A wake moment correction method for sleep monitoring

Abstract

The present application belongs to the technical field of sleep monitoring, and discloses a wake moment correction method for sleep monitoring, which comprises the following steps: acquiring a wake moment detection value W N of the present detection; performing first correction on W N‑1 to W N according to the wake moment detection values W1 to W N of the previous N-1 detections, to obtain a wake moment correction value W” N‑1 ; performing second correction on W” N according to the wake moment output values W'1 to W' N of the previous N-1 corrections, to obtain the wake moment output value W' of the present detection. The wake moment correction method can be applied to a sleep monitoring device, and the wake moment detection value W N directly detected by the sleep monitoring device is corrected twice according to historical data. For a device with a large deviation in measurement results, the accuracy of the wake moment output value W' N can be significantly improved after correction.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of sleep monitoring, and in particular relates to a wake-up time correction method for sleep monitoring. BACKGROUND

[0002] Sleep quality is an important factor to ensure physical health, and with the improvement of people's living standards, the importance of sleep quality is also increasing. In order to monitor the sleep quality, with the development of science and technology, the existing technology has appeared the technical scheme of measuring various physiological indexes of human body in sleep by instrument, and then realizing sleep quality evaluation. Specifically, the current sleep monitoring methods mainly include polysomnography, electroencephalogram double frequency index, sleep state video monitoring, blood oxygen saturation sleep monitoring, temperature change recorder, activity recorder, etc.

[0003] The evaluation of sleep quality needs to collect various data by sleep monitoring equipment during the user's sleep process for detection, and one of the important detections is to distinguish the sleep state of the user, so as to determine the sleep-in time, wake-up time, sleep stage, sleep-in duration, bed non-sleep duration, total sleep duration, etc. of the user in this sleep process. Among them, the accurate detection of sleep-in time and wake-up time will directly affect the judgment of whether the total sleep duration of the user of the sleep monitoring equipment is accurate. However, the existing sleep monitoring equipment inevitably has detection errors, especially for the detection of wake-up time. When detecting based on the user's body movement signal, if the bed movement signal is detected, it cannot be determined whether the user has woken up or is in sleep. Only after the user leaves the bed for a period of time, the wake-up time can be determined by determining the time when the user leaves the bed. The error generated in this case is difficult to eliminate by improving the accuracy of the equipment detection.

[0004] Therefore, on the basis of the existing sleep monitoring technology, how to correct the wake-up time detected by the sleep monitoring equipment so that the corrected wake-up time is closer to the actual wake-up time of the user has become a problem to be solved.

[0005] Therefore, the present application is proposed. SUMMARY

[0006] The technical problem to be solved by the present application is to overcome the shortcomings of the prior art and provide a wake-up time correction method for sleep monitoring, which can correct the wake-up time detection value directly detected according to the historical data of the user's sleep, thereby improving the accuracy of the judgment of the wake-up time.

[0007] To solve the above technical problems, the basic idea of the technical scheme of the present application is:

[0008] A wake-up time correction method for sleep monitoring, comprising:

[0009] Obtain the detection value W during the awake period of this test. N ;

[0010] Based on the awake time values ​​W1 to W from the previous N-1 tests. N-1 For W N The first correction is performed, yielding the correction value W for the conscious moment. N ;

[0011] Based on the output values ​​W'1 to W' of the awake moments after the previous N-1 corrections. N-1 To W” N A second correction is performed to obtain the output value W' for the current conscious moment. N The correction process is now complete.

[0012] Furthermore, the first revision includes:

[0013] According to ΔW i =W N -W i Calculate the detection value W during this awakening period. N The value of the i-th awake moment among the awake moment detection values ​​of the previous N-1 detections. i The difference ΔW between i Where i is any integer in the interval [1, N-1];

[0014] Based on the calculated N-1 differences ΔW i For W N The correction is performed to obtain the correction value W for the conscious moment. N .

[0015] Furthermore, a first duration threshold T1 is preset, based on ΔW i For W N The corrections include:

[0016] Compare N-1 |ΔW i |, determine the minimum value|ΔW i | min and the minimum value |ΔW i | min The corresponding awake time detection value W i,min ;

[0017] If |ΔW i | min If ≤T1, then the correction value W for the conscious moment is... N =W N ;

[0018] If |ΔW i | min >T1, then for WN The first offset correction is performed to obtain the correction value W for the conscious moment. N The first offset correction includes:

[0019] If W N >W i,min Then the correction value W for the conscious moment. N =W N -u1;

[0020] If W N <W i,min Then the correction value W for the conscious moment. N =W N +u1;

[0021] The offset u1 satisfies: 0 < u1 ≤ T1.

[0022] Furthermore, the offset u1 is a preset constant; or, the offset u1 is a value relative to the current region and / or the detected value W at the time of awakening. N Parameters related to the time interval in which it is located.

