A sleep state analysis method for wearable devices and related components

Abstract

The present application relates to the technical field of sleep analysis, and discloses a sleep state analysis method for a wearable device and related components, including: obtaining acceleration-related data collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor, wherein the acceleration-related data includes X-axis, Y-axis, and Z-axis acceleration sequences. Determine the maximum score value among the scores corresponding to the acceleration sequences of each axis within a preset time period. Determine the correlation coefficients between the maximum score value and the environmental variable-related data, as well as the physiological sign-related data, and analyze each correlation coefficient to determine the factors causing changes in the user's sleep state. Thus, based on the maximum score value among the scores corresponding to the acceleration sequences of the wearable device on each axis, analyze the correlation coefficients between the maximum score value and the environmental variable-related data, as well as the physiological sign-related data, to determine the factors causing changes in the user's sleep state, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the technical field of sleep analysis, and in particular to a sleep state analysis method for a wearable device and related components. Background Art

[0002] With the continuous development of smart technology, smart products are widely used in all aspects of people's lives. At present, the functions of wearable devices (such as smart watches and smart bracelets) are becoming more and more abundant. Most wearable devices include sleep monitoring functions, which are mainly used to monitor the user's current sleep state, among which the sleep state includes deep sleep, light sleep and awake state.

[0003] Although wearable devices can use sleep algorithms to analyze the user's current sleep state, they cannot analyze and determine the reason why the user wakes up from deep sleep or light sleep. As users' demand for smart products and quality of life becomes higher and higher, it becomes crucial to analyze and determine the reason why the user wakes up from deep sleep or light sleep.

[0004] It can be seen that analyzing and determining the reasons why a user switches from a deep sleep state or a light sleep state to an awake state and improving the user experience are issues that need to be urgently addressed by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a sleep state analysis method and related components for a wearable device to analyze and determine the factors that cause changes in the user's sleep state, thereby improving the user experience.

[0006] To solve the above technical problems, the present application provides a sleep state analysis method for a wearable device, comprising:

[0007] Acquire acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor; wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence;

[0008] Determine the maximum score among the scores corresponding to the acceleration sequences of each axis within a preset time period;

[0009] respectively determining the correlation coefficient between the maximum score value and the data related to the environmental variables, and the correlation coefficient between the maximum score value and the data related to the physiological signs;

[0010] The factors affecting the user's sleep state are analyzed based on the correlation coefficients.

[0011] Preferably, the environmental variable-related data includes at least environmental noise data and environmental temperature data, and the physiological sign-related data includes at least heart rate data and body temperature data. Then, respectively determining the correlation coefficient between the maximum score value and the environmental variable-related data, and the correlation coefficient between the maximum score value and the physiological sign-related data includes:

[0012] Obtaining an average value of the environmental noise data, an average value of the environmental temperature data, an average value of the heart rate data, and an average value of the body temperature data within the preset time period;

[0013] Determine respectively the correlation coefficient between the maximum score value and the average value of the environmental noise data, the correlation coefficient between the maximum score value and the average value of the environmental temperature data, the correlation coefficient between the maximum score value and the average value of the heart rate data, and the correlation coefficient between the maximum score value and the average value of the body temperature data.

[0014] Preferably, analyzing the factors affecting the change in the user's sleep state according to the correlation coefficients includes:

[0015] Determining whether each of the correlation coefficients is less than a preset threshold;

[0016] If so, it is determined that the factors causing the change in the user's sleep state are unknown;

[0017] If not, the correlation coefficients are sorted to obtain the maximum correlation coefficient to determine the user's sleep state change factor.

[0018] Preferably, determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period includes:

[0019] Dividing the X-axis acceleration sequence, the Y-axis acceleration sequence, and the Z-axis acceleration sequence within the preset time period into a preset number of groups on average;

[0020] Get the average value corresponding to each group of acceleration sequences;

[0021] Determining the weight corresponding to the average value of each group of acceleration sequences according to the preset number of groups and the pre-set weight distribution principle;

[0022] Determine the X-axis acceleration score, Y-axis acceleration score, and Z-axis acceleration score based on the average value corresponding to each group of acceleration sequences and the weight corresponding to the average value of each group of acceleration sequences;

[0023] The X-axis acceleration score, the Y-axis acceleration score, and the Z-axis acceleration score are sorted to obtain the maximum score.

[0024] Preferably, before determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period, the method further includes:

[0025] determining whether the user's sleep state has changed based on the acceleration-related data and the physiological sign-related data;

[0026] If yes, proceed to the step of determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period;

[0027] If not, proceed to the step of obtaining acceleration-related data of the wearable device collected by the acceleration sensor, environmental variable-related data collected by the environmental sensor, and physiological sign-related data collected by the physiological sign sensor.

