CN115732087A

CN115732087A - Wearable device based in-bed state monitoring method and device and computer device

Info

Publication number: CN115732087A
Application number: CN202110987315.XA
Authority: CN
Inventors: 张翼; 郝得宁; 戴晓伟; 汪孔桥
Original assignee: Anhui Huami Health Technology Co Ltd
Current assignee: Anhui Huami Health Technology Co Ltd
Priority date: 2021-08-26
Filing date: 2021-08-26
Publication date: 2023-03-03

Abstract

The utility model discloses a wearable device-based in-bed state monitoring method and device, computer equipment and a storage medium, and relates to the technical field of computers, in particular to the field of artificial intelligence such as cloud computing and deep learning. The specific implementation scheme is as follows: acquiring an acceleration signal output by the wearable device within a preset time period; determining the motion characteristics of the monitored object in the preset time period according to the acceleration signal; determining the attitude characteristics of the monitored object in the preset time period according to the acceleration signal; and determining the in-bed state of the monitored object in the preset time period according to the posture characteristic and the motion characteristic. Therefore, the in-bed state of the monitored object is determined by fusing the motion characteristic and the posture characteristic, and the accuracy and the reliability of the monitoring result are improved.

Description

Wearable device based in-bed state monitoring method and device and computer device

Technical Field

The utility model relates to the technical field of computers, in particular to the field of artificial intelligence such as cloud computing and deep learning, and specifically relates to a wearable device-based in-bed state monitoring method and apparatus and a computer device.

Background

With the continuous improvement of the life quality of people and the continuous acceleration of the life rhythm, the sleep problem becomes an important factor influencing the life and work of people, and more people begin to pay attention to the sleep problem.

The sleep efficiency is used as an important index for evaluating the sleep quality and is obtained by dividing the sleep duration by the bed time. In order to calculate sleep efficiency, in-bed time monitoring methods based on various devices are also receiving attention from many parties. In the related art, the sleep monitoring method based on the devices such as the monitoring video and the intelligent mattress is difficult to be suitable for daily monitoring due to single use scene and insufficient portability. Therefore, how to conveniently and accurately monitor the in-bed state in daily life is a problem which needs to be solved urgently at present.

Disclosure of Invention

The disclosure provides a wearable device-based in-bed state monitoring method and device, computer equipment and a storage medium.

According to a first aspect of the present disclosure, there is provided a wearable device-based in-bed status monitoring method, including:

acquiring an acceleration signal output by a sensor in the wearable device within a preset time period;

determining the motion characteristics of the monitored object in the preset time period according to the acceleration signal;

determining the attitude characteristics of the monitored object in the preset time period according to the acceleration signal;

and determining the in-bed state of the monitored object in the preset time period according to the posture characteristic and the motion characteristic.

Optionally, the determining, according to the acceleration signal, the motion characteristic of the monitored object in the preset time period includes:

dividing the preset time period into a plurality of time windows based on the designated time length;

determining the average absolute deviation corresponding to each time window according to the acceleration of each moment in each time window;

determining a type label corresponding to each time window according to the size relation between the average absolute deviation corresponding to each time window and an activity threshold, wherein the type label is used for representing the activity state of the monitoring object in the corresponding time window;

and determining the motion characteristics of the monitored object in the preset time period according to the type label of each time window in the preset time period.

Optionally, after determining the type label corresponding to each time window, the method further includes:

determining the time corresponding to the activity variable point in the preset time period according to the type label corresponding to each time window;

determining the time interval between each time window and the adjacent previous activity change point;

and updating the motion characteristics of the monitored object in the preset time period according to the time interval corresponding to each time window.

Optionally, the determining, according to the type label of each time window in the preset time period, the motion characteristic of the monitored object in the preset time period includes:

determining a time window type sequence in the preset time period according to the type label of each time window in the preset time period;

and/or the presence of a gas in the gas,

and determining the number of the windows of each type in the preset time period according to the type label of each time window in the preset time period.

Optionally, the determining, according to the acceleration signal, the posture characteristic of the monitored object within the preset time period includes:

determining the acceleration of the window corresponding to each time window according to the acceleration of each moment in each time window;

under the condition that the window acceleration corresponding to any time window is within a specified range, determining an acceleration vector corresponding to any time window;

determining a distance value between each acceleration vector and a designated spherical area;

and determining the posture characteristic of the monitored object in the preset time period according to the plurality of distance values in the preset time period.

Optionally, after determining the window acceleration corresponding to each time window, the method further includes:

and under the condition that the window acceleration corresponding to any time window is not in the specified range, determining the posture characteristic of the monitored object in the preset time period according to the window accelerations corresponding to the other time windows in the preset time period.

Optionally, the determining, according to the posture feature and the motion feature, a bed state of the monitored object in the preset time period includes:

determining a first in-bed state of the monitored object within the preset time period according to the posture characteristic;

determining a second in-bed state of the monitored object within the preset time period according to the motion characteristics;

determining that the in-bed state of the monitored subject within the preset time period is a first in-bed state if the first in-bed state is the same as the second in-bed state.

Optionally, after the determining that the monitored subject is in the second in-bed state within the preset time period, the method further includes:

when the first in-bed state is different from the second in-bed state and any one of the first in-bed state and the second in-bed state is a non-in-bed state, determining that the in-bed state of the monitored object in the preset time period is a non-in-bed state.

Optionally, the determining, according to the posture feature and the motion feature, a bed state of the monitored object within the preset time period includes:

dividing the preset time period into a plurality of time segments based on the time threshold;

determining a third in-bed state of the monitored object in each time slice according to the posture characteristic corresponding to each time slice;

determining a fourth in-bed state of the monitored object in each time segment according to the motion characteristics corresponding to each time segment;

and determining the in-bed state of the monitored object in each time slice in the preset time period according to the third in-bed state and the fourth in-bed state corresponding to each time slice in the preset time period.

