WO2024088049A1

WO2024088049A1 - Sleep monitoring method and electronic device

Info

Publication number: WO2024088049A1
Application number: PCT/CN2023/123527
Authority: WO
Inventors: 王润森; 顾叔衡; 韩羽佳; 何志健; 薛坤; 圣荣
Original assignee: 华为技术有限公司
Priority date: 2022-10-26
Filing date: 2023-10-09
Publication date: 2024-05-02
Also published as: CN117958746A

Abstract

The present application relates to the technical field of terminals, and provides a sleep monitoring method and an electronic device. The specific solution comprises: an electronic device acquires acceleration data of a first electronic device within a monitoring period. The electronic device determines, according to the acceleration data, motion data of a user using the first electronic device, wherein the motion data comprises at least one of activity data, a step number and an arm action. The electronic device determines at least two first time points according to the motion data, the first time point being a suspected getting-into-bed and getting-out-of-bed time point of the user. Furthermore, the electronic device determines a getting-into-bed time point and a getting-out-of-bed time point of the user according to the at least two first time points, and can monitor the sleep of the user according to the getting-into-bed time point and the getting-out-of-bed time point. Therefore, the electronic device can accurately and quickly determine the getting-into-bed time point and the getting-out-of-bed time point of the user, so that the accuracy of sleep monitoring is improved.

Description

Sleep monitoring method and electronic device

This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on October 26, 2022, with application number 202211321498.2 and application name “A Sleep Monitoring Method and Electronic Device”, the entire contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the field of terminal technology, and in particular to a sleep monitoring method and electronic equipment.

Background technique

With the increasingly intense work and life pace in modern society, more and more people living under high pressure have developed sleep disorders such as insomnia. Insomnia is a symptom of difficulty in falling asleep naturally, for example, difficulty in falling asleep (or difficulty in falling asleep), or difficulty in maintaining deep sleep for a long time (or difficulty in maintaining sleep). Severe and persistent insomnia not only has chronic and long-term physiological consequences on the human body, but also makes the human mind prone to negative emotions such as anxiety and depression, resulting in serious physical and psychological disease burdens. Therefore, it is necessary to diagnose and treat insomnia in a timely manner.

In the diagnosis and treatment of insomnia, sleep efficiency is usually used as a reference indicator to analyze the user's sleep quality. Sleep efficiency is the ratio of the user's actual total sleep time to the total time in bed, where the total time in bed is the difference between the time the user gets out of bed and the time he or she goes to bed. However, current electronic devices are unable to accurately and conveniently identify the user's actual actions of getting in and out of bed, and thus are unable to accurately determine the user's time of going to bed and time of getting out of bed. This may result in an overestimation or underestimation of the user's actual sleep efficiency, making it impossible to accurately monitor the user's sleep and accurately analyze the user's sleep quality.

Summary of the invention

The embodiments of the present application provide a sleep monitoring method and electronic device, which can accurately determine the time when a user goes to bed and gets out of bed, thereby improving the accuracy of sleep monitoring.

To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

In a first aspect, a sleep monitoring method is provided, the method comprising: an electronic device obtains acceleration data of a first electronic device within a monitoring period. The electronic device determines motion data of a user using the first electronic device based on the acceleration data, wherein the motion data includes at least one of activity data, number of steps, and arm movements, and the activity data is used to characterize the user's exercise intensity. The electronic device determines at least two first time points based on the motion data, and the first time points are suspected time points for the user to get in and out of bed. Further, the electronic device determines the time point for the user to go to bed and the time point for the user to get out of bed based on the at least two first time points. The electronic device monitors the user's sleep based on the time point for going to bed and the time point for the user to get out of bed.

In this method, the electronic device can determine the user's activity data, step count, and one or more types of motion data of the arm motion based on the acceleration data. The electronic device can identify the user's getting in and out of bed motion based on the motion data and determine the suspected time point of the user getting in and out of bed. Further, the electronic device determines the user's bed time and bed-leaving time based on the suspected bed-leaving time. In this way, the electronic device can accurately and quickly determine the user's bed-leaving time and bed-leaving time, thereby improving the accuracy of sleep monitoring.

In an implementable manner of the first aspect, the above-mentioned monitoring period includes multiple monitoring time points, and the motion data includes motion data of multiple monitoring time points. The electronic device determines at least two first time points based on the motion data, including: for each monitoring time point in the multiple monitoring time points, the electronic device determines the change data of the motion data within a preset time before the monitoring time point. If the change data meets the preset conditions, the electronic device determines that the monitoring time point is the first time point. In this implementation manner, since the motion data is used to characterize the movement of the user using the electronic device, the motion data will change during the user's movement. Therefore, the electronic device can accurately identify the user's getting in and out of bed actions based on the change data of the motion data, and determine the user's suspected getting in and out of bed time point (i.e., the first time point), so as to further determine the user's going to bed time point and getting out of bed time point.

In an implementation of the first aspect, when the motion data includes activity data, the preset condition includes: within a first preset period before the monitoring time point, the change data of the activity data is greater than a first threshold. When the motion data includes the number of steps, the preset condition includes: within a second preset period before the monitoring time point, the change data of the number of steps is greater than a second threshold. In the case where the motion data includes arm movements, the preset conditions include: within a third preset period before the monitoring time point, the number of times the arm movement satisfies the preset movement is greater than a third threshold; the preset movement includes: arm swinging movement and arm vertical downward movement. In this implementation, the electronic device can accurately identify the user's getting in and out of bed movement through the preset conditions corresponding to the activity data, the number of steps, and the arm movement, so as to further determine the suspected time point of the user getting in and out of bed.

In an implementation of the first aspect, the monitoring period includes multiple monitoring time points, and the motion data includes motion data of multiple monitoring time points. The method for an electronic device to determine at least two first time points based on the motion data includes: the electronic device inputs the motion data of multiple monitoring time points into a preset detection model to obtain at least two first time points. In this implementation, the electronic device can quickly determine the suspected time points of the user getting in and out of bed through the detection model based on the motion data, thereby improving the efficiency of the electronic device in determining the suspected time points of the user getting in and out of bed.

In an implementation of the first aspect, the detection model is constructed by the following method: the electronic device obtains a sample set, the sample set includes motion data at multiple time points, and multiple time points for getting in and out of bed. The electronic device uses the sample set to train an initial model of the detection model to construct the detection model. In this way, by training the initial model of the detection model with the sample set, the detection accuracy of the constructed detection model can be improved, thereby improving the accuracy of the electronic device in determining the suspected time points of the user getting in and out of bed.

In an implementation of the first aspect, the acceleration data includes: a first acceleration, a second acceleration, and a third acceleration, which are perpendicular to each other. When the motion data includes activity data, the electronic device determines the activity data based on the acceleration data, including: using the following formula (1) to determine the activity data:

Wherein, A is the activity data, _a1 is the first acceleration, _a2 is the second acceleration, and _a3 is the third acceleration.

In this implementation, the electronic device determines the activity data through the first acceleration, the second acceleration and the third acceleration which are perpendicular to each other, so that the activity data can more truly reflect the user's exercise intensity, thereby improving the accuracy of the electronic device in determining the suspected time points of the user getting in and out of bed based on the activity data.

In an implementable manner of the first aspect, the acceleration data includes: a first acceleration, a second acceleration, and a third acceleration, which are perpendicular to each other. In the case where the motion data includes activity data, the activity data is the first acceleration in the acceleration data, and the first acceleration is an acceleration in the same horizontal plane as the raised arm and perpendicular to the direction of the arm. In this implementation, the electronic device uses the acceleration in the direction in which the user has significant movement to characterize the activity data according to the actual application scenario. In this way, the activity data determined by the electronic device can not only truly reflect the user's exercise intensity, but also improve the efficiency of the electronic device in determining the activity data based on the acceleration data.

In an implementation of the first aspect, when the frequency of the first dominant feature of the arm action being greater than the fourth threshold meets the first preset frequency, the electronic device determines that the arm action meets the arm swing action. The first dominant feature is used to characterize the intensity of the action that is in the same horizontal plane as the raised arm and perpendicular to the direction of the arm. Specifically, the first dominant feature is determined using the following formula (2):

Among them, _B1 is the first dominant feature, _ag,X is the acceleration caused by gravity along the arm direction, _ag,Y is the acceleration caused by gravity in the same horizontal plane as the raised arm and perpendicular to the arm direction, and _ag,Z is the acceleration caused by gravity in the same vertical plane as the raised arm and perpendicular to the arm direction. In this way, the electronic device can judge the movement of the arm according to the first dominant feature to accurately determine whether the arm movement meets the arm swinging movement.

In an implementation of the first aspect, when the frequency of the second dominant feature of the arm action being greater than the fifth threshold meets the second preset frequency, the electronic device determines that the arm action meets the arm vertical downward action. The second dominant feature is used to characterize the intensity of the action along the arm direction. Specifically, the second dominant feature is determined using the following formula (3):

Among them, _B2 is the second dominant feature, _ag,X is the acceleration caused by gravity along the arm direction, _ag,Y is the acceleration caused by gravity in the same horizontal plane as the raised arm and perpendicular to the arm direction, and _ag,Z is the acceleration caused by gravity in the same vertical plane as the raised arm and perpendicular to the arm direction. In this way, the electronic device can judge the movement of the arm according to the second dominant feature to accurately determine that the arm movement satisfies the vertical downward movement of the arm.

In an implementation of the first aspect, the electronic device determines the user's bedtime based on at least two first time points. The method for determining the time of going to bed and the time of getting out of bed includes: the electronic device obtains the time of falling asleep and the time of waking up of the user. The electronic device determines the first time point before the time of falling asleep and with the smallest time difference with the time of falling asleep as the time of going to bed; the electronic device determines the first time point after the time of waking up and with the smallest time difference with the time of getting out of bed as the time of getting out of bed. In this implementation, the electronic device determines the suspected time of going to bed and getting out of bed that is closest to the time of falling asleep as the time of going to bed, and determines the suspected time of going to bed and getting out of bed that is closest to the time of waking up as the time of getting out of bed. In this way, the time of going to bed and getting out of bed of the user can be truly reflected, and the accuracy of the electronic device in determining the time of going to bed and getting out of bed can be improved.

In an implementable manner of the first aspect, a method for an electronic device to determine a user's bedtime and bed-leaving time based on at least two first time points includes: the electronic device receives a suspected bedtime and bed-leaving time from a second electronic device. The electronic device determines the bedtime and bed-leaving time based on the at least two first time points, the suspected bedtime and bed-leaving time. In this way, the electronic device can determine the bedtime and bed-leaving time in combination with the suspected bedtime and bed-leaving time of the second electronic device, which can improve the accuracy of the electronic device in determining the bedtime and bed-leaving time.