[0023] Furthermore, it also includes: according to |ΔW i | min and / or W1 to W N-1 The value of one or more defined offsets u1 in the equation.

[0024] Furthermore, a second duration threshold T2 is preset, and T2 > T1; if |ΔW i | min If T2 is greater than or equal to T2, then the correction value W for the conscious moment is... N =W N .

[0025] Furthermore, the second revision includes:

[0026] According to ΔW' i =W” N -W' i Calculate the correction value W for this moment of wakefulness. N The output value W' of the i-th awake moment among the previous N-1 corrected awake moment output values. i The difference between ΔW' i Where i is any integer in the interval [1, N-1];

[0027] Based on the calculated N-1 differences ΔW' i To W” N The correction yields the output value W' at the moment of wakefulness. N .

[0028] Furthermore, a third duration threshold T3 is preset, based on ΔW' i To W” N The corrections include:

[0029] Compare N-1 |ΔW' i |, determine the minimum value|ΔW' i | min and the minimum value |ΔW' i | min The corresponding output value W' during the waking moment i,min ;

[0030] If |ΔW' i | min If T3 is greater than or equal to T3, then the output value W' is equal to T3 at the time of awakening. N =W” N ; and / or, if |ΔW' i | min =0, then the output value W' is 0 when awake. N =W” N .

[0031] Furthermore, if |ΔW' i | min <T3, then for W” N The second offset correction yields the output value W' at the moment of wakefulness. N The second offset correction includes:

[0032] If W” N >W' i,min Then the output value W' is during the conscious moment. N =W” N -u2;

[0033] If W” N <W' i,min Then the output value W' is during the conscious moment. N =W” N +u2;

[0034] The offset u2 satisfies: 0 < u2 ≤ T3.

[0035] Furthermore, the offset u2 is a preset constant;

[0036] Alternatively, the offset u2 is relative to the current region and / or the detected value W at the time of wakefulness. N Parameters related to the time interval in which it is located;

[0037] Alternatively, the offset u2 is equal to |ΔW' i | min and / or W'1 to W' N-1 One or more related parameters in the table.

[0038] Compared with the prior art, the present application has the following beneficial effects.

[0039] In the present application, the correction of the wake-up time includes two times, that is, the first modification according to the wake-up time detection value of the historical record and the second correction according to the wake-up time output value of the historical record. Since the user's sleep generally has the characteristics of regularity and rhythm, the corrected wake-up time is closer to the real situation compared with the directly detected wake-up time, thereby improving the accuracy of the sleep monitoring device in judging the wake-up time.

[0040] In the present application, the wake-up time of the present time is offset to the closest wake-up time in the historical data during the correction process, which is more in line with the user's general sleep real situation and is conducive to ensuring the accuracy of the wake-up time judgment. By setting the time threshold, when the wake-up time of the present time deviates from the wake-up time in the historical data by more than the time threshold, the correction is not performed, thereby avoiding the problem that the wake-up time detected this time is incorrectly corrected when the wake-up time of the present time and the wake-up time before that have a large difference due to some special circumstances of the user.

[0041] In the present application, the offset amount used in the correction process can be determined by the region where the user is located and / or the time interval corresponding to the wake-up time, thereby being more in line with the current user's sleep habits. Alternatively, the offset amount can also be determined by the specific deviation between the wake-up time of the present time and the closest wake-up time in the historical data, thereby achieving a more accurate correction result.

[0042] The specific embodiments of the present application will be described in further detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings, which are part of the present application, serve to provide a further understanding of the present application, and the schematic embodiments of the present application and their descriptions serve to explain the present application but do not constitute an improper limitation on the present application. Obviously, the accompanying drawings described below are only some embodiments, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings:

[0044] Figure 1 is a flowchart of the wake-up time correction method in the embodiments of the present application.

[0045] It should be noted that these drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below with reference to the accompanying drawings. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0047] like Figure 1 As shown, the wakefulness correction method for sleep monitoring in this invention includes the following steps:

[0048] Obtain the detection value W during the awake period of this test. N ;

[0049] Based on the awake time values ​​W1 to W from the previous N-1 tests. N-1 For W N The first correction is performed, yielding the correction value W for the conscious moment. N ;

[0050] Based on the output values ​​W'1 to W' of the awake moments after the previous N-1 corrections. N-1 To W” N A second correction is performed to obtain the output value W' for the current conscious moment. N The correction process is now complete.

[0051] Since users' sleep patterns are generally regular, in the above scheme, the wakefulness detection value W obtained in this test... N The system corrects the wakefulness time twice based on historical records. This is especially useful for sleep monitoring devices with significant measurement discrepancies. The correction significantly improves the accuracy of wakefulness time determination, thereby enhancing the monitoring of the user's sleep.

