A method, device and storage medium for identifying deep sleep period in sleep period

Abstract

The present application relates to the technical field of sleep staging, and specifically provides a method and device for identifying deep sleep period in sleep period and a storage medium, aiming to solve the problem that the existing sleep staging method cannot accurately identify deep sleep period. To this end, the method of the present application comprises: performing data preprocessing based on the obtained sleep feature data of a user to obtain a feature data sequence; identifying a deep sleep period in the sleep period to be tested according to a currently stored average baseline value and the feature data sequence; wherein the initial value of the average baseline value is obtained in combination with medical-grade sleep feature data, and the feature data sequence is obtained based on the combined result of body movement data and heart rate data. The deep sleep period identified by the present application scheme can be more close to the sleep staging detection result of the medical-grade monitoring equipment, and therefore the present application scheme can effectively improve the accuracy of identifying deep sleep period in sleep staging.

Description

Technical Field

[0001] This invention relates to the field of sleep stage technology, specifically providing a method, apparatus, and storage medium for identifying deep sleep stages during sleep. Background Technology

[0002] With economic development and improved living standards, people are paying increasing attention to their health, and sleep monitoring is a crucial aspect of this field. Currently, common sleep monitoring devices include smart bracelets and smartwatches, which can monitor daily sleep quality and effectively provide feedback on key information such as physiological signals during sleep. Sleep staging divides the sleep process into different stages based on varying physiological signals during sleep, such as deep sleep, light sleep, and rapid eye movement (REM) sleep. Accurate sleep staging results can help us understand a user's health and stress levels, and also assist professionals in developing interventions to improve sleep.

[0003] Existing technologies typically rely on body movement and heart rate signals fed back by sleep monitoring devices to determine the light sleep stage and deep sleep stage in sleep stages. Moreover, deep sleep stage is usually identified by judging body movement signals based on body movement thresholds. This method has low accuracy in identifying deep sleep stage.

[0004] Accordingly, there is a need in the field for a solution that can accurately identify the deep sleep phase during sleep to address the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects, the present invention is proposed to provide a method, apparatus and storage medium for identifying deep sleep during sleep, which solves or at least partially solves the technical problem of the inability to accurately identify deep sleep.

[0006] In a first aspect, the present invention provides a method for identifying deep sleep during sleep, comprising:

[0007] Obtain sleep characteristic data of the user during the sleep period to be tested;

[0008] Based on the user's sleep characteristic data, data preprocessing is performed to obtain a characteristic data sequence;

[0009] Obtain the currently stored average baseline value, and identify the deep sleep period in the sleep period to be tested based on the average baseline value and the feature data sequence.

[0010] Preferably, the user sleep characteristic data for the sleep period to be tested is specifically user sleep characteristic data for a preset sleep duration; the user sleep characteristic data includes at least body movement data and heart rate data; the data preprocessing based on the user sleep characteristic data to obtain the characteristic data sequence specifically includes:

[0011] Based on the preset sleep duration and the preset number of segment intervals, the body movement data and the heart rate data are divided into multiple segment intervals to obtain body movement data and heart rate data, and the body movement data and heart rate data of each segment interval correspond one-to-one.

[0012] The feature data sequence is obtained by merging body motion data and heart rate data for each segment interval.

[0013] Preferably, obtaining the feature data sequence by merging the body motion data and heart rate data based on each segment interval specifically includes:

[0014] Normalize the body motion data and heart rate data for each segment interval to obtain the body motion value sequence and heart rate value sequence for each segment interval;

[0015] Based on the body motion value sequence and the heart rate value sequence, the feature value of each segment interval is obtained;

[0016] The feature data sequence is formed based on the feature values ​​of each segment interval.

[0017] In one technical solution of the above method, the currently stored average baseline value is an initial value of the average baseline value obtained by combining medical-grade sleep feature data;

[0018] The initial value for obtaining the average baseline value by combining medical-grade sleep characteristic data specifically includes:

[0019] Acquire historical sleep characteristic data of a preset sleep duration, and perform data preprocessing based on the historical sleep characteristic data to obtain a characteristic data sequence;

[0020] Obtain a reference value; the reference value is the percentage of deep sleep obtained based on medical-grade sleep characteristic data analysis of the preset sleep duration.

[0021] The initial value of the average baseline value is determined based on the preset benchmark value, the feature data sequence, and the reference value.

