A method, apparatus, and storage medium for identifying a rapid eye movement period in a sleep session

Abstract

This invention relates to the field of sleep staging technology, specifically to a method, apparatus, and storage medium for identifying REM (Rapid Eye Movement) sleep stages, aiming to solve the problem that existing sleep staging methods cannot accurately identify REM stages. To this end, the method of this invention includes: dividing the acquired user heart rate data of the sleep stage to be tested into multiple segmented intervals; obtaining sleep heart rate data for each segmented interval based on the currently stored average baseline value; identifying the proportion of REM stages in each segmented interval based on the obtained sleep heart rate data; and thus obtaining the REM stage in the entire sleep stage to be tested. The initial value of the average baseline value is obtained by combining medical-grade sleep feature data. The solution provided by this invention can effectively improve the accuracy of REM stage identification 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 the REM sleep stage. 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] In existing technologies, the light sleep stage and deep sleep stage can usually be accurately determined by the body movement and heart rate signals fed back by the sleep monitoring device. However, it cannot accurately identify the REM stage. Moreover, given the individual differences among users of sleep monitoring devices, the sleep stage detection results of existing technologies also have the problems of large differences and inaccuracy.

[0004] Accordingly, there is a need in the field for a solution that can accurately identify REM sleep phases to address the aforementioned problems. Summary of the Invention

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

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

[0007] Acquire user heart rate data during the sleep period to be tested, and divide the user heart rate data during the sleep period to be tested into multiple segment intervals of user heart rate data;

[0008] Obtain the currently stored average baseline value, and obtain the sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval;

[0009] By analyzing the sleep heart rate data of each segment interval, the percentage of REM sleep in each segment interval is obtained;

[0010] The REM (Rapid Eye Movement) phase in the sleep period to be tested is identified based on the proportion of REM phase in each segment interval.

[0011] Preferably, the user heart rate data for the sleep period to be tested is specifically the user heart rate data for a preset sleep duration; the step of dividing the user heart rate data for the sleep period to be tested into multiple segment intervals specifically involves: determining the segment interval length and the number of segment intervals based on the preset sleep duration, and dividing the user heart rate data into multiple segment intervals based on the segment interval length and the number of segment intervals.

[0012] The above-mentioned method of obtaining sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval specifically involves: smoothing the user heart rate data corresponding to each segment interval, and calculating the difference between the smoothed heart rate data and the average baseline value to obtain the sleep heart rate data for each segment interval.

[0013] In one technical solution of the above method, the currently stored average baseline value is an updated average baseline value;

[0014] The method further includes the step of updating the currently stored average baseline value, specifically as follows: based on the proportion of rapid eye movement (REM) in each segment interval and the preset value range, the average baseline value corresponding to each segment interval is adjusted according to a preset method, and a new average baseline value is determined based on the adjusted average baseline value of each segment interval, and the currently stored average baseline value is updated with the new average baseline value.

[0015] The step of adjusting the average baseline value corresponding to each segment interval according to a preset method based on the REM phase ratio and preset value range of each segment interval is as follows: For each segment interval, if the REM phase ratio of the segment interval exceeds the preset value range, the sleep heart rate data and average baseline value of the segment interval are re-determined according to a preset formula until the REM phase ratio of the segment interval obtained from the re-determined sleep heart rate data meets the preset value range, and the adjusted average baseline value corresponding to the segment interval is obtained.

[0016] 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;

[0017] The initial value for obtaining the average baseline value by combining medical-grade sleep characteristic data specifically includes:

[0018] Acquire medical-grade sleep feature data and sample user heart rate data of equal length. Obtain the average heart rate based on the sample user heart rate data. Obtain sample sleep heart rate data based on the average heart rate and the sample user heart rate data. Divide the sample sleep heart rate data and the medical-grade sleep feature data into segments with the same number of intervals to obtain sample sleep heart rate data and medical-grade sleep feature data corresponding to each segment interval.

[0019] For each segment interval, the proportion of rapid eye movement (REM) sleep obtained based on the medical-grade sleep feature data is recorded as the first proportion value; the proportion of REM sleep obtained based on the sample sleep heart rate data is recorded as the second proportion value.