[0052] As a preferred embodiment of the present invention, the first modification includes:

[0053] According to ΔW i =W N -W i Calculate the detection value W during this awakening period. N The value of the i-th awake moment among the awake moment detection values ​​of the previous N-1 detections. i The difference ΔW between i Where i is any integer in the interval [1, N-1];

[0054] Based on the calculated N-1 differences ΔW i For W N The correction is performed to obtain the correction value W for the conscious moment. N .

[0055] Furthermore, compare N-1 |ΔW i|, determine the minimum value|ΔW i | min And based on the minimum value |ΔW i | min For W N The correction is performed to obtain the correction value W for the conscious moment. N .

[0056] As another preferred embodiment of the present invention, the second modification includes:

[0057] According to ΔW' i =W” N -W' i Calculate the correction value W for this moment of wakefulness. N The output value W' of the i-th awake moment among the previous N-1 corrected awake moment output values. i The difference between ΔW' i Where i is any integer in the interval [1, N-1];

[0058] Based on the calculated N-1 differences ΔW' i To W” N The correction yields the output value W' at the moment of wakefulness. N .

[0059] Furthermore, compare N-1 |ΔW' i |, determine the minimum value|ΔW' i | min And based on the minimum value |ΔW' i | min To W” N The correction yields the output value W' at the moment of wakefulness. N .

[0060] In the description of this invention, the lucid moment data can be a lucid moment detection value, a lucid moment correction value, or a lucid moment output value. In the above scheme, the difference between the current lucid moment data and multiple historical lucid moment data is calculated to find the historical lucid moment data closest to the current one. This data is then used to correct the current lucid moment data. This eliminates the influence of significantly biased historical lucid moment data on the correction result, leading to a more accurate lucid moment output value W'. N .

[0061] Example 1

[0062] The embodiment provides a wake-up time correction method for sleep monitoring, which can be applied to a sleep monitoring device to correct a wake-up time detection value detected by the sleep monitoring device, so that a wake-up time output value closer to the real wake-up time of a user is obtained.

[0063] It should be noted that the sleep monitoring device can adopt any method in the prior art to detect the wake-up time of the user, for example, the wake-up time is determined according to the heart rate increase, which is not limited herein.

[0064] As shown in the wake-up time correction method provided by the embodiment, the method comprises the following steps: Figure 1

[0065] obtaining a wake-up time detection value W N of the current detection;

[0066] performing first correction on W N according to wake-up time detection values W N-1 of the previous N-1 detections, to obtain a wake-up time correction value W" N ;

[0067] performing second correction on W" N according to wake-up time output values W' N-1 of the previous N-1 detections, to obtain a wake-up time output value W' N of the current detection, and completing the correction process.

[0068] In the embodiment, N is a positive integer greater than or equal to 3. That is, the wake-up time detection value W N of the current detection is corrected based on the previous two wake-up time data in the historical record.

[0069] The sleep condition of the user generally has regularity, that is, excluding some special cases, the actual wake-up time of the same user each day should fluctuate within a certain range, and there is rarely, even almost no case that there is a large difference between the actual wake-up times each day. The scheme of the embodiment utilizes the wake-up time data in the historical record of the sleep monitoring device, and performs first and second correction on the wake-up time data of the current detection, which is beneficial to improve the inaccuracy of the wake-up time detection.

[0070] In a further scheme of the embodiment, the first correction specifically comprises:

[0071] calculating the wake-up time detection value W N of the current detection and the i-th wake-up time detection value W i in the wake-up time detection values of the previous N-1 detections according to AW i =W N -W i , and obtaining the wake-up time correction value W" N .i The difference ΔW between i Where i is any integer in the interval [1, N-1];

[0072] Based on the calculated N-1 differences ΔW i For W N The correction is performed to obtain the correction value W for the conscious moment. N .

[0073] Furthermore, compare N-1 |ΔW i |, determine the minimum value|ΔW i | min and the minimum value |ΔW i | min The corresponding awake time detection value W i,min According to |ΔW i | min and / or W i,min For W N The correction is performed to obtain the correction value W for the conscious moment. N .

[0074] Taking N=5 as an example, the values ​​of i are 1, 2, 3, and 4 respectively. That is to say, the data of the current time of consciousness is corrected based on the data of the previous 4 times of consciousness.

[0075] Initially, the previous four alertness detection values ​​W1, W2, W3, and W4 are retrieved and subtracted from the current alertness detection value W5, resulting in four differences ΔW1, ΔW2, ΔW3, and ΔW4. Then, these ΔW1, ΔW2, ΔW3, and ΔW4 are compared, and the minimum absolute value is determined, such as |ΔW3|. The corresponding alertness detection value is W3. Finally, the alertness detection value W5 is corrected based on |ΔW3| and W3 to obtain the corrected alertness value W”5.