Optionally, the determining, according to the third in-bed state and the fourth in-bed state corresponding to each time slice in the preset time period, the in-bed state of the monitored object in each time slice in the preset time period includes:

and under the condition that at least one in-bed state corresponding to the ith time slice is in a bed leaving state, at least one in-bed state corresponding to the (i + m) th time slice is in a bed leaving state, and m is smaller than a specified value, determining that the in-bed states corresponding to the ith time slice and the (i + 1) th time slice are in the bed leaving state, wherein i and m are positive integers.

and when at least one in-bed state corresponding to the jth time slice is in an out-of-bed state and at least one in-bed state corresponding to other time slices adjacent to the jth time slice is in a suspected out-of-bed state, determining that the in-bed state corresponding to the other time slices adjacent to the jth time slice is in an out-of-bed state, wherein j is a positive integer.

According to a second aspect of the present disclosure, there is provided a wearable device-based in-bed status monitoring apparatus, comprising:

the first acquisition module is used for acquiring an acceleration signal output by a sensor in the wearable device within a preset time period;

the first determination module is used for determining the motion characteristics of the monitored object in the preset time period according to the acceleration signal;

the second determination module is used for determining the attitude characteristics of the monitored object in the preset time period according to the acceleration signal;

and the third determination module is used for determining the in-bed state of the monitored object in the preset time period according to the posture characteristic and the motion characteristic.

Optionally, the acceleration signal is an acceleration at each time, and the first determining module includes:

the dividing unit is used for dividing the preset time period into a plurality of time windows based on the specified time length;

the first determining unit is used for determining the average absolute deviation corresponding to each time window according to the acceleration of each moment in each time window;

a second determining unit, configured to determine a type label corresponding to each time window according to a size relationship between an average absolute deviation corresponding to each time window and an activity threshold, where the type label is used to characterize an activity state of the monitored object in the corresponding time window;

and the third determining unit is used for determining the motion characteristics of the monitored object in the preset time period according to the type labels of the time windows in the preset time period.

Optionally, after determining the type tag corresponding to each time window, the first determining module is further configured to:

determining the corresponding time of the activity variable point in the preset time period according to the type label corresponding to each time window;

Optionally, the third determining unit is specifically configured to:

and/or the presence of a gas in the gas,

Optionally, the acceleration signal is an acceleration at each time, and the second determining module is specifically configured to:

under the condition that the window acceleration corresponding to any one time window is within a specified range, determining an acceleration vector corresponding to any one time window;

and determining the posture characteristics of the monitoring object in the preset time period according to the plurality of distance values in the preset time period.

Optionally, after determining the window acceleration corresponding to each time window, the second determining module is further configured to:

Optionally, the third determining module includes:

a fourth determining unit, configured to determine, according to the posture feature, a first in-bed state of the monitored object within the preset time period;

a fifth determining unit, configured to determine, according to the motion feature, a second in-bed state of the monitored subject within the preset time period;

a sixth determining unit, configured to determine that the in-bed state of the monitored object in the preset time period is the first in-bed state if the first in-bed state is the same as the second in-bed state.

Optionally, after the determining of the second in-bed state of the monitored subject within the preset time period, the sixth determining unit is further configured to:

when the first in-bed state is different from the second in-bed state and any one of the first in-bed state and the second in-bed state is a non-in-bed state, determining that the in-bed state of the monitoring object in the preset time period is a non-in-bed state.

Optionally, the duration of the preset time period is greater than a time threshold, and the third determining module includes:

a second dividing unit, configured to divide the preset time period into a plurality of time segments based on the time threshold;

a seventh determining unit, configured to determine, according to the posture feature corresponding to each time slice, a third in-bed state of the monitored object in each time slice;

an eighth determining unit, configured to determine, according to a motion feature corresponding to each time slice, a fourth in-bed state of the monitored object in each time slice;

a ninth determining unit, configured to determine, according to a third in-bed state and a fourth in-bed state corresponding to each time slice in the preset time period, the in-bed state of each time slice of the monitored object in the preset time period.

Optionally, the ninth determining unit is specifically configured to:

According to a third aspect of the present disclosure, there is provided a wearable device comprising:

an acceleration sensor;

a wearable accessory;

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a method as described in an embodiment of the above aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program for causing a computer to perform the method of the above-described embodiment of the aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of an embodiment of the above-mentioned aspect.

The wearable device-based in-bed state monitoring method, the wearable device-based in-bed state monitoring device, the wearable device-based in-bed state monitoring computer equipment and the wearable device-based in-bed state monitoring storage medium have at least the following beneficial effects:

the wearable device firstly acquires an acceleration signal output within a preset time period, then determines the motion characteristic of the monitored object within the preset time period according to the acceleration signal, determines the posture characteristic of the monitored object within the preset time period according to the acceleration signal, and finally determines the in-bed state of the monitored object within the preset time period according to the posture characteristic and the motion characteristic. Therefore, the in-bed state of the monitored object is determined by fusing the motion characteristic and the posture characteristic, and the accuracy and the reliability of the monitoring result are improved.

Further, in the embodiment of the disclosure, the wearable device first acquires an acceleration signal output within a preset time period, then determines a motion characteristic of the monitored object within the preset time period according to the acceleration signal, determines an attitude characteristic of the monitored object within the preset time period according to the acceleration signal, then determines a first in-bed state of the monitored object within the preset time period according to the attitude characteristic, determines a second in-bed state of the monitored object within the preset time period according to the motion characteristic, and finally determines the in-bed state of the monitored object within the preset time period according to the first in-bed state and the second in-bed state within the preset time period. Therefore, the in-bed state in the preset time period is respectively determined through the motion characteristics and the posture characteristics, and the accuracy and the reliability of the monitoring result are improved.