[0028] Preferably, the sleep state analysis method of the wearable device further includes:

[0029] When it is determined that the user's sleep change factor is heart rate, determining whether the average value of the heart rate data within the preset time period exceeds a preset range;

[0030] If it exceeds the preset range, an alarm signal will be issued.

[0031] Preferably, the sleep state analysis method for a wearable device further includes:

[0032] Determining the user's sleep duration and awake times based on the acceleration-related data and the physiological sign-related data;

[0033] The user's sleep quality is analyzed based on the sleep duration, the number of awake times and sleep state change factors.

[0034] In order to solve the above technical problems, the present application also provides a sleep state analysis device for a wearable device, comprising:

[0035] An acquisition module is configured to acquire acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor; wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence;

[0036] The first determination module is used to determine the maximum score among the scores corresponding to the acceleration sequences of each axis within a preset time period;

[0037] a second determining module, configured to respectively determine a correlation coefficient between the maximum score value and the data related to the environmental variables, and a correlation coefficient between the maximum score value and the data related to the physiological signs;

[0038] The analysis module is used to analyze the factors affecting the change of the user's sleep state according to the correlation coefficients.

[0039] In order to solve the above technical problems, the present application also provides a wearable device, comprising a memory for storing a computer program;

[0040] A processor is configured to implement the steps of the sleep state analysis method for a wearable device when executing the computer program.

[0041] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the sleep state analysis method of the wearable device are implemented.

[0042] The present invention provides a sleep state analysis method for a wearable device, comprising: obtaining acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor, wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence. The maximum score among the scores corresponding to the acceleration sequences of each axis within a preset time period is determined. Furthermore, the correlation coefficient between the maximum score and the environmental variable-related data, as well as the correlation coefficient between the maximum score and the physiological sign-related data, is determined, and factors contributing to changes in the user's sleep state are analyzed based on the correlation coefficients. Thus, the technical solution provided by the present application determines factors contributing to changes in the user's sleep state based on the maximum score among the scores corresponding to the acceleration sequences of the wearable device on each axis, analyzes the correlation coefficients between the maximum score and the environmental variable-related data, and analyzes the correlation coefficients between the maximum score and the physiological sign-related data. This determines the reason for the user's transition from a sleep state to a wakeful state, and helps the user improve their sleep quality and user experience.

[0043] In addition, the present application also provides a sleep state analysis-related component of a wearable device, which corresponds to the above-mentioned sleep state analysis method of the wearable device and has the same effect as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 A flowchart of a sleep state analysis method for a wearable device provided in an embodiment of the present application;

[0046] Figure 2 A flowchart of a sleep state analysis method for a wearable device provided in another embodiment of the present application;

[0047] Figure 3 A structural diagram of a sleep state analysis device for a wearable device provided in an embodiment of the present application;

[0048] Figure 4 A structural diagram of a wearable device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] The core of this application is to provide a sleep state analysis method for a wearable device and related components. The method obtains the acceleration sequence of the wearable device on each axis collected by the acceleration sensor, and determines the maximum score of the acceleration sequence on each axis according to a preset duration. In addition, the correlation coefficient between the maximum score and environmental variable-related factors, as well as the correlation coefficient between the maximum score and physiological sign-related data, is determined respectively, and the factors affecting the user's sleep state change are analyzed based on the correlation coefficients.

[0051] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0052] With the continuous development of smart technology, smart products are widely used in all aspects of people's lives. At present, wearable devices, such as smart watches and smart bracelets, are becoming more and more functional. Most wearable devices include sleep monitoring functions, which are mainly used to monitor the user's current sleep state, among which sleep states include deep sleep, light sleep and awake state.

[0053] Although wearable devices can use sleep algorithms to analyze the user's current sleep state, they cannot analyze and determine the reason why the user wakes up from deep sleep or light sleep. As users' demand for smart products and quality of life becomes higher and higher, it becomes crucial to analyze and determine the reason why the user wakes up from deep sleep or light sleep.

[0054] To determine factors that may cause changes in the sleep state of a user using a wearable device, an embodiment of the present application provides a sleep state analysis method for a wearable device. The method obtains acceleration sequences of the wearable device on the X, Y, and Z axes, as captured by an acceleration sensor, and determines the maximum score among the scores corresponding to the acceleration sequences on each axis. Furthermore, the method determines the correlation coefficient between the maximum score and data related to environmental variables captured by an environmental sensor, as well as the correlation coefficient between data related to physiological signs captured by a physiological sign sensor. The correlation coefficients are then analyzed to determine the factors that may cause changes in the user's sleep state.