In an implementable manner of the first aspect, the method for an electronic device to determine a bedtime and a getting-out-of-bed time point based on at least two first time points, a suspected bedtime and a suspected getting-out-of-bed time point includes: if there is a first time point among the at least two first time points whose time difference with the suspected bedtime is less than a sixth threshold, the electronic device determines the suspected bedtime as the bedtime. If there is a first time point among the at least two first time points whose time difference with the suspected getting-out-of-bed time point is less than a seventh threshold, the electronic device determines the suspected getting-out-of-bed time point as the getting-out-of-bed time point. In this way, the electronic device, in combination with the suspected bedtime and suspected getting-out-of-bed time points provided by the second electronic device, can eliminate interference from other users and accurately determine the bedtime and getting-out-of-bed time points of the user using the first electronic device.

In an implementable manner of the first aspect, a method for an electronic device to determine a user's bedtime and bed-leaving time based on at least two first time points includes: the electronic device displays at least two first time points. The electronic device receives a user's selection operation for a second time point and a third time point among the at least two first time points. The electronic device determines the second time point and the third time point as the bedtime and bed-leaving time based on the selection operation. In this implementation manner, the electronic device determines the bedtime and bed-leaving time based on the user's selection operation. That is, the user determines the bedtime and bed-leaving time based on at least two suspected bedtime and bed-leaving time points, which can improve the user experience.

In an implementable manner of the first aspect, the method further includes: the electronic device obtains the user's sleeping time and waking time. The electronic device displays at least two first time points, a first time point before the sleeping time, and a first time point after the waking time. The electronic device receives the user's selection operation for the second time point and the third time point of the at least two first time points. According to the selection operation, the electronic device determines the second time point and the third time point as the bedtime and the bedtime. In this implementation, the electronic device removes the suspected bedtime that may cause interference according to the sleeping time and the bedtime. The electronic device only displays to the user the suspected bedtime before the sleeping time, and the suspected bedtime after the bedtime, so that the user can quickly determine the bedtime and the bedtime, further improving the user's experience.

In an implementable manner of the first aspect, the method further includes: the electronic device determines the accumulated activity data after the first time point according to the acceleration data. If the time when the accumulated activity data is less than the eighth threshold satisfies the preset time, the electronic device obtains the sleeping parameter, and the sleeping parameter is used to characterize the user's sleeping situation. If the sleeping parameter does not meet the ninth threshold, the electronic device displays a first prompt message, and the first prompt message is used for the user to confirm whether to turn on the sleep mode. The electronic device receives the user's confirmation operation to turn on the sleep mode. The electronic device responds to the confirmation operation and turns on the sleep mode. In this implementation, after the electronic device determines the suspected time point of the user getting in and out of bed, it can determine whether the user has been in bed for a long time without entering the sleep state according to the accumulated activity data and the sleeping parameter. If the user has been in bed for a long time without entering the sleep state, the electronic device displays a first prompt message to the user for the user to confirm whether to turn on the sleep mode. If the electronic device receives the user's confirmation operation to turn on the sleep mode, the sleep mode is turned on to help the user quickly enter the sleep state, thereby improving the user's user experience.

In an implementation of the first aspect, after the electronic device receives a confirmation operation of the user to turn on the sleep mode, the method further includes: the electronic device responds to the confirmation operation and sends a sleep mode turn-on instruction to a third electronic device, where the sleep mode turn-on instruction is used to trigger the third electronic device to turn on the sleep mode. In this implementation, the electronic device responds to the confirmation operation and can send a sleep mode turn-on instruction to the third electronic device, so that the third electronic device also turns on the sleep mode, thereby jointly helping the user quickly enter the sleep state, further improving the user's experience.

In one implementation of the first aspect, the electronic device processes the user's sleep according to the bedtime and the bedtime. The method for monitoring the sleep status of a user includes: the electronic device determines the sleep latency time and the bed rest time according to the time of going to bed and the time of getting out of bed, the sleep latency time is the difference between the time of going to bed and the time of falling asleep, and the bed rest time is the difference between the time of going to bed and the time of getting out of bed. The electronic device displays the sleep analysis result of the user according to the sleep latency time and the bed rest time. In this implementation, the electronic device can determine the sleep latency time and the bed rest time according to the time of going to bed and the time of getting out of bed, so as to further determine and display the sleep analysis result of the user, so as to facilitate the user to find sleep problems in time and improve the user experience.

In an implementation of the first aspect, when the sleep latency time is greater than the tenth threshold, the sleep analysis result includes: the sleep latency time, the bed rest time and the second prompt information, and the second prompt information is used to remind the user that the bed rest time is too long. In this way, the electronic device can enable the user to promptly discover the problem of lying in bed for too long by displaying the second prompt information, thereby improving the user's use experience.

In an implementation of the first aspect, when the number of days when the sleep latency duration is greater than the tenth threshold is greater than the day threshold, the sleep analysis result includes: a third prompt information, the third prompt information is used to display the factors causing the sleep latency duration to be greater than the tenth threshold, and/or display sleep improvement suggestions and sleep improvement tasks. In this implementation, the electronic device can enable the user to promptly discover sleep problems by displaying the third prompt information, and can promptly adjust sleep habits and improve sleep quality according to the sleep improvement suggestions and sleep improvement tasks. In this way, the user experience is further improved.

In a second aspect, an electronic device is provided, comprising: an acquisition module and a processing module. The acquisition module is used to acquire acceleration data of a first electronic device during a monitoring period. The processing module is used to determine motion data of a user using the first electronic device based on the acceleration data, the motion data comprising: at least one of activity data, number of steps, and arm movements, and the activity data is used to characterize the user's exercise intensity. The processing module is also used to determine at least two first time points based on the motion data, the first time point being the suspected time point for the user to get in and out of bed. The processing module is also used to determine the user's bedtime and bed-leaving time points based on the at least two first time points. The processing module is also used to monitor the user's sleep based on the bedtime and bed-leaving time points.

In a third aspect, an electronic device is provided, comprising: a memory, and one or more processors; the memory is coupled to the processor; wherein computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes any of the methods described in the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions, which, when executed on an electronic device, causes the electronic device to execute any of the methods described in the first aspect.

In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer, an electronic device executes any method described in the first aspect.

It can be understood that the beneficial effects that can be achieved by the electronic device of the third aspect, the computer-readable storage medium of the fourth aspect, and the computer program product of the fifth aspect can be referred to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application;

FIG2 is a schematic diagram of the hardware structure of an electronic device shown in an embodiment of the present application;

FIG3 is a schematic diagram of a sleep monitoring method according to an embodiment of the present application;

FIG4 is a statistical diagram of activity data shown in an embodiment of the present application;

FIG5 is a step count diagram shown in an embodiment of the present application;

FIG6( a ) is an acceleration waveform diagram 1 shown in an embodiment of the present application;

FIG6( b ) is a second acceleration waveform diagram shown in an embodiment of the present application;

FIG6( c ) is a third acceleration waveform diagram shown in an embodiment of the present application;

FIG. 7 is a flowchart of a method for a smart watch to determine a first time point according to an embodiment of the present application;

FIG8 is a second flow chart of a method for a smart watch to determine a first time point according to an embodiment of the present application;

FIG9 is a third flow chart of a method for a smart watch to determine a first time point according to an embodiment of the present application;

FIG10 is a fourth flow chart of a method for a smart watch to determine a first time point according to an embodiment of the present application;

FIG11 is a schematic diagram of an application scenario of a sleep monitoring method according to an embodiment of the present application;

FIG12 is a flowchart of a method for determining a time to go to bed and a time to get out of bed by a smart watch according to an embodiment of the present application;

FIG13 is a schematic diagram showing the principle of determining the time to go to bed and the time to get out of bed by a smart watch according to an embodiment of the present application;

FIG14 is a second flow chart of a method for determining a time to go to bed and a time to get out of bed by a smart watch according to an embodiment of the present application;

FIG15 is a schematic diagram 1 showing a first time point according to an embodiment of the present application;

FIG16 is a second schematic diagram showing a first time point according to an embodiment of the present application;

FIG17 is a flowchart diagram of a method for determining a time to go to bed and a time to get out of bed by a smart watch according to an embodiment of the present application;

FIG18 is a fourth flow chart of a method for determining a bedtime and a bedtime by a smartwatch according to an embodiment of the present application;

FIG19 is a second schematic diagram of an application scenario of the sleep monitoring method shown in an embodiment of the present application;

FIG20 is a third schematic diagram of an application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG21 is a fourth schematic diagram of an application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG22 is a flowchart of a method for performing sleep monitoring using a smartwatch according to an embodiment of the present application;

FIG23 is a fifth schematic diagram of an application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG24 is a second flow chart of a method for performing sleep monitoring using a smartwatch according to an embodiment of the present application;

FIG25 is a sixth schematic diagram of an application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG26 is a seventh schematic diagram of an application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG27 is a third flow chart of a method for performing sleep monitoring by a smartwatch according to an embodiment of the present application;

FIG28 is a schematic diagram of an eighth application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG29 is a ninth schematic diagram of an application scenario of the sleep monitoring method according to an embodiment of the present application;

FIG30 is a schematic diagram of the composition of an electronic device shown in an embodiment of the present application;

FIG31 is a schematic diagram of the composition of a chip system shown in an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. Among them, in the description of the present application, unless otherwise specified, "/" indicates that the objects associated before and after are in an "or" relationship, for example, A/B can represent A or B; "and/or" in the present application is only a kind of association relationship describing the associated objects, indicating that there can be three relationships, for example, A and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or its similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference. At the same time, in the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for easy understanding.

At present, people pay more and more attention to sleep disorders such as insomnia. Among them, cognitive behavioral therapy for insomnia (CBTI) therapy is a commonly used therapy for insomnia. CBTI therapy mainly adopts the sleep restriction method. Specifically: the sleep restriction method first limits the bed time of insomnia patients to continuously improve the sleep efficiency of insomnia patients. Then, while ensuring sleep efficiency, the bed time of insomnia patients is gradually increased to improve the insomnia of insomnia patients. It can be seen that in the diagnosis and treatment of insomnia problems, in order to analyze the sleep quality of insomnia patients, sleep efficiency is usually used as a reference indicator. Sleep efficiency is the ratio of the actual total sleep time of insomnia patients to the total bed time. Among them, the total bed time is the difference between the time when insomnia patients get out of bed and the time when they go to bed.

Usually, the total time in bed can be obtained by manually recording the time of getting out of bed and the time of going to bed. Specifically, after the user finishes sleeping every day, he manually records his own time of going to bed and the time of getting out of bed, so as to further determine the total time in bed based on the time of going to bed and the time of getting out of bed. However, since the user needs to record after each sleep, the time of getting out of bed and the time of going to bed cannot be obtained in time, which will affect the timeliness of insomnia detection and treatment. In addition, the manual recording method will have recording errors and memory biases, resulting in low accuracy of the recorded time of going to bed and the time of getting out of bed.