[0020] Based on the first percentage value and the second percentage value, the heart rate baseline value corresponding to each segment interval is adjusted according to a preset method, and the initial value of the average baseline value is determined according to the adjusted heart rate baseline value of each segment interval.

[0021] The step of adjusting the heart rate baseline value corresponding to each segment interval according to the first percentage value and the second percentage value in a preset manner is as follows: For each segment interval, if the difference between the second percentage value and the first percentage value exceeds a preset value, the sleep heart rate data and heart rate baseline value of that segment interval are re-determined according to a preset formula until the difference between the second percentage value and the first percentage value corresponding to that segment interval obtained from the re-determined sleep heart rate data does not exceed the preset value, thereby obtaining the adjusted heart rate baseline value of that segment interval.

[0022] Preferably, the above method further includes a step of performing continuous data processing on the identified REM sleep phases during the sleep period to be tested, specifically as follows:

[0023] If the non-rapid eye movement (NREM) period between two adjacent REM sleep periods in the sleep period to be tested is less than a preset time length, then the NREM period will be re-identified as a REM period.

[0024] 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 methods for identifying REM sleep.

[0025] 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 REM sleep phases.

[0026] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0027] In implementing the technical solution of the present invention, the user heart rate data of the sleep period to be tested is first divided into multiple segment intervals. Based on the stored average baseline value, the sleep heart rate data of each segment interval can be obtained. Based on the obtained sleep heart rate data, the proportion of REM sleep in each segment interval is identified, thereby obtaining the REM sleep in the entire sleep period to be tested. The initial value of the average baseline value is obtained by combining medical-grade sleep feature data. The REM sleep in the solution of the present invention can be more closely related to the sleep staging detection results of medical-grade monitoring equipment. Therefore, the solution of the present invention can effectively improve the accuracy of REM sleep in the sleep staging. Attached Figure Description

[0028] 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:

[0029] 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;

[0030] Figure 2 This is a schematic flowchart of the main steps of a method for identifying REM sleep according to an embodiment of the present invention;

[0031] Figure 3 This is a schematic diagram of the main structure of a rapid eye movement phase recognition device according to an embodiment of the present invention. Detailed Implementation

[0032] 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.

[0033] 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.

[0034] Here we will first explain some of the terms involved in this invention.

[0035] NREM: Non-rapid eye movement sleep, which is further divided into deep sleep and light sleep.

[0036] REM: Rapid Eye Movement sleep, which is more likely to occur in the later stages of sleep. REM characteristics include tics, jerks, rapid movements, numbness, and rapid eye movements. From NREM to REM: the heart rate rises more slowly (reaching its peak within 6-10 minutes) and remains at a high level for a long time (greater than the heart rate during light sleep).

[0037] PSG: Polysomnography, mainly used in clinical medicine to collect electrophysiological signals such as electrocardiogram, electroencephalogram, and electrooculogram for sleep staging studies.

[0038] Current sleep stage theory divides human sleep into REM (concentrated in the last few hours of sleep, more likely to occur in the later stages of sleep) and NREM (non-reactive sleep). NREM is further divided into deep sleep and light sleep. Medically, however, sleep stages are commonly divided into stages I, II, III, and IV, with stages closer to IV being closer to deep sleep and stages closer to I being closer to light sleep. After falling asleep, a person first enters stage I sleep, followed by stages II, III, and IV sleep, then transitions from deep sleep to light sleep in sequence. Upon returning to stage II sleep, REM sleep usually occurs, followed by another sleep cycle, progressing from light to deep and then back to light, interspersed with REM sleep. This cycle repeats approximately 4-5 times per night, with each cycle lasting about 90 minutes. The first cycle is longer, and subsequent cycles gradually become shorter.

[0039] In one application scenario of this invention, REM sleep identification during sleep is performed using a retrospective sleep staging method, which involves staging after obtaining complete sleep monitoring data. Sleep staging based on historical data yields more accurate results, and the staging results can be used to display sleep reports to users.

[0040] This invention provides a method for identifying REM sleep. First, it requires obtaining an initial average baseline value using medical-grade sleep characteristic data. This initial value is then stored in a heart rate monitoring device. When a user uses the heart rate monitoring device for the first time, the average baseline value obtained will be the pre-stored initial value. For example, the heart rate monitoring device could be a smartwatch.

