Sleep monitoring method and system

Abstract

The invention discloses a sleep monitoring method and system. The method comprises the steps that a processing air pressure signal segment of an air bag mattress is collected, and a corresponding standard deviation is calculated; when the standard deviation is smaller than a preset first threshold value, a peak point of the air pressure signal segment is calculated and processed, and the bed state of the user is judged based on the peak point to judge whether the signal segment is qualified; otherwise, counting the body movement condition in the sleep process according to the air pressure data in the processed air pressure signal segment; performing feature extraction processing on the qualified air pressure signal segment to obtain a reconstructed respiration signal waveform and calculating a human body respiration rate; and generating a sleep report based on the body movement condition and the human respiration rate in the sleep process. According to the invention, the judgment of the user on / off the bed in the sleeping process, the statistics of the body movement times and the monitoring of the human body breathing rate are realized through the air pressure change on the air bag mattress, the monitoring mode does not influence the comfort of the user in the sleeping process, and meanwhile, accurate and comprehensive sleep monitoring analysis is provided for the user.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep monitoring, and in particular to a sleep monitoring method and system. Background Art

[0002] Sleep plays an important role in the human body, and monitoring sleep quality is essential for maintaining health. Sleep monitoring can analyze sleep conditions, help identify factors that affect sleep and provide corresponding treatments to reduce the risk of respiratory events. Long-term continuous sleep monitoring helps to detect abnormal conditions in advance, and simple conditioning can effectively prevent diseases, improve health, and avoid the occurrence of serious diseases. As people pay more attention to healthy sleep, the smart mattress market is also expanding.

[0003] However, existing sleep monitoring technologies have some limitations. For example, the Chinese patent with publication number CN116763099A discloses a cECG-based intelligent sleeping posture recognition mattress system that can accurately realize sleeping posture recognition, but it is necessary to arrange contact ECG electrodes on the mattress, which affects the comfort of sleep and the ease of use of the equipment. The Chinese patent with publication number CN117322837A discloses a sleep monitoring method and an airbag mattress, which analyzes the user's body movement frequency through the changes in the airbag pressure of the airbag mattress, and then monitors the user's sleep state, but does not obtain more in-depth physiological parameter information such as the user's breathing rate during sleep, thereby limiting the comprehensiveness of its monitoring effect. Summary of the invention

[0004] The present invention provides a sleep monitoring method and system, which are used to solve the technical problem that the existing sleep monitoring technology fails to provide users with comfortable and comprehensive sleep monitoring services.

[0005] A first aspect of the present invention provides a sleep monitoring method, the method comprising:

[0006] Collecting the initial air pressure signal of the airbag mattress in real time, preprocessing the collected initial air pressure signal to obtain a processed air pressure signal;

[0007] Buffering air pressure data of a plurality of processed air pressure signals to obtain processed air pressure signal segments, and calculating standard deviations corresponding to the air pressure data in the processed air pressure signal segments;

[0008] When the standard deviation is less than the preset first threshold, the peak point corresponding to the air pressure data in the processed air pressure signal segment is calculated, the bed status of the user is determined based on the peak point, and whether the cached processed air pressure signal segment is qualified is determined according to the bed status; when the standard deviation is not less than the preset first threshold, the body movement during sleep is counted according to the air pressure data in the processed air pressure signal segment;

[0009] caching air pressure data of a plurality of qualified processed air pressure signal segments to obtain qualified air pressure signal segments; performing feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed breathing signal waveform, and calculating a human breathing rate based on the reconstructed breathing signal waveform;

[0010] A sleep report is generated based on the statistical body movements during sleep and the calculated human breathing rate.

[0011] Specifically, the step of collecting the initial air pressure signal of the airbag mattress in real time, preprocessing the collected initial air pressure signal, and obtaining a processed air pressure signal includes:

[0012] Collect the initial air pressure signal of the airbag mattress in real time;

[0013] Performing analog-to-digital conversion on the initial air pressure signal to obtain a digital initial air pressure signal;

[0014] The processed air pressure signal is obtained by performing noise reduction processing on the digital initial air pressure signal.

