, the time point when the target subject enters deep sleep may refer to: determining a time point when the first PPG signal quality data starts to be stably distributed in the deep sleep time alternative interval as a time point when the target object enters deep sleep; or, in response to the first PPG signal quality data remaining stably distributed from the start position of the deep sleep onset time interval, determining a point in time at which the first PPG signal quality data starts to be stably distributed in the previous time interval of the deep sleep onset time interval as a point in time at which the target subject enters deep sleep.

The determining the time point when the target subject enters the deep sleep based on the distribution state of the second PPG signal quality data in the deep sleep time alternative interval may refer to: determining a starting time point of continuous zero distribution of second PPG signal quality data in the deep sleep time alternative interval as a time point of the target object entering deep sleep; or in response to the second PPG signal quality data maintaining the zero distribution from the start position of the deep sleep onset time interval, determining a start time point of the second PPG signal quality data continuing the zero distribution in the previous time interval of the deep sleep onset time interval as a time point of the target subject entering the deep sleep.

The determining the time point when the target subject ends the deep sleep based on the distribution state of the first PPG signal quality data in the deep sleep end time candidate interval may refer to: determining a time point of the first PPG signal quality data beginning discrete distribution in the deep sleep ending time alternative interval as a time point of ending deep sleep of the target object; or, in response to the first PPG signal quality data maintaining a discrete distribution from the starting position of the deep sleep end time candidate interval, determining a point in time at which the first PPG signal quality data starts the discrete distribution in the previous time interval of the deep sleep end time candidate interval as a point in time at which the target subject ends the deep sleep;

The determining the time point when the target subject ends the deep sleep based on the distribution state of the second PPG signal quality data in the deep sleep end time candidate interval may refer to: determining a time point at which second PPG signal quality data starts to appear in the deep sleep ending time alternative interval as a time point at which the target object ends deep sleep; or in response to the starting position of the deep sleep end time candidate interval being the second PPG signal quality data, determining a point in time at which the second PPG signal quality data starts to appear in the previous time interval of the deep sleep end time candidate interval as a point in time at which the target subject ends the deep sleep.

In this embodiment, after determining the time point when the target object enters the deep sleep and the time point when the target object ends the deep sleep in the above steps, the deep sleep duration of the target object may also be determined by the following manner: and determining a time interval between a time point when the target object enters deep sleep and a time point when the target object finishes deep sleep as a deep sleep time interval of the target object, and determining a time length corresponding to the first PPG signal quality data in the deep sleep time interval as a deep sleep time length of the target object.

In this embodiment, before the first PPG signal quality data or the second PPG signal quality data corresponding to each first feature window are obtained by calculation, the sleeping time point of the target object may be further determined by the following manner, so as to determine that the target object has fallen asleep:

firstly, sliding window is carried out on the PPG signal quality of a target object based on preset second characteristic windows, third PPG signal quality data or fourth PPG signal quality data corresponding to each second characteristic window is obtained through calculation, the third PPG signal quality data represent PPG signal quality to be higher than a second quality threshold, the second PPG signal quality data represent PPG signal quality to be lower than the second quality threshold, and compared with judging the sleeping time or the getting-up time of the target object when the user is in a more resting state during deep sleep, the requirements on the PPG signal quality are higher when the deep sleep condition of the user is monitored, so that the second quality threshold is set to be lower than the first quality threshold;

and secondly, determining an alternative sleep time interval from each preset second time interval based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval. The preset second time interval is used for functionally distinguishing the preset first time interval, the preset first time interval is used for determining a deep sleep time alternative interval and a deep sleep end time alternative interval, and the preset second time interval is used for determining the alternative sleep time interval. The determining, based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, the alternative sleep time interval from the preset second time interval may specifically be: and determining the third target time interval as an alternative sleep time interval in response to the proportion of the third PPG signal quality data in the third target time interval in each preset second time interval being higher than a fifth proportion threshold or the proportion of the fourth PPG signal quality data being lower than a sixth proportion threshold, wherein the fifth proportion threshold is not smaller than the sixth proportion threshold.