[0055] Figure 1 A flowchart of a sleep state analysis method for a wearable device provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0056] S10: Acquire acceleration-related data of the wearable device collected by the acceleration sensor, environmental variable-related data collected by the environmental sensor, and physiological sign-related data collected by the physiological sign sensor; wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence.

[0057] In a specific embodiment, when a user wears a wearable device to sleep, he or she will inevitably turn over and do other actions during sleep. At this time, the wearable device will also change in physical distance, thereby generating acceleration in different directions. The acceleration sensor in the wearable device collects acceleration-related data, wherein the acceleration-related data includes an acceleration sequence in the X-axis direction, an acceleration sequence in the Y-axis direction, and an acceleration sequence in the Z-axis direction. It can be understood that the acceleration sequence refers to a plurality of acceleration values ​​obtained. The acceleration-related data collected by the acceleration sensor is obtained through step S10. In addition, the environmental variable-related data collected by the environmental sensor in the wearable device and the physiological sign-related data collected by the physiological sign sensor are obtained.

[0058] The environmental variable-related data includes at least environmental noise data and environmental temperature data, and the corresponding environmental sensors include noise acquisition sensors and environmental temperature sensors. The physiological sign-related data includes at least heart rate data and body temperature data, and the corresponding physiological sign sensors are heart rate acquisition sensors and body temperature sensors. It should be noted that in addition to the above environmental variable-related data and physiological sign-related data, any other relevant data that may affect changes in the user's sleep state may also be included, and this application does not limit this.

[0059] In addition, it should be noted that acceleration sensors, environmental sensors and physiological sign sensors can collect data in real time and store it in real time, or they can collect data in real time but only store data within a period of time, thereby saving storage space. This application does not limit this.

[0060] S11: Determine the maximum score among the scores corresponding to the acceleration sequences of each axis within a preset time period.

[0061] After acquiring acceleration-related data (i.e., the X-axis acceleration sequence, Y-axis acceleration sequence, and Z-axis acceleration sequence) in step S10, the scores corresponding to the acceleration sequences on each axis are calculated based on the preset duration, and the maximum score is determined from these scores. It is worth noting that, to conserve computing resources and avoid constant score calculations, the maximum score is determined only after a change in the user's sleep state is determined based on the acceleration-related data and vital sign-related data, allowing analysis of the factors contributing to the change. Therefore, the preset duration refers to the time period from the current moment when the user's sleep state changed, forward by the preset duration.

[0062] Among them, when determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time length, the acceleration sequences on each axis within the preset time length are evenly divided into a preset number of groups, and then the average value of each group of acceleration sequences of each axis is obtained, and the average value of each group of acceleration sequences is weighted according to the preset number of groups and a pre-set weight distribution principle. Finally, the score corresponding to each axis is obtained based on the average value and its corresponding weight, and the maximum score is determined therefrom.

[0063] It is understandable that the data closer to the current moment is more likely to affect the user's sleep state, so the preset weight distribution principle is that the closer the group is to the current moment within the preset time period, the greater the weight corresponding to the group.

[0064] S12: Determine the correlation coefficient between the maximum score value and the data related to the environmental variables, and the correlation coefficient between the maximum score value and the data related to the physiological signs.

[0065] After obtaining the maximum score value through step S11, the correlation coefficient between the maximum score value and the environmental variable related data is determined. When the environmental variable related data is environmental noise data and environmental temperature data, the average value of the environmental noise data and the average value of the environmental temperature data within the preset time length are first obtained respectively. Further, the correlation coefficient between the maximum score value and the average value of the environmental noise data, as well as the correlation coefficient between the maximum score value and the average value of the environmental temperature data, are determined respectively.

[0066] Of course, after obtaining the maximum score, the correlation coefficient between the maximum score and the physiological sign related data is determined. When the physiological sign related data is heart rate data and body temperature data, similarly, the average value of the heart rate data and the average value of the body temperature data in the preset time period are first obtained, and then the correlation coefficient between the maximum score and the average value of the heart rate data, as well as the correlation coefficient between the maximum score and the average value of the body temperature data, are determined respectively.

[0067] It should be noted that when environmental variable-related data and physiological sign-related data are analyzed with other factors, the average value within the preset time period is also obtained, and the correlation coefficient between the average value and the maximum score is determined.

[0068] S13: Analyze factors affecting the user's sleep state based on the correlation coefficients.