[0015] Specifically, when the standard deviation is less than a preset first threshold, calculating the peak point corresponding to the air pressure data in the processed air pressure signal segment, judging the bed status of the user based on the peak point, and judging whether the cached processed air pressure signal segment is qualified according to the bed status, includes:

[0016] When the standard deviation is less than a preset first threshold, calculating a peak point corresponding to the air pressure data in the processed air pressure signal segment, and judging whether the user is in bed or out of bed based on the peak point;

[0017] If the user is in bed, determining that the cached processed air pressure signal segment is qualified;

[0018] If the user is out of bed, the cached processed air pressure signal segment is determined to be unqualified.

[0019] Specifically, when the standard deviation is less than a preset first threshold, calculating the peak point corresponding to the air pressure data in the processed air pressure signal segment, and judging whether the user is in bed or out of bed based on the peak point, includes:

[0020] When the standard deviation is less than a preset first threshold, Fourier transform is performed on the air pressure data in the processed air pressure signal segment to obtain a frequency spectrum of the processed air pressure signal segment;

[0021] Capturing peak points from a preset frequency band in the spectrum diagram of the processed air pressure signal segment, and determining a target peak point in the preset frequency band;

[0022] When the target peak point exceeds a preset second threshold, it is determined that the user is in bed; otherwise, it is determined that the user is out of bed.

[0023] Specifically, when the standard deviation is not less than a preset first threshold, the step of collecting statistics of body movements during sleep according to the air pressure data in the processed air pressure signal segment includes:

[0024] When the standard deviation is not less than a preset first threshold, calculating the absolute value of the difference between the starting air pressure data and the ending air pressure data in the processed air pressure signal segment;

[0025] If the absolute value is within a preset interval, it is determined to be a body movement event.

[0026] Specifically, the step of performing feature extraction processing on the qualified air pressure signal segment to obtain a reconstructed breathing signal waveform, and calculating the human breathing rate based on the reconstructed breathing signal waveform includes:

[0027] Performing discrete wavelet transform on the qualified air pressure signal fragments to decompose them into small qualified air pressure signal fragments in different frequency bands;

[0028] Select a small segment of qualified air pressure signal in the low frequency band for wavelet reconstruction to obtain a reconstructed breathing signal waveform;

[0029] The human body respiration rate is calculated based on the reconstructed respiration signal waveform.

[0030] Specifically, the step of calculating the human respiratory rate based on the reconstructed respiratory signal waveform includes:

[0031] Sequentially screening out multiple maximum values ​​in the reconstructed respiratory signal waveform in a normal respiratory cycle to determine multiple peaks of the reconstructed respiratory signal waveform;

[0032] Calculating the time intervals between adjacent wave peaks, determining a plurality of effective time intervals from the time intervals between adjacent wave peaks based on a preset time value, thereby determining an effective maximum value;

[0033] The human respiratory rate is calculated based on the number of effective maxima.

[0034] A second aspect of the present invention provides a sleep monitoring system, the system comprising:

[0035] An air pressure signal acquisition module is used to acquire the initial air pressure signal of the airbag mattress in real time;

[0036] A signal preprocessing module is used to preprocess the collected initial air pressure signal to obtain a processed air pressure signal;

[0037] A sleep status monitoring module, used for caching the air pressure data of multiple processed air pressure signals to obtain processed air pressure signal segments, calculating the standard deviation corresponding to the air pressure data in the processed air pressure signal segments; when the standard deviation is less than a preset first threshold, calculating the peak point corresponding to the air pressure data in the processed air pressure signal segments, judging the user's bed status based on the peak point, and judging whether the cached processed air pressure signal segments are qualified according to the bed status; when the standard deviation is not less than the preset first threshold, counting the body movement during sleep according to the air pressure data in the processed air pressure signal segments;

[0038] A respiratory rate monitoring module, used to cache the air pressure data of a plurality of qualified processed air pressure signal segments to obtain qualified air pressure signal segments; perform feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed respiratory signal waveform, and calculate the human respiratory rate based on the reconstructed respiratory signal waveform;

[0039] The sleep report generation module is used to generate a sleep report based on the statistical body movement during sleep and the calculated human breathing rate.

[0040] A third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the sleep monitoring methods described above when executing the computer program.

[0041] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the sleep monitoring methods described above.