Finally, a sleep time point of the target subject is determined based on the distribution state of the third PPG signal quality data or the distribution state of the fourth PPG signal quality data in the alternative sleep time interval. The determining, based on the distribution state of the third PPG signal quality data in the alternative sleep time interval, a sleep time point of the target object may specifically be: determining a time point at which the third PPG signal quality data starts to be stably distributed in the alternative sleep time interval as a sleep time point of the target subject; or, in response to the third PPG signal quality data remaining stably distributed from the starting position of the alternative sleep time interval, determining a point in time at which the third PPG signal quality data starts to be stably distributed in the last time interval of the alternative sleep time interval as a sleep time point of the target subject. Based on the distribution state of the fourth PPG signal quality data in the alternative sleep time interval, determining the sleep time point of the target object may specifically be: determining a starting time point of continuous zero distribution of the fourth PPG signal quality data in the alternative sleep time interval as a sleep time point of the target object; alternatively, in response to the fourth PPG signal quality data maintaining a zero distribution from a starting position of the alternative fall asleep time interval, a starting time point of the fourth PPG signal quality data continuing the zero distribution in a last time interval of the alternative fall asleep time interval is determined as the fall asleep time point of the target subject.

According to the sleep quality monitoring method provided by the embodiment of the application, the PPG signal quality of a target object in a sleep state is windowed based on the preset first characteristic window, first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window is obtained through calculation, the first PPG signal quality data represents that the PPG signal quality is higher than a first quality threshold, and the second PPG signal quality data represents that the PPG signal quality is lower than the first quality threshold; determining a deep sleep time alternative interval and a deep sleep ending time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval; the method comprises the steps of determining a time point when a target subject enters deep sleep based on the distribution state of first PPG signal quality data or the distribution state of second PPG signal quality data in a deep sleep time alternative interval, and determining a time point when the target subject ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in a deep sleep end time alternative interval. The method utilizes the characteristic that the PPG signal quality has poor motion disturbance resistance (namely, the waveform of PPG original data is very easy to be destroyed in the active state of a user), determines a time alternative interval for deep sleep and a time alternative interval for deep sleep ending through the proportion of the PPG signal quality, and further accurately determines the time point of a target object entering deep sleep and the time point for ending deep sleep based on the distribution state of the PPG signal quality data. Compared with the traditional deep sleep monitoring mode, the method has higher sensitivity and accuracy on the judgment result of the deep sleep time, is less influenced by other actions in the sleep process, has lower false alarm rate, and avoids the problem of false judgment of the judgment result of the deep sleep time caused by the mechanical noise and data drift problem of the sensor of the accelerometer or gyroscope.

The foregoing embodiments provide a sleep quality monitoring method, and correspondingly, another embodiment of the present application further provides a sleep quality monitoring device, and since the device embodiment is substantially similar to the method embodiment, the description is relatively simple, and details of relevant technical features should be referred to the corresponding description of the method embodiment provided above, and the following description of the device embodiment is merely illustrative.

Referring to fig. 2 for understanding the embodiment, fig. 2 is a block diagram of a unit of a sleep quality monitoring apparatus according to the present embodiment, and as shown in fig. 2, the sleep quality monitoring apparatus according to the present embodiment includes:

a PPG signal quality data obtaining unit 201, configured to perform sliding window on PPG signal quality of a target subject in a sleep state based on a preset first feature window, calculate and obtain first PPG signal quality data or second PPG signal quality data corresponding to each first feature window, where the first PPG signal quality data represents PPG signal quality higher than a first quality threshold, and the second PPG signal quality data represents PPG signal quality lower than the first quality threshold;

an alternative interval determining unit 202, configured to determine a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on a proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval;

A deep sleep time point determining unit 203, configured to determine a time point when the target subject enters deep sleep based on a distribution state of the first PPG signal quality data or a distribution state of the second PPG signal quality data in the deep sleep time alternative interval, and determine a time point when the target subject ends deep sleep based on a distribution state of the first PPG signal quality data or a distribution state of the second PPG signal quality data in the deep sleep end time alternative interval.

Sliding window is carried out on the PPG signal quality of a target object in a sleep state based on preset first characteristic windows, first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window is obtained through calculation, the first PPG signal quality data represent PPG signal quality to be higher than a first quality threshold, and the second PPG signal quality data represent PPG signal quality to be lower than the first quality threshold;

determining a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval;

Determining a time point when the target subject enters deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep time candidate interval, and determining a time point when the target subject ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep end time candidate interval.