Further, in the embodiment of the present disclosure, the wearable device first divides a preset time period into a plurality of time segments based on a time threshold, then determines a motion feature and an attitude feature of the monitoring subject in each time segment according to the acceleration signal, then determines a third in-bed state of the monitoring subject in each time segment according to the attitude feature corresponding to each time segment, determines a fourth in-bed state of the monitoring subject in each time segment according to the motion feature corresponding to each time segment, and finally determines the in-bed state of each time segment of the monitoring subject in the preset time period according to the third in-bed state and the fourth in-bed state corresponding to each time segment in the preset time period. Therefore, the in-bed state of the monitored object in the preset time period is determined according to the motion characteristic and the posture characteristic of each time slice, and the accuracy and the reliability of in-bed state monitoring are improved.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic flow diagram of a wearable device-based in-bed status monitoring method provided in accordance with the present disclosure;

fig. 2 is a schematic flow diagram of another wearable device-based in-bed status monitoring method provided in accordance with the present disclosure;

fig. 3 is a schematic flow chart diagram of still another wearable device based in-bed status monitoring method provided in accordance with the present disclosure;

fig. 4 is a block diagram of a wearable device-based in-bed state monitoring apparatus provided in the present disclosure;

fig. 5 is a block diagram of an electronic device provided in the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The wearable device-based in-bed state monitoring method provided by the disclosure can be executed by the wearable device-based in-bed state monitoring device provided by the disclosure, and can also be executed by the wearable device provided by the disclosure. Wherein, wearable equipment can be for intelligent wrist-watch, intelligent bracelet and other have acceleration sensor's equipment, and this disclosure does not restrict this.

The following describes a wearable device-based in-bed state monitoring method, an apparatus and a computer device according to the present disclosure with reference to the drawings.

Fig. 1 is a schematic flow chart of a wearable device-based in-bed state monitoring method according to an embodiment of the present disclosure.

As shown in fig. 1, the wearable device-based in-bed status monitoring method may include the steps of:

step 101, acquiring an acceleration signal output by the wearable device within a preset time period.

It can be appreciated that, in order to carry out accurate analysis to the in-bed state of user, this disclosure utilizes the wearable equipment that the portability is good, and the various scenes of daily use of being convenient for carry out in-bed state monitoring to the user. When the user wears the wearable device, the sensor in the wearable device can visually reflect the behavior of the user. For example, the acceleration signal output by the sensor may reflect the movement of the limb of the user in which the wearable device is located.

It should be noted that, in the present disclosure, the acceleration signal may be output by a sensor in the wearable device, and the acceleration signal may be a single-axis acceleration sensor, a double-axis acceleration sensor, or a three-axis acceleration sensor, which is not limited in the present disclosure.

It can be understood that, in order to more accurately estimate the activity state of the user, the present disclosure may select a three-axis acceleration sensor, that is, by respectively acquiring acceleration signals in three axes of a spatial coordinate system, the result determined based on the acceleration signals is more reliable. The following embodiments of the present disclosure are described by taking the acceleration signal as a triaxial acceleration signal as an example.

The preset time period may be a preset time period with any length.

In general, since the state of the user in the bed is generally a continuous event, in the present disclosure, the acceleration signal within a preset time period may be acquired. I.e. the acceleration signal, may be a sequence comprising a series of acceleration values.

And step 102, determining the motion characteristics of the monitored object in a preset time period according to the acceleration signal.

In the present disclosure, the acceleration signal may be first analyzed to determine an operation characteristic of the monitoring object within a preset time period corresponding to the acceleration signal. For example, if each acceleration value in the acceleration signal is smaller than a threshold, it may be determined that the motion characteristic of the monitored object in a preset time period is: no movement; or, if each acceleration value in the acceleration signal is greater than a threshold, it may be determined that the motion characteristic of the monitored object in a preset time period is: sports, etc., to which the present disclosure is not limited.

Optionally, if the time length corresponding to the preset time period is longer, in the present disclosure, the preset time period may be further divided into a plurality of time windows based on the specified time length, and then an average absolute deviation corresponding to each time window is determined according to the acceleration at each time in each time window, and then the motion characteristic in the preset time period is determined based on the average absolute deviation of each time window. Namely, the step 102, may include:

dividing a preset time period into a plurality of time windows based on the specified time length;

determining a type label corresponding to each time window according to the size relation between the average absolute deviation corresponding to each time window and the activity threshold, wherein the type label is used for representing the activity state of the monitoring object in the corresponding time window;

and determining the motion characteristics of the monitored object in the preset time period according to the type labels of the time windows in the preset time period.

The specified time length may be preset, or may also be determined according to the current time by the wearable device, for example, when the user starts to sleep or in the early morning, there may be frequent actions such as turning over, and when the user deeply sleeps, the probability of the actions is low, so that the specified time length corresponding to late night may be set to be longer, and the specified time length corresponding to early morning or early sleep may be set to be shorter.

It should be noted that, when determining the average absolute deviation corresponding to each time window, the device needs to calculate the combined acceleration by first combining the three-axis acceleration measurement values obtained by the sensor. For convenience of explanation, the three-axis acceleration measurement value corresponding to each time of each time window is respectively recorded as acc in the disclosure _x 、acc _y And acc _z 。

Furthermore, the equipment can measure the acc according to the triaxial acceleration _x 、acc _y And acc _z The total acceleration gacc at each time in the time window is calculated by using the following formula:

it should be noted that the present device may also calculate a total acceleration of the current time window by calculating three-axis acceleration measurement values of the current time window, where the total acceleration may be used as the window acceleration of the current time window.