[0069] After obtaining the correlation coefficients in step S12, the correlation coefficients are analyzed to determine the factors that may have contributed to the user's sleep state change. It is understood that the correlation coefficient ranges from 0 to 1, with the closer the correlation coefficient is to 1, the higher the correlation, and vice versa. Therefore, when analyzing the factors that may have contributed to the user's sleep state change, the correlation coefficients are ranked, with larger correlation coefficients indicating a greater correlation with the user's sleep state change. For example, when the correlation coefficient between the heart rate data and the maximum score is the largest, the factor contributing to the user's sleep state change is determined to be heart rate.

[0070] Of course, there may be cases where the factors causing the change in the user's sleep state are unknown. Therefore, when performing analysis, when all correlation coefficients are less than a preset threshold, it is determined that the cause of the change in the user's sleep state is unknown.

[0071] When it is determined that the factor affecting the user's sleep state is heart rate, in order to promptly detect physical discomfort of the user, after determining that the heart rate causes the change in sleep state, it is determined whether the average value of the heart rate data within the preset time period exceeds the preset range. If it exceeds the preset range, it indicates that the user may be physically unwell, and an alarm signal is sent at this time.

[0072] During implementation, after obtaining acceleration-related data and physiological sign-related data, the user's sleep duration and number of awake times are analyzed and determined, and the user's sleep quality is analyzed based on the sleep duration, number of awake times and sleep state change factors.

[0073] The sleep state analysis method for a wearable device provided in an embodiment of the present application includes: obtaining acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor, wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence. Determining the maximum score among the scores corresponding to the acceleration sequences of each axis within a preset time period. In addition, determining the correlation coefficient between the maximum score and the environmental variable-related data, as well as the correlation coefficient between the maximum score and the physiological sign-related data, and analyzing the factors that affect the user's sleep state based on the correlation coefficients. As can be seen, the technical solution provided by the present application determines the factors that affect the user's sleep state based on the maximum score among the scores corresponding to the acceleration sequences of the wearable device on each axis, analyzing the correlation coefficients between the maximum score and the environmental variable-related data, as well as the correlation coefficients between the maximum score and the physiological sign-related data, thereby determining the reasons for the user's transition from a sleep state to a wakeful state, helping the user improve sleep quality and enhance user experience.

[0074] In a specific embodiment, the environmental variable-related data includes at least environmental noise data and environmental temperature data, and the physiological sign-related data includes at least heart rate data and body temperature data. Then, respectively determining the correlation coefficient between the maximum score and the environmental variable-related data, and the correlation coefficient between the maximum score and the physiological sign-related data includes:

[0075] Obtain the average value of ambient noise data, ambient temperature data, heart rate data, and body temperature data within a preset time period;

[0076] The correlation coefficient between the maximum score and the average value of the ambient noise data, the correlation coefficient between the maximum score and the average value of the ambient temperature data, the correlation coefficient between the maximum score and the average value of the heart rate data, and the correlation coefficient between the maximum score and the average value of the body temperature data are determined respectively.

[0077] Excessive noise or significant changes in ambient temperature can often cause people to wake up from deep or light sleep. Therefore, when analyzing changes in a user's sleep state, the environmental variable data collected by the environmental sensor includes at least ambient noise data and ambient temperature data. Furthermore, sudden changes in the user's heart rate or body temperature can also cause changes in the user's sleep state. Therefore, the physiological sign data collected by the physiological sign sensor includes at least heart rate data and body temperature data.

[0078] It is understandable that analyzing different types of data means analyzing different factors that affect the user's sleep, such as environmental noise, ambient temperature, heart rate and body temperature. This application does not limit the specific types of factors analyzed.

[0079] After obtaining the ambient noise data, ambient temperature data, heart rate data, and body temperature data, the average values ​​of ambient noise data Xv, ambient temperature data Xt1, heart rate data Xs, and body temperature data Xt2 over a preset time period are obtained. The correlation coefficient P1 between the maximum score value Xm and the average value of ambient noise data Xv, the correlation coefficient P2 between the maximum score value Xm and the average value of ambient temperature data Xt1, the correlation coefficient P3 between the maximum score value Xm and the average value of heart rate data Xs, and the correlation coefficient P4 between the maximum score value Xm and the average value of body temperature data Xt2 are determined. Thus, the factors contributing to changes in the user's sleep state are determined based on the correlation coefficients P1, P2, P3, and P4.

[0080] It is worth noting that when determining the correlation coefficients P1, P2, P3 and P4, they are determined according to the following formula:

[0081]

[0082] Where ρ is the correlation coefficient, Cov(Xm,T) is the covariance between Xm and T, D(Xm) is the variance of Xm, D(T) is the variance of T, Xm is the maximum score, and T is the average value.