In some embodiments, the apparatus further comprises: the depth sleep duration determining unit is configured to determine a time interval between a time point when the target object enters into the depth sleep and a time point when the target object ends the depth sleep as a depth sleep time interval of the target object, and determine a time length corresponding to the first PPG signal quality data in the depth sleep time interval as a depth sleep duration of the target object.

In some embodiments, the determining, from each preset first time interval, a deep sleep time alternative interval and a deep sleep end time alternative interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval includes:

Determining the first target time interval as a deep sleep time alternative interval in response to the proportion of the first PPG signal quality data in a first target time interval in each preset first time interval being higher than a first proportion threshold or the proportion of the second PPG signal quality data being lower than a second proportion threshold; and determining the second target time interval as a deep sleep ending time alternative interval in response to the proportion of the first PPG signal quality data in a second target time interval in each preset first time interval being lower than a third proportion threshold or the proportion of the second PPG signal quality data being higher than a fourth proportion threshold, wherein the first proportion threshold is not smaller than the second proportion threshold and the third proportion threshold is not larger than the fourth proportion threshold.

In some embodiments, determining a point in time at which the target subject enters deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep onset time interval comprises: determining a time point when the first PPG signal quality data starts to be stably distributed in the deep sleep time alternative interval as a time point when the target subject enters deep sleep; or, in response to the first PPG signal quality data remaining stably distributed from the starting position of the deep sleep onset time alternative interval, determining a point in time at which the first PPG signal quality data starts to be stably distributed in a previous time interval of the deep sleep onset time alternative interval as a point in time at which the target subject enters deep sleep;

The determining, based on the distribution state of the second PPG signal quality data in the deep sleep time alternative interval, a time point at which the target subject enters deep sleep includes: determining a starting time point of continuous zero distribution of the second PPG signal quality data in the deep sleep time alternative interval as a time point of the target object entering deep sleep; or, in response to the second PPG signal quality data maintaining a zero distribution from a starting position of the deep sleep onset time alternative interval, determining a starting time point of the second PPG signal quality data continuing the zero distribution in a previous time interval of the deep sleep onset time alternative interval as a time point of the target subject entering deep sleep.

In some embodiments, the determining a point in time at which a target subject ends deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep end time candidate interval includes: determining a time point of the first PPG signal quality data beginning discrete distribution in the deep sleep ending time alternative interval as a time point of ending deep sleep of the target subject; or, in response to the first PPG signal quality data remaining discretely distributed from a starting position of the deep sleep end time alternative interval, determining a point in time at which the first PPG signal quality data starts discretely distributed in a previous time interval of the deep sleep end time alternative interval as a point in time at which the target subject ends deep sleep;

Determining a point in time at which the target subject ends deep sleep based on a distribution state of the second PPG signal quality data in the deep sleep end time candidate interval, comprising: determining a time point at which the second PPG signal quality data starts to appear in the deep sleep end time alternative interval as a time point at which the target subject ends deep sleep; or in response to the starting position of the deep sleep ending time alternative interval being the second PPG signal quality data, determining a time point at which the second PPG signal quality data starts to appear in a previous time interval of the deep sleep ending time alternative interval as a time point at which the target subject ends deep sleep.

In some embodiments, before the calculating obtains the first PPG signal quality data or the second PPG signal quality data corresponding to each first feature window, the apparatus further comprises:

sliding window is carried out on the PPG signal quality of the target object based on preset second characteristic windows, third PPG signal quality data or fourth PPG signal quality data corresponding to each second characteristic window is obtained through calculation, the third PPG signal quality data represents that the PPG signal quality is higher than a second quality threshold, the second PPG signal quality data represents that the PPG signal quality is lower than the second quality threshold, and the second quality threshold is smaller than the first quality threshold;

And determining an alternative sleep time interval from each preset second time interval based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, and determining a sleep time point of the target object based on the distribution state of the third PPG signal quality data or the distribution state of the fourth PPG signal quality data in the alternative sleep time interval.

In some embodiments, the determining, based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, an alternative sleep time interval from the preset second time interval includes: and determining the third target time interval as an alternative sleep time interval in response to the proportion of the third PPG signal quality data in the third target time interval in each preset second time interval being higher than a fifth proportion threshold or the proportion of the fourth PPG signal quality data being lower than a sixth proportion threshold, wherein the fifth proportion threshold is not smaller than the sixth proportion threshold.