After the total acceleration of each time in each time window is obtained, the device may calculate a mean value mean of the total acceleration of each time window according to the number n of times included in each time window and the total acceleration of each time in each time window _gacc The formula is as follows:

wherein, gacc _i The sum of the accelerations corresponding to the ith moment is, and i is a positive integer.

The device can then average the mean of the resultant accelerations for each time window _gacc And the resultant acceleration gacc for each time instant in each time window _i Calculating the average absolute deviation MAD corresponding to each time window, wherein the formula is as follows:

further, the device may determine the type label corresponding to each time window according to a size relationship between the average absolute deviation corresponding to each time window and the activity threshold. The activity threshold may be preset in the wearable device, or may also be automatically generated for the wearable device according to the historical motion information of the monitored object, which is not limited in this disclosure.

The type tag in the present disclosure may be "low activity level", "medium activity level", "high activity level", and the like, which is not limited by the present disclosure. It can be understood that the number of activity thresholds may be determined according to the number of type tags, for example, if there are two type tags corresponding to a time window, that is, "low activity amount" and "high activity amount", respectively, then the device may set one activity threshold. According to the size relationship between the average absolute deviation corresponding to each time window and the activity threshold, the device may mark the time window with the average absolute deviation lower than or equal to the activity threshold as "low activity amount", and mark the time window with the average absolute deviation higher than the activity threshold as "high activity amount", which is not limited in the present disclosure.

Alternatively, if there are three type tags corresponding to the time window, which are respectively "low activity level", "medium activity level", and "high activity level", the device may set two activity thresholds, where the disclosure designates a small activity threshold and a large activity threshold as B. According to the magnitude relationship between the average absolute deviation corresponding to each time window and the activity threshold, the time window with the average absolute deviation lower than or equal to the activity threshold a may be labeled as "low activity amount", the time window with the average absolute deviation higher than the activity threshold B may be labeled as "high activity amount", and the time window with the average absolute deviation higher than the activity threshold a and less than or equal to the activity threshold B may be labeled as "medium activity amount", which is not limited by the present disclosure.

In this disclosure, to facilitate the wearable device to perform statistical analysis on the type tags of each window in the continuous period, different types of tags may be characterized by different feature values. For example, the feature value corresponding to "low activity level" is 0, the feature value corresponding to "medium activity level" is 1, and the feature value corresponding to "high activity level" is 2.

Correspondingly, after the type label, i.e., the feature value, of each time window is determined, the feature values corresponding to the time windows may be fused, for example, arranged, or weighted and summed, so as to determine the motion feature of the preset time period. For example, if the preset time period is divided into 5 time windows, and the characteristic values corresponding to the 5 time windows are sequentially: 0. 0, 1, 0, the motion feature corresponding to the preset time period may be that the plurality of feature values are sequentially arranged to form a feature vector, i.e., [0, 1, 0]. Alternatively, the plurality of feature values may be subjected to weighted summation or the like to determine the motion feature corresponding to the continuous period. The present disclosure is not limited thereto.

And 103, determining the posture characteristics of the monitored object in a preset time period according to the acceleration signal.

In the present disclosure, the acceleration signal may be first analyzed to determine an attitude characteristic of the monitoring object within a preset time period corresponding to the acceleration signal. For example, if each acceleration value in the acceleration signal is smaller than a threshold, it may be determined that the posture characteristic of the monitored object in a preset time period is: a resting posture; or, if each acceleration value in the acceleration signal is greater than a threshold, it may be determined that the posture characteristic of the monitored object in a preset time period is: sitting or standing, etc., as the present disclosure does not limit.

Optionally, if the time length corresponding to the preset time period is long, in the present disclosure, the preset time period may be further divided into a plurality of time windows based on the specified time length, then the window acceleration corresponding to each time window is determined, and then the posture characteristic in the preset time period is determined according to the window acceleration corresponding to each time window. That is, the step 103 may include:

determining the acceleration of a window corresponding to each time window according to the acceleration of each moment in each time window;

determining the distance value between each acceleration vector and the designated spherical area;

and determining the posture characteristics of the monitored object in the preset time period according to the plurality of distance values in the preset time period.

For the specific implementation process of determining the window acceleration, reference may be made to the detailed description at step 102, which is not described herein again.

Under the condition that the window acceleration corresponding to any time window is in the specified range, the device can determine the acceleration vector corresponding to any time window.

Alternatively, the ranges specified in this disclosure may be 1g ± 0.1g, 1g ± 0.2g, 1g ± 0.5g, and so forth, without limitation.

Wherein g is the acceleration of gravity.

Specifically, if the acceleration of the window corresponding to any time window is within a specified range, it indicates that the acceleration vector is stable. Then, the device may first obtain the window acceleration of the time window, and then normalize the three-axis acceleration based on the window acceleration, so as to obtain a unit vector of the current window in three axial directions.

For example, if the current window acceleration is gacc, the three-axis acceleration measurements are acc _x 、 acc _y And acc _z Respectively normalizing the three axial acceleration measurement values based on the window acceleration, namely calculating three components u of the three axial acceleration measurement values on a three-dimensional rectangular coordinate system _x 、u _y And u _z The formula is as follows:

u _x ＝acc _x /gacc

u _y ＝acc _y /gacc

u _z ＝acc _z /gacc

further, based on u _x 、u _y And u _z Obtaining the included angle u between the acceleration vector and the x-axis _long And included angle u with the z-axis _la Wherein the disclosure is presented in u _long As longitude, in u _la As the latitude, the specific calculation process is as follows:

if u is _x ＜0，u _y If greater than 0, then u _long ＝atan(u _y /u _x )+pi；

If u is _x ＜0，u _y U is less than or equal to 0 _long ＝atan(u _y /u _x )-pi；

If u is _x =0, then u _long ＝atan(u _y /eps)；

If u is _x If u is greater than 0 _long ＝atan(u _y /u _x )；

In addition, u _la ＝asin(u _z )。

Furthermore, the present device may determine the spherical distance Dis between the vector of the current time window and the marked region point according to a spherical distance formula, where the formula is as follows:

Dis＝acos(cos(u _la )*cos(i _la )*cos(u _long -i _long )+sin(u _la )*sin(i _la ))

wherein, longitude i _long The included angle between the vector formed by connecting the marked region point and the origin of the spherical coordinate system and the x axis, latitude i _la Is its angle to the z-axis, longitude u _long Is the angle between the acceleration vector and the x-axis, latitude u _la Is the angle between the acceleration vector and the z-axis.