[0042] It can be seen from the above technical solutions that the present invention has the following advantages:

[0043] The present invention provides a sleep monitoring method and system, wherein the method comprises: collecting an initial air pressure signal of an airbag mattress in real time, preprocessing the collected initial air pressure signal to obtain a processed air pressure signal; caching air pressure data of a plurality of processed air pressure signals to obtain processed air pressure signal segments, and calculating the standard deviation corresponding to the air pressure data in the processed air pressure signal segments; when the standard deviation is less than a preset first threshold, calculating the peak point corresponding to the air pressure data in the processed air pressure signal segments, judging the user's bed status based on the peak point, and judging whether the cached processed air pressure signal segments are qualified according to the bed status; when the standard deviation is not less than the preset first threshold, counting body movement during sleep according to the air pressure data in the processed air pressure signal segments; caching air pressure data of a plurality of qualified processed air pressure signal segments to obtain qualified air pressure signal segments; performing feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed respiratory signal waveform, and calculating the human respiratory rate based on the reconstructed respiratory signal waveform; and generating a sleep report based on the statistical body movement during sleep and the calculated human respiratory rate.

[0044] The present invention uses the change of air pressure on the airbag mattress to determine whether the user is in / out of bed, count the number of body movements, and monitor the human breathing rate during sleep. This monitoring method will not affect the user's comfort during sleep, and at the same time provides the user with accurate and comprehensive sleep monitoring analysis, thereby solving the technical problem that the existing sleep monitoring technology fails to provide users with comfortable and comprehensive sleep monitoring services. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0046] Figure 1 A flowchart of a sleep monitoring method provided by an embodiment of the present invention;

[0047] Figure 2 A structural block diagram of a sleep monitoring system provided by an embodiment of the present invention;

[0048] Figure 3 A specific working flow diagram of the sleep status monitoring module provided by an embodiment of the present invention;

[0049] Figure 4 A specific working flow diagram of the respiratory rate monitoring module provided by an embodiment of the present invention;

[0050] Figure 5 Typical air pressure waveform diagrams for both in-bed and out-of-bed situations provided by the embodiment of the present invention;

[0051] Figure 6 A comparison chart of air pressure segment spectra in two situations of being in bed and out of bed provided by an embodiment of the present invention;

[0052] Figure 7 This is a waveform diagram of the respiratory signal before and after processing by the respiratory rate monitoring module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The embodiments of the present invention provide a sleep monitoring method and system, which are used to solve the technical problem that the existing sleep monitoring technology fails to provide users with comfortable and comprehensive sleep monitoring services.

[0054] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 The first aspect of the present invention provides a sleep monitoring method, the method comprising:

[0056] Step 101, collecting the initial air pressure signal of the airbag mattress in real time, and preprocessing the collected initial air pressure signal to obtain a processed air pressure signal.

[0057] It should be noted that when the user moves on the airbag mattress, the airbag in the airbag mattress will be subjected to corresponding pressure, causing the internal air pressure to change. This step uses the collected initial air pressure signal of the airbag mattress to determine whether the user is in / out of bed during sleep, count the number of body movements, and monitor the human respiratory rate. This monitoring method will not affect the user's comfort during sleep.

[0058] It is understandable that the airbag mattress can be a single bed or a double bed. If it is a double bed, the airbags on the left and right sides of the mattress are not connected to avoid confusion in the collected air pressure data, thereby avoiding affecting the subsequent sleep monitoring effect.

[0059] In this step, the preprocessing process includes: performing analog-to-digital conversion on the initial air pressure signal through an analog-to-digital converter to obtain a digital initial air pressure signal; performing noise reduction processing such as notching and filtering on the digital initial air pressure signal through a digital filter to obtain a processed air pressure signal, thereby improving the signal-to-noise ratio of the signal to highlight the characteristics of the required effective signal.

[0060] Step 102 , buffering air pressure data of a plurality of processed air pressure signals to obtain processed air pressure signal segments, and calculating the standard deviation corresponding to the air pressure data in the processed air pressure signal segments.

[0061] It should be noted that this step uses a sliding window to cache data. Each time the cache window is updated, it moves by a step of half the window size. That is, after each movement, the window will include half of the old data and half of the new data in the previous window. This method can improve data utilization and result accuracy.