In the related art, the total time a user spends in bed can also be determined by electronic devices. For example, the total time a user spends in bed can be determined based on the time the electronic device is used. If a user uses an electronic device (such as a mobile phone) before and after falling asleep, then when the user uses the electronic device, it is determined that the user is not in bed, otherwise it is determined that the user is in bed. The sub-device usage time is essentially not the difference between the user's actual bedtime and bedtime, and cannot truly reflect the user's actual bedtime. Therefore, the accuracy of determining the user's total bedtime based on the electronic device usage time is low.

For another example, the user's total bed time can also be determined through smart home (such as smart mattress). Specifically, the smart mattress can detect the user's bed-going and bed-getting actions based on its own force changes. Exemplarily, if the smart mattress detects that the force at a time point becomes larger and meets the preset conditions, it is determined that the user has a bed-going action at that time point, and this time point is the bed-going time point. If the smart mattress detects that the force at a time point becomes smaller and meets the preset conditions, it is determined that the user has a bed-getting action at that time point, and this time point is the bed-getting time point. Then the smart mattress can obtain the total bed time based on the bed-getting time point and the bed-getting time point.

For another example, the total time a user spends in bed can be determined by image recognition using devices such as cameras and radars. Specifically, devices such as cameras and radars can obtain the user's motion information (such as the user's motion image), detect the user's actions of getting into bed and getting out of bed, and then determine the time points of getting out of bed and going to bed to obtain the total time spent in bed.

However, the above-mentioned smart mattresses, cameras, radars and other equipment are expensive and not widely available. Moreover, in multi-user application scenarios, it is impossible to accurately determine the time for each user to get out of bed and the time for going to bed, resulting in low accuracy in the total bed time determined for each user.

For another example, the user's posture can be detected by an acceleration sensor to determine the user's total bed time. Specifically, by acquiring the acceleration data of the acceleration sensor worn on the user's arm or chest, the user's postures such as lying, standing, sitting, and walking are detected, and the user's bed-going and bed-out actions are identified in combination with the change of posture. However, by detecting the user's posture by an acceleration sensor, only the user's posture change can be determined, such as the user's transition from a lying position to a standing position, or from a standing position to a lying position. It is not possible to determine whether the user is actually lying on the bed to sleep, or lying on the sofa to watch TV in the lying position, so that the user's bed-going and bed-out actions cannot be accurately identified. Moreover, in actual applications, due to different users' wearing and living habits, the postures of different users vary greatly. Therefore, it is difficult to perform posture recognition through the acceleration data of the acceleration sensor, and the accuracy is low.

In summary, in the above-mentioned related technologies, electronic devices cannot accurately and conveniently identify the user's actual actions of getting in and out of bed, and thus cannot accurately determine the time when the user goes to bed and gets out of bed, and further cannot determine the user's accurate bedtime. This may overestimate or underestimate the user's actual sleep efficiency, and cannot accurately monitor the user's sleep and accurately analyze the user's sleep quality.

An embodiment of the present application provides a sleep monitoring method, which can be applied to electronic devices. Using the method provided in this embodiment, the electronic device can determine the motion data of the user using the electronic device based on the acceleration data of the electronic device, so as to identify the user's getting in and out of bed actions, and determine the suspected time points of the user getting in and out of bed. Further, the electronic device can determine the user's bed time and bed-leaving time based on the suspected bed-leaving time points, so as to monitor the user's sleep. In this way, the electronic device can accurately determine the user's bed time and bed-leaving time based on the acceleration data, thereby improving the accuracy of sleep monitoring.

Exemplarily, the electronic devices in the embodiments of the present application may be mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, notebook computers, ultra-mobile personal computers (UMPC), netbooks, as well as cellular phones, personal digital assistants (PDA), augmented reality (AR) devices, virtual reality (VR) devices, artificial intelligence (AI) devices, wearable devices, and wearable devices include but are not limited to smart watches, smart bracelets, smart anklets, wireless headphones, smart glasses, smart helmets, etc. The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.

The following description will be given by taking the electronic device 100 as a wearable device as an example.

For example, Fig. 1 shows a schematic diagram of the structure of an electronic device 100, which can be worn on a user's wrist. The electronic device 100 includes a display screen 101 and a fixing strap 102, wherein the display screen 101 is used to display time and other related content when the user touches and clicks, and the fixing strap 102 is used to fix the electronic device 100 on the user's wrist.

Exemplarily, FIG. 2 shows a schematic diagram of a hardware structure of the electronic device 100 .

The electronic device 100 may include a processor 110, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a sensor module 180, a button 190, a motor 191, an indicator 192, and a display screen 194. The sensor module 180 may include a gyroscope sensor 180A, an acceleration sensor 180B, a touch sensor 180C, an ambient light sensor 180D, and the like.

It is understandable that the structure shown in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In some embodiments, the electronic device 100 may include more or fewer components than shown, or combine some components, or separate some components, or arrange the components differently. The components shown may be implemented in hardware, software, or a combination of software and hardware.

The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and/or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated in one or more processors.

The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

The USB interface 130 is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transmit data between the electronic device 100 and a peripheral device. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices, etc.

The charging management module 140 is used to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from a wired charger through the USB interface 130. In some wireless charging embodiments, the charging management module 140 may receive wireless charging input through a wireless charging coil of the electronic device 100. While the charging management module 140 is charging the battery 142, it may also power the electronic device through the power management module 141.

The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and/or the charging management module 140, and provides power to the processor 110, the internal memory 121, the external memory, the display screen 194, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

The mobile communication module 150 can provide solutions for wireless communications including 2G/3G/4G/5G applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

The wireless communication module 160 can provide wireless communication solutions for the electronic device 100, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and filters it, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and transmit it via the antenna 2. Converted into electromagnetic waves and radiated out.

In some embodiments, the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and/or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and/or a satellite based augmentation system (SBAS).

The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 194 is used to display images, videos, etc. In this embodiment, the display screen 194 can be the display screen 101 shown in FIG. 1. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diodes (QLED), etc. In some embodiments, the electronic device 100 can include 1 or N display screens 194, where N is a positive integer greater than 1.

The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

The electronic device 100 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, and the application processor.

The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110.

The speaker 170A, also called a "speaker", is used to convert an audio electrical signal into a sound signal. The electronic device 100 can listen to music or listen to a hands-free call through the speaker 170A.

The receiver 170B, also called a "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 receives a call or voice message, the voice can be received by placing the receiver 170B close to the human ear.

Microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to microphone 170C to input the sound signal into microphone 170C. The electronic device 100 can be provided with at least one microphone 170C. In other embodiments, the electronic device 100 can be provided with two microphones 170C, which can not only collect sound signals but also realize noise reduction function. In other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify the sound source, realize directional recording function, etc.

The gyro sensor 180A can be used to determine the motion posture of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 around three axes (i.e., the x, y, and z axes) can be determined by the gyro sensor 180A. The gyro sensor 180A can be used for anti-shake shooting. For example, when the shutter is pressed, the gyro sensor 180A detects the angle of the electronic device 100 shaking, calculates the distance that the lens module needs to compensate based on the angle, and allows the lens to offset the shaking of the electronic device 100 through reverse movement, thereby achieving Anti-shake. The gyroscope sensor 180A can also be used for navigation and somatosensory gaming scenarios.

The acceleration sensor 180B can detect the magnitude of the acceleration of the electronic device 100 in all directions (generally three axes). When the electronic device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the electronic device and is applied to applications such as horizontal and vertical screen switching and pedometers.

The ambient light sensor 180D is used to sense the brightness of the ambient light. The electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived brightness of the ambient light. The ambient light sensor 180D can also be used to automatically adjust the white balance when taking pictures. The ambient light sensor 180D can also cooperate with the proximity light sensor 180G to detect whether the electronic device 100 is in a pocket to prevent accidental touches.

The fingerprint sensor 180H is used to collect fingerprints. The electronic device 100 can use the collected fingerprint characteristics to implement fingerprint unlocking, access application locks, fingerprint photography, fingerprint call answering, etc.

The touch sensor 180C is also called a "touch panel". The touch sensor 180C can be set on the display screen 194, and the touch sensor 180C and the display screen 194 form a touch screen, also called a "touch screen". The touch sensor 180C is used to detect touch operations acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194. In other embodiments, the touch sensor 180C can also be set on the surface of the electronic device 100, which is different from the position of the display screen 194.

The key 190 includes a power key, a volume key, etc. The key 190 may be a mechanical key or a touch key. The electronic device 100 may receive key input and generate key signal input related to user settings and function control of the electronic device 100.

Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 194, motor 191 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

The indicator 192 may be an indicator light, which may be used to indicate the charging status, power changes, messages, missed calls, notifications, etc.

In some embodiments, if the electronic device 100 is a mobile phone, the electronic device 100 may also include: an external memory interface, an earphone interface, a camera, and a subscriber identification module (SIM) card interface.

The external memory interface can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface to implement a data storage function. For example, files such as music and videos can be stored in the external memory card.

The headphone jack is used to connect a wired headphone. The headphone jack may be a USB interface 130, or a 3.5 mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

The SIM card interface is used to connect the SIM card. The SIM card can be connected to and separated from the electronic device 100 by inserting it into the SIM card interface or pulling it out from the SIM card interface. The electronic device 100 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface can support Nano SIM card, Micro SIM card, SIM card, etc. Multiple cards can be inserted into the same SIM card interface at the same time. The types of the multiple cards can be the same or different. The SIM card interface can also be compatible with different types of SIM cards. The SIM card interface can also be compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to realize functions such as calls and data communications. In some embodiments, the electronic device 100 uses an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.

The following takes the electronic device as a wearable device as an example, specifically, the wearable device is a smart watch, which is worn on the wrist of the user, and the sleep monitoring of the user is performed by the smart watch as an example to illustrate the sleep monitoring method provided in the embodiment of the present application. The method in the following embodiment can be implemented in an electronic device having the hardware structure shown in Figure 2. Figure 3 is a flow chart of the sleep monitoring method shown in the embodiment of the present application. As shown in Figure 3, the method may include the following S101-S105:

S101. The smart watch obtains acceleration data of the smart watch within a monitoring period.

Specifically, when the user wants to perform sleep monitoring, the sleep monitoring function of the smart watch can be turned on. In response to the turn-on operation, the smart watch starts the sleep monitoring function to monitor the sleep of the user. When the user wants to end the sleep monitoring, the sleep monitoring function of the smart watch can be turned off. In response to the turn-off operation, the smart watch can turn off the sleep monitoring function to end the monitoring of the user's sleep. The time period from when the sleep monitoring function of the smart watch is turned on to when the sleep monitoring function is turned off can be the above-mentioned monitoring time period. Smart watches can obtain acceleration data in real time during the monitoring period to further determine the user's motion data.