The area point is any point in the designated spherical area, or a designated point, and the disclosure does not limit this.

For example, if the preset time period is divided into 5 time windows, and each time window corresponds to a distance value, the present device may directly sum the 5 distance values or perform weighted summation according to weights, and further the present device may use the finally summed value as the posture characteristic, which is not limited in the present disclosure.

Alternatively, the present disclosure may vector add window accelerations corresponding to 5 time windows directly to obtain a sum vector. Further, the present disclosure may use a spherical distance value between the sum vector and any point in the designated spherical area as the orientation feature, which is not limited by the present disclosure.

And 104, determining the in-bed state of the monitored object within a preset time period according to the posture characteristic and the motion characteristic.

Specifically, the device may determine the in-bed state of the monitored object within a preset time period according to the posture characteristic and the motion characteristic of the user, which may be "out of bed", "suspected out of bed", and "not out of bed", and the disclosure does not limit this. The combined features of the device comprise posture features and motion features, so that the device can determine the in-bed state of the monitored object in a preset time period from two angles, and therefore, the sleep time can be calculated more accurately, the application of the wearable device is expanded, and the result of the determined in-bed state is more accurate and reliable.

In the embodiment of the disclosure, the wearable device firstly acquires an acceleration signal output by the sensor within a preset time period, then determines a motion characteristic of the monitored object within the preset time period according to the acceleration signal, determines an attitude characteristic of the monitored object within the preset time period according to the acceleration signal, and finally determines the in-bed state of the monitored object within the preset time period according to the attitude characteristic and the motion characteristic. Therefore, the in-bed state of the monitored object is determined by fusing the motion characteristic and the posture characteristic, and the accuracy and the reliability of the monitoring result are improved.

Fig. 2 is a schematic flow chart of a wearable device-based in-bed status monitoring method according to an embodiment of the present disclosure.

As shown in fig. 2, the wearable device-based in-bed status monitoring method may include the steps of:

step 201, acquiring an acceleration signal output by the wearable device within a preset time period.

And step 202, determining the motion characteristics of the monitored object within a preset time period according to the acceleration signal.

It should be noted that, when determining the motion characteristic of the monitored object in the preset time period according to the acceleration signal, the present device needs to divide the preset time period into a plurality of time windows based on the specified time length, and determine the type label of each time window, and the specific implementation process may refer to step 102.

Optionally, the device may determine the number of each type of window in the preset time period according to the type label of each time window in the preset time period, so that the device may determine the motion characteristic of the preset time period based on the number of each type of window in the preset time period.

For example, if there are N time windows included in the predetermined time period, there are three type tags corresponding to the time windows, which are "low activity level" and "medium activity level" respectivelyMomentum and high activity, the device may respectively record the number of windows corresponding to the three types of tags as count _low 、count _mid 、count _high 。

Wherein count _low +count _mid +count _high ＝N

Then, the number of each type of label corresponding to the plurality of time windows included in the continuous time period can be used to represent the motion characteristic of the preset time period, such as [ count ] _low 、count _mid 、count _high ]The present disclosure does not limit this.

In addition, the device can also determine a time window type sequence in the preset time period according to the type label of each time window in the preset time period.

For example, if 5 time windows are included in the preset time period, the device may determine the type tags of the 5 time windows one by one, and further obtain the time window type sequence in the preset time period. For example, if the type tags of the 5 time windows are "low activity level", "high activity level", and "high activity level" in chronological order, respectively, and the "low activity level" type tag is denoted as M and the "high activity level" is denoted as N, the time window type sequence may be "M, N".

Furthermore, after determining the time window type sequence, the device may determine the number of each type of window in a preset time period, for example, the device may learn, from "M, N", that there are 3 time windows of the "low activity amount" type and 2 time windows of the "high activity amount" type, which is not limited in this disclosure. <xnotran> , M 1,N 2, "M, M, M, N, N" [1, 1, 1, 2, 2], , . </xnotran>

It should be noted that, after the device determines the type label corresponding to each time window of the monitoring object according to the acceleration signal, the device may determine the activity change point within the preset time period through the type label corresponding to each time window. The active change points may be used to determine a motion characteristic of the time interval, and accordingly, the present disclosure may update the motion characteristic accordingly.

That is, the step 202 may further include:

and updating the motion characteristics of the monitored object in a preset time period according to the time interval corresponding to each time window.

For example, if a preset time period is divided into 5 time windows, wherein the type labels corresponding to the first three time windows are all "low activity amount", and the type labels corresponding to the second two time windows are all "medium activity amount", the device may use the time point between the "low activity amount" time window and the "medium activity amount" time window as the activity change point.

In the present disclosure, a time point when the time window is changed from "low activity level" to "medium activity level" may be referred to as a "medium activity change point", and a time point when the "medium activity level" is changed to "high activity level" may be referred to as a "high activity change point", which is not limited in the present disclosure.