[0076] In the above scheme, the difference between the current lucid moment data and multiple historical lucid moment data is calculated to find the historical lucid moment data that is closest to the current one. This closest historical lucid moment data is then used to correct the current lucid moment data. This eliminates the influence of significantly inaccurate historical lucid moment data on the correction result, leading to a more accurate lucid moment output value. For example, if a user woke up early the previous day due to work or other needs, resulting in a previous lucid moment data that is significantly earlier than other dates in the historical data, correcting the current lucid moment data based on the previous lucid moment data would obviously not yield a correction result close to the actual situation.

[0077] In a further embodiment, a first duration threshold T1 is preset, and |ΔW| is determined. i | minand W i,min Afterwards, |ΔW i | min and T1, and according to the comparison result, how to make the correction is determined.

[0078] Specifically, if |ΔW i | min ≤ T1, the wake time correction value W N = W N , which is equivalent to not correcting the value of the current wake time data in the first correction process.

[0079] If |ΔW i | min > T1, the first offset correction is made to W N to obtain the wake time correction value W N , and the first offset correction includes:

[0080] If W N > W i,min , the wake time correction value W N = W N - u1.

[0081] If W N < W i,min , the wake time correction value W N = W N + u1.

[0082] Wherein, the offset u1 satisfies: 0 < u1≤ T1.

[0083] In this embodiment, the offset u1 is a preset constant. That is, the offset u1 is the same every time the first offset correction is made.

[0084] The value of the offset u1 can be set according to the accuracy of the detection result of the sleep monitoring device when it is shipped. When it is determined every time that the first offset correction is needed, the current wake time detection value is offset by a fixed size.

[0085] Alternatively, the user can also set the value of the offset u1 autonomously, for example, after using the sleep monitoring device for a certain period of time, the user sets the value of the offset u1 autonomously according to the deviation between the detection result of the wake time and the true situation. After the user sets the value of the offset u1, when it is determined every time that the first offset correction is needed, the current wake time detection value is offset by a fixed size according to the offset u1 set by the user.

[0086] In detail, in the embodiment, when detecting and recording the wake-up time detection value, the actual detection result is first approximately processed to obtain the wake-up time detection value to be corrected. In the embodiment, the approximate processing refers to processing in units of 10 minutes, and the principle of rounding off is used for approximation. For example, if the actual detection result is 05:42:30, the wake-up time detection value after the approximate processing is 05:40:00. It should be noted that the specific value of the unit length can also be other lengths of time.

[0087] The first correction process in the embodiment is exemplified below, where the value of N is 5.

[0088] The second row in Table 1 lists the wake-up time detection value W5 of this time and the wake-up time detection values W1 to W4 of the previous four times, and the third row is the absolute value of the difference |ΔW1| to |ΔW4| calculated. It can be seen that the minimum absolute value of the difference is |ΔW3| = 20 min.

[0089] Table 1

[0090] i 5 4 3 2 1 [WC i ]]> 05:40:00 06:40:00 05:20:00 07:40:00 03:40:00 | ΔW i |]]> — 01:00:00 00:20:00 02:00:00 02:00:00

[0091] If the value of the first time threshold T1 is 30 min, |ΔW3| < T1, and the first correction result of the wake-up time detection value W5 is: the wake-up time correction value W”5 = W5 = 05:40:00.

[0092] If the value of the first time threshold T1 is 15 min, |ΔW3| > T1, and the first offset correction of the wake-up time detection value W5 is needed. Assuming that the value of the offset u1 is 10 min, and since W5 > W3, the first correction result is: the wake-up time correction value W”5 = W5 - u1 = 05:30:00.

[0093] In the above scheme, by pre-setting the first time threshold T1, when the wake-up time detection value of this time is relatively close to the wake-up time detection value recorded in the history, it is indicated that the data detected this time is more likely to be reliable, and therefore no offset correction is needed. If the wake-up time detection value of this time is still different from the wake-up time detection value closest to it in the history, it is indicated that the data detected this time is more likely to have errors, and therefore a certain degree of offset correction is needed in the direction close to the closest historical wake-up time data, which can improve the possibility of obtaining a more accurate result.

[0094] In the preferred scheme of the embodiment, a second time threshold T2 is also pre-set, and T2 > T1. If |ΔW i | min ≥ T2, the wake-up time correction value W” N = W N .

[0095] For example, the second duration threshold T2 = 120 min, |ΔW i | min =150min, at this time |ΔW i | min >T2. Although it also satisfies |ΔW i | min The condition is greater than T1, but no offset correction is performed. The value of the data at the current waking moment is retained during the first correction process.