In one implementation, the smart watch can obtain acceleration data through the acceleration sensor 180B shown in FIG. 2. The acceleration sensor 180B can detect the magnitude of the acceleration of the smart watch in different directions to determine the user's motion data. For example, if the smart watch needs to detect the user's arm movement, it can obtain the acceleration along the arm direction, the acceleration in the same horizontal plane as the horizontally raised arm and perpendicular to the arm direction, and the acceleration in the same vertical plane as the horizontally raised arm and perpendicular to the arm direction, so as to accurately identify the user's arm movement.

In the embodiment of the present application, the above acceleration data may include accelerations in three axes (or three directions), for example, may include: a first acceleration, a second acceleration, and a third acceleration whose directions are perpendicular to each other.

S102: The smart watch determines the motion data of the user using the smart watch according to the acceleration data.

In the embodiment of the present application, the motion data can be used to characterize the motion of the user using the smart watch, and the motion data can be determined by the smart watch based on the acceleration data. Since the user will generate different accelerations in different directions during the motion, the smart watch can determine the user's motion data based on the acceleration data.

In some embodiments, due to the different motion conditions of the user in bed and out of bed, for example, the user's activity in bed is less than that out of bed, the number of steps of the user will decrease after getting into bed, the number of steps of the user will increase after getting out of bed, and the number of arm swinging movements of the user in bed will be less than the number of arm swinging movements of the user out of bed, etc. Exemplarily, as shown in FIG4, the activity data statistics graph shown in the embodiment of the present application, as can be seen from FIG4, due to the different motion conditions of the user, the activity of the user is different at different times. As shown in FIG5, the step statistics graph shown in the embodiment of the present application, as can be seen from FIG5, due to the different motion conditions of the user, the number of steps of the user is also different at different times. Therefore, in this embodiment, in order for the smart watch to accurately identify the user's getting in and out of bed movements, the motion data may include: at least one of activity data, step number, and arm movements, wherein the activity data is used to characterize the user's motion intensity.

Smart watches can determine activity data, steps, and arm movements based on acceleration data, specifically:

In the case where the motion data includes activity data, in one implementation, the smartwatch can determine the activity data based on accelerations in three directions that are perpendicular to each other. Exemplarily, the acceleration data acquired by the smartwatch includes: a first acceleration, a second acceleration, and a third acceleration in directions that are perpendicular to each other. Then the smartwatch can use the following formula (1) to determine the activity data:

In another implementation, if in actual application, the user's movements in one direction are more significant, the acceleration in this direction can be used to characterize the activity data. In the application scenario of the embodiment of the present application, the smart watch is worn on the user's wrist. When the user gets in and out of bed, the movement in the direction that is in the same horizontal plane as the raised arm and perpendicular to the arm is more significant. Therefore, the smart watch can also determine the activity data based on the acceleration in this direction, such as using the acceleration in this direction as the user's activity data.

In the case where the motion data includes the number of steps, the smart watch can determine the number of steps based on the periodic change characteristics of the acceleration data. Specifically, when the user is exercising, an acceleration is generated in three directions in space (for example, along the forward direction of the user's movement, in the horizontal plane perpendicular to the forward direction of the user's movement, and in the vertical plane perpendicular to the forward direction of the user's movement). During the user's movement, the acceleration in at least one of the three directions changes periodically over time. For example, when the user runs forward in a straight line, as the user's feet are alternately lifted and landed, the acceleration perpendicular to the forward direction in the vertical plane will show periodic changes. The periodically changing acceleration changes with time, with the value of the periodically changing acceleration as the vertical axis and time as the horizontal axis, the curve of the periodically changing acceleration generally presents a sine curve. During the user's movement, each step will correspond to a peak in a sine curve, and a peak can be recorded as one step. In this way, the smart watch can determine the number of steps based on the acceleration data.

In the case where the motion data includes arm movements, the acceleration data acquired by the smartwatch may include accelerations in multiple directions. The smartwatch may determine the dominant feature in each direction based on the accelerations in multiple directions to determine the user's arm movements, wherein the dominant feature is used to characterize the intensity of the user's movements. If the user's arm movement in one direction is more significant, the intensity of the movement in that direction is greater, i.e., the dominant feature is greater.

Since the original acceleration in each direction includes the acceleration caused by gravity and the acceleration generated by muscle force, in order for the smart watch to accurately judge the user's arm movement, the smart watch needs to remove the acceleration generated by muscle force from the acceleration in each direction and retain the acceleration caused by gravity. For example, the smart watch can use bandpass filtering The acceleration generated by muscle force in the original acceleration is extracted by the method, and the remaining acceleration in the original acceleration is the acceleration caused by gravity. The waveform shown in Figure 6(a) is the original acceleration waveform in the first direction. The waveform shown in Figure 6(b) is the acceleration waveform in the first direction generated by muscle force extracted by bandpass filtering. The waveform shown in Figure 6(c) is the acceleration waveform in the first direction caused by gravity. The smart watch can determine the acceleration corresponding to the waveform shown in Figure 6(c) as the acceleration caused by gravity in the first direction.

In one implementation, the smartwatch can determine the dominant feature of each direction based on the acceleration caused by gravity in different directions. Taking the calculation of the dominant feature of the first direction as an example, the dominant feature of the first direction can be calculated by the following formula (2):

Wherein, B is the dominant feature of the first direction, a _g,1 is the acceleration caused by gravity in the first direction, a _g,2 is the acceleration caused by gravity in the second direction, and a _g,3 is the acceleration caused by gravity in the third direction. The first direction, the second direction and the third direction are perpendicular to each other.

Furthermore, the smartwatch determines the user's arm movement according to the dominant features in each direction. The direction with the larger dominant feature is the more significant the user's arm movement in that direction. For example, if the dominant feature along the first direction is larger, it can be determined that the user's arm has significant movement along the first direction. In this way, the smartwatch accurately determines the user's arm movement according to the dominant features in different directions.

S103. The smart watch determines at least two first time points according to the motion data, where the first time points are suspected time points for the user to get in and out of bed.

In the embodiment of the present application, since the motion data is used to characterize the motion of the user using the smart watch, the smart watch can identify the user's getting in and out of bed actions based on the motion data, thereby determining the user's suspected getting in and out of bed time points. Usually, within a monitoring period, the user has at least one going-in-bed action and one getting-out-of-bed action. Therefore, in order to improve the accuracy of determining the time points of going to bed and getting out of bed, the smart watch can determine at least two first time points (i.e., suspected getting-in-bed time points) based on the motion data, so as to further determine the time points of going to bed and getting out of bed.

In some embodiments, the smart watch can determine the first time point according to the change of motion data during the monitoring period. Specifically, in this embodiment, the monitoring period includes multiple monitoring time points, and the time intervals between two adjacent monitoring time points may be the same or different, and this application does not make specific limitations on this. The following embodiments are explained by taking the monitoring period including multiple monitoring time points with the same time interval as an example, that is, the smart watch obtains the acceleration data of the smart watch once at the same time interval during the monitoring period, for example, every 1 second (s). In this way, the motion data includes motion data of multiple monitoring time points.

The smartwatch determines the change data of the motion data within the preset time before each monitoring time point, and determines the monitoring time point as the first time point if the smartwatch determines that the change data meets the preset conditions.

In one implementation, when the motion data includes activity data, the above-mentioned preset condition includes: within a first preset period before the monitoring time point, the change data of the activity data is greater than a first threshold. The change data of the activity data is one or more of the following: the mean of the activity data, the variance of the activity data, etc. The first threshold can be set according to actual application requirements. The smaller the first threshold, the higher the accuracy of the smart watch in determining the first time point. This application does not specifically limit the first threshold.

In one example, taking the change data of the activity data as the mean value of the activity data as an example, the preset condition may include: within 30 seconds before the monitoring time point, the mean value of the activity data is greater than 1 meter per square second (m/s ² ). Specifically, as shown in FIG7 , the method for the smart watch to determine the first time point according to the activity data in the monitoring period includes the following S201-S203:

S201. The smart watch determines the average value of the activity data within 30 seconds before each monitoring time point in the monitoring period based on the activity data of multiple monitoring time points in the motion data.

S202: The smart watch determines whether the average value of the activity data within 30 seconds before each monitoring time point is greater than 1 m/s ² .

S203: If the smart watch determines that the average value of the activity data within 30 seconds before the monitoring time point is greater than 1 m/s ² , the monitoring time point is determined to be the first time point.

In another example, in order to more realistically reflect the change in activity and improve the accuracy of the smart watch in determining the suspected time point of the user getting in and out of bed, the change data of the activity data can also be the variance of the activity data. The preset condition can include: within 60 seconds before the monitoring time point, the variance of the activity data is greater than 0.5. Specifically, as shown in FIG8 , the method for the smart watch to determine the first time point based on the activity data in the monitoring period includes the following S301-S303:

S301. The smart watch determines the variance of the activity data within 60 seconds before each monitoring time point in the monitoring period based on the activity data of multiple monitoring time points in the motion data.

S302: The smart watch determines whether the variance of the activity data within 60 seconds before each monitoring time point is greater than 0.5.

S303: If the smart watch determines that the variance of the activity data within 60 seconds before the monitoring time point is greater than 0.5, the monitoring time point is determined to be the first time point.

In another example, the smart watch can also determine whether the corresponding monitoring time point is the first time point through the above S201-S203 and the above S301-S303 according to the mean of the activity data and the variance of the activity data, respectively. For example, the smart watch can determine that the monitoring time point is the first time point when the mean of the activity data and the variance of the activity data at the monitoring time point simultaneously meet the corresponding preset conditions (such as being greater than the corresponding threshold). In this way, the accuracy of the smart watch in determining the suspected time point of getting in and out of bed of the user based on the activity data can be further improved.

In one implementation, when the motion data includes the number of steps, the above-mentioned preset conditions include: within a second preset period before the monitoring time point, the change data of the number of steps is greater than a second threshold. The change data of the number of steps includes one or more of the following: cumulative number of steps, mean number of steps, variance of number of steps, etc. Similar to the setting method of the first threshold, the second threshold can be set according to actual application requirements. The smaller the second threshold, the higher the accuracy of the smart watch in determining the first time point. This application does not specifically limit the second threshold.