[0083] In the sleep state analysis method for a wearable device provided in an embodiment of the present application, the environmental variable-related data includes at least ambient noise data and ambient temperature data, and the physiological sign-related data includes at least heart rate data and body temperature data. This allows for the selection of multiple factors influencing a user's sleep state for analysis, thereby improving the accuracy of the results. Furthermore, by determining the correlation coefficient between the average value of each influencing data over a preset time period and the maximum value of the corresponding score in each axis acceleration sequence, the factors that cause changes in the user's sleep state are determined, helping the user analyze the factors that cause sleep state changes and improving the user experience.

[0084] Based on the above embodiment, after obtaining the correlation coefficient P1 related to ambient noise, the correlation coefficient P2 related to ambient temperature, the correlation coefficient P3 related to heart rate, and the correlation coefficient P4 related to body temperature, the factors affecting the user's sleep state change are analyzed based on the correlation coefficients, including:

[0085] Determine whether each correlation coefficient is less than a preset threshold;

[0086] If so, it is determined that the factors causing the change in the user's sleep state are unknown;

[0087] If not, sort the correlation coefficients to obtain the maximum correlation coefficient to determine the user's sleep state change factor.

[0088] It is understandable that the correlation coefficient value is between 0 and 1, and the closer it is to 1, the higher the correlation. Of course, the closer it is to 0, the lower the correlation. In fact, when each correlation coefficient is less than a preset threshold, the reason for the change in the user's sleep state cannot be determined at this time. Therefore, after obtaining the correlation coefficients P1, P2, P3 and P4, it is determined whether each correlation coefficient is less than the preset threshold. For example, the preset threshold is 0.3. If all correlation coefficients are less than 0.3, it is determined that the reason for the change in the user's sleep state is unknown. When there is a correlation coefficient greater than 0.3 among the correlation coefficients, the correlation coefficients are sorted, and the factor corresponding to the maximum correlation coefficient in the sorting result is determined to be the factor causing the change in the user's sleep state. For example, when the correlation coefficient P1 related to ambient noise is the largest, the change in the user's sleep state is related to ambient noise.

[0089] The sleep state analysis method for a wearable device provided in an embodiment of the present application analyzes factors that affect a user's sleep state based on various correlation coefficients. If all correlation coefficients are less than a preset threshold, the factor affecting the user's sleep state is determined to be unknown. Otherwise, the correlation coefficients are sorted to obtain the maximum correlation coefficient to determine the factor affecting the user's sleep state. This avoids misjudging a user's sleep state change when all correlation coefficients are small.

[0090] Figure 2 This is a flowchart of a sleep state analysis method for a wearable device provided in another embodiment of the present application. In a specific implementation, as shown in FIG. Figure 2 As shown, determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period includes:

[0091] S20: Divide the X-axis acceleration sequence, the Y-axis acceleration sequence, and the Z-axis acceleration sequence within the preset time period into a preset number of groups on an even basis.

[0092] S21: Obtain the average value corresponding to each group of acceleration sequences.

[0093] After obtaining the X-axis acceleration sequence, Y-axis acceleration sequence, and Z-axis acceleration sequence collected by the acceleration sensor, the X-axis acceleration sequence, Y-axis acceleration sequence, and Z-axis acceleration sequence of the preset duration are evenly divided into a preset number of groups, and the average value corresponding to each group of acceleration sequences on each axis is obtained.

[0094] S22: Determine the weight corresponding to the average value of each group of acceleration sequences according to the preset number of groups and the pre-set weight distribution principle.

[0095] It's understandable that data closer to the current moment is more relevant to changes in the user's sleep state, meaning it's more useful. Therefore, when assigning weights to the average values ​​of each acceleration series, the average values ​​of groups closer to the current moment are assigned a greater weight. Thus, based on this weight assignment principle and the preset number of groups, the weights for each group of acceleration series average values ​​are determined.

[0096] For example, the X-axis acceleration sequence is divided into L groups, with the average values ​​of each group being X1, X2, ..., Xn. Based on the preset number of groups and a pre-set weighting principle, the weights assigned to each group are S1, S2, ..., Sn. As S1 through Sn increase, the corresponding acceleration is closer to the data collected at the current moment. Similarly, weights are assigned to the corresponding average values ​​of the Y-axis and Z-axis acceleration sequences.

[0097] S23: Determine an X-axis acceleration score, a Y-axis acceleration score, and a Z-axis acceleration score according to the average value corresponding to each group of acceleration sequences and the weight corresponding to the average value of each group of acceleration sequences.

[0098] S24: Sort the X-axis acceleration score, the Y-axis acceleration score, and the Z-axis acceleration score to obtain the maximum score.

[0099] According to the weights corresponding to the average values ​​of the acceleration sequences of each group determined in step S22, the X-axis acceleration score, the Y-axis acceleration score and the Z-axis acceleration score are determined, and the X-axis acceleration score, the Y-axis acceleration score and the Z-axis acceleration score are sorted to obtain the maximum score.