[0022] The process of determining the initial value of the average baseline value based on the preset benchmark value, the feature data sequence, and the reference value specifically includes:

[0023] The number of feature values ​​less than the preset benchmark value in the feature data sequence is statistically obtained, and the current deep sleep period percentage is obtained based on the number of feature values ​​and the preset number of segment intervals;

[0024] The preset baseline value is adjusted based on the current deep sleep percentage and the reference value until the difference between the current deep sleep percentage obtained based on the adjusted preset baseline value and the reference value is less than the preset value. The initial value of the average baseline value is then determined based on the adjusted preset baseline value.

[0025] Preferably, the process of identifying the deep sleep period in the sleep period to be tested based on the average baseline value and the feature data sequence specifically involves: statistically obtaining the number of feature values ​​in the feature data sequence that are less than the average baseline value; obtaining the current deep sleep period percentage based on the number of feature values ​​and the number of preset segment intervals; and identifying the deep sleep period in the sleep period to be tested based on the current deep sleep period percentage.

[0026] In one technical solution of the above method, the currently stored average baseline value is an updated average baseline value;

[0027] The method also includes a step of updating the currently stored average baseline value, as follows:

[0028] If the current deep sleep percentage corresponding to the deep sleep period in the sleep period to be tested exceeds the preset range, the average baseline value is adjusted based on the current deep sleep percentage and the preset range until the current deep sleep percentage obtained based on the adjusted average baseline value does not exceed the preset range, and the currently stored average baseline value is updated with the average baseline value obtained based on the adjusted average baseline value.

[0029] Preferably, the method further includes a step of performing data continuity processing on the deep sleep period in the identified sleep period to be tested, specifically as follows: if the non-deep sleep period between two adjacent deep sleep periods in the sleep period to be tested is less than a preset time length, then the non-deep sleep period is re-identified as a deep sleep period.

[0030] In a second aspect, the present invention provides a control device comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and executed by the processor to perform the method described in any of the above-described technical solutions for identifying the deep sleep phase during sleep.

[0031] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the method described in any of the above-described methods for identifying deep sleep phases during sleep.

[0032] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0033] In implementing the technical solution of the present invention, firstly, data preprocessing is performed based on the acquired user sleep characteristic data to obtain a characteristic data sequence; then, the deep sleep stage in the sleep period to be tested is identified based on the currently stored average baseline value and the characteristic data sequence; wherein the initial value of the average baseline value is obtained by combining medical-grade sleep characteristic data, and the characteristic data sequence is obtained based on the combined result of body movement data and heart rate data. The deep sleep stage identified by the solution of the present invention can be closer to the sleep stage detection result of medical-grade monitoring equipment. Therefore, the solution of the present invention can effectively improve the accuracy of deep sleep stage identification in sleep stages. Attached Figure Description

[0034] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0035] Figure 1 This is a flowchart of a method for obtaining an initial value of the average baseline by combining medical-grade sleep feature data according to an embodiment of the present invention;

[0036] Figure 2 yes Figure 1 A flowchart illustrating the specific implementation steps of step S13 shown in the figure;

[0037] Figure 3 This is a schematic flowchart of the main steps of a method for identifying deep sleep during sleep according to an embodiment of the present invention;

[0038] Figure 4 yes Figure 3 A flowchart illustrating the specific implementation steps of step S22 shown in the figure;

[0039] Figure 5 This is a schematic diagram of the main structure of a deep sleep identification device according to an embodiment of the present invention. Detailed Implementation

[0040] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0041] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0042] In one application scenario of this invention, the identification of deep sleep during sleep is achieved using a retrospective sleep staging method, which involves staging after obtaining complete sleep monitoring data. Based on historical data, sleep staging identification is more accurate, and the staging results can be used to display sleep reports to users.

[0043] This invention provides a method for identifying deep sleep during sleep. First, it requires obtaining an initial average baseline value by combining medical-grade sleep characteristic data, and then storing this initial value in a sleep monitoring device. When a user uses the sleep monitoring device for the first time, the average baseline value obtained will be the pre-stored initial value. For example, the sleep monitoring device can be a smart bracelet, smartwatch, or sleep tracker.

[0044] See appendix Figure 1 , Figure 1 This invention provides a main process flow for obtaining an initial value of the average baseline by combining medical-grade sleep feature data, as shown in the embodiments of the present invention. Figure 1 The steps shown are mainly S11-S13.