In one example, taking the cumulative number of steps as the change data of the activity data, the preset condition may include: the cumulative number of steps is greater than 100 steps within 15 seconds before the monitoring time point. Specifically, as shown in FIG9 , the method for the smart watch to determine the first time point according to the number of steps in the monitoring period includes the following S401-S403:

S401. The smart watch determines the cumulative number of steps within 15 seconds before each monitoring time point in the monitoring period according to the number of steps at multiple monitoring time points in the motion data.

S402: The smart watch determines whether the cumulative number of steps within 15 seconds before each monitoring time point is greater than 100 steps.

S403: If the smart watch determines that the cumulative number of steps within 15 seconds before the monitoring time point is greater than 100 steps, the monitoring time point is determined to be the first time point.

It should be noted that the smart watch can also determine whether the corresponding monitoring time point is the first time point based on one or more data such as the cumulative number of steps, the mean of the number of steps, and the variance of the number of steps. For example, the smart watch can determine that the monitoring time point is the first time point when the cumulative number of steps, the mean of the number of steps, and the variance of the number of steps at the monitoring time point simultaneously meet the corresponding preset conditions (such as being greater than the corresponding threshold). In this way, the accuracy of the smart watch in determining the suspected time point of getting in and out of bed based on the number of steps can be further improved.

In one implementation, when the motion data includes arm movements, the above-mentioned preset conditions include: within a third preset period before the monitoring time point, the number of times that the arm movement satisfies the preset movement is greater than a third threshold. Wherein, the preset movement includes one or more of the following: arm swinging movement and arm vertical downward movement. Since, usually, the arm swinging movement of the user in bed is less than the arm swinging movement of the user under the bed, and there is usually an arm vertical downward movement when the user goes to bed. Therefore, the smart watch can identify the arm swinging movement and/or the arm vertical downward movement to determine whether there is a suspected movement of getting in and out of bed, thereby determining the suspected time point of the user's getting in and out of bed. It is understandable that in some application scenarios, different preset movements can also be set in combination with the user's habitual movements of getting in and out of bed, such as the movement of raising the arm at a preset angle. The third threshold can be set according to the user's habit of arm swinging movement and arm vertical downward movement. If the user's daily arm swinging movement and arm vertical downward movement are less, a smaller third threshold can be set to improve the accuracy of the smart watch in identifying the arm swinging movement and arm vertical downward movement. The third threshold is not specifically limited in this application.

In an example, taking the preset action including the arm swinging action and the arm vertical downward action as an example, the preset condition may include: within 30 seconds before the monitoring time point, the arm action satisfies the arm swinging action and the arm vertical downward action for more than 10 times. Specifically, as shown in FIG10 , the method for the smart watch to determine the first time point according to the arm action in the monitoring period includes the following S501-S503:

S501. The smart watch determines the number of times the arm movements satisfy the arm swinging movement and the arm vertical downward movement within 30 seconds before each monitoring time point in the monitoring period according to the arm movements at multiple monitoring time points in the motion data.

S502: The smart watch determines whether the number of times within 30 seconds before each monitoring time point is greater than 10 times.

S503: If the smart watch determines that the number of times within 30 seconds before the monitoring time point is greater than 10 times, the monitoring time point is determined to be the first time point.

In some embodiments, because the user's arms move in the same horizontal plane as the raised arms and perpendicular to the arms when they are swinging, there will be a greater acceleration in this direction, and the advantageous characteristics in this direction will also be greater. Therefore, in the above S501, the smart watch can determine whether the user's arm movement satisfies the arm swinging movement by calculating the dominant features along the same horizontal plane as the raised arm and perpendicular to the arm direction.

Specifically, the smart watch can determine the first advantage feature of the monitoring time point by using the following formula (3):

Among them, _B1 is the first dominant feature, _ag,X is the acceleration caused by gravity along the arm direction, _ag,Y is the acceleration caused by gravity in the same horizontal plane as the raised arm and perpendicular to the arm direction, and _ag,Z is the acceleration caused by gravity in the same vertical plane as the raised arm and perpendicular to the arm direction.

If before the monitoring time point, the frequency of the first advantage feature being greater than the fourth threshold meets the first preset frequency, the smart watch determines that the arm movement at the monitoring time point meets the arm swinging movement. Among them, the setting method of the fourth threshold and the first preset frequency can refer to the setting method of the first threshold mentioned above, which will not be repeated here. Exemplarily, if before the monitoring time point, the frequency of the first advantage feature being greater than 1.47 meets 2 times/5s, the smart watch determines that the arm movement at the monitoring time point meets the arm swinging movement.

In some embodiments, since the user's arm will have a larger acceleration in the direction along the arm when performing a vertical downward movement, the dominant feature in this direction is also greater. Therefore, in the above S501, the smart watch can determine whether the user's arm movement satisfies the arm vertical downward movement by calculating the dominant feature along the arm direction.

Specifically, the smart watch can determine the second advantage feature of the monitoring time point by using the following formula (4):

Among them, _B2 is the second dominant feature, _ag,X is the acceleration caused by gravity along the arm direction, _ag,Y is the acceleration caused by gravity in the same horizontal plane as the raised arm and perpendicular to the arm direction, and _ag,Z is the acceleration caused by gravity in the same vertical plane as the raised arm and perpendicular to the arm direction.

If before the monitoring time point, the frequency of the second advantage feature being greater than the fifth threshold meets the second preset frequency, the smart watch determines that the arm movement at the monitoring time point meets the arm vertical downward movement. Among them, the setting method of the fifth threshold and the second preset frequency can refer to the setting method of the first threshold mentioned above, which will not be repeated here. Exemplarily, if before the monitoring time point, the frequency of the second advantage feature being greater than 1.49 meets 2 times/5s, the smart watch determines that the arm movement at the monitoring time point meets the arm vertical downward movement.

In some embodiments, in order to further improve the accuracy of the smart watch in determining the suspected time point of the user getting in and out of bed based on the motion data, the motion data may include at least two of: activity data, number of steps, and arm movements. The smart watch comprehensively determines the suspected time point of the user getting in and out of bed based on the corresponding S201-S203, S301-S303, S401-S403, and S501-S503, that is, determines the above-mentioned first time. For example, the motion data includes: activity data, number of steps, and arm movements. The smart watch can determine whether the activity change data, the number of steps change data, and the number of arm movements that meet the preset actions at the monitoring time point all meet the corresponding preset conditions through the above S201-S203, S301-S303, S401-S403, and S501-S503, respectively. If they all meet the corresponding preset conditions, the monitoring time point is determined to be the first time point.

In addition, it should be noted that the examples for each threshold (such as the first threshold, the second threshold and the third threshold) and each preset time period (such as the first preset time period, the second preset time period and the third preset time period) in the above examples are merely examples. In this embodiment, the values of each threshold and each preset time period are not limited to the above examples, and their actual values can be pre-set according to actual needs.

In some embodiments, the smart watch can determine the first time point through a preset detection model based on the motion data in the monitoring period. Specifically, in the present embodiment, the monitoring period includes multiple monitoring time points. The motion data includes motion data of multiple monitoring time points. The smart watch can input the motion data of multiple monitoring time points into a preset detection model to obtain at least two first time points. The detection model can determine whether the change data of the motion data at the monitoring time point meets the preset conditions. If the preset conditions are met, the monitoring time point is output as the result of the first time point, wherein the change data of the motion data and the preset conditions, please refer to the relevant description above, which will not be repeated here.

In some embodiments, the smart watch can also obtain a sample set, which includes multiple time points for getting in and out of bed and change data of motion data at each time point for getting in and out of bed. The smart watch uses the sample set to train an initial model of the detection model to construct the detection model.

Exemplarily, the smartwatch uses the sample set to train the initial model of the detection model through a random forest training method. The detection model can be composed of multiple decision trees, for example, 100 decision trees. The change data of the motion data includes: the mean of the activity data, the variance of the activity data, the cumulative number of steps, and the arm movement satisfying the arm swing movement. Taking the number of times the arm moves vertically downward as an example, the preset conditions include: (1) within 30 seconds before the monitoring time point, the mean of the activity data is greater than 1m/ ^s2 , (2) within 60 seconds before the monitoring time point, the variance of the activity data is greater than 0.5, (3) within 15 seconds before the monitoring time point, the cumulative number of steps is greater than 100 steps, (4) within 30 seconds before the monitoring time point, the number of times the arm movement satisfies the arm swinging movement and the arm vertical downward movement is greater than 10 times. Then each decision tree in the detection model is a 5-layer binary tree, and the branch nodes and root nodes of each decision tree are the above-mentioned change data. At the branch nodes and root nodes, it is judged whether the change data meets the corresponding preset conditions. If the change data does not meet the preset conditions, it enters the left subtree at the next layer, otherwise it enters the right subtree. The final leaf node value on each path in the decision tree is the probability value that the monitoring time point is the first time point. Each decision tree in the detection model will obtain a probability value that the monitoring time point is the first time point. Finally, multiple decision trees in the detection model determine whether the monitoring time point is the first time point by voting (such as whether the number of statistical probability values greater than the probability threshold meets the threshold condition). If the monitoring time point is the first time point, the monitoring time point is output.

In some embodiments, Figure 11 is a schematic diagram of an application scenario of the sleep monitoring method shown in an embodiment of the present application. As shown in Figure 11, after the smart watch determines at least two first time points, the smart watch can also respond to a viewing operation initiated by the user and display the determined at least two first time points (suspected time points for getting in and out of bed) to the user through a display screen, so that the user can check the first time points in time, thereby improving the user's experience.

In some embodiments, the smart watch can also display the activity data and/or number of steps corresponding to the first time point to the user through the display screen. Specifically, referring to FIG. 11 , the user can select one of the first time points, such as “22:08”, and send a viewing operation of viewing the activity data and/or number of steps to the smart watch by clicking the “22:08” area. The smart watch receives and responds to the user’s viewing operation, and displays the activity data and/or number of steps at “22:08” through the display screen. This makes it easier for the user to obtain the activity data, number of steps and other sports data at the first time point, further improving the user’s experience.

S104: The smart watch determines the user's bedtime and bedtime based on at least two first time points.

In the embodiment of the present application, in the above S103, at least two first times determined by the smart watch are suspected to be the time for going to bed and getting out of bed, and it is necessary to further determine the accurate time for the user to go to bed and get out of bed based on the at least two first time points.

In some embodiments, as shown in FIG12 , the smartwatch can determine the user's bedtime and bedtime based on at least two first time points in combination with the user's sleep time and wake-up time. Specifically, the following steps S601-S602 are included:

S601. The smart watch obtains the user's sleeping time and waking time, wherein the sleeping time is the time when the user enters the sleeping state from the awake state, and the waking time is the time when the user enters the awake state from the sleeping state.