[0096] This is because, while most sleep monitoring devices have limited accuracy in detecting wakefulness, their detection error is generally manageable, barring device malfunctions, and will not deviate significantly from reality. Therefore, when a particular wakefulness measurement differs significantly from historical wakefulness data, it's highly likely that the user's wakefulness that day was indeed different from usual. In this case, retaining the current wakefulness data without offset correction is more likely to yield a wakefulness assessment closer to reality.

[0097] The first correction process in the waking moment correction method of this embodiment has been described above. The following will further explain how to perform the second correction after the first correction is completed.

[0098] Specifically, in this embodiment, the second modification includes:

[0099] According to ΔW' i =W” N -W' i Calculate the correction value W for this moment of wakefulness. N The output value W' of the i-th awake moment among the previous N-1 corrected awake moment output values. i The difference between ΔW' i Where i is any integer in the interval [1, N-1];

[0100] Based on the calculated N-1 differences ΔW' i To W” N The correction yields the output value W' at the moment of wakefulness. N .

[0101] The above process is similar to the first correction, except that the correction is based on multiple historical wakefulness output values, i.e., the wakefulness data after each correction, instead of the wakefulness detection value. By using multiple historical wakefulness detection values ​​and wakefulness output values ​​from the sleep monitoring device to perform a double correction on the current wakefulness data, the final corrected wakefulness data can be further improved to better approximate the actual situation.

[0102] In this embodiment, a third time length threshold T3 is also preset, and the third time length threshold T3 is determined according to AW i W N The correction includes:

[0103] comparing N-1 absolute values of AW i , to determine the minimum absolute value of AW i | min and the minimum absolute value of AW i | min corresponding to the awake time output value W i,min ;

[0104] If AW i | min ≥ T3, then the awake time output value W N = W N ;

[0105] If AW i | min = 0, then the awake time output value W N = W N .

[0106] If 0 < AW i | min < T3, then a second offset correction is performed on W N to obtain the awake time output value W N .

[0107] The second offset correction includes:

[0108] If W N > W i,min , then the awake time output value W N = W N - u2;

[0109] If W N < W i,min , then the awake time output value W N = W N + u2.

[0110] The offset u2 satisfies: 0 < u2 ≤ T3.

[0111] In this embodiment, the offset u2 is similar to the offset u1, and is also a preset constant. That is, the offset u2 is the same each time the second offset correction is performed.

[0112] In detail, the value of the offset u2 can be set at the factory of the sleep monitoring device or can be set by the user. In each correction process, if it is determined that the second offset correction is needed, the current wake-up time correction value is fixedly offset.

[0113] The second correction process in this embodiment is illustrated below with N = 5.

[0114] Table 2-1 is related wake-up time data after the second correction based on Table 1 (i.e., the first duration threshold T1 is 30 min), which shows the current wake-up time correction value W”5, the previous four wake-up time output values W’1 to W’4, and the absolute values of the differences |AW’1| to |AW’4| between the current wake-up time correction value W”5 and the previous four wake-up time output values W’1 to W’4. It can be seen that the smallest absolute value of the difference is |AW’3| = 0.

[0115] Table 2-1

[0116] i 5 4 3 2 1 <![CDATA[W” i ]]> 05:40:00 — — — —

[00100] W i ]]> — 06:30:00 05:40:00 07:40:00 03:50:00 | ΔW i |]]> — 00:50:00 00:00:00 02:00:00 01:50:00

[0117] In this case, the result of the second correction of the wake-up time correction value W”5 is that the wake-up time output value W’5 = W”5 = 05:40:00.

[0118] Since the historical wake-up time data has a result consistent with the current wake-up time data, it indicates that the current wake-up time data is probably accurate, i.e., the current wake-up time correction value W” can be directly output as the wake-up time output value W’.

[0119] Another example of wake-up time data is given in Table 2-2, in which the smallest absolute value of the difference is |AW’2| = 170 min.

[0120] Table 2-2

[0121] i 5 4 3 2 1 <![CDATA[W” i ]]> 05:40:00 — — — — [WC i ]]> — 02:20:00 09:20:00 08:30:00 09:40:00 | ΔW i |]]> — 03:20:00 03:40:00 02:50:00 04:00:00

[0122] When the value of the third duration threshold T3 is 120 min, |AW’2| > T3, and no correction is performed at this time, i.e., the result of the second correction of the wake-up time correction value W”5 is that the wake-up time output value W’5 = W”5 = 05:40:00.

[0123] Similarly to the first correction process, if the current wake-up time data is greatly deviated from the historical wake-up time data, it is generally caused by special circumstances rather than the detection error of the device itself. At this time, the current wake-up time data is retained for output, which is more likely to be consistent with the actual situation.