[0100] For example, the X-axis acceleration sequence is divided into L groups, with the average values ​​of each acceleration sequence being X1, X2, ..., Xn. Based on the preset number of groups and a pre-set weighting principle, the weights assigned to each group of acceleration sequence averages are S1, S2, ..., Sn, respectively. As S1 through Sn gradually increase, the corresponding acceleration is closer to the data collected at the current moment. Thus, the X-axis acceleration score X0 = S1*X1+S2*X2+ ...+Sn*Xn.

[0101] Similarly, determine the Y-axis acceleration score Y0 and the Z-axis acceleration score Z0, and sort X0, Y0, and Z0 to obtain the maximum score Xm.

[0102] The sleep state analysis method for a wearable device provided in an embodiment of the present application processes acceleration sequence-related data collected by an acceleration sensor to obtain the maximum score among the scores corresponding to the acceleration sequence of each axis within a preset time period. Based on the maximum score, the correlation coefficient between the maximum score and data related to environmental variables, as well as the correlation coefficient between the maximum score and data related to physiological signs, are determined to determine the factors affecting the user's sleep state, thereby helping the user improve their sleep and enhancing the user experience.

[0103] In fact, based on the acceleration-related data collected by the acceleration sensor and the physiological sign-related data collected by the physiological sign sensor, it is possible to directly determine whether the user's sleep state has changed. To avoid wasting computing resources, the technical solution provided by this application determines the maximum score among the scores corresponding to the acceleration series of each axis within a preset time period after determining that the user's sleep state has changed based on the acceleration-related data and the physiological sign-related data. This allows the correlation coefficient between the maximum score and the environmental variable-related data, as well as the correlation coefficient between the maximum score and the physiological sign-related data, to determine the factors that affect the user's sleep state. Otherwise, the acceleration-related data, environmental variable-related data, and physiological sign-related data can be continuously collected.

[0104] It should be noted that in order to avoid wasting storage space, only acceleration-related data, environmental variable-related data and physiological sign-related data within a period of time can be stored. This application does not limit this. Of course, the duration of the data storage must be greater than the preset duration.

[0105] The sleep state analysis method for a wearable device provided in an embodiment of the present application first determines whether the user's sleep state has changed based on acceleration-related data and physiological sign-related data before determining the maximum score among the scores corresponding to the acceleration sequences of each axis within a preset duration. If the user's sleep state has changed, the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset duration is determined, thereby saving computing resources.

[0106] It is understandable that when the user's sleeping state is related to the heart rate, the user may be physically unwell. Therefore, in order to promptly remind the user when the user is physically unwell, when it is determined that the factor of change in the user's sleep is the heart rate, it is judged whether the average value corresponding to the heart rate data in the preset time period exceeds the preset range. If it exceeds the range, it indicates that the user is physically unwell, and an alarm signal is issued to remind surrounding people to provide rescue.

[0107] The sleep state analysis method for a wearable device provided in an embodiment of the present application sends an alarm signal when it is determined that the user's sleep change factor is the heart rate, and when it is determined that the average value of the heart rate data within a preset time period exceeds a preset range. While monitoring the user's sleep state, the user's physical health is also monitored to improve the user experience.

[0108] In a specific implementation, the user's sleep duration and number of awakenings can be determined based on acceleration-related data and physiological sign-related data. In order to provide sleep analysis and assistance to the user, the technical solution provided in the embodiment of the present application can analyze the user's sleep quality based on sleep duration, number of awakenings and sleep state change factors.

[0109] For example, sleep quality is divided into three levels: high quality, medium quality, and low quality. If the sleep duration reaches the required daily sleep duration for an adult (e.g., 8 hours), the number of awakenings is less than a preset number, and the factors affecting the sleep state are not related to the physical condition, then the current user's sleep quality is determined to be high quality.

[0110] If the sleep duration reaches the required sleep duration for an adult per day (for example, 8 hours), but the number of awakenings exceeds the preset number, and the factors affecting the sleep state are not related to the physical state, it is determined that the current user's sleep quality reaches a medium quality level.

[0111] If the sleep duration does not reach the required sleep duration for adults per day (for example, 8 hours), the number of awakenings is less than the preset number, and the sleep state change factor is related to the physical condition, it is determined that the current user's sleep quality reaches a low quality level.

[0112] Of course, it should be noted that the classification of levels and the basis for classification are not limited in this application. In addition, the analysis results of sleep therapy can be transmitted to a terminal bound to the wearable device for viewing. The analysis results can be output as a table or a pie chart, and the application does not limit the presentation format.