Because the user's physiological characteristics are different when they are asleep and awake. For example, when they are asleep, their pulse rate will slow down, their breathing rate will slow down, and their blood oxygen level will decrease. When the user wakes up from sleep, the above physiological characteristics will also change when they are awake. Therefore, by detecting the user's physiological characteristics, it can be determined whether the user is asleep or awake.

For example, a smartwatch can obtain the user's heart rate, blood oxygen and other data through a photoelectric sensor, such as a photoplethysmograph (PPG) sensor. Specifically, the PPG sensor emits a light beam of a certain wavelength to the user's skin (usually green light is used to measure heart rate and red light is used to measure blood oxygen), and then the PPG sensor receives the transmitted or reflected light beam, and processes the periodic light intensity changes caused by blood circulation detected in this process to obtain the user's heart rate data. The PPG sensor can also obtain the user's blood oxygen data. Since the reflectivity of blood with different oxygen content is different, its changes can also be detected by the PPG sensor, and then processed and estimated by an algorithm to obtain blood oxygen data. The smartwatch can monitor the user's blood oxygen, heart rate, heart rate variability (HRV) and other change trends and absolute values based on the heart rate data to determine the user's awake state and sleep state, and further determine the user's sleep time and wake-up time.

S602: The smartwatch determines the first time point before the sleeping time point and with the smallest time difference from the sleeping time point among the at least two first time points as the bedtime point. The smartwatch determines the first time point after the waking up time point and with the smallest time difference from the waking up time point among the at least two first time points as the getting out of bed time.

Since the user usually goes to sleep after going to bed, and gets out of bed after waking up from sleep, the smart watch can determine the first time point closest to the sleeping time as the bedtime, and the first time point closest to the waking time as the getting out of bed time.

FIG13 is a schematic diagram of the principle of a smart watch determining the time to go to bed and the time to get out of bed shown in an embodiment of the present application. As shown in FIG13 , the smart watch determines: first time point a, first time point b, first time point c, first time point d, first time point e, first time point f, first time point g and first time point h, a total of 8 first time points. Among them, the first time point a, the first time point b and the first time point c are before the time point of falling asleep, but the time difference between the first time point c and the time point of falling asleep is the smallest. Therefore, the first time point c is determined as the time point of going to bed. The first time point f, the first time point g and the first time point h are before the time point of waking up, but the time difference between the first time point f and the time point of waking up is the smallest. Therefore, the first time point f is determined as the time point of getting out of bed.

In some embodiments, the smart watch can also determine the user's bedtime and bedtime based on at least two first time points and the user's selection operation. Specifically, as shown in FIG14 , the smart watch can determine the user's bedtime and bedtime based on at least two first time points through the following S701-S703:

S701. The smart watch displays at least two first time points.

In one implementation, as shown in FIG. 15 , the smart watch may display at least two first time points through the display screen 101 , and multiple first time points (i.e., suspected time points for getting in and out of bed) may be displayed on the display screen 101 for the user to view the first time points.

In another implementation, as shown in FIG16 , the smart watch can also send at least two first time points to a fourth electronic device, which can be a large-screen electronic device such as a mobile phone or a tablet computer, and the fourth electronic device (mobile phone) displays at least two first time points through a display screen. In this way, when the smart watch determines more first time points in S103, more first time points can be displayed to the user at one time, so that the user can quickly browse the first time points, thereby improving the user's experience.

S702: The smart watch receives a selection operation from the user.

In some embodiments, the user selects a second time point and a third time point among the at least two first time points according to the displayed at least two first time points, wherein the second time point is a time point for going to bed determined by the user among the at least two first time points, and the third time point is a time point for getting out of bed determined by the user among the at least two first time points.

Exemplarily, as shown in Figures 15 and 16, the user can select the time point by clicking the display area of the first time point displayed, or click the selection control corresponding to the first time point to select the time point. Afterwards, the user can confirm the operation on the corresponding time point by clicking the confirmation control. It is understandable that the selection control and the confirmation control are exemplary names. The embodiments of the present application do not limit the naming of the selection control and the confirmation control, and can also be replaced with other names with the same or similar functions.

S703: The smart watch determines the second time point and the third time point as the bedtime and the bedtime, respectively, according to the selection operation.

In some embodiments, in order to facilitate the user to make a quick selection, the smart watch can improve the efficiency of determining the time of going to bed and the time of getting out of bed. The smart watch can also remove some misjudged first time points according to the time of falling asleep and the time of waking up from bed, for example, remove the first time point between the time of falling asleep and the time of waking up from bed. In this way, the interference to the user can be reduced, allowing the user to quickly select the time of going to bed and getting out of bed. Specifically, as shown in Figure 17, the smart watch can also determine the time of going to bed and the time of getting out of bed according to at least two first times through the following S801-S804:

S801. The smart watch obtains the user's sleeping time and waking time.

Among them, the sleeping time point and the waking time point are used to remove the misjudged first time point.

S802: The smart watch displays at least two first time points: a first time point before the time of falling asleep and a first time point after the time of waking up.

In one implementation, S802 is similar to the implementation described in S701 above. The smart watch can send the first time point before the time of falling asleep and the first time point after the time of waking up to a fourth electronic device, and the fourth electronic device displays at least two first time points through a display screen, and can also be displayed on the smart watch, which is not repeated here.

S803: The smart watch receives a selection operation by the user.

In some embodiments, the user initiates a selection operation of a second time point and a third time point among the at least two first time points displayed to the smartwatch, wherein the second time point is a time point for going to bed determined by the user among the at least two first time points, and the third time point is a time point for getting out of bed determined by the user among the at least two first time points.

S804: The smart watch determines the second time point and the third time point as the bedtime and the bedtime, respectively, according to the selection operation.

In this way, the smart watch can be implemented through the above S701-S703 and S801-S804 to determine the user's bedtime and bedtime according to at least two first time points and the user's operation.

In some multi-user application scenarios, if there are multiple users getting in and out of bed on a bed, the existing related technologies cannot accurately determine the time when each user goes in and out of bed. For example, the time when a user goes in and out of bed is determined by a smart mattress. The smart mattress can determine the existence of the action of getting in and out of bed based on its force conditions, but it cannot determine which user among the multiple users has the action of getting in and out of bed, resulting in the inability to accurately obtain the time when each user goes in and out of bed. Going to bed and getting out of bed time.

In order to solve the above problems, in some embodiments, the second electronic device (such as a smart mattress) can send the suspected bedtime and suspected bedtime of multiple users (multiple) to the smart watch. The smart watch can determine whether there is a first time point close to the suspected bedtime and suspected bedtime based on at least two first time points. If there is no close first time point, it means that the suspected bedtime and suspected bedtime sent by the second electronic device do not belong to the user using the smart watch, but may belong to other users. If there is a close first time point, it means that the suspected bedtime and suspected bedtime sent by the second electronic device belong to the user using the smart watch. Further, the smart watch can determine the user's bedtime and bedtime based on at least two first time points and the suspected bedtime and suspected bedtime of the second electronic device.

Specifically, as shown in FIG. 18 , in some implementations, the method for the smart watch to determine the user's bedtime and bedtime based on at least two first time points includes:

S901. The smart watch receives a suspected bedtime and a suspected bedtime from a second electronic device.

S902. If there is a first time point among at least two first time points whose time difference with the suspected bedtime point is less than the sixth threshold, the smart watch determines the suspected bedtime point as the bedtime point; if there is a first time point among at least two first time points whose time difference with the suspected getting out of bed time is less than the seventh threshold, the smart watch determines the suspected getting out of bed time as the getting out of bed time.

The sixth threshold and the seventh threshold may be the same or different. The sixth threshold and the seventh threshold may be set according to actual application requirements. The smaller the sixth threshold and the seventh threshold, the higher the accuracy of the smart watch in determining the time of going to bed and the time of getting out of bed. This application does not specifically limit the sixth threshold and the seventh threshold.

In another implementation, the method for a smartwatch to determine the user's bedtime and bed-out time based on at least two first time points includes: the smartwatch receives a suspected bedtime and bed-out time from a second electronic device. If there is a first time point among the at least two first time points whose time difference with the suspected bedtime is less than a sixth threshold, the smartwatch determines the first time point as the bedtime; if there is a first time point among the at least two first time points whose time difference with the suspected bed-out time is less than a seventh threshold, the smartwatch determines the first time point as the bed-out time.

In another implementation, after the smartwatch determines that there is a first time point whose time difference with the suspected bedtime is less than the sixth threshold value among at least two first time points, and there is a first time point whose time difference with the suspected bedtime is less than the seventh threshold value among at least two first time points, the following may be displayed to the user: the suspected bedtime, the suspected bedtime, the first time point whose time difference with the suspected bedtime is less than the sixth threshold value, and the first time point whose time difference with the suspected bedtime is less than the seventh threshold value. The smartwatch receives the user's selection operation of the bedtime and bedtime selected for the above-displayed time points. In response to the selection operation, the smartwatch determines the user's bedtime and bedtime.

In some embodiments, Figure 19 is a second schematic diagram of an application scenario of the sleep monitoring method shown in an embodiment of the present application. As shown in Figure 19, after the smart watch determines the time to go to bed and the time to get out of bed, the smart watch can also respond to the user's viewing operation and display the determined time to go to bed and the time to get out of bed to the user through the display screen, so that the user can check the time to go to bed and the time to get out of bed in time, thereby improving the user's experience.

S105. The smart watch monitors the user's sleep according to the time when the user goes to bed and when the user gets out of bed.

Specifically, the smart watch can determine the user's sleep data such as bed time, sleep latency time, sleep efficiency, etc. according to the time the user goes to bed and gets out of bed, and monitor the user's sleep based on the sleep data to analyze the user's sleep quality.

In some embodiments, the smartwatch can determine the sleep latency and bed time according to the time of going to bed and getting out of bed. Among them, the sleep latency is the time between the user going to bed and entering the sleep state, and the sleep latency can be obtained by calculating the difference between the time of going to bed and the time of falling asleep. The bed time is the time between the user going to bed and getting out of bed, and the bed time can be obtained by calculating the difference between the time of going to bed and the time of getting out of bed. The smartwatch can analyze the user's sleep according to the sleep latency and bed time, and display the user's sleep analysis results. Exemplarily, as shown in Figure 20, the smartwatch can display the user's sleep efficiency, bed time and sleep latency through the display screen, so that the user can intuitively understand their sleep situation.

In some embodiments, the smartwatch can combine the sleep parameters with the bedtime and the bedtime to obtain the user's sleep structure diagram. As shown in FIG21 , the smartwatch can display the user's sleep structure diagram through a display screen. The sleep structure diagram can intuitively reflect the user's sleep quality during the monitoring period, and may include data such as the user's bedtime and bedtime.