According to the sleep quality monitoring device provided by the embodiment, the time alternative interval for deep sleep and the time alternative interval for deep sleep are determined according to the proportion of the PPG signal quality by utilizing the characteristic that the PPG signal quality has poor motion disturbance resistance (namely, the waveform of PPG original data is very easy to destroy in the active state of a user), and the time point when a target object enters deep sleep and the time point when deep sleep is finished are further accurately determined based on the distribution state of PPG signal quality data. Compared with the traditional deep sleep monitoring mode, the device has higher sensitivity and accuracy on the judgment result of the deep sleep time, is less influenced by other actions in the sleep process, has lower false alarm rate, and avoids the problem that the traditional deep sleep time judgment result has false judgment due to the mechanical noise and data drift problem of the sensor of the accelerometer or gyroscope.

In the foregoing embodiments, a sleep quality monitoring method and a sleep quality monitoring apparatus are provided, and in addition, another embodiment of the present application further provides a wearable device, where the wearable device may perform the sleep quality monitoring method as shown above, or operate the sleep quality monitoring apparatus as shown above, and since the wearable device embodiment is substantially similar to the method embodiment, the description is relatively simple, and details of relevant technical features should be referred to the corresponding descriptions of the method embodiment provided above, and the following description of the wearable device embodiment is merely illustrative. The wearable device embodiment is as follows:

fig. 3 is a schematic diagram of the wearable device provided in the present embodiment.

As shown in fig. 3, the wearable device provided in this embodiment includes: a processor 301 and a memory 302;

the memory 302 is used to store computer instructions for data processing which, when read and executed by the processor 301, perform the following operations:

sliding window is carried out on the PPG signal quality of a target object in a sleep state based on preset first characteristic windows, first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window is obtained through calculation, the first PPG signal quality data represent PPG signal quality to be higher than a first quality threshold, and the second PPG signal quality data represent PPG signal quality to be lower than the first quality threshold;

Determining a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval;

determining a time point when the target subject enters deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep time candidate interval, and determining a time point when the target subject ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep end time candidate interval.

In some embodiments, further comprising: and determining a time interval between a time point when the target object enters deep sleep and a time point when the target object finishes deep sleep as a deep sleep time interval of the target object, and determining a time length corresponding to the first PPG signal quality data in the deep sleep time interval as a deep sleep time length of the target object.

In some embodiments, the determining, from each preset first time interval, a deep sleep time alternative interval and a deep sleep end time alternative interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval includes: determining the first target time interval as a deep sleep time alternative interval in response to the proportion of the first PPG signal quality data in a first target time interval in each preset first time interval being higher than a first proportion threshold or the proportion of the second PPG signal quality data being lower than a second proportion threshold; and determining the second target time interval as a deep sleep ending time alternative interval in response to the proportion of the first PPG signal quality data in a second target time interval in each preset first time interval being lower than a third proportion threshold or the proportion of the second PPG signal quality data being higher than a fourth proportion threshold, wherein the first proportion threshold is not smaller than the second proportion threshold and the third proportion threshold is not larger than the fourth proportion threshold.

In some embodiments, the determining a point in time when the target subject enters deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep onset time candidate interval includes: determining a time point when the first PPG signal quality data starts to be stably distributed in the deep sleep time alternative interval as a time point when the target subject enters deep sleep; or, in response to the first PPG signal quality data remaining stably distributed from the starting position of the deep sleep onset time alternative interval, determining a point in time at which the first PPG signal quality data starts to be stably distributed in a previous time interval of the deep sleep onset time alternative interval as a point in time at which the target subject enters deep sleep;

the determining, based on the distribution state of the second PPG signal quality data in the deep sleep time alternative interval, a time point at which the target subject enters deep sleep includes: determining a starting time point of continuous zero distribution of the second PPG signal quality data in the deep sleep time alternative interval as a time point of the target object entering deep sleep; or, in response to the second PPG signal quality data maintaining a zero distribution from a starting position of the deep sleep onset time alternative interval, determining a starting time point of the second PPG signal quality data continuing the zero distribution in a previous time interval of the deep sleep onset time alternative interval as a time point of the target subject entering deep sleep.