[0113] The sleep state analysis method for a wearable device provided in an embodiment of the present application determines the user's sleep duration and number of awake times based on acceleration-related data and physiological sign-related data, and analyzes the user's sleep quality based on the sleep duration, number of awake times, and sleep state change factors, providing the user with sleep quality analysis results to help the user improve sleep treatment.

[0114] In the above embodiments, a sleep state analysis method for a wearable device is described in detail. This application also provides corresponding embodiments of a sleep state analysis device for a wearable device. It should be noted that this application describes the embodiments of the device from two perspectives: one based on functional modules and the other based on hardware structure.

[0115] Figure 3 This is a structural diagram of a sleep state analysis device for a wearable device provided in an embodiment of the present application, such as Figure 3 As shown, the device includes:

[0116] The acquisition module 10 is used to obtain acceleration-related data of the wearable device collected by the acceleration sensor, environmental variable-related data collected by the environmental sensor, and physiological sign-related data collected by the physiological sign sensor; wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence.

[0117] The first determining module 11 is configured to determine a maximum score among scores corresponding to acceleration sequences of each axis within a preset time period.

[0118] The second determination module 12 is used to respectively determine the correlation coefficient between the maximum score value and the data related to the environmental variables, and the correlation coefficient between the maximum score value and the data related to the physiological signs.

[0119] The analysis module 13 is used to analyze factors affecting the user's sleep state according to the correlation coefficients.

[0120] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, and they will not be repeated here.

[0121] The sleep state analysis device for a wearable device provided in an embodiment of the present application includes: obtaining acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor, wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence. The maximum score value among the scores corresponding to the acceleration sequences of each axis within a preset time period is determined. Furthermore, the correlation coefficient between the maximum score value and the environmental variable-related data, as well as the correlation coefficient between the maximum score value and the physiological sign-related data, is determined, and factors that affect the user's sleep state are analyzed based on the correlation coefficients. Thus, the technical solution provided by the present application determines the factors that affect the user's sleep state based on the maximum score value among the scores corresponding to the acceleration sequences of the wearable device on each axis, analyzes the correlation coefficients between the maximum score value and the environmental variable-related data, and analyzes the correlation coefficients between the maximum score value and the physiological sign-related data, to determine the factors that affect the user's sleep state, thereby determining the reason why the user transitions from a sleep state to a wakeful state, helping the user improve sleep quality and enhance user experience.

[0122] Figure 4 A structural diagram of a wearable device provided in another embodiment of the present application is shown as follows: Figure 4 As shown, a wearable device includes: a memory 20 for storing a computer program;

[0123] The processor 21 is configured to implement the steps of the sleep state analysis method for a wearable device as described in the above embodiment when executing a computer program.

[0124] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), and a programmable logic array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0125] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the sleep state analysis method of the wearable device disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include but is not limited to the relevant data involved in the sleep state analysis method of the wearable device.

[0126] In some embodiments, a wearable device may further include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0127] Those skilled in the art will understand that Figure 4 The structure shown in the figure does not constitute a limitation of a wearable device and may include more or fewer components than shown in the figure.

[0128] A wearable device provided in an embodiment of the present application includes a memory and a processor. When the processor executes a program stored in the memory, it can implement the following method: a sleep state analysis method for a wearable device.

[0129] The wearable device provided in the embodiment of the present application determines the maximum score of the corresponding score of each axis based on the acceleration sequence of the wearable device on each axis, analyzes the correlation coefficient between the maximum score and data related to environmental variables, and the correlation coefficient between the maximum score and data related to physiological signs to determine the factors affecting the user's sleep state, thereby determining the reason why the user transitions from a sleep state to a wakeful state, helping the user improve sleep quality and enhancing user experience.

[0130] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiment.

[0131] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution 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, and the computer software product is stored in a storage medium and executes 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, etc. Various media that can store program code.

[0132] The above is a detailed introduction to the sleep state analysis method and related components of a wearable device provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

[0133] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

Claims

1. A sleep state analysis method for a wearable device, characterized in that: include: Acquire acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor; wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence; Determining the maximum score among the scores corresponding to the acceleration sequences of each axis within a preset duration; determining the maximum score by evenly dividing the acceleration sequences on each axis within the preset duration into a preset number of groups, obtaining the average value of each group of acceleration sequences for each axis, assigning weights to the average values ​​of each group of acceleration sequences based on the preset number of groups and a pre-set weight distribution principle, and finally obtaining scores corresponding to each axis based on the average values ​​and their corresponding weights, from which the maximum score is determined; the pre-set weight distribution principle is that the groups closer to the current moment within the preset duration have greater corresponding weights; respectively determining the correlation coefficient between the maximum score value and the data related to the environmental variables, and the correlation coefficient between the maximum score value and the data related to the physiological signs; The factors affecting the user's sleep state are analyzed based on the correlation coefficients.