In some embodiments, the smartwatch can determine whether the user has stayed in bed too long before going to bed that day based on the sleep latency duration. And send a prompt to the user. As shown in FIG22, it specifically includes the following S1001-S1003:

S1001. The smart watch determines the sleep latency duration according to the bedtime and sleep onset time.

S1002. The smart watch determines whether the sleep latency duration is greater than a tenth threshold value. The tenth threshold value is a sleep latency threshold value. The tenth threshold value can be set according to actual application conditions, for example, can be set to 30 minutes (min).

S1003: If the sleep latency is greater than the tenth threshold, the smartwatch may display a second prompt message on the display screen, the second prompt message being used to remind the user that the user has been in bed for too long. In order to enable the user to understand the sleep condition in more detail, the sleep latency and bed rest time of the user are displayed while displaying the second prompt message.

In one implementation, the user can clearly and completely browse the sleep latency, bed time and second prompt information to improve the user experience. The smart watch can also send the sleep latency, bed time and second prompt information to the fourth electronic device. The fourth electronic device can be a large-screen electronic device such as a mobile phone or a tablet computer, and the fourth electronic device displays the sleep latency, bed time and second prompt information through the display screen. Taking the fourth electronic device as a mobile phone as an example, as shown in Figure 23, the display interface of the mobile phone display screen displays the sleep latency, bed time and second prompt information. The second prompt information may include: It is detected that you have been in bed for too long, and a long time in bed may be one of the reasons affecting sleep quality. The second prompt information may also include: avoid staying in bed for too long. Staying in bed for too long will weaken the direct connection between the bed and sleep, making it difficult to fall asleep and affecting sleep quality. It is recommended to leave the bed and go to bed when you feel sleepy.

In some embodiments, the smartwatch can also analyze the user's sleep within a certain period (e.g., 30 days) according to the user's sleep latency within the period, and generate a sleep analysis result for the period. As shown in FIG. 24 , it specifically includes the following S1101-S1103:

S1101. The smart watch determines the number of days in a preset cycle in which the sleep latency duration is greater than a tenth threshold.

S1102: The smartwatch determines whether the number of days in which the sleep latency duration is greater than the tenth threshold is greater than the day threshold, where the day threshold may be, for example, 20 days. The day threshold may be set according to actual needs, and this application does not make any specific limitation on this.

S1103. If the smart watch determines that the number of days when the sleep latency duration is greater than the tenth threshold is greater than the day threshold, a third prompt message is displayed, where the third prompt message is used to display factors causing the sleep latency duration to be greater than the tenth threshold, and/or to display sleep improvement suggestions and sleep improvement tasks.

Exemplarily, factors that cause the sleep latency duration to be greater than the tenth threshold may include one or more of the following: strenuous exercise before bedtime, long naps during the day, naps within 6 hours before bedtime, playing with mobile phones before bedtime, lying in bed for too long, and environmental noise. Among them, the smart watch can determine whether the user has strenuous exercise before bedtime based on the amount of activity, and the smart watch can determine whether the user has problems such as long naps during the daytime, naps within 6 hours before bedtime, and lying in bed for too long based on the time of going to bed, getting out of bed, falling asleep, and waking up. The smart watch can determine whether the user plays with the mobile phone before bedtime based on the time the user uses the mobile phone. The smart watch determines whether there is environmental noise by detecting the decibel of the ambient sound. For example, sleep improvement suggestions include one or more of the following: regular user wake-up time, restricting user naps, etc. Sleep improvement includes one or more of the following: relieving stress through mindfulness breathing, playing sleep-aiding music, etc.

In one implementation, the user can browse the third prompt information clearly and completely, thereby improving the user's experience. The smart watch can also send the third prompt information to a fourth electronic device, which can be a large-screen electronic device such as a mobile phone or a tablet computer, and the fourth electronic device displays the third prompt information through a display screen. Exemplarily, taking the fourth electronic device as a mobile phone as an example, as shown in FIG25, the third prompt information is displayed in the display interface of the mobile phone display screen, and the third prompt information includes factors affecting sleep; as shown in FIG26, the third prompt information is displayed in the display interface of the mobile phone display screen, and the third prompt information includes improvement suggestions. It can be understood that the display content in FIG25 and FIG26 is only an exemplary description, and the specific content of the third prompt information can be set according to actual needs. The display content in FIG25 and FIG26 can be integrated in the same page display interface and displayed to the user at the same time. It can also be divided into multiple pages of display interfaces and displayed to the user in pages, and this application does not make specific limitations on this.

In some embodiments, after determining the first time point, the smart watch can also determine whether the user has entered a sleeping state. If the user has not entered a sleeping state, the user is prompted whether to turn on the sleeping mode. Specifically, as shown in FIG. 27 , in S103, in the process of the smart watch determining the first time point according to the motion data, after the smart watch determines a first time point, it can also include S1201-S1205:

S1201. The smart watch determines the accumulated activity data after the first time point based on the acceleration data.

S1202. The smart watch determines whether the time during which the accumulated activity data is less than an eighth threshold value satisfies a preset time, so as to determine whether the user remains in bed.

S1203. If the time during which the accumulated activity data is less than the eighth threshold value satisfies the preset time, the smart watch obtains sleeping parameters, which are used to characterize the user's sleeping condition. The sleeping parameters may include, for example, heart rate data, blood oxygen data, etc.

S1204: The smart watch determines whether the sleeping parameters meet a ninth threshold.

S1205. If the sleeping parameter does not meet the ninth threshold, it is determined that the user has not entered the sleep state. The smart watch can display a first prompt message through the display screen to determine whether the user has turned on the sleep mode. Exemplarily, as shown in FIG28, the display screen of the smart watch displays a first prompt message, and the content of the first prompt message includes "whether to enter the sleep mode". The content of the first prompt message is an exemplary description, and the specific content of the first prompt message can be set according to actual needs, and this application does not make specific limitations.

When the user wants to turn on the sleep mode, he can click the control for confirmation in the display screen of the smart watch, for example, the "yes" control in Figure 28. The smart watch receives the user's operation on the control and responds to the operation to turn on the sleep mode. It can be understood that the "yes" control is an exemplary name. The embodiment of the present application does not limit the naming of the "yes" control, and it can also be replaced with a name with the same or similar functions such as a confirmation control.

After the smartwatch turns on the sleep mode, the settings of the smartwatch can be adjusted to help the user of the smartwatch quickly fall asleep. For example, the sleep mode may include: the smartwatch turns on the silent mode or the do not disturb mode, the smartwatch reduces the brightness of the display (blue light), the smartwatch plays sleep-inducing music (such as the sound of wind, rain, or gurgling stream), etc.

In some embodiments, in scenarios where a smart watch is used in conjunction with other electronic devices, for example, a smart watch is used in conjunction with a smart home device (such as a smart desk lamp, smart curtains, smart speakers, etc.), in order to enable the user to enter a sleep state more quickly and improve the user's experience, the smart watch can also send instructions to the smart home device to trigger the smart home device to turn on the sleep mode.

Specifically, after receiving the user's confirmation operation to turn on the sleep mode, the smart watch can also respond to the confirmation operation and send a sleep mode turn-on instruction to the third electronic device, and the sleep mode turn-on instruction is used to trigger the third electronic device to turn on the sleep mode. Among them, the third electronic device may include one or more electronic devices. Exemplary, take the joint use of a smart watch with a smart desk lamp, smart curtains and a smart speaker as an example. After the smart watch responds to the confirmation operation sent by the user, it can send a sleep mode turn-on instruction to the smart desk lamp, smart curtains and smart speakers. In response to the sleep mode turn-on instruction, the smart desk lamp can reduce the brightness of the light. In response to the sleep mode turn-on instruction, the smart curtains can close the curtains to block the light outside the window. In response to the sleep mode turn-on instruction, the smart speaker can play sleep-aiding music. In this way, it can help users fall asleep quickly.

In some embodiments, in the above S1201, the smart watch determines the accumulated activity data after the first time point according to the acceleration data, and the smart watch will also determine other first time points according to the activity data. If the smart watch determines a new first time point, S1202 is stopped and S1201 is re-executed to determine the accumulated activity data after the first time point most recently determined by the smart watch. In this way, in S1201, the smart watch keeps determining the accumulated activity data after the most recently determined first time point, which can improve the accuracy of the smart watch in determining whether to send the first prompt information.

In some embodiments, the smartwatch can also recommend a bedtime or a get-out-of-bed time that meets the sleep efficiency for the user based on the planned sleep efficiency and the planned bedtime or get-out-of-bed time input by the user. For example, if the user inputs a planned sleep efficiency of 80% and a planned get-out-of-bed time of 7:30, the smartwatch can calculate the recommended bedtime, as shown in FIG29 , and the smartwatch can display the recommended bedtime as 23:30.

By adopting the technical solution provided in this embodiment, the smart watch can determine the user's motion data based on acceleration data, and the motion data includes at least one of activity data, number of steps, and arm movements. The smart watch can identify the user's getting in and out of bed movements based on the motion data and determine the suspected time points of the user getting in and out of bed. Furthermore, the smart watch determines the user's bed time and bed-leaving time based on the suspected bed-leaving time points. In this way, the smart watch can accurately and quickly determine the user's bed time and bed-leaving time, thereby improving the accuracy of sleep monitoring.

It should be noted that the sleep monitoring method provided in the embodiment of the present application can also be applied to electronic devices other than wearable devices. Taking the electronic device as a mobile phone as an example, when the mobile phone is always held in the user's hand, the execution subject of the above S101-S105 can be replaced with the mobile phone, and the mobile phone can implement the sleep monitoring method provided in the embodiment of the present application through the above S101-S105.

When it is impossible to ensure that the mobile phone is always held in the user's hand, that is, when the acceleration data in the mobile phone cannot truly reflect the user's movement, the mobile phone implements the sleep monitoring method provided in the embodiment of the present application through the above S101-S105. In S101, the mobile phone can obtain acceleration data through other electronic devices. For example, the mobile phone can obtain the acceleration data of the user during the monitoring period through a wearable device worn on the user's wrist (such as a smart watch, smart bracelet, etc.). In addition, in S104, the mobile phone can also obtain the time of falling asleep and the time of waking up from sleep through other electronic devices (such as wearable devices) for determining The user's bedtime and bedtime. The remaining S102, S103 and S105 can be replaced by a mobile phone as the execution subject, so that the mobile phone can monitor the user's sleep.

It is understandable that, in order to realize the above functions, the above electronic device includes hardware structures and/or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

The embodiment of the present application can group the functional modules of the electronic device according to the above method example. For example, each functional module can be grouped according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the grouping of modules in the embodiment of the present application is schematic and is only a logical functional grouping. There may be other grouping methods in actual implementation.

In one embodiment, please refer to FIG30 , which is a schematic diagram of the composition of an electronic device provided in the embodiment of the present application. As shown in FIG30 , the electronic device may include: an acquisition module 201 and a processing module 202 .