[0041] 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 S101-S105.

[0042] Step S101: Obtain medical-grade sleep feature data and sample user heart rate data of equal length;

[0043] In this embodiment, medical-grade sleep characteristic data refers to sleep characteristic data obtained by collecting electrophysiological signals using medical-grade acquisition devices such as polysomnography (PSG), and sample user heart rate data refers to historical user heart rate data obtained by monitoring heart rate devices such as smart bracelets and watches.

[0044] For example, if you want to obtain sleep data for a duration of 7 hours and 30 minutes, and each hour corresponds to 200 data points, then the total length of the obtained sleep data is 1500.

[0045] Step S102: Obtain the average heart rate based on the sample user heart rate data, and obtain sample sleep heart rate data based on the average heart rate and the sample user heart rate data;

[0046] In one embodiment, the sample heart rate data is first smoothed to obtain smoothed heart rate data, and the average heart rate of the smoothed heart rate data is obtained. The sample sleep heart rate data is then obtained based on the difference between the smoothed heart rate data and the average heart rate. The average heart rate can be calculated by averaging multiple acquisitions of smoothed heart rate data.

[0047] For example: HRinSlp = HR1result1S - MeanHR; where HRinSlp represents sample sleep heart rate data, HR1result1S represents smoothed heart rate data, and MeanHR represents the average heart rate.

[0048] In this embodiment, the method may further include calculating a heart rate baseline based on sample sleep heart rate data. The method for calculating the heart rate baseline is not unique; for example, the heart rate baseline may be calculated using the following method:

[0049] HRLevel = (sum(SortHR(1:round(LenHRinSlpPo / 2),1)) / (round(LenHRinSlpPo / 2)*3)); where HRLevel represents the baseline heart rate, LenHRinSlpPo represents the length of the heart rate data with values ​​greater than zero in the sleep heart rate data, and SortHR represents the data after sorting the heart rate data with values ​​greater than zero in descending order.

[0050] Step S103: Divide the sample sleep heart rate data and the medical-grade sleep feature data into segments with the same number of intervals to obtain sample sleep heart rate data and medical-grade sleep feature data corresponding to each segment interval.

[0051] In this embodiment, by combining the changing patterns of user sleep duration and medical-grade sleep staging charts, medical-grade sleep feature data can be divided into 4-5 segment intervals. The division criteria for the corresponding sample sleep heart rate data are not limited; for example, the sample sleep heart rate data can be divided according to equal length.

[0052] For example, the medical-grade sleep feature data is divided into 5 segment intervals. Similarly, the sample sleep heart rate data is also divided into 5 segment intervals. The first segment interval of the medical-grade sleep feature data corresponds to the first segment interval of the sample sleep heart rate data, the second segment interval of the medical-grade sleep feature data corresponds to the second segment interval of the sample sleep heart rate data, and so on, to obtain sample sleep heart rate data and medical-grade sleep feature data that correspond one-to-one with each segment interval.

[0053] Step S104: For each segment interval, the proportion of rapid eye movement (REM) sleep obtained based on the medical-grade sleep feature data is recorded as the first proportion value; the proportion of REM sleep obtained based on the sample sleep heart rate data is recorded as the second proportion value;

[0054] In this embodiment, the methods for obtaining the REM sleep phase percentage based on the medical-grade sleep feature data and the REM sleep phase percentage based on sample sleep heart rate data can be directly obtained using existing sleep staging methods based on sleep feature data, and are not limited here. For example, the REM sleep phase percentage can be directly obtained based on sleep feature data and existing sleep staging models.

[0055] For example, the percentages of rapid eye movement (REM) sleep based on the medical-grade sleep feature data are 12%, 24%, 19%, 22%, and 30%, respectively. That is, the first percentage value corresponding to the first segment interval of the medical-grade sleep feature data is 12%, the first percentage value corresponding to the second segment interval is 24%, the first percentage value corresponding to the third segment interval is 19%, the first percentage value corresponding to the fourth segment interval is 22%, and the first percentage value corresponding to the fifth segment interval is 30%.

[0056] Step S105: Based on the first percentage value and the second percentage value, adjust the heart rate baseline value corresponding to each segment interval according to a preset method, and determine the initial value of the average baseline value according to the adjusted heart rate baseline value of each segment interval.