In some embodiments, the determining a point in time at which a target subject ends deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep end time candidate interval includes: determining a time point of the first PPG signal quality data beginning discrete distribution in the deep sleep ending time alternative interval as a time point of ending deep sleep of the target object; or, in response to the first PPG signal quality data remaining discretely distributed from a starting position of the deep sleep end time alternative interval, determining a point in time at which the first PPG signal quality data starts discretely distributed in a previous time interval of the deep sleep end time alternative interval as a point in time at which the target subject ends deep sleep;

determining a point in time at which the target subject ends deep sleep based on a distribution state of the second PPG signal quality data in the deep sleep end time candidate interval, comprising: determining a time point at which the second PPG signal quality data starts to appear in the deep sleep end time alternative interval as a time point at which the target subject ends deep sleep; or in response to the starting position of the deep sleep ending time alternative interval being the second PPG signal quality data, determining a time point at which the second PPG signal quality data starts to appear in a previous time interval of the deep sleep ending time alternative interval as a time point at which the target subject ends deep sleep.

In some embodiments, before the calculating obtains the first PPG signal quality data or the second PPG signal quality data corresponding to each first feature window, the method further comprises: sliding window is carried out on the PPG signal quality of the target object based on preset second characteristic windows, third PPG signal quality data or fourth PPG signal quality data corresponding to each second characteristic window is obtained through calculation, the third PPG signal quality data represents that the PPG signal quality is higher than a second quality threshold, the second PPG signal quality data represents that the PPG signal quality is lower than the second quality threshold, and the second quality threshold is smaller than the first quality threshold;

and determining an alternative sleep time interval from each preset second time interval based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, and determining a sleep time point of the target object based on the distribution state of the third PPG signal quality data or the distribution state of the fourth PPG signal quality data in the alternative sleep time interval.

In some embodiments, the determining, based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, an alternative sleep time interval from the preset second time interval includes: and determining the third target time interval as an alternative sleep time interval in response to the proportion of the third PPG signal quality data in the third target time interval in each preset second time interval being higher than a fifth proportion threshold or the proportion of the fourth PPG signal quality data being lower than a sixth proportion threshold, wherein the fifth proportion threshold is not smaller than the sixth proportion threshold.

In some embodiments, the determining a point in time of falling asleep of the target subject based on the distribution state of the third PPG signal quality data in the alternative falling asleep time interval comprises: determining a point in time at which the third PPG signal quality data starts to be steadily distributed in the alternative sleep-on time interval as a sleep-on time point of the target subject; or, in response to the third PPG signal quality data remaining steadily distributed from the starting position of the alternative sleep-on time interval, determining a point in time at which the third PPG signal quality data starts steadily distributed in the last time interval of the alternative sleep-on time interval as a sleep-on time point of the target subject;

the determining a sleep time point of the target subject based on a distribution state of the fourth PPG signal quality data in the alternative sleep time interval comprises: determining a starting time point of the fourth PPG signal quality data continuous zero distribution in the alternative sleep time interval as a sleep time point of the target subject; or, in response to the fourth PPG signal quality data maintaining a zero distribution from a starting position of the alternative sleep-on time interval, determining a starting time point of the fourth PPG signal quality data continuing zero distribution in a last time interval of the alternative sleep-on time interval as a sleep-on time point of the target subject.

According to the wearable device provided by the embodiment, the time alternative interval for deep sleep and the time alternative interval for deep sleep are determined according to the proportion of the PPG signal quality by utilizing the characteristic that the PPG signal quality has poor motion disturbance resistance (namely, the waveform of PPG original data is very easy to destroy in the active state of a user), and the time point when a target object enters deep sleep and the time point when deep sleep is finished are further accurately determined based on the distribution state of PPG signal quality data. Compared with the traditional deep sleep monitoring mode, the wearable device has higher sensitivity and accuracy on the judgment result of the deep sleep time, is less influenced by other actions in the sleep process, has lower false alarm rate, and avoids the problem that the traditional deep sleep time judgment result has false judgment due to the mechanical noise and data drift problem of the sensor of the accelerometer or gyroscope.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

1. Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer readable media, as defined herein, does not include non-transitory computer readable media (transmission media), such as modulated data signals and carrier waves.