[0045] Step S11: Obtain historical sleep feature data of a preset sleep duration, and perform data preprocessing based on the historical sleep feature data to obtain a feature data sequence;

[0046] In this embodiment, the historical sleep feature data includes heart rate data and body movement data. The specific method for obtaining the feature data sequence through data preprocessing based on the heart rate data and body movement data is as follows:

[0047] First, based on the preset sleep duration and the preset number of segment intervals, the body movement data and heart rate data are divided into multiple segment intervals, with each segment interval corresponding to a specific body movement data and heart rate data.

[0048] For example, if the preset sleep duration is 9 hours, and each hour corresponds to 200 data points, it is equivalent to obtaining body movement data and heart rate data with a data length of 1800. If the preset number of segment intervals is 100, then 100 segments of body movement data and 100 segments of heart rate data can be obtained. The length of each segment interval is 18. For example, each segment interval can be represented as segment interval 1, segment interval 2, segment interval 3, ..., segment interval 100.

[0049] Secondly, the body motion data and heart rate data for each segment interval are normalized to obtain the body motion value sequence and heart rate value sequence for each segment interval; based on the body motion value sequence and heart rate value sequence, the feature value of each segment interval is obtained, and the feature data sequence is formed based on the feature value of each segment interval.

[0050] Understandably, since heart rate values ​​during sleep typically range from 45 to 80, heart rate values ​​that are equal to 0 or too low can be removed from the heart rate data in each segment before the heart rate data is normalized.

[0051] For example, the body motion value sequence and heart rate value sequence of the normalized segmented interval 1 can be represented as [body motion 1, body motion 2, body motion 3, ..., body motion 18] and [heart rate 1, heart rate 2, heart rate 3, ..., heart rate 18], respectively. Similarly, the body motion value sequence and heart rate value sequence of the normalized segmented interval 100 can be represented as [body motion 1783, body motion 1784, body motion 1785, ..., body motion 1800] and [heart rate 1783, heart rate 1784, heart rate 1785, ..., heart rate 1800], respectively.

[0052] The feature value CombArray of each segment interval obtained based on the body motion value sequence NormBodyMotion(w1) and the heart rate value sequence NormHR(w1) is represented as follows:

[0053] CombArray(i)=sum(NormBodyMotion(w1)*NormHR(w1));

[0054] Where i = 1:100, CombArray(i) represents the feature value of the i-th segment interval, w1 = 1:18 for i = 1, w1 = 19:37 for i = 1, ..., w1 = 1783:1800 for i = 100.

[0055] For example, the characteristic value corresponding to segment interval 1 is CombArray(1) = body motion 1 * heart rate 1 + body motion 2 * heart rate 2 ... body motion 17 * heart rate 17 + body motion 18 * heart rate 18.

[0056] Correspondingly, the feature data sequence formed based on the feature values ​​of each segment interval can be represented as [CombArray(1), CombArray(2), ..., CombArray(100)].

[0057] Furthermore, when the preset sleep duration and the preset number of segment intervals are not divisible, the data length of each segment interval can be determined by rounding down. For example, if the data length of each segment interval is 18, and the data length of the last segment interval is less than 18, then the data of the previous segment interval is used to replace the current data of the last segment interval.

[0058] Step S12: Obtain a reference value; the reference value is the percentage of deep sleep obtained based on medical-grade sleep characteristic data analysis of the preset sleep duration;

[0059] In this embodiment, medical-grade sleep characteristic data refers to sleep characteristic data obtained from electrophysiological signals collected using medical-grade acquisition devices such as polysomnography (PSG), and can be referred to as PSG data. Similarly, this sleep characteristic data includes body movement data and heart rate data.

[0060] The percentage of deep sleep obtained from the analysis of medical-grade sleep characteristic data based on the preset sleep duration can be directly obtained using existing methods for sleep staging based on PSG data, and is not limited here. For example, the percentage of deep sleep in the sleep period can be directly obtained based on PSG data and existing sleep staging models. If the obtained percentage of deep sleep is 36%, then the reference value is taken as 36%.

[0061] Step S13: Determine the initial value of the average baseline value based on the preset benchmark value, the feature data sequence, and the reference value.

[0062] In one implementation, this step is specifically implemented as follows: Figure 2 As shown, it includes the following steps S131 and S132.