[0057] In one implementation, for each segmented interval, if the difference between the second percentage value and the first percentage value exceeds a preset value, the sleep heart rate data and the heart rate baseline value for that segmented interval are re-determined according to a preset formula, until the difference between the second percentage value and the first percentage value corresponding to that segmented interval obtained from the re-determined sleep heart rate data does not exceed the preset value, thus obtaining the adjusted heart rate baseline value for that segmented interval. The preset value is greater than or equal to 0.

[0058] For example, the first percentage value corresponding to the first segment interval of medical-grade sleep feature data is 12%, and the second percentage value corresponding to the first segment interval of sample sleep heart rate data is 5%. That is, the second percentage value is less than the first percentage value. According to the preset formula: sleep heart rate data = HR1result1S - (MeanHR - HRLevel / 2 * countMinus), and heart rate baseline value = MeanHR - HRLevel / 2 * countMinus, the sleep heart rate data and heart rate baseline value are re-determined. Wherein, HR1result1S represents smoothed heart rate data, MeanHR represents the average heart rate, HRLevel represents the heart rate baseline, and countMinus represents the count value of the number of adjustments. Each adjustment increments the count value by one until the second percentage value corresponding to the segment interval obtained based on the re-determined sleep heart rate data is closest to the first percentage value. That is, the degree of closeness is determined according to the preset value, and the heart rate baseline value calculated by the formula during this adjustment process is determined as the adjusted heart rate baseline value of the first segment interval. For example, the adjusted heart rate baseline value of the first segment interval is equal to 59.2223.

[0059] For example, the first proportion value corresponding to the second segment interval of medical-grade sleep feature data is 24%, and the second proportion value of the second segment interval of sample sleep heart rate data is 35%, that is, the second proportion value is greater than the first proportion value. According to the preset formula: sleep heart rate data = HR1result1S-(MeanHR+HRLevel / 2*countMinus), and heart rate baseline value = MeanHR+HRLevel / 2*countMinus, the sleep heart rate data and heart rate baseline value are re-determined until the second proportion value corresponding to the segment interval obtained based on the re-determined sleep heart rate data is closest to the first proportion value, that is, the degree of closeness is determined according to the preset value, and the heart rate baseline value calculated by the formula in this adjustment process is determined as the adjusted heart rate baseline value of the second segment interval. For example, the adjusted heart rate baseline value of the second segment interval is equal to 57.2223.

[0060] Similarly to the example above, the heart rate baseline values ​​corresponding to the third, fourth, and fifth segment intervals can be determined sequentially, and the initial value of the average baseline value can be determined based on the obtained heart rate baseline values ​​of the five segment intervals. For example, the average value of the obtained heart rate baseline values ​​of the five segment intervals can be determined as the initial value, or the numerical sequence composed of the obtained heart rate baseline values ​​of the five segment intervals can be determined as the initial value.

[0061] Furthermore, it is also possible to acquire sample sleep heart rate data and medical-grade sleep feature data for multiple consecutive days, and obtain initial values ​​of multiple average baseline values ​​based on the above steps S101-S105. The final initial value to be stored is determined based on the multiple initial values ​​obtained. For example, the final initial value to be stored is obtained by averaging the multiple initial values ​​obtained.

[0062] See appendix Figure 2 , Figure 2 This is a schematic flowchart illustrating the main steps of a method for identifying REM sleep according to an embodiment of the present invention. Figure 2 As shown, the method for identifying REM in this embodiment of the invention mainly includes the following steps S201-S204.

[0063] Step S201: Obtain the user's heart rate data during the sleep period to be tested, and divide the user's heart rate data during the sleep period to be tested into multiple segment intervals of user heart rate data;

[0064] In this embodiment, the user heart rate data during the sleep period to be measured is specifically the user heart rate data for a preset sleep duration. The length and number of segment intervals can be determined based on the preset sleep duration, and the user heart rate data is divided into multiple segment intervals based on the length and number of segment intervals.