[0124] Another example of the wake-up time data is given in Table 2-3, in which the minimum absolute difference value is |AW'3|=20 min.

[0125] Table 2-3

[0126] i 5 4 3 2 1 <![CDATA[W” i ]]> 05:40:00 — — — — [WC i ]]> — 06:30:00 06:00:00 07:40:00 03:50:00 | ΔW i |]]> — 00:50:00 00:20:00 02:00:00 01:50:00

[0127] If T3=120 min, and 0<|AW'3|<T3 is satisfied, the second offset correction is performed on the wake-up time correction value W"5. Assuming that the offset value u2 is 10 min, and W"5

[0128] The principle of the second offset correction on the wake-up time correction value W" is similar to that of the first offset correction, which is to offset in the direction of the closest historical wake-up time data, so as to obtain the final corrected wake-up time output value W'.

[0129] In this embodiment, the wake-up time detection value W N The first correction is performed according to the multiple wake-up time detection values W1 to W N-1 The second correction is performed according to the multiple wake-up time output values W'1 to W" N-1 The second correction is performed according to the multiple wake-up time output values W'1 to W" N Compared with the real wake-up time of the user, the accuracy is effectively improved, thereby improving the accuracy of the sleep monitoring device in judging the wake-up time, which is helpful to obtain more accurate sleep data, so as to better evaluate the sleep quality of the user.

[0130] Embodiment Two

[0131] The difference between this embodiment and the above-mentioned embodiment one is that the offset value u1 and the offset value u2 are parameters related to the current region and / or the time interval in which the wake-up time detection value W N is located.

[0132] The time interval in which the wake-up time detection value W N is located refers to that the time of a day is divided into multiple time intervals in a set time length, and the time interval in which the detected wake-up time detection value W N falls is the time interval. For example, the time is divided into multiple time intervals such as 03:00:00-05:00:00, 05:00:00-07:00:00, 07:00:00-09:00:00, etc. in 2 hours. If W N=05:40:00, the time interval in which it is located is 05:00:00~07:00:00.

[0133] It should be noted that for the wake time detection value of the time node falling between two time periods, it is determined to fall into the latter time period. For example, W N =05:00:00, the time interval in which it is located is 05:00:00~07:00:00. But it can be understood that the wake time detection value of the time node falling between two time periods can also be determined to fall into the former time period.

[0134] Specifically, in the embodiment, the sleep monitoring device is in communication connection with the server, the server can receive and record the wake time data uploaded by multiple sleep monitoring devices, and can also record the respective values of the offset u1 and the offset u2 used in the correction process of the wake time data.

[0135] In detail, the above data information is recorded in the server in the form of a statistical table, and the server stores different statistical tables corresponding to different regions or geographical time zones. In each statistical table, the collected wake time detection values W N are classified according to the time interval in which they are located, and the corresponding relationship between the wake time detection values W N and the respective values of the offset u1 and the offset u2 used in the correction is recorded under different time intervals, and the probability of the occurrence of different values of the offset u1 and the probability of the occurrence of different values of the offset u2 in the same time interval are counted.

[0136] In the wake time correction, for the first correction process, if it is determined that the first offset correction is needed, the corresponding statistical table is first called from the server according to the region or geographical time zone of the sleep monitoring device, and then the data of the same time interval is called in the statistical table according to the judgment of the time interval in which the current wake time detection value W N is located. From the called data, the value of the offset u1 with the highest probability of occurrence is determined, that is, the value of the offset u1 used in the majority of correction results in the same time interval, and the first offset correction is performed on the current wake time detection value W N .

[0137] Similarly, for the second correction process, if it is determined that the second offset correction is needed, the corresponding statistical table is first called from the server according to the region or geographical time zone of the sleep monitoring device, and then the data of the same time interval is called in the statistical table according to the judgment of the time interval in which the current wake time detection value W NThe determination of the time interval in which the user is located, the data of the same time interval are called in the statistical table. The value of the offset u2 with the highest occurrence probability is determined from the called data, that is, the value of the offset u2 used by the majority of correction results in the same time interval, and the correction value W N The second offset correction is performed.

[0138] The sleep habits of users often differ by region. In the embodiment, the current region is considered as an influencing factor in the determination of the values of the offsets u1 and u2 used in the correction process, which helps to improve the accuracy of the correction result. At the same time, for the case where the wake-up time falls into different time intervals, the range of detection errors often also differs. In the embodiment, the determination of the values of the offsets u1 and u2 is obtained by statistical analysis of a large amount of data, and the values of the offsets u1 and u2 finally used are the values of the offsets u1 and u2 used by the majority of correction results in the same time interval, which can further ensure the accuracy of the correction result.

[0139] Embodiment Three

[0140] The difference between the embodiment and the above-mentioned embodiment two is that the offset u1 and the offset u2 are parameters related to the current use environment and / or application scenario.