[0062] Exemplarily, a 30-second time step can be used as the time window. When caching for the first time, the pressure data of the processed air pressure signal for 30 seconds is cached as the first cache to obtain the processed air pressure signal segment; when caching for the next time, the first 15 seconds of the time window cache half of the data of the processed air pressure signal segment obtained by the first cache, and the next 15 seconds cache the pressure data of the currently collected processed air pressure signal, and so on.

[0063] In this step, the calculated standard deviation corresponding to the air pressure data in the processed air pressure signal segment is used as the execution judgment criterion of step 103, which can quickly and sensitively capture the user's movement changes.

[0064] Step 103, when the standard deviation is less than the preset first threshold, calculate the peak point corresponding to the air pressure data in the processed air pressure signal segment, judge the user's bed status based on the peak point, and judge whether the cached processed air pressure signal segment is qualified according to the bed status; when the standard deviation is not less than the preset first threshold, count the body movements during sleep according to the air pressure data in the processed air pressure signal segment.

[0065] See also Figure 3 When the standard deviation is less than the preset first threshold, it indicates that the user has not taken any action. At this time, it is necessary to make a qualified judgment on the quality of processing the air pressure signal segment; and when the standard deviation is not less than the preset first threshold, it indicates that the user has taken action. At this time, it is necessary to further confirm whether the user has made any body movement in order to record the corresponding body movement situation.

[0066] It should be noted that the above-mentioned "actions" refer to the movements of the user during normal activities, such as getting out of bed, turning over, lying down and sitting up, etc.; while "body movements" refer to the movements of the user during sleep, such as turning over during sleep.

[0067] Specifically, when the standard deviation is less than a preset first threshold, the peak point corresponding to the air pressure data in the air pressure signal segment is calculated, and the bed status of the user is determined based on the peak point. The process of determining whether the cached processed air pressure signal segment is qualified according to the bed status includes the following steps:

[0068] Step S10, when the standard deviation is less than a preset first threshold, the peak point corresponding to the air pressure data in the air pressure signal segment is calculated and processed, and based on the peak point, it is determined whether the user is in bed or out of bed.

[0069] In step S10, the air pressure data in the processed air pressure signal segment is firstly Fourier transformed to obtain a frequency spectrum of the processed air pressure signal segment; then, the peak point is captured from the preset frequency band range in the frequency spectrum of the processed air pressure signal segment to determine the target peak point of the preset frequency band range; finally, when the target peak point exceeds the preset second threshold value, it is determined that the user is in bed; otherwise, it is determined that the user is out of bed.

[0070] It is understandable that the preset frequency range can be the frequency range of normal breathing, that is, 0.1Hz-0.9Hz; if the target peak point of the preset frequency range exceeds the preset second threshold, it is determined that there is regular breathing activity in the signal segment, indicating that the user is in bed; otherwise, it is considered that the signal segment has irregular fluctuations and is determined to be out of bed. Among them, a typical comparison of air pressure fluctuations in the out of bed state and the in bed state is shown in the figure below. Figure 5 As shown in the figure, the corresponding spectrum diagram is compared as follows Figure 6 shown.

[0071] Step S11: if the user is in bed, the cached processed air pressure signal segment is determined to be qualified; if the user is out of bed, the cached processed air pressure signal segment is determined to be unqualified.

[0072] It should be noted that the qualified processed air pressure signal segments are used for subsequent statistical analysis of the human respiratory rate, while the unqualified processed air pressure signal segments can be discarded.

[0073] Specifically, when the standard deviation is not less than the preset first threshold, the step of collecting statistics on body movements during sleep based on the air pressure data in the processed air pressure signal segment includes:

[0074] Step S20: When the standard deviation is not less than the preset first threshold, the absolute value of the difference between the initial air pressure data and the final air pressure data in the processed air pressure signal segment is calculated.

[0075] It should be noted that when the standard deviation is not less than the preset first threshold, it indicates that the user has made an action. At this time, the air pressure values ​​before and after the action can be compared to see if they are similar. If they are similar, it can be considered that the user has made a body movement.

[0076] Step S21: If the absolute value is within a preset interval, it is determined to be a body movement event.

[0077] It is understandable that the preset interval can be set according to the user's actual sleeping conditions.