[0065] In practical applications, when sleep duration is greater than or equal to 7 hours, it is usually divided into segments with a duration of 1.5 hours for each segment. For example, if sleep duration is 7 hours, the number of segments corresponding to the intervals is 5 after rounding. When sleep duration is less than 7 hours, it is divided into segments with a duration of 1.2 hours for each segment. For example, if sleep duration is 5 hours, the number of segments corresponding to the intervals is 4.

[0066] Understandably, sleep duration can also be converted into data length for division. For example, if the preset sleep duration is 8 hours, and each hour corresponds to a data length of 200, then the total length of the obtained user heart rate data is 1600.

[0067] Step S202: Obtain the currently stored average baseline value, and obtain the sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval;

[0068] Understandably, when a user uses a heart rate 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.

[0069] In this embodiment, the currently stored average baseline value can be a single numerical value or a sequence of numerical values. The step of obtaining the sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval specifically involves: smoothing the user heart rate data corresponding to each segment interval, and calculating the difference between the smoothed heart rate data and the average baseline value to obtain the sleep heart rate data for each segment interval.

[0070] It is understood that if the average baseline value is a numerical value, the sleep heart rate data for each segment interval is determined by calculating the difference between the smoothed heart rate data corresponding to each segment interval and this numerical value.

[0071] If the average baseline value is a numerical sequence, the corresponding numerical sequence can be obtained based on the number of segmented intervals. For example, if there are four segmented intervals, the currently stored average baseline value can be [A1, A2, A3, A4]; if there are five segmented intervals, the currently stored average baseline value can be [A1, A2, A3, A4, A5]. For each segmented interval, based on the correspondence between the segmented interval and the numerical sequence, the difference between the smoothed heart rate data corresponding to each segmented interval and the corresponding average baseline value is calculated to determine the sleep heart rate data for each segmented interval. For example, the smoothed heart rate data corresponding to the first segmented interval corresponds to the average baseline value A1, and so on.

[0072] Step S203: Analyze the sleep heart rate data of each segment interval to obtain the proportion of REM sleep in each segment interval;

[0073] Specifically, in this embodiment, the proportion of rapid eye movement (REM) phase is obtained by analyzing sleep heart rate data and based on the heart rate change rate and the sustained fluctuation of heart rate.

[0074] In one implementation, the REM sleep data can be obtained directly using existing methods for sleep staging based on heart rate data, thereby determining the proportion of REM sleep. For example, for sleep heart rate data, the proportion of REM sleep can be obtained by comparing the length of data conforming to a preset heart rate change pattern with the total length of sleep heart rate data. Alternatively, sleep heart rate data can be directly used as input data, and the REM sleep stage can be output using an existing sleep staging model; this is not a limitation.

[0075] In one application scenario of this embodiment, since the reasonable range of REM proportion during the entire sleep period is 20% to 25% according to objective laws, after obtaining the REM proportion of each segment interval based on the above step S203, it is also included to judge whether the REM proportion of each segment interval conforms to the above reasonable range. If it does not conform, the average baseline value can be adaptively adjusted to obtain a REM proportion that conforms to the above reasonable range again.

[0076] Accordingly, after step S203, the method further includes updating the currently stored average baseline value, specifically as follows: based on the identified proportion of rapid eye movement (REM) intervals and a preset value range, the average baseline value corresponding to each segment interval is adjusted according to a preset method, and a new average baseline value is determined based on the adjusted average baseline values ​​of each segment interval. The currently stored average baseline value is then updated using the new average baseline value. For example, the preset value range is 20% to 25%. It is understood that, correspondingly, the currently stored average baseline value obtained in step S202 can be an updated average baseline value.

[0077] In one specific implementation, for each segment interval, if the proportion of REM sleep in that segment interval exceeds a preset value range, the sleep heart rate data and average baseline value of that segment interval are re-determined according to a preset formula until the proportion of REM sleep in that segment interval obtained from the re-determined sleep heart rate data meets the preset value range, thereby obtaining the adjusted average baseline value corresponding to that segment interval.

[0078] For example, the preset formula is as follows:

[0079] Sleep heart rate data = HR1result1S - (MeanHR ± HRLevel / 2 * countMinus);

[0080] Average baseline value = MeanHR - HRLevel / 2 * countMinus;

[0081] Where HR1result1S represents smoothed heart rate data, i.e., the smoothed heart rate data obtained in step S102 above, MeanHR represents the average heart rate, HRLevel represents the heart rate baseline, and countMinus represents the count value of the number of adjustments, which increments by one with each adjustment. For details on the acquisition and calculation of each data involved in the formula, please refer to [reference needed]. Figure 1 Description of the corresponding steps.