[0141] Similar to embodiment two, the server can collect a large amount of wake-up time data uploaded by different sleep monitoring devices, and record them as multiple statistical tables according to different use environments / application scenarios. And in the statistical table, the probabilities of different values of the offset u1 and the offset u2 under the same use environment / application scenario are counted.

[0142] When correcting the wake-up time data, the sleep monitoring device determines the current use environment and / or application scenario, calls the corresponding statistical table from the server, and calls the value of the offset u1 with the highest occurrence probability from the statistical table for the first correction and the value of the offset u2 with the highest occurrence probability for the second correction.

[0143] In a further scheme of the embodiment, the above-mentioned way of determining the values of the offsets u1 and u2 according to the current use environment and / or application scenario can also be combined with the way of determining the values of the offsets u1 and u2 in embodiment two, and the current region, the wake-up time detection value W N The time interval in which the user is located, and the current use environment and application scenario are helpful to further improve the correction accuracy.

[0144] In the embodiment, the offset size of the wake-up time data in the correction process is determined according to the current use environment and / or application scenario, which is helpful to obtain a correction result more in line with the current actual situation.

[0145] Embodiment Four

[0146] The difference between this embodiment and the above-mentioned embodiment one is that the values of the offset u1 and the offset u2 are determined according to the historical wake-up time data.

[0147] In one scheme of this embodiment, when the first correction is performed, the wake-up time correction method further comprises: determining the value of the offset u1 according to |ΔW i | min .

[0148] Specifically, the value of the offset u1 increases with the increase of |ΔW i | min . The greater the difference between the current wake-up time detection value W N and the closest historical wake-up time detection value, the greater the value of the corresponding offset u1, that is, the greater the offset correction amplitude of the wake-up time detection value W N .

[0149] Similarly, when the second correction is performed, the wake-up time correction method further comprises: determining the value of the offset u2 according to |ΔW’ i | min .

[0150] Specifically, the value of the offset u2 increases with the increase of |ΔW’ i | min . The greater the difference between the current wake-up time correction value W” N and the closest historical wake-up time output value, the greater the value of the corresponding offset u2, that is, the greater the offset correction amplitude of the wake-up time correction value W” N .

[0151] Preferably, in this embodiment, the values of the offsets u1 and u2 can be determined by the following methods, that is, u1=C1×|ΔW i | min , u2=C2×|ΔW’ i | min , wherein C1 and C2 are preset proportional coefficients.

[0152] In the above scheme, according to the difference between the current wake-up time data and the historical wake-up time data, the correction amplitude of the current wake-up time data is determined, and the greater the difference between the historical records, the greater the corresponding offset correction amplitude, so that the final corrected wake-up time output value is stable within a certain range, and the correction result is more accurate.

[0153] In another scheme of this embodiment, according to W1 to WN-1 The values ​​of one or more defined offsets u1 in the equation are determined according to W'1 to W'. N-1 One or more specific offset values ​​u2 are selected from the given values.

[0154] Specifically, when W N >W i,min At that time, you can select W1 to W N-1 All of the following satisfy W N >W i The detection values ​​during moments of wakefulness, and their corresponding |ΔW i | Perform a weighted average to obtain the value of the offset u1. Where, |ΔW i The larger the value of |, the smaller its corresponding weighting coefficient.

[0155] And if W N <W i,min Then select W1 to W N-1 All of the following satisfy W N <W i The detection values ​​during moments of wakefulness, and their corresponding |ΔW i | Perform a weighted average to obtain the value of the offset u1. Where, |ΔW i The larger the value of |, the smaller its corresponding weighting coefficient. The magnitude of each weighting coefficient should satisfy the following condition: the final calculated offset u1 ≤ T1.

[0156] Similarly, when W” N >W' i,min When, you can select W'1 to W' N-1 All of the following satisfy W” N >W' i The output value at the moment of wakefulness, and the corresponding |ΔW' i | Perform a weighted average to obtain the value of the offset u2. Where, |ΔW' i The larger the value of |, the smaller its corresponding weighting coefficient.

[0157] And if W” N <W' i,min Then select W'1 to W' N-1 All of the following satisfy W” N <W' i The output value at the moment of wakefulness, and the corresponding |ΔW' i | Perform a weighted average to obtain the value of the offset u2. Where, |ΔW' i The larger the value of |, the smaller its corresponding weighting coefficient. The magnitude of each weighting coefficient should satisfy: the final calculated offset u2 ≤ T3.

[0158] In the above scheme, the specific values of the offset u1 and the offset u2 are determined according to comprehensive analysis of the multiple wake-up time data in the history record, which can avoid the error correction that may occur when the offset value is determined according to single historical data.