It will be appreciated that if there are multiple active change points in successive time periods, then correspondingly, time intervals may occur. The device may determine the time interval between each time window and the previous active change, such as the time interval CP between the current window and the last "high active change _high Time interval CP from last' middle activity change point _mid Or the time interval from the last adjacent active change point of either type, which the present disclosure does not limitAnd (4) determining. It will be appreciated that the apparatus may use this time interval as a movement characteristic for determining the in-bed status of the monitored subject.

Further, the device can update the motion characteristics of the monitored object in the preset time period according to the time interval corresponding to each time window. It can be understood that, after acquiring the time interval between each time window of the current preset time period and the adjacent previous activity change point, the present disclosure also determines the motion characteristic of the "time interval", and further, the present apparatus may re-determine or supplement the motion characteristic of the monitored object in the preset time period, which is not limited by the present disclosure.

And step 203, determining the posture characteristics of the monitored object in a preset time period according to the acceleration signal.

Specifically, if the window acceleration corresponding to any time window is within the specified range, the present disclosure may determine the posture characteristic according to the specific implementation manner of step 103, and if the window acceleration corresponding to any time window is not within the specified range, the present apparatus may determine the posture characteristic of the monitoring object within the preset time period according to the window accelerations corresponding to the remaining time windows within the preset time period.

It can be understood that, if the window acceleration corresponding to any time window is not within the specified range, the present device may determine the window accelerations corresponding to the remaining time windows. For example, if there are currently 5 time windows and it can be determined that the window acceleration of the 2 nd time window is out of the specified range, the apparatus may calculate the window accelerations of the remaining 4 time windows, for example, vector-summing the window accelerations of the 4 time windows to obtain a sum vector. Further, referring to step 103, a spherical distance value between the sum vector and any point in the designated spherical area may be calculated as the posture feature, which is not limited by the present disclosure. Or, the present disclosure may directly sum the window acceleration of the remaining 4 time windows and the spherical distance value of any point in the designated spherical area, or perform weighted summation according to a weight, and the present apparatus may use the last summed value as the attitude characteristic, which is not limited by the present disclosure.

Step 204, determining a first in-bed state of the monitored object within a preset time period according to the posture characteristics.

Optionally, when the first in-bed state is determined, the device may compare the feature value corresponding to the posture feature in the preset time period with a preset threshold value by using a threshold value comparison method. The preset threshold may be one or more, which is not limited herein. If there is only one preset threshold, if the current characteristic value is higher than the threshold, the first in-bed state of the monitored object within the preset time period may be determined as the "out-of-bed state", and if the current characteristic value is smaller than the threshold, the first in-bed state of the monitored object within the preset time period may be determined as the "in-bed state", which is not limited in this disclosure.

And step 205, determining a second in-bed state of the monitored object within a preset time period according to the motion characteristics.

Optionally, when determining the second in-bed state, the apparatus may input each motion feature into a pre-trained decision tree model to obtain an output result of the second in-bed state. The motion characteristics may be the number of each time window of each type tag in a preset time period, the time interval between each time window and the adjacent previous activity change point in the preset time period, and the like, which is not limited in this disclosure.

Alternatively, the second in-bed state may be further determined to be "out-of-bed", "suspected out-of-bed", or "out-of-bed", without being limited in this disclosure, by inputting the motion feature vector of the monitored object, and acquiring the matching degree between the monitored object and the feature vector of each sample in the template library.

Step 206, determining the in-bed state of the monitored object within the preset time period according to the first in-bed state and the second in-bed state within the preset time period.

Alternatively, in a case where the first in-bed state is the same as the second in-bed state, the present apparatus may determine that the in-bed state of the monitoring subject within the preset time period is the first in-bed state. It is to be understood that, if the first in-bed state is the same as the second in-bed state, for example, both the first in-bed state and the second in-bed state are "out of bed", the present apparatus may use the first in-bed state "out of bed" as the in-bed state of the monitoring object in the preset time period, and since the first in-bed state is the same as the second in-bed state, the present apparatus may also use the second in-bed state as the in-bed state of the monitoring object in the preset time period, which is not limited in this disclosure.

In addition, if the first in-bed state is different from the second in-bed state, and any one of the first in-bed state and the second in-bed state is a non-in-bed state, the present apparatus may determine that the in-bed state of the monitoring subject in the preset time period is a non-in-bed state. The out-of-bed state may be "out-of-bed" or "suspected out-of-bed", which is not limited herein.

For example, if the first in-bed state is "out-of-bed" and the second in-bed state is "out-of-bed", since the first in-bed state is not in-bed, the apparatus may determine that the in-bed state of the monitored object within the preset time period is not in-bed state. Or, if the second in-bed state is "suspected to be out of bed", the present apparatus may also determine that the in-bed state of the monitored object within the preset time period is a non-in-bed state, which is not limited in this disclosure.

In the embodiment of the disclosure, the wearable device firstly acquires an acceleration signal output by a sensor within a preset time period, then determines a motion characteristic of a monitored object within the preset time period according to the acceleration signal, determines an attitude characteristic of the monitored object within the preset time period according to the acceleration signal, then determines a first in-bed state of the monitored object within the preset time period according to the attitude characteristic, determines a second in-bed state of the monitored object within the preset time period according to the motion characteristic, and finally determines the in-bed state of the monitored object within the preset time period according to the first in-bed state and the second in-bed state within the preset time period. Therefore, the in-bed state in the preset time period is respectively determined through the motion characteristics and the posture characteristics, and the accuracy and the reliability of the monitoring result are improved.

As shown in fig. 3, the wearable device based in-bed state monitoring method may include the following steps:

step 301, acquiring an acceleration signal output by the wearable device within a preset time period.

Step 302, under the condition that the duration of the preset time period is greater than the time threshold, dividing the preset time period into a plurality of time segments based on the time threshold.