[0063] Step S131: Count the number of feature values ​​in the feature data sequence that are less than the preset benchmark value, and obtain the current deep sleep period percentage based on the number of feature values ​​and the preset number of segment intervals;

[0064] For example, with a preset baseline value of 400, the number of feature values ​​(CombArray(i)) less than 400 in the feature data sequence is counted. The preset number of segment intervals is the total number of feature values ​​in the feature data sequence. Therefore, the current deep sleep percentage can be obtained by comparing the ratio of the number of feature values ​​less than the preset baseline value to the preset number of intervals. For instance, if the number of feature values ​​less than the preset baseline value of 400 is 20 and the preset number of intervals is 100, then the current deep sleep percentage is 20%.

[0065] Step S132: Adjust the preset baseline value based on the current deep sleep percentage and the reference value until the difference between the current deep sleep percentage obtained based on the adjusted preset baseline value and the reference value is less than the preset value, and determine the initial value of the average baseline value based on the adjusted preset baseline value.

[0066] For example, the current deep sleep percentage is 20%, the reference value is 36%, and the preset value is used to represent how close the current deep sleep percentage is to the reference value. The minimum preset value can be 0. When the current deep sleep percentage, obtained based on the adjusted preset benchmark value, is adjusted from 20% to 36%, the adjusted preset benchmark value is determined as the initial value of the average baseline value. For example, by adjusting the preset benchmark value from 400 to 480, the corresponding current deep sleep percentage can be adjusted from 20% to 36%.

[0067] Furthermore, it is also possible to obtain historical sleep characteristic data for multiple consecutive days, obtain initial values ​​of multiple average baseline values ​​based on the above steps S11-S13, and determine the final initial value to be stored based on the obtained initial values. For example, if the three initial values ​​obtained based on three consecutive days of data are 480, 478, and 490, the final initial value to be stored can be obtained by calculating the mode or the average value.

[0068] See appendix Figure 3 , Figure 3 This is a schematic flowchart illustrating the main steps of a method for identifying deep sleep during sleep according to an embodiment of the present invention. Figure 3 As shown, the method for identifying deep sleep in this embodiment of the invention mainly includes the following steps S21-S23.

[0069] Step S21: Obtain user sleep characteristic data for the sleep period to be tested;

[0070] In this embodiment, the user sleep characteristic data of the sleep period to be tested is specifically the user sleep characteristic data of a preset sleep duration; the user sleep characteristic data includes at least body movement data and heart rate data.

[0071] Step S22: Perform data preprocessing based on the user sleep feature data to obtain a feature data sequence;

[0072] In one specific implementation, this step is specifically implemented as follows: Figure 4 As shown, it may include the following steps S221 and S222.

[0073] Step S221: Based on the preset sleep duration and the preset number of segment intervals, divide the body movement data and heart rate data into multiple segment intervals, and the body movement data and heart rate data of each segment interval correspond one-to-one.

[0074] Step S222: Based on the body movement data and heart rate data of each segment interval, the feature data sequence is obtained by data merging.

[0075] In this embodiment, this step is implemented as follows:

[0076] Normalize the body motion data and heart rate data for each segment interval to obtain the body motion value sequence and heart rate value sequence for each segment interval;

[0077] The feature value of each segment interval is obtained by multiplying the body motion value sequence and the heart rate value sequence;

[0078] The feature data sequence is formed based on the feature values ​​of each segment interval.

[0079] Step S23: Obtain the currently stored average baseline value, and identify the deep sleep period in the sleep period to be tested based on the average baseline value and the feature data sequence.

[0080] Understandably, when a user uses a deep sleep monitoring device for the first time, the currently stored average baseline value is obtained based on... Figure 1 The initial value of the average baseline determined by the method shown.

[0081] Specifically, in this embodiment, the number of feature values ​​less than the average baseline value in the feature data sequence is statistically obtained, and the current deep sleep period ratio is obtained based on the number of feature values ​​and the number of preset segment intervals; the deep sleep period in the sleep period to be tested is identified based on the current deep sleep period ratio.

[0082] In one application scenario of this embodiment, since the reasonable range of the proportion of deep sleep during the entire sleep period is 25% to 40% according to objective laws, after obtaining the proportion of deep sleep based on the above step S23, it is also necessary to determine whether the obtained proportion of deep sleep conforms to the above reasonable range. If it does not conform, the average baseline value can be adaptively adjusted to obtain a proportion of deep sleep that conforms to the above reasonable range. The specific adjustment method can be referred to the description of the above step S132, which will not be repeated here.