[0078] Step 104, cache the air pressure data of multiple qualified processed air pressure signal segments to obtain qualified air pressure signal segments; perform feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed breathing signal waveform, and calculate the human breathing rate based on the reconstructed breathing signal waveform.

[0079] It is understandable that this step also uses a sliding window method to cache data. The caching method is the same as step 102, and a 30-second time step can also be used as the time window, which will not be described in detail here.

[0080] See also Figure 4 The steps of extracting features from the qualified air pressure signal segments to obtain a reconstructed breathing signal waveform and calculating the human breathing rate based on the reconstructed breathing signal waveform include:

[0081] Step S20, performing discrete wavelet transform on the qualified air pressure signal segments to decompose them into small qualified air pressure signal segments of different frequency bands.

[0082] It can be understood that the discrete wavelet transform process can decompose the qualified air pressure signal fragments into multiple frequency bands to obtain small qualified air pressure signal fragments corresponding to the high frequency band, the middle frequency band and the low frequency band.

[0083] Step S21, selecting a small segment of qualified air pressure signal in the low frequency band for wavelet reconstruction to obtain a reconstructed breathing signal waveform.

[0084] It should be noted that in this step, it is necessary to select a small segment of a qualified air pressure signal in the frequency band (ie, low frequency band) where normal breathing is located for wavelet reconstruction, so as to obtain a relatively smooth reconstructed breathing signal waveform.

[0085] See also Figure 7 , Figure 7 The comparison of the waveform without wavelet reconstruction and the waveform after wavelet reconstruction is shown; Figure 7 In the waveform diagram, the waveform after wavelet reconstruction is smoother than that without wavelet reconstruction.

[0086] Step S22, calculating the human body breathing rate based on the reconstructed breathing signal waveform.

[0087] Specifically, multiple maximum values ​​are selected in sequence in the reconstructed breathing signal waveform according to the normal breathing cycle to determine multiple peaks of the reconstructed breathing signal waveform; the time interval between adjacent peaks is calculated, and multiple valid time intervals are determined from the time intervals between adjacent peaks based on the preset time value, thereby determining the valid maximum value; the human respiratory rate is calculated based on the number of valid maximum values. The above-mentioned "human respiratory rate" refers to the number of breaths of the user in 1 minute.

[0088] For example, the normal breathing cycle can be used as the screening time range for screening out the maximum values ​​in the reconstructed breathing signal waveform, such as 2 seconds as a screening cycle, so as to screen out multiple maximum values ​​and determine the peaks corresponding to the maximum values; calculate the time interval t between adjacent peaks, if the time interval t between adjacent peaks is less than the preset time value, it indicates that the time interval t between the adjacent peaks is invalid, and only the larger maximum values ​​corresponding to the adjacent peaks are retained, and the smaller ones are discarded, so as to determine multiple valid maximum values. Figure 7 For example, if the reconstructed breathing signal waveform corresponds to 30 seconds of waveform data, then the number of determined valid maximum values ​​can be multiplied by 2 to obtain the human breathing rate; if the reconstructed breathing signal waveform corresponds to 20 seconds of waveform data, then the number of determined valid maximum values ​​can be multiplied by 3 to obtain the human breathing rate.

[0089] Step 105: Generate a sleep report based on the statistically analyzed body movements during sleep and the calculated human breathing rate.

[0090] The present invention can count the sleep monitoring results obtained by the user during sleep every day, such as human breathing rate and body movement, and generate a sleep report based on the sleep monitoring results obtained; wherein, the sleep report may include basic sleep data, body movement analysis, human breathing rate analysis and sleep quality assessment, etc., to provide users with comprehensive sleep monitoring and analysis.

[0091] Basic sleep data may include overall sleep duration, time to fall asleep, and time to wake up; body movement analysis may include overall body movement times, frequent body movement periods, and body movement types; human respiratory rate analysis may include average respiratory rate, respiratory rate fluctuations, and respiratory abnormalities; sleep quality assessment may include sleep continuity analysis, sleep depth analysis, and respiratory quality analysis, etc. Then, users can use the corresponding sleep report as a reference for sleep monitoring, and adjust the sleeping environment, improve work and rest habits, and pay attention to respiratory health, etc., so as to further improve the user's sleep quality.