Specifically, if the duration of the preset time period is greater than the time threshold, it indicates that the preset time period is too long. In order to more accurately determine the in-bed state of the monitored subject, the present disclosure will divide the preset time period into a plurality of time segments based on a time threshold, wherein. The plurality of time segments may be equally divided or unequally divided, which is not limited by the present disclosure.

And step 303, determining the motion characteristics of the monitored object in each time segment according to the acceleration signal.

In the present disclosure, the acceleration signal may be first analyzed to determine a motion characteristic of the monitoring object in each time segment corresponding to the acceleration signal. For example, if the acceleration value in the acceleration signal in any time segment is smaller than the threshold, it may be determined that the motion characteristic of the monitored object in the time segment is: no movement; or, if the acceleration value in the acceleration signal in any time segment is greater than the threshold, the motion characteristic of the monitored object in the time segment may be determined as: sports, etc., to which the present disclosure is not limited.

And step 304, determining the posture characteristic of the monitored object in each time segment according to the acceleration signal.

In the present disclosure, a distance value between each window acceleration and the designated spherical area may also be determined according to the window acceleration corresponding to each time segment, and then the posture characteristic within the preset time period may be determined based on the distance value between the window acceleration corresponding to each time segment and the designated spherical area. For example, if the distance value between the window acceleration in any time segment and the designated spherical area is smaller than the threshold, it may be determined that the posture characteristic of the monitored object in the time segment is: a resting posture; or, if the distance value between the window acceleration in any time slice and the designated spherical area is greater than the threshold, it may be determined that the posture characteristic of the monitored object in the preset time period is: sitting or standing, etc., as the present disclosure does not limit.

And 305, determining a third in-bed state of the monitored object in each time slice according to the corresponding posture characteristic of each time slice.

In this disclosure, the present device may calculate an acceleration vector at each time by determining an acceleration at each time corresponding to each time slice. And then calculating the distance value between each acceleration vector and the designated spherical area according to the acceleration vector at each moment, summing or weighting and summing the distance values at each moment, and finally taking the obtained value as the attitude characteristic. The present device may compare the feature value corresponding to the posture feature in the preset time period with the preset threshold value by using a threshold value comparison method, so as to determine the third in-bed state, which may specifically refer to step 204, which is not repeated herein.

And step 306, determining a fourth in-bed state of the monitored object in each time slice according to the motion characteristics corresponding to each time slice.

In this disclosure, the specific process of determining the in-bed state of the monitored object according to the motion characteristic corresponding to each time segment may refer to a preset time period, in step 205, which is not described herein again.

Step 307, determining the in-bed state of the monitoring object in each time slice within the preset time period according to the third in-bed state and the fourth in-bed state corresponding to each time slice within the preset time period.

Alternatively, since it takes time for a monitoring subject to switch from one in-bed state to another, in the present disclosure, when two identical in-bed states include other types of in-bed states therebetween and the time interval between the two identical in-bed states is short, the other in-bed states between the two identical in-bed states may also be switched to the same in-bed states as the two identical in-bed states.

That is, when at least one in-bed state corresponding to the ith time slice is an out-of-bed state, at least one in-bed state corresponding to the (i + m) th time slice is an out-of-bed state, and m is smaller than a specified value, the present apparatus may determine that the in-bed states corresponding to the respective time slices between the ith time slice and the (i + m) th time slice are out-of-bed states, where i and m are positive integers.

It is understood that two time slices and each time slice between the two time slices can be considered as the out-of-bed state if the interval between the two time slices is smaller than the specified value and at least one of the two time slices corresponds to the out-of-bed state.

For example, if the present apparatus divides the continuous time period into 6 time slices, the corresponding sequence numbers are 1, 2, 3, 4, 5, and 6, respectively. According to the acceleration information corresponding to each time slice, it is determined that both the time slice 4 and the time slice 6 are in the out-of-bed state, and the difference value "1" between the two time slices is smaller than the specified value "2", so that the present device can regard both the time slice 4 and the time slice 6 as well as the time slice 5 therebetween as the out-of-bed state, which is not limited by the present disclosure.

Alternatively, in view of the fact that the monitored subject may be identified as a "suspected out-of-bed state" by the process of converting the out-of-bed state into the in-bed state or converting the in-bed state into the out-of-bed state, and the sleep quality is determined based on the in-bed time length and the sleep time length, in order to further improve the accuracy of the sleep quality determined by the wearable device, the "suspected out-of-bed state" adjacent to the "out-of-bed state" may be uniformly converted into the "out-of-bed state" in the present disclosure.

That is, when at least one in-bed state corresponding to the jth time slice is a bed leaving state and at least one in-bed state corresponding to another time slice adjacent to the jth time slice is a "suspected bed leaving state", the present apparatus may determine that the in-bed state corresponding to another time slice adjacent to the jth time slice is a "bed leaving state", where j is a positive integer.

It is understood that, if at least one of the third in-bed state and the fourth in-bed state corresponding to the jth time slice is in the out-of-bed state, and at least one of the in-bed states corresponding to the jth time slice adjacent to the jth time slice is in the suspected "out-of-bed state", the present apparatus may regard all other time slices adjacent to the jth time slice as the "out-of-bed state".

It can be understood that, by determining the bed-in state of the current detection object in the above result fusion manner, the stability and reliability of bed-in state monitoring can be improved, and the result is more stable.