[0083] Accordingly, based on the above step S23, the step of updating the currently stored average baseline value is also included, as follows:

[0084] If the percentage of deep sleep in the identified sleep period exceeds a preset range, the average baseline value is adjusted based on the current deep sleep percentage and the preset range until the current deep sleep percentage obtained based on the adjusted average baseline value does not exceed the preset range. The currently stored average baseline value is then updated using the adjusted average baseline value. For example, the preset range is 25% to 40%. Correspondingly, the currently stored average baseline value obtained in step S23 can be an updated average baseline value.

[0085] For example, if the proportion of deep sleep in the identified sleep period is 60%, which exceeds the upper limit of the preset range value of 40%, the proportion of deep sleep can be optimized to less than or equal to 40% by adjusting the average baseline value, and the average baseline value corresponding to the optimized proportion of deep sleep can be used as the new average baseline value to update the currently stored average baseline value.

[0086] Furthermore, following step S23, the method may further include a step of continuously processing the deep sleep phase within the identified sleep phases to be tested, as follows:

[0087] If the non-deep sleep period between two adjacent deep sleep periods in the sleep period to be tested is less than a preset time length, then the non-deep sleep period will be re-identified as a deep sleep period.

[0088] For example, the distribution of deep sleep periods in the identified sleep period is as follows: a 2-minute deep sleep period is followed by a 4-minute REM sleep period, and then another 5-minute deep sleep period, with a preset duration of 10 minutes. Through data continuity processing, the 4-minute REM sleep period between the two deep sleep periods can be re-identified and classified as a deep sleep period, resulting in a continuous 11-minute deep sleep period. This processing method reduces fragmented deep sleep periods in the sleep period being tested, achieving the effect of data continuity.

[0089] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0090] Furthermore, the present invention also provides a deep sleep period recognition device.

[0091] See appendix Figure 5 , Figure 5 This is a main structural block diagram of a deep sleep identification device according to an embodiment of the present invention. Figure 5 As shown, the deep sleep identification device in this embodiment of the invention mainly includes a first acquisition module 301, a data processing module 302, a second acquisition module 303, and an identification module 304. In some embodiments, one or more of the first acquisition module 301, data processing module 302, second acquisition module 303, and identification module 304 can be combined into a single module. Wherein:

[0092] First acquisition module 301: used to acquire user sleep characteristic data of the sleep period to be tested;

[0093] Data processing module 302: used to perform data preprocessing on the user sleep feature data acquired by the first acquisition module 301 to obtain a feature data sequence;

[0094] Second acquisition module 303: used to acquire the currently stored average baseline value;

[0095] Identification module 304: used to identify the deep sleep period in the sleep period to be tested based on the average baseline value obtained by the second acquisition module 303 and the feature data sequence obtained by the data processing module 302.

[0096] For a description of the specific functions of each module in this embodiment, please refer to the description of steps S21 to S23 above.

[0097] The aforementioned deep sleep detection device is used to perform Figure 3 The embodiments of the deep sleep identification method shown are similar in technical principle, the technical problems solved and the technical effects produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the deep sleep identification device can be referred to the contents described in the embodiments of the deep sleep identification method, and will not be repeated here.

[0098] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0099] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the method of identifying deep sleep stages in the sleep cycle described in the above-described method embodiments. The processor can be configured to execute the program in the storage device, which includes, but is not limited to, the program for executing the method of identifying deep sleep stages in the sleep cycle described in the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. This control device can be a control device device comprising various electronic devices.

[0100] Furthermore, the present invention also provides a sleep monitoring device, including the above-mentioned control device, which can be a smart bracelet, smartwatch, sleep belt, or other similar products.

[0101] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for performing the method of identifying deep sleep stages in sleep stages as described in the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described method of identifying deep sleep stages in sleep stages. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0102] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, a part of its hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0103] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0104] The relevant user personal information that may be involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and includes personal information that users actively provide or that is generated as a result of using the product / service, as well as personal information obtained with user authorization.

[0105] The personal information processed in this application will vary depending on the specific product / service scenario and will be determined based on the specific scenario in which the user uses the product / service. This may involve information related to the user's sleep. This application will treat the user's personal information and its processing with the utmost diligence.