2. It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

While the application has been described in terms of preferred embodiments, it is not intended to be limiting, but rather, it will be apparent to those skilled in the art that various changes and modifications can be made herein without departing from the spirit and scope of the application as defined by the appended claims.

Claims (9)

1. A sleep quality monitoring method, the method comprising:

sliding window is carried out on the PPG signal quality of a target object in a sleep state based on preset first characteristic windows, first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window is obtained through calculation, the first PPG signal quality data represent PPG signal quality to be higher than a first quality threshold, and the second PPG signal quality data represent PPG signal quality to be lower than the first quality threshold;

determining a deep sleep time alternative interval and a deep sleep end time alternative interval from each preset first time interval based on the proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval, wherein the method comprises the following steps: determining the first target time interval as a deep sleep time alternative interval in response to the proportion of the first PPG signal quality data in a first target time interval in each preset first time interval being higher than a first proportion threshold or the proportion of the second PPG signal quality data being lower than a second proportion threshold; and determining the second target time interval as a deep sleep end time alternative interval in response to the proportion of the first PPG signal quality data in a second target time interval in each preset first time interval being lower than a third proportion threshold or the proportion of the second PPG signal quality data being higher than a fourth proportion threshold, wherein the first proportion threshold is not smaller than the second proportion threshold and the third proportion threshold is not larger than the fourth proportion threshold;

Determining a time point when the target subject enters deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep time candidate interval, and determining a time point when the target subject ends deep sleep based on the distribution state of the first PPG signal quality data or the distribution state of the second PPG signal quality data in the deep sleep end time candidate interval.

2. The method according to claim 1, wherein the method further comprises:

and determining a time interval between a time point when the target object enters deep sleep and a time point when the target object finishes deep sleep as a deep sleep time interval of the target object, and determining a time length corresponding to the first PPG signal quality data in the deep sleep time interval as a deep sleep time length of the target object.

3. The method of claim 1, wherein the determining a point in time at which the target subject enters deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep onset time interval comprises:

Determining a time point when the first PPG signal quality data starts to be stably distributed in the deep sleep time alternative interval as a time point when the target subject enters deep sleep; or, in response to the first PPG signal quality data remaining stably distributed from the starting position of the deep sleep onset time alternative interval, determining a point in time at which the first PPG signal quality data starts to be stably distributed in a previous time interval of the deep sleep onset time alternative interval as a point in time at which the target subject enters deep sleep;

the determining, based on the distribution state of the second PPG signal quality data in the deep sleep time alternative interval, a time point at which the target subject enters deep sleep includes:

determining a starting time point of continuous zero distribution of the second PPG signal quality data in the deep sleep time alternative interval as a time point of the target object entering deep sleep; or, in response to the second PPG signal quality data maintaining a zero distribution from a starting position of the deep sleep onset time alternative interval, determining a starting time point of the second PPG signal quality data continuing the zero distribution in a previous time interval of the deep sleep onset time alternative interval as a time point of the target subject entering deep sleep.

4. The method of claim 1, wherein the determining a point in time at which the target subject ends deep sleep based on a distribution state of the first PPG signal quality data in the deep sleep end time candidate interval comprises:

determining a time point of the first PPG signal quality data beginning discrete distribution in the deep sleep ending time alternative interval as a time point of ending deep sleep of the target subject; or, in response to the first PPG signal quality data remaining discretely distributed from a starting position of the deep sleep end time alternative interval, determining a point in time at which the first PPG signal quality data starts discretely distributed in a previous time interval of the deep sleep end time alternative interval as a point in time at which the target subject ends deep sleep;

the determining, based on the distribution state of the second PPG signal quality data in the deep sleep end time candidate interval, a point in time at which the target subject ends deep sleep includes:

determining a time point at which the second PPG signal quality data starts to appear in the deep sleep end time alternative interval as a time point at which the target subject ends deep sleep; or in response to the starting position of the deep sleep ending time alternative interval being the second PPG signal quality data, determining a time point at which the second PPG signal quality data starts to appear in a previous time interval of the deep sleep ending time alternative interval as a time point at which the target subject ends deep sleep.