[0082] Specifically, if the proportion of REM sleep is higher than the upper limit of the preset range, the sleep heart rate data will be recalculated during the adjustment process according to the formula: Sleep Heart Rate Data = HR1result1S - (MeanHR + HRLevel / 2 * countMinus).

[0083] If the percentage of REM sleep is lower than the lower limit of the set range, the sleep heart rate data will be recalculated during the adjustment process according to the formula: Sleep Heart Rate Data = HR1result1S - (MeanHR - HRLevel / 2 * countMinus).

[0084] For example, if the proportion of rapid eye movement (REM) in a certain segment is 60%, which exceeds the upper limit of the preset range value of 25%, the proportion of REM can be optimized to less than or equal to 25% by adjusting the average baseline value, and the average baseline value corresponding to the optimized REM proportion is used as the new average baseline value to update the currently stored average baseline value.

[0085] Step S204: Identify the REM (Rapid Eye Movement) phase in the sleep period to be tested based on the proportion of REM phase in each segment interval.

[0086] Specifically, in this embodiment, the data length corresponding to the REM period in each segment interval can be determined based on the proportion of REM period in each segment interval, and the distribution of REM period in the entire sleep period under test can be identified based on the data length corresponding to the REM period in each segment interval.

[0087] Furthermore, following step S204, the method may further include a step of performing continuous data processing on the identified REM sleep phases within the sleep phase to be tested, as follows:

[0088] If the non-rapid eye movement (NREM) period between two adjacent REM sleep periods in the sleep period to be tested is less than a preset time length, then the NREM period will be re-identified as a REM period.

[0089] For example, the distribution of REM sleep periods identified in the sleep period being tested can be as follows: a 2-minute REM sleep period is followed by a 4-minute light sleep period, and then another 5-minute REM sleep period. The preset duration is 10 minutes. Through data continuity processing, the 4-minute light sleep period between the two REM sleep periods can be re-identified and reclassified as a REM sleep period, resulting in a continuous 11-minute REM sleep period. This processing method reduces fragmented REM sleep periods in the sleep period being tested, achieving the effect of data continuity.

[0090] 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.

[0091] Furthermore, the present invention also provides a rapid eye movement phase recognition device.

[0092] See appendix Figure 3 , Figure 3 This is a main structural block diagram of a rapid eye movement phase recognition device according to an embodiment of the present invention. Figure 3 As shown, the rapid eye movement (REM) phase recognition device in this embodiment of the invention mainly includes a first acquisition module 301, a second acquisition module 302, an analysis module 303, and a recognition module 304. In some embodiments, one or more of the first acquisition module 301, the second acquisition module 302, the analysis module 303, and the recognition module 304 can be combined into a single module.

[0093] The first acquisition module 301 is used to acquire the user's heart rate data during the sleep period to be tested, and to divide the user's heart rate data during the sleep period to be tested into multiple segment intervals of user heart rate data.

[0094] The second acquisition module 302 is used to acquire the currently stored average baseline value, and to obtain the sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval.

[0095] Analysis module 303: Used to analyze sleep heart rate data for each segment interval to obtain the percentage of REM sleep in each segment interval;

[0096] Recognition module 304: used to identify the rapid eye movement (REM) phase in the sleep period to be tested based on the proportion of REM phase in each segment interval.

[0097] For a detailed description of the specific functions of each of the above modules, please refer to [link / reference]. Figure 2 Description of the corresponding embodiments.

[0098] The aforementioned rapid eye movement recognition device is used to perform Figure 2 The illustrated method embodiments for identifying REM sleep are similar in technical principle, the technical problems they solve, and the technical effects they produce. 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 REM sleep identification device can be found in the embodiments of the method for identifying REM sleep, which will not be repeated here.

[0099] 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.

[0100] 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 REM sleep 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 REM sleep 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.

[0101] Furthermore, the present invention also provides a sleep monitoring device, including the above-mentioned control device, which can be a smart bracelet, smartwatch or other products.