[0106] This application attaches great importance to the security of users' personal information and has taken reasonable and feasible security protection measures that comply with industry standards to protect users' information and prevent unauthorized access, disclosure, use, modification, damage or loss of personal information.

[0107] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for identifying deep sleep during sleep, characterized in that, The method includes: Obtain sleep characteristic data of the user during the sleep period to be tested; Based on the user's sleep characteristic data, data preprocessing is performed to obtain a characteristic data sequence; Obtain the currently stored average baseline value, and identify the deep sleep period in the sleep period to be tested based on the average baseline value and the feature data sequence; When the currently stored average baseline value is the initial value of the average baseline value obtained by combining medical-grade sleep feature data; The initial value for obtaining the average baseline value by combining medical-grade sleep characteristic data specifically includes: Acquire historical sleep characteristic data of a preset sleep duration, and perform data preprocessing based on the historical sleep characteristic data to obtain a characteristic data sequence; Obtain a reference value; the reference value is the percentage of deep sleep obtained based on medical-grade sleep characteristic data analysis of the preset sleep duration. The initial value of the average baseline value is determined based on the preset benchmark value, the feature data sequence, and the reference value.

2. The method according to claim 1, characterized in that: The user sleep characteristic data for the sleep period to be tested specifically refers to user sleep characteristic data for a preset sleep duration; the user sleep characteristic data includes at least body movement data and heart rate data. The process of obtaining the feature data sequence through data preprocessing based on the user's sleep feature data specifically includes: Based on the preset sleep duration and the preset number of segment intervals, the body movement data and the heart rate data are divided into multiple segment intervals to obtain body movement data and heart rate data, and the body movement data and heart rate data of each segment interval correspond one-to-one. The feature data sequence is obtained by merging body motion data and heart rate data for each segment interval.

3. The method according to claim 2, characterized in that: The process of obtaining the feature data sequence by merging body motion data and heart rate data based on each segment interval specifically includes: Normalize the body motion data and heart rate data for each segment interval to obtain the body motion value sequence and heart rate value sequence for each segment interval; Based on the body motion value sequence and the heart rate value sequence, the feature value of each segment interval is obtained; The feature data sequence is formed based on the feature values ​​of each segment interval.

4. The method according to claim 1, characterized in that, The process of determining the initial value of the average baseline value based on the preset benchmark value, the feature data sequence, and the reference value specifically includes: The number of feature values ​​less than the preset benchmark value in the feature data sequence is statistically obtained, and the current deep sleep period percentage is obtained based on the number of feature values ​​and the preset number of segment intervals; The preset baseline value is adjusted based on the current deep sleep percentage and the reference value until the difference between the current deep sleep percentage obtained based on the adjusted preset baseline value and the reference value is less than the preset value. The initial value of the average baseline value is then determined based on the adjusted preset baseline value.

5. The method according to claim 1, characterized in that, The step of identifying the deep sleep period in the sleep period to be tested based on the average baseline value and the feature data sequence specifically involves: statistically obtaining the number of feature values ​​in the feature data sequence that are less than the average baseline value; obtaining the current deep sleep period ratio based on the number of feature values ​​and the number of preset segment intervals; and identifying the deep sleep period in the sleep period to be tested based on the current deep sleep period ratio.

6. The method according to claim 1, characterized in that, When the currently stored average baseline value is an updated average baseline value; The method also includes a step of updating the currently stored average baseline value, as follows: If the current deep sleep percentage corresponding to the deep sleep period in the sleep period to be tested exceeds the preset range, the average baseline value is adjusted based on the current deep sleep percentage and the preset range until the current deep sleep percentage obtained based on the adjusted average baseline value does not exceed the preset range, and the currently stored average baseline value is updated with the average baseline value obtained based on the adjusted average baseline value.

7. The method according to claim 1, characterized in that, The method further includes a step of performing continuous data processing on the deep sleep phase within the identified sleep phases to be tested, specifically as follows: If the non-deep sleep period between two adjacent deep sleep periods in the sleep period to be tested is less than a preset time length, then the non-deep sleep period will be re-identified as a deep sleep period.

8. A control device, comprising a processor and a storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the method for identifying deep sleep during sleep as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the method for identifying deep sleep during sleep as described in any one of claims 1 to 7.

Images