5. The method of claim 1, wherein prior to the computing obtaining the first PPG signal quality data or the second PPG signal quality data corresponding to each first feature window, the method further comprises:

sliding window is carried out on the PPG signal quality of the target object based on preset second characteristic windows, third PPG signal quality data or fourth PPG signal quality data corresponding to each second characteristic window is obtained through calculation, the third PPG signal quality data represents that the PPG signal quality is higher than a second quality threshold, the second PPG signal quality data represents that the PPG signal quality is lower than the second quality threshold, and the second quality threshold is smaller than the first quality threshold;

and determining an alternative sleep time interval from each preset second time interval based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval, and determining a sleep time point of the target object based on the distribution state of the third PPG signal quality data or the distribution state of the fourth PPG signal quality data in the alternative sleep time interval.

6. The method of claim 5, wherein the determining an alternative sleep-in time interval from the preset second time interval based on the proportion of the third PPG signal quality data or the fourth PPG signal quality data in the preset second time interval comprises:

And determining the third target time interval as an alternative sleep time interval in response to the proportion of the third PPG signal quality data in the third target time interval in each preset second time interval being higher than a fifth proportion threshold or the proportion of the fourth PPG signal quality data being lower than a sixth proportion threshold, wherein the fifth proportion threshold is not smaller than the sixth proportion threshold.

7. The method of claim 5, wherein the determining the point in time of falling asleep of the target subject based on the distribution state of the third PPG signal quality data in the alternative time interval of falling asleep comprises:

determining a point in time at which the third PPG signal quality data starts to be steadily distributed in the alternative sleep-on time interval as a sleep-on time point of the target subject; or, in response to the third PPG signal quality data remaining steadily distributed from the starting position of the alternative sleep-on time interval, determining a point in time at which the third PPG signal quality data starts steadily distributed in the last time interval of the alternative sleep-on time interval as a sleep-on time point of the target subject;

the determining a sleep time point of the target subject based on a distribution state of the fourth PPG signal quality data in the alternative sleep time interval comprises:

Determining a starting time point of the fourth PPG signal quality data continuous zero distribution in the alternative sleep time interval as a sleep time point of the target subject; or, in response to the fourth PPG signal quality data maintaining a zero distribution from a starting position of the alternative sleep-on time interval, determining a starting time point of the fourth PPG signal quality data continuing zero distribution in a last time interval of the alternative sleep-on time interval as a sleep-on time point of the target subject.

8. A sleep quality monitoring device, the device comprising:

the system comprises a PPG signal quality data obtaining unit, a first quality control unit and a second quality control unit, wherein the PPG signal quality obtaining unit is used for sliding window on the PPG signal quality of a target object in a sleep state based on a preset first characteristic window, calculating and obtaining first PPG signal quality data or second PPG signal quality data corresponding to each first characteristic window, the first PPG signal quality data represents that the PPG signal quality is higher than a first quality threshold, and the second PPG signal quality data represents that the PPG signal quality is lower than the first quality threshold;

an alternative interval determining unit, configured to determine, from each preset first time interval, a deep sleep time alternative interval and a deep sleep end time alternative interval based on a proportion of the first PPG signal quality data or the second PPG signal quality data in the preset first time interval, where the determining unit includes: determining the first target time interval as a deep sleep time alternative interval in response to the proportion of the first PPG signal quality data in a first target time interval in each preset first time interval being higher than a first proportion threshold or the proportion of the second PPG signal quality data being lower than a second proportion threshold; and determining the second target time interval as a deep sleep end time alternative interval in response to the proportion of the first PPG signal quality data in a second target time interval in each preset first time interval being lower than a third proportion threshold or the proportion of the second PPG signal quality data being higher than a fourth proportion threshold, wherein the first proportion threshold is not smaller than the second proportion threshold and the third proportion threshold is not larger than the fourth proportion threshold;

A deep sleep time point determining unit, configured to determine a time point when the target subject enters deep sleep based on a distribution state of the first PPG signal quality data or a distribution state of the second PPG signal quality data in the deep sleep time candidate interval, and determine a time point when the target subject ends deep sleep based on a distribution state of the first PPG signal quality data or a distribution state of the second PPG signal quality data in the deep sleep end time candidate interval.

9. A wearable device, characterized in that the wearable device is executable to perform the method of any of claims 1-7.