2. The sleep state analysis method of a wearable device according to claim 1, wherein: The environmental variable-related data includes at least environmental noise data and environmental temperature data, and the physiological sign-related data includes at least heart rate data and body temperature data. Determining the correlation coefficient between the maximum score value and the environmental variable-related data, and the correlation coefficient between the maximum score value and the physiological sign-related data, respectively, includes: Obtaining an average value of the environmental noise data, an average value of the environmental temperature data, an average value of the heart rate data, and an average value of the body temperature data within the preset time period; Determine respectively the correlation coefficient between the maximum score value and the average value of the environmental noise data, the correlation coefficient between the maximum score value and the average value of the environmental temperature data, the correlation coefficient between the maximum score value and the average value of the heart rate data, and the correlation coefficient between the maximum score value and the average value of the body temperature data.

3. The sleep state analysis method of a wearable device according to claim 2, wherein: Analyzing the factors affecting the user's sleep state according to the correlation coefficients includes: Determining whether each of the correlation coefficients is less than a preset threshold; If so, it is determined that the factors causing the change in the user's sleep state are unknown; If not, the correlation coefficients are sorted to obtain the maximum correlation coefficient to determine the user's sleep state change factor.

4. The sleep state analysis method of a wearable device according to claim 1, wherein: Determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period includes: Dividing the X-axis acceleration sequence, the Y-axis acceleration sequence, and the Z-axis acceleration sequence within the preset time period into the preset number of groups on average; Get the average value corresponding to each group of acceleration sequences; Determining the weight corresponding to the average value of each group of acceleration sequences according to the preset number of groups and the preset weight distribution principle; Determine the X-axis acceleration score, Y-axis acceleration score, and Z-axis acceleration score based on the average value corresponding to each group of acceleration sequences and the weight corresponding to the average value of each group of acceleration sequences; The X-axis acceleration score, the Y-axis acceleration score, and the Z-axis acceleration score are sorted to obtain the maximum score.

5. The sleep state analysis method of a wearable device according to claim 1, wherein: Before determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period, the method further includes: determining whether the user's sleep state has changed based on the acceleration-related data and the physiological sign-related data; If yes, proceed to the step of determining the maximum score among the scores corresponding to the acceleration sequences of each axis within the preset time period; If not, proceed to the step of obtaining acceleration-related data of the wearable device collected by the acceleration sensor, environmental variable-related data collected by the environmental sensor, and physiological sign-related data collected by the physiological sign sensor.

6. The sleep state analysis method of a wearable device according to claim 2, wherein: Also includes: When it is determined that the user's sleep change factor is heart rate, determining whether the average value of the heart rate data within the preset time period exceeds a preset range; If it exceeds the preset range, an alarm signal will be issued.

7. The sleep state analysis method of a wearable device according to claim 1, wherein: Also includes: Determining the user's sleep duration and awake times based on the acceleration-related data and the physiological sign-related data; The user's sleep quality is analyzed based on the sleep duration, the number of awake times and sleep state change factors.

8. A sleep state analysis device for a wearable device, characterized in that: include: An acquisition module is configured to acquire acceleration-related data of the wearable device collected by an acceleration sensor, environmental variable-related data collected by an environmental sensor, and physiological sign-related data collected by a physiological sign sensor; wherein the acceleration-related data includes an X-axis acceleration sequence, a Y-axis acceleration sequence, and a Z-axis acceleration sequence; A first determination module is configured to determine a maximum score among scores corresponding to acceleration sequences of each axis within a preset duration. The maximum score is determined by evenly dividing the acceleration sequences on each axis within the preset duration into a preset number of groups, obtaining an average value of each group of acceleration sequences for each axis, assigning weights to the average values ​​of each group of acceleration sequences based on the preset number of groups and a pre-set weight distribution principle, and finally obtaining scores corresponding to each axis based on the average values ​​and their corresponding weights, from which the maximum score is determined. The pre-set weight distribution principle is that groups closer to the current moment within the preset duration have greater corresponding weights. a second determining module, configured to respectively determine a correlation coefficient between the maximum score value and the data related to the environmental variables, and a correlation coefficient between the maximum score value and the data related to the physiological signs; The analysis module is used to analyze the factors affecting the change of the user's sleep state according to the correlation coefficients.

9. A wearable device, characterized in that: including a memory for storing a computer program; A processor, configured to implement the steps of the sleep state analysis method for a wearable device according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the sleep state analysis method for a wearable device according to any one of claims 1 to 7 are implemented.

Images