[0159] In this embodiment, the values of the offsets u1 and u2 are determined according to the deviation between the wake-up time data in the history record and the current wake-up time data. Compared with the history record, the larger the deviation, the greater the correction range. The final corrected wake-up time output value can fall within a certain range, which is consistent with the real situation of the general user's sleep process, and the correction success rate is higher.

[0160] The above only describes the preferred embodiments of the present application and is not intended to limit the present application in any form. Although the present application has been disclosed as above with the preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above-mentioned technical content without departing from the technical solution of the present application, and any simple modification, equivalent change and modification of the above embodiments made according to the technical essence of the present application still belong to the scope of the present application.

Claims

1. A method for correcting wakefulness time in sleep monitoring, characterized in that, include: Obtain the detection value W during the awake period of this test. N ; Based on the awake time values ​​W1 to W from the previous N-1 tests. N-1 For W N The first correction yields the correction value W'' for moments of wakefulness. N ; Based on the output values ​​W'1 to W' of the awake moments after the previous N-1 corrections. N-1 To W'' N A second correction is performed to obtain the output value W' for the current conscious moment. N Complete the correction process; The first revision includes: According to ΔW i =W N -W i Calculate the detection value W during this awakening period. N The value of the i-th awake moment among the awake moment detection values ​​of the previous N-1 detections. i The difference ΔW between i Where i is any integer in the interval [1, N-1]; Based on the calculated N-1 differences ΔW i For W N The correction is performed to obtain the correction value W'' for the conscious moment. N Specifically, this includes: comparing N-1 |ΔW i |, determine the minimum value|ΔW i | min and the minimum value |ΔW i | min The corresponding awake time detection value W i,min ; If |ΔW i | min If ≤T1, then the correction value W'' for the conscious moment N =W N ; If |ΔW i | min >T1, then for W N The first offset correction yields the correction value W'' for the conscious moment. N The first offset correction includes: If W N >W i,min Then the correction value W'' during waking hours N =W N -u1; If W N <W i,min Then the correction value W'' during waking hours N =W N +u1; Where T1 is the preset first duration threshold, and the offset u1 satisfies: 0 < u1 ≤ T1.

2. The method for correcting wakefulness time for sleep monitoring according to claim 1, characterized in that, The offset u1 is a preset constant; or, the offset u1 is the value detected by the current region and / or the awake time W. N Parameters related to the time interval in which it is located.

3. The method for correcting wakefulness time for sleep monitoring according to claim 1, characterized in that, Also includes: According to |ΔW i | min and / or W1 to W N-1 The value of one or more defined offsets u1 in the equation.

4. The method for correcting wakefulness time for sleep monitoring according to claim 1, characterized in that, A second duration threshold T2 is preset, and T2 > T1; if |ΔW i | min If T2 is greater than or equal to T2, then the correction value W'' for the conscious moment is... N =W N .

5. The method for correcting wakefulness time for sleep monitoring according to any one of claims 1-4, characterized in that, The second revision includes: According to ΔW' i =W'' N -W' i Calculate the correction value W'' for this period of wakefulness. N The output value W' of the i-th awake moment among the previous N-1 corrected awake moment output values. i The difference between ΔW' i Where i is any integer in the interval [1, N-1]; Based on the calculated N-1 differences ΔW' i To W'' N The correction yields the output value W' at the moment of wakefulness. N .

6. The method for correcting wakefulness time for sleep monitoring according to claim 5, characterized in that, A third duration threshold T3 is preset, based on ΔW' i To W'' N The corrections include: Compare N-1 |ΔW' i |, determine the minimum value|ΔW' i | min and the minimum value |ΔW' i | min The corresponding output value W' during the waking moment i,min ; If |ΔW' i | min If T3 is greater than or equal to T3, then the output value W' is equal to T3 at the time of awakening. N =W'' N ; and / or, if |ΔW' i | min =0, then the output value W' is 0 when awake. N =W'' N .

7. The method for correcting wakefulness time for sleep monitoring according to claim 6, characterized in that, If |ΔW' i | min <T3, then for W'' N The second offset correction yields the output value W' at the moment of wakefulness. N The second offset correction includes: If W'' N >W' i,min Then the output value W' is during the conscious moment. N =W'' N -u2; If W'' N <W' i,min Then the output value W' is during the conscious moment. N =W'' N +u2; The offset u2 satisfies: 0 < u2 ≤ T3.

8. The method for correcting wakefulness time for sleep monitoring according to claim 7, characterized in that, The offset u2 is a preset constant; Alternatively, the offset u2 is relative to the current region and / or the detected value W at the time of wakefulness. N Parameters related to the time interval in which it is located; Alternatively, the offset u2 is equal to |ΔW' i | min and / or W'1 to W' N-1 One or more related parameters in the table.

Images