[0092] See also Figure 2 The second aspect of the present invention further provides a sleep monitoring system, the system comprising:

[0093] An air pressure signal acquisition module is used to acquire the initial air pressure signal of the airbag mattress in real time;

[0094] A signal preprocessing module is used to preprocess the collected initial air pressure signal to obtain a processed air pressure signal;

[0095] A sleep status monitoring module is used to cache the air pressure data of multiple processed air pressure signals to obtain processed air pressure signal segments, calculate the standard deviation of the air pressure data in the processed air pressure signal segments; when the standard deviation is less than a preset first threshold, calculate the peak point corresponding to the air pressure data in the processed air pressure signal segments, judge the user's bed status based on the peak point, and judge whether the cached processed air pressure signal segments are qualified according to the bed status; when the standard deviation is not less than the preset first threshold, count the body movement during sleep according to the air pressure data in the processed air pressure signal segments;

[0096] A respiratory rate monitoring module is used to cache the air pressure data of multiple qualified processed air pressure signal segments to obtain qualified air pressure signal segments; perform feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed respiratory signal waveform, and calculate the human respiratory rate based on the reconstructed respiratory signal waveform;

[0097] The sleep report generation module is used to generate a sleep report based on the statistical body movement during sleep and the calculated human breathing rate.

[0098] In the present invention, the air pressure signal acquisition module is connected to the air bag in the air bag mattress through an air tube; the air pressure signal acquisition module includes a pressure sensor device, a capacitive coupling device and a signal conditioning circuit connected in sequence; the pressure sensor device is used to convert the air pressure change of the air bag into an electrical signal; the capacitive coupling device is used to transmit the electrical signal of the pressure sensor device to the signal conditioning circuit, so as to realize non-contact signal transmission between the pressure sensor device and the signal conditioning circuit, and at the same time, the capacitive coupling device can multiply amplify and suppress noise of the electrical signal sensed by the pressure sensor device, so as to capture the originally weak air pressure fluctuation change caused by physiological activities; the signal conditioning circuit is used to convert the received electrical signal into an initial air pressure signal; wherein, the initial air pressure signal is an analog signal.

[0099] The signal preprocessing module includes an analog-to-digital converter and a digital filter. The analog-to-digital converter is used to convert the initial air pressure signal into a digital initial air pressure signal, and the digital filter is used to perform noise reduction processing on the digital initial air pressure signal to obtain a processed air pressure signal.

[0100] The third aspect of the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the sleep monitoring method described above when executing the computer program.

[0101] The fourth aspect of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the sleep monitoring method as described above when the computer program is executed by a processor.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0107] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A sleep monitoring method, characterized in that: The method comprises: Collecting the initial air pressure signal of the airbag mattress in real time, preprocessing the collected initial air pressure signal to obtain a processed air pressure signal; Buffering air pressure data of a plurality of processed air pressure signals to obtain processed air pressure signal segments, and calculating standard deviations corresponding to the air pressure data in the processed air pressure signal segments; When the standard deviation is less than the preset first threshold, the peak point corresponding to the air pressure data in the processed air pressure signal segment is calculated, the bed status of the user is determined based on the peak point, and whether the cached processed air pressure signal segment is qualified is determined according to the bed status; when the standard deviation is not less than the preset first threshold, the body movement during sleep is counted according to the air pressure data in the processed air pressure signal segment; caching air pressure data of a plurality of qualified processed air pressure signal segments to obtain qualified air pressure signal segments; performing feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed breathing signal waveform, and calculating a human breathing rate based on the reconstructed breathing signal waveform; A sleep report is generated based on the statistical body movements during sleep and the calculated human breathing rate.

2. The sleep monitoring method according to claim 1, characterized in that: The step of collecting the initial air pressure signal of the airbag mattress in real time and preprocessing the collected initial air pressure signal to obtain a processed air pressure signal includes: Collect the initial air pressure signal of the airbag mattress in real time; Performing analog-to-digital conversion on the initial air pressure signal to obtain a digital initial air pressure signal; The processed air pressure signal is obtained by performing noise reduction processing on the digital initial air pressure signal.