The acquisition module 201 is used to acquire acceleration data of the first electronic device within a monitoring period.

The processing module 202 is used to determine the motion data of the user using the first electronic device according to the acceleration data, where the motion data includes at least one of activity data, number of steps and arm movements, and the activity data is used to characterize the user's exercise intensity.

The processing module 202 is further configured to determine at least two first time points according to the motion data, wherein the first time points are suspected time points when the user gets in and out of bed.

The processing module 202 is further configured to determine a bedtime and a bedtime of the user according to the at least two first time points.

The processing module 202 is further configured to monitor the user's sleep according to the time when the user goes to bed and the time when the user gets out of bed.

The present application also provides a sleep monitoring device, which can be applied to the electronic device in the above embodiment. The device may include: a processor, and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the functions or steps performed by the smart watch in the above method embodiment when executing the instructions.

The embodiment of the present application also provides an electronic device, which may include: a display screen, a memory, and one or more processors. The display screen, the memory, and the processor are coupled. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device can execute the various functions or steps performed by the smart watch in the above method embodiment. Of course, the electronic device includes but is not limited to the above display screen, the memory, and one or more processors. For example, the structure of the electronic device can refer to the structure of the electronic device shown in Figure 2.

The embodiment of the present application also provides a chip system, which can be applied to the electronic devices in the aforementioned embodiments. As shown in Figure 31, the chip system includes at least one processor 301 and at least one interface circuit 302. The processor 301 can be the processor in the above-mentioned electronic device. The processor 301 and the interface circuit 302 can be interconnected through a line. The processor 301 can receive and execute computer instructions from the memory of the above-mentioned electronic device through the interface circuit 302. When the computer instructions are executed by the processor 301, the electronic device can execute the various steps executed by the smart watch in the above-mentioned embodiment. Of course, the chip system can also include other discrete devices, which are not specifically limited in the embodiment of the present application.

An embodiment of the present application also provides a computer-readable storage medium for storing computer instructions executed by the above-mentioned electronic device (such as a smart watch).

An embodiment of the present application also provides a computer program product, including computer instructions executed by the above-mentioned electronic device (such as a smart watch).

Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the coupling between the displayed or discussed Or the direct coupling or communication connection may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

A sleep monitoring method, characterized in that the method comprises:

Acquiring acceleration data of the first electronic device during a monitoring period;

determining motion data of a user using the first electronic device according to the acceleration data, the motion data comprising at least one of activity data, number of steps, and arm movements, the activity data being used to characterize the user's exercise intensity;

Determine at least two first time points according to the motion data, where the first time points are suspected time points for the user to get in and out of bed;

Determine a bedtime and a bedtime of the user according to the at least two first time points;

The user's sleep is monitored according to the going to bed time and the getting out of bed time.
The method according to claim 1, characterized in that the monitoring period includes multiple monitoring time points, and the motion data includes motion data of the multiple monitoring time points;

The determining at least two first time points according to the motion data includes:

For each of the multiple monitoring time points, determining change data of the motion data within a preset time before the monitoring time point;

If the change data meets a preset condition, the monitoring time point is determined to be the first time point.
The method according to claim 2, characterized in that

In the case where the motion data includes the activity amount data, the preset condition includes: within a first preset period before the monitoring time point, the change data of the activity amount data is greater than a first threshold;

In the case where the motion data includes the number of steps, the preset condition includes: within a second preset period before the monitoring time point, the change data of the number of steps is greater than a second threshold;

When the motion data includes the arm movement, the preset condition includes: within a third preset time period before the monitoring time point, the number of times the arm movement satisfies the preset movement is greater than a third threshold; the preset movement includes: arm swinging movement and arm vertical downward movement.
The method according to claim 1, characterized in that the monitoring period includes multiple monitoring time points, and the motion data includes motion data of the multiple monitoring time points;

The determining at least two first time points according to the motion data includes:

The motion data of the multiple monitoring time points are input into a preset detection model to obtain the at least two first time points.
The method according to any one of claims 1 to 4, characterized in that the acceleration data comprises: a first acceleration, a second acceleration and a third acceleration whose directions are perpendicular to each other;

In a case where the motion data includes the activity amount data, determining the activity amount data according to the acceleration data includes:

The activity data is determined using the following formula (1):

Wherein, A is the activity data, a1 is the first acceleration, a2 is the second acceleration, and a3 is the third acceleration.
The method according to any one of claims 1 to 4, characterized in that the acceleration data comprises: a first acceleration, a second acceleration and a third acceleration whose directions are perpendicular to each other;

In the case where the motion data includes the activity volume data, the activity volume data is the first acceleration in the acceleration data, and the first acceleration is an acceleration whose direction is in the same horizontal plane as the raised arm and is perpendicular to the direction of the arm.
The method according to claim 3 is characterized in that the arm action satisfies the arm swing action when the frequency at which the first dominant feature of the arm action is greater than a fourth threshold satisfies a first preset frequency, and the first dominant feature is used to characterize the intensity of the action that is in the same horizontal plane as the raised arm and perpendicular to the direction of the arm;

The first advantageous feature is determined by the following formula (2):

Wherein, B1 is the first advantageous feature, ag,X is the acceleration caused by gravity along the arm direction, ag,Y is the acceleration relative to the horizontally raised hand. The arms are in the same horizontal plane and perpendicular to the direction of the arm based on the acceleration caused by gravity, and ag,Z is the acceleration caused by gravity in the same vertical plane as the raised arm and perpendicular to the direction of the arm.
The method according to claim 3 is characterized in that when the frequency at which the second dominant feature of the arm motion is greater than a fifth threshold satisfies a second preset frequency, it is determined that the arm motion satisfies the arm vertical downward motion, and the second dominant feature is used to characterize the motion intensity along the arm direction;

The second advantageous feature is determined by the following formula (3):

Among them, B2 is the second advantageous feature, ag,X is the acceleration caused by gravity along the direction of the arm, ag,Y is the acceleration caused by gravity in the same horizontal plane as the raised arm and perpendicular to the direction of the arm, and ag,Z is the acceleration caused by gravity in the same vertical plane as the raised arm and perpendicular to the direction of the arm.
The method according to any one of claims 1 to 8, characterized in that the method of determining the user's bedtime and bedtime according to the at least two first time points comprises:

Obtaining the user's sleep onset and wake-up time;

The going-to-bed time point and the getting-out-of-bed time point are determined according to the at least two first time points, the falling-to-sleep time point and the waking-up time point.
The method according to claim 9, characterized in that the method of determining the bedtime and the bed-leaving time according to the at least two first time points, the sleep onset time point and the sleep-out time point comprises:

Determine the first time point, among the at least two first time points, which is before the sleeping time point and has the smallest time difference with the sleeping time point as the bedtime point;

The first time point among the at least two first time points, which is after the sleeping time point and has the smallest time difference with the sleeping time point, is determined as the getting out of bed time point.
The method according to any one of claims 1 to 8, characterized in that the method of determining the user's bedtime and bedtime according to the at least two first time points comprises:

receiving a suspected bedtime and a suspected bedtime from a second electronic device;

The bedgoing time point and the getting out of bed time point are determined according to the at least two first time points, the suspected bedgoing time point and the suspected getting out of bed time point.
The method according to claim 11, characterized in that the method of determining the bedgoing time point and the getting out of bed time point according to the at least two first time points, the suspected bedgoing time point and the suspected getting out of bed time point comprises:

If there is a first time point among the at least two first time points whose time difference with the suspected bedtime point is less than a sixth threshold, the suspected bedtime point is determined as the bedtime point;

If there is a first time point among the at least two first time points whose time difference with the suspected getting out of bed time point is less than a seventh threshold, the suspected getting out of bed time point is determined as the getting out of bed time point.
The method according to any one of claims 1 to 8, characterized in that the method of determining the user's bedtime and bedtime according to the at least two first time points comprises:

displaying the at least two first time points;

receiving a user's selection operation on a second time point and a third time point among the at least two first time points;

According to the selection operation, the second time point and the third time point are determined as the bed-going time point and the bed-getting-out time point.
The method according to any one of claims 1 to 8, characterized in that the method further comprises:

Obtaining the user's sleep onset and wake-up time;

Displaying, among the at least two first time points, a first time point before the sleeping time point and a first time point after the waking time point;

receiving a user's selection operation on a second time point and a third time point among the at least two first time points;

According to the selection operation, the second time point and the third time point are determined as the bed-going time point and the bed-getting-out time point.
The method according to any one of claims 1 to 14, characterized in that the method further comprises:

Determining, based on the acceleration data, accumulated activity data after the first time point;

If the time during which the accumulated activity data is less than the eighth threshold value satisfies a preset time, a sleeping parameter is obtained, where the sleeping parameter is used to characterize the sleeping condition of the user;

If the sleeping parameter does not meet the ninth threshold, displaying a first prompt message, wherein the first prompt message is used for the user to confirm whether to turn on the sleep mode;

Receiving a confirmation operation from a user to start the sleep mode;

In response to the confirmation operation, the sleep mode is activated.
The method according to claim 15, characterized in that after receiving the user's confirmation operation of turning on the sleep mode, the method further comprises:

In response to the confirmation operation, a sleep mode activation instruction is sent to the third electronic device, where the sleep mode activation instruction is used to trigger the third electronic device to activate the sleep mode.
The method according to any one of claims 1 to 16, characterized in that the method of monitoring the sleep of the user according to the going to bed time and the getting out of bed time comprises:

Determine the sleep latency duration and bed rest duration according to the bed-going time and the bed-getting time, wherein the sleep latency duration is the difference between the bed-going time and the sleeping time, and the bed rest duration is the difference between the bed-going time and the bed-getting time;

The sleep analysis result of the user is displayed according to the sleep latency duration and the bed rest duration.
The method according to claim 17, characterized in that, when the sleep latency duration is greater than a tenth threshold, the sleep analysis result includes:

The sleep latency duration, the bed rest duration and second prompt information, wherein the second prompt information is used to remind the user that the bed rest time is too long.
The method according to claim 17 or 18, characterized in that, when the number of days during which the sleep latency duration is greater than the tenth threshold is greater than a day threshold, the sleep analysis result includes:

The third prompt information is used to display factors causing the sleep latency duration to be greater than a tenth threshold, and/or to display sleep improvement suggestions and sleep improvement tasks.
An electronic device, characterized in that it comprises: a memory and one or more processors; the memory is coupled to the processor; wherein computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the method as described in any one of claims 1-19.
A computer-readable storage medium, characterized in that it includes computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 19.
A computer program product, characterized in that when the computer program product is run on a computer, the electronic device executes the method according to any one of claims 1 to 19.