[0102] 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 REM sleep in the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described method of identifying REM sleep. 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.

[0103] 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, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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 REM sleep, characterized in that, The method includes: Acquire user heart rate data during the sleep period to be tested, and divide the user heart rate data during the sleep period to be tested into multiple segment intervals of user heart rate data; Obtain the currently stored average baseline value, and obtain the sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval; the currently stored average baseline value is the initial value of the average baseline value obtained by combining medical-grade sleep feature data; By analyzing the sleep heart rate data of each segment interval, the percentage of REM sleep in each segment interval is obtained; The REM (Rapid Eye Movement) phase in the sleep period to be tested is identified based on the proportion of REM phase in each segment interval; The method further includes the step of updating the currently stored average baseline value, specifically as follows: based on the proportion of rapid eye movement (REM) in each segment interval and the preset value range, the average baseline value corresponding to each segment interval is adjusted according to a preset method, and a new average baseline value is determined based on the adjusted average baseline value of each segment interval, and the currently stored average baseline value is updated with the new average baseline value.

2. The method according to claim 1, characterized in that: The user heart rate data during the sleep period to be tested is specifically the user heart rate data for a preset sleep duration. The process of dividing the user's heart rate data during the sleep period to be measured into multiple segment intervals specifically involves: determining the length and number of segment intervals based on the preset sleep duration, and dividing the user's heart rate data into multiple segment intervals based on the length and number of segment intervals.

3. The method according to claim 1, characterized in that: The specific steps for obtaining sleep heart rate data for each segment interval based on the average baseline value and the user heart rate data corresponding to each segment interval are as follows: smoothing the user heart rate data corresponding to each segment interval, and calculating the difference between the smoothed heart rate data and the average baseline value to obtain the sleep heart rate data for each segment interval.

4. The method according to claim 1, characterized in that: The step of adjusting the average baseline value corresponding to each segment interval according to a preset method based on the REM phase ratio and preset value range of each segment interval is as follows: For each segment interval, if the REM phase ratio of the segment interval exceeds the preset value range, the sleep heart rate data and average baseline value of the segment interval are re-determined according to a preset formula until the REM phase ratio of the segment interval obtained from the re-determined sleep heart rate data meets the preset value range, and the adjusted average baseline value corresponding to the segment interval is obtained.

5. The method according to claim 1, characterized in that: The initial value for obtaining the average baseline value by combining medical-grade sleep characteristic data specifically includes: Acquire medical-grade sleep feature data and sample user heart rate data of equal length. Obtain the average heart rate based on the sample user heart rate data. Obtain sample sleep heart rate data based on the average heart rate and the sample user heart rate data. Divide the sample sleep heart rate data and the medical-grade sleep feature data into segments with the same number of intervals to obtain sample sleep heart rate data and medical-grade sleep feature data corresponding to each segment interval. For each segment interval, the proportion of rapid eye movement (REM) sleep obtained based on the medical-grade sleep feature data is recorded as the first proportion value; the proportion of REM sleep obtained based on the sample sleep heart rate data is recorded as the second proportion value. Based on the first percentage value and the second percentage value, the heart rate baseline value corresponding to each segment interval is adjusted according to a preset method, and the initial value of the average baseline value is determined according to the adjusted heart rate baseline value of each segment interval.

6. The method according to claim 5, characterized in that: The step of adjusting the heart rate baseline value corresponding to each segment interval according to the first percentage value and the second percentage value in a preset manner is as follows: For each segment interval, if the difference between the second percentage value and the first percentage value exceeds a preset value, the sleep heart rate data and heart rate baseline value of that segment interval are re-determined according to a preset formula until the difference between the second percentage value and the first percentage value corresponding to that segment interval obtained from the re-determined sleep heart rate data does not exceed the preset value, thereby obtaining the adjusted heart rate baseline value of that segment interval.

7. The method according to claim 1, characterized in that, The method further includes a step of performing continuous data processing on the identified REM sleep phases during the sleep period to be tested, as follows: If the non-rapid eye movement (NREM) period between two adjacent REM sleep periods in the sleep period to be tested is less than a preset time length, then the NREM period will be re-identified as a REM 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 REM sleep phases 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 REM sleep phases as described in any one of claims 1 to 7.

Images