3. The sleep monitoring method according to claim 1, characterized in that: When the standard deviation is less than a preset first threshold, the steps of calculating the peak point corresponding to the air pressure data in the processed air pressure signal segment, judging the bed status of the user based on the peak point, and judging whether the cached processed air pressure signal segment is qualified according to the bed status include: When the standard deviation is less than a preset first threshold, calculating a peak point corresponding to the air pressure data in the processed air pressure signal segment, and judging whether the user is in bed or out of bed based on the peak point; If the user is in bed, determining that the cached processed air pressure signal segment is qualified; If the user is out of bed, the cached processed air pressure signal segment is determined to be unqualified.

4. The sleep monitoring method according to claim 3, characterized in that: The step of calculating the peak point corresponding to the air pressure data in the processed air pressure signal segment when the standard deviation is less than the preset first threshold, and judging whether the user is in bed or out of bed based on the peak point, comprises: When the standard deviation is less than a preset first threshold, Fourier transform is performed on the air pressure data in the processed air pressure signal segment to obtain a frequency spectrum of the processed air pressure signal segment; Capturing peak points from a preset frequency band in the spectrum diagram of the processed air pressure signal segment, and determining a target peak point in the preset frequency band; When the target peak point exceeds a preset second threshold, it is determined that the user is in bed; otherwise, it is determined that the user is out of bed.

5. The sleep monitoring method according to claim 1, characterized in that: When the standard deviation is not less than a preset first threshold, the step of collecting statistics of body movements during sleep according to the air pressure data in the processed air pressure signal segment comprises: When the standard deviation is not less than a preset first threshold, calculating the absolute value of the difference between the starting air pressure data and the ending air pressure data in the processed air pressure signal segment; If the absolute value is within a preset interval, it is determined to be a body movement event.

6. The sleep monitoring method according to claim 1, characterized in that: The step of performing feature extraction processing on the qualified air pressure signal segment to obtain a reconstructed breathing signal waveform, and calculating the human body breathing rate based on the reconstructed breathing signal waveform comprises: Performing discrete wavelet transform on the qualified air pressure signal fragments to decompose them into small qualified air pressure signal fragments in different frequency bands; Select a small segment of qualified air pressure signal in the low frequency band for wavelet reconstruction to obtain a reconstructed breathing signal waveform; The human body respiration rate is calculated based on the reconstructed respiration signal waveform.

7. The sleep monitoring method according to claim 6, characterized in that: The step of calculating the human body respiration rate based on the reconstructed respiration signal waveform comprises: Sequentially screening out a plurality of maximum values ​​in the reconstructed respiratory signal waveform in a normal respiratory cycle to determine a plurality of peaks of the reconstructed respiratory signal waveform; Calculating the time intervals between adjacent wave peaks, determining a plurality of effective time intervals from the time intervals between adjacent wave peaks based on a preset time value, thereby determining an effective maximum value; The human respiratory rate is calculated based on the number of effective maxima.

8. A sleep monitoring system, characterized in that: The system comprises: An air pressure signal acquisition module is used to acquire the initial air pressure signal of the airbag mattress in real time; A signal preprocessing module is used to preprocess the collected initial air pressure signal to obtain a processed air pressure signal; A sleep status monitoring module, used for caching the air pressure data of multiple processed air pressure signals to obtain processed air pressure signal segments, calculating the standard deviation corresponding to the air pressure data in the processed air pressure signal segments; when the standard deviation is less than a preset first threshold, calculating the peak point corresponding to the air pressure data in the processed air pressure signal segments, judging the user's bed status based on the peak point, and judging whether the cached processed air pressure signal segments are qualified according to the bed status; when the standard deviation is not less than the preset first threshold, counting the body movement during sleep according to the air pressure data in the processed air pressure signal segments; A respiratory rate monitoring module, used to cache the air pressure data of a plurality of qualified processed air pressure signal segments to obtain qualified air pressure signal segments; perform feature extraction processing on the qualified air pressure signal segments to obtain a reconstructed respiratory signal waveform, and calculate the human respiratory rate based on the reconstructed respiratory signal waveform; The sleep report generation module is used to generate a sleep report based on the statistical body movement during sleep and the calculated human breathing rate.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the sleep monitoring method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the sleep monitoring method according to any one of claims 1 to 7 are implemented.

Images