According to the embodiment of the disclosure, wearable equipment firstly divides a preset time period into a plurality of time segments based on a time threshold, then determines motion characteristics and posture characteristics of a monitored object in each time segment according to an acceleration signal, then determines a third in-bed state of the monitored object in each time segment according to the posture characteristics corresponding to each time segment, determines a fourth in-bed state of the monitored object in each time segment according to the motion characteristics corresponding to each time segment, and finally determines the in-bed state of the monitored object in each time segment in the preset time period according to the third in-bed state and the fourth in-bed state corresponding to each time segment in the preset time period. Therefore, the in-bed state of the monitored object in the preset time period is determined according to the motion characteristic and the posture characteristic of each time slice, and the accuracy and the reliability of in-bed state monitoring are improved.

In order to implement the above embodiments, the embodiments of the present disclosure further provide an in-bed state monitoring device based on a wearable device. Fig. 4 is a structural block diagram of a bed state monitoring device based on a wearable device according to an embodiment of the present disclosure.

As shown in fig. 4, the wearable device-based in-bed status monitoring apparatus 400 includes: a first obtaining module 410, a first determining module 420, a second determining module 430, and a third determining module 440.

A first obtaining module 410, configured to obtain an acceleration signal output by a sensor in the wearable device within a preset time period;

a first determining module 420, configured to determine, according to the acceleration signal, a motion characteristic of the monitored object within the preset time period;

a second determining module 430, configured to determine, according to the acceleration signal, an attitude feature of the monitored object within the preset time period;

a third determining module 440, configured to determine, according to the posture feature and the motion feature, a bed presence state of the monitored subject within the preset time period.

Optionally, the acceleration signal is an acceleration at each time, and the first determining module 420 includes:

a second determining unit, configured to determine a type label corresponding to each time window according to a size relationship between an average absolute deviation corresponding to each time window and an activity threshold, where the type label is used to characterize an activity state of the monitoring object in the corresponding time window;

Optionally, after determining the type tag corresponding to each time window, the first determining module 420 is further configured to:

Optionally, the third determining unit is specifically configured to:

and/or the presence of a gas in the atmosphere,

Optionally, the acceleration signal is an acceleration at each time, and the second determining module 420 is specifically configured to:

Optionally, the third determining module includes:

a fifth determining unit, configured to determine, according to the motion feature, a second in-bed state of the monitored object within the preset time period;

Optionally, the ninth determining unit is specifically configured to:

In the embodiment of the disclosure, the wearable device firstly acquires an acceleration signal output within a preset time period, then determines a motion characteristic of the monitored object within the preset time period according to the acceleration signal, determines an attitude characteristic of the monitored object within the preset time period according to the acceleration signal, and finally determines the in-bed state of the monitored object within the preset time period according to the attitude characteristic and the motion characteristic. Therefore, the in-bed state of the monitored object is determined by fusing the motion characteristic and the posture characteristic, and the accuracy and the reliability of the monitoring result are improved.

The present disclosure also provides a wearable device, a readable storage medium, a computer program product, according to embodiments of the present disclosure.

FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 501 performs the various methods and processes described above, such as wearable device-based in-bed status monitoring methods. For example, in some embodiments, the wearable device-based in-bed status monitoring method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the wearable device based in-bed status monitoring method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the wearable device-based in-bed status monitoring method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for monitoring the state of a patient in bed based on wearable equipment is characterized by comprising the following steps:

acquiring an acceleration signal output by the wearable device within a preset time period;

2. The method of claim 1, wherein the acceleration signal is an acceleration at each time, and the determining the motion characteristics of the monitored object within the preset time period according to the acceleration signal comprises:

determining a type label corresponding to each time window according to the size relation between the average absolute deviation corresponding to each time window and an activity threshold, wherein the type label is used for representing the activity state of the monitored object in the corresponding time window;

3. The method of claim 2, wherein after said determining a type label for each of said time windows, further comprising:

4. The method of claim 2, wherein the determining the motion characteristics of the monitored object in the preset time period according to the type labels of the time windows in the preset time period comprises:

and/or the presence of a gas in the gas,

5. The method of claim 1, wherein the acceleration signal is an acceleration at each time, and the determining the posture characteristic of the monitored object within the preset time period according to the acceleration signal comprises:

6. The method of claim 5, wherein after said determining a window acceleration for each of said time windows, further comprising:

7. The method of any one of claims 1-6, wherein said determining the in-bed status of the monitored subject over the preset time period based on the posture characteristic and the motion characteristic comprises:

determining a first in-bed state of the monitored object within the preset time period according to the posture characteristics;

8. The method of claim 7, further comprising, after said determining a second in-bed state of the monitored subject within the preset time period:

9. The method of any one of claims 1-6, wherein the duration of the preset time period is greater than a time threshold, and the determining the in-bed state of the monitored subject within the preset time period according to the posture characteristic and the motion characteristic comprises:

and determining the in-bed state of the monitoring object in each time slice within the preset time period according to the third in-bed state and the fourth in-bed state corresponding to each time slice within the preset time period.

10. The method of claim 9, wherein the determining the in-bed state of the monitoring subject for each time slice within the preset time period according to the third in-bed state and the fourth in-bed state corresponding to each time slice within the preset time period comprises:

and under the condition that at least one in-bed state corresponding to the ith time slice is in a bed leaving state, at least one in-bed state corresponding to the (i + m) th time slice is in a bed leaving state, and m is smaller than a specified value, determining that the in-bed states corresponding to the ith time slice and each time slice between the (i + 1) th time slice are in the bed leaving state, wherein i and m are positive integers.

11. The method of claim 9, wherein the determining the in-bed status of the monitoring subject in each time slice within the preset time period according to the third in-bed status and the fourth in-bed status corresponding to each time slice within the preset time period comprises:

12. An in-bed state monitoring device based on wearable equipment, characterized by comprising:

and the third determining module is used for determining the in-bed state of the monitored object in the preset time period according to the posture characteristic and the motion characteristic.

13. A wearable device, comprising:

an acceleration sensor;

a wearable accessory;

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-11.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-11.