Sleep analysis method, apparatus, and electronic device

Abstract

The application provides a sleep analysis method and device and electronic equipment, and relates to the technical field of health monitoring. The method comprises the following steps: acquiring a radar echo signal, the radar echo signal being an echo signal received after a radar device sends a radar signal to a target object; acquiring body movement information and a breathing phase signal of the target object according to the radar echo signal; and performing sleep staging identification according to the body movement information and the breathing phase signal to acquire sleep analysis data. In the embodiment of the application, the non-contact device is used to detect the radar echo signal, so that the user experience can be improved, the change of sleep depth can be reflected, the sleep analysis data can be acquired, errors that may occur when a single information is used for determination can be avoided, and the flexibility and accuracy of sleep analysis can be improved.

Description

Technical Field

[0001] This application relates to the field of health monitoring technology, and in particular to a sleep analysis method, device, and electronic device. Background Technology

[0002] With the continuous development and improvement of medical technology, modern people are paying more and more attention to their sleep health. Sleep can be composed of several orderly stages, referred to as sleep stages, mainly including deep sleep, light sleep, and REM sleep. Sleep stages can be used to assess sleep quality, including the proportion of deep sleep and sleep cycles.

[0003] In related technologies, measurement primarily relies on contact devices attached to the human body to obtain real-time vital signs for sleep staging. These methods require direct or indirect contact with the body, which significantly limits their application scope, impacts user experience, and hinders long-term monitoring and sleep analysis. Non-contact devices, on the other hand, segment sleep by detecting body movements and their changes during sleep. However, their accuracy is low and they cannot fully reflect changes in sleep depth. Therefore, improving the flexibility and accuracy of sleep analysis without compromising user experience has become a crucial research direction. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art. Therefore, one objective of this application is to propose a sleep analysis method.

[0005] The second objective of this application is to propose a sleep analysis device.

[0006] The third objective of this application is to propose an electronic device.

[0007] The fourth objective of this application is to provide a non-transitory computer-readable storage medium.

[0008] The fifth objective of this application is to provide a computer program product.

[0009] To achieve the above objectives, a sleep analysis method is proposed in the first aspect of this application, comprising:

[0010] Acquire radar echo signals, which are the echo signals received after the radar equipment sends radar signals to the target object;

[0011] The target's motion information and respiratory phase signal are obtained based on the radar echo signal;

[0012] Sleep stages are identified based on body movement information and respiratory phase signals to obtain sleep analysis data.

[0013] This application embodiment utilizes non-contact devices to detect radar echo signals, which can improve user experience, reflect changes in sleep depth, and thus obtain sleep analysis data. This can avoid errors that may occur when making judgments based on a single piece of information, and improve the flexibility and accuracy of sleep analysis.

[0014] To achieve the above objectives, a second aspect of this application provides a sleep analysis device, comprising:

[0015] The first acquisition module is used to acquire radar echo signals, which are the echo signals received after the radar equipment sends radar signals to the target object.

[0016] The second acquisition module is used to acquire the body movement information and respiratory phase signal of the target object based on the radar echo signal;

[0017] The sleep analysis module is used to identify sleep stages based on body movement information and respiratory phase signals, and to obtain sleep analysis data.

[0018] To achieve the above objectives, a third aspect of this application provides an electronic device comprising:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the sleep analysis method provided in the first aspect embodiment of this application.

[0022] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions are used to cause a computer to execute the sleep analysis method provided in the first aspect of this application.

[0023] To achieve the above objectives, a fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the sleep analysis method provided in the first aspect of this application. Attached Figure Description

[0024] Figure 1 This is a flowchart of a sleep analysis method according to an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of a sleep analysis method according to an embodiment of this application;

[0026] Figure 3 This is a flowchart of a sleep analysis method according to an embodiment of this application;

[0027] Figure 4 This is a flowchart of a sleep analysis method according to an embodiment of this application;

[0028] Figure 5 This is a flowchart of a sleep analysis method according to an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of a sleep analysis method according to an embodiment of this application;

[0030] Figure 7 This is a structural block diagram of a sleep analysis device according to an embodiment of this application;

[0031] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0033] The sleep analysis method, apparatus, and electronic device of this application are described below with reference to the accompanying drawings.

[0034] Figure 1 This is a flowchart of a sleep analysis method according to an embodiment of this application, as shown below. Figure 1 As shown, the method includes the following steps:

[0035] S101, acquire radar echo signal. The radar echo signal is the echo signal received after the radar equipment sends a radar signal to the target object.

[0036] like Figure 2 As shown in this embodiment, the radar device 210 sends radar signals to the target object 220 and receives echo signals, i.e., radar echo signals. After receiving the radar echo signals, the radar device sends them to the control console 230 for sleep analysis. The radar device 210 can wirelessly communicate with the control console 230. The control console 230 can be a system platform or a server, serving as a control center primarily responsible for data processing and the transmission and reception of intelligent control commands.

[0037] Optionally, to improve the accuracy of sleep analysis, in this embodiment, the radar device can be a millimeter-wave radar device, which is a radar device that operates in the millimeter-wave band. Typically, millimeter waves operate in the 30–300 GHz frequency range (wavelength 1–10 mm) and can be used to distinguish and identify very small targets.

[0038] S102, acquires the target's motion information and respiratory phase signal based on the radar echo signal.

[0039] In some implementations, bandpass filters are used to filter radar echo signals to obtain the breathing phase signal of the target object.

[0040] In this embodiment, the motion information of the target object includes candidate locations and candidate times for the motion to occur. In some implementations, radar echo signals are analyzed. The signal energy of each part of the radar echo signal can reflect the motion energy of the target object. Based on the strength of the motion energy, candidate locations for the target object to move can be obtained, and then candidate times corresponding to the candidate locations can be obtained. The stronger the motion energy, the greater the probability that the target object will move; the weaker the motion energy, the less likely the target object will move.

[0041] S103 identifies sleep stages based on body movement information and respiratory phase signals, and obtains sleep analysis data.

[0042] Analyzing body movement information reveals that if the number of body movements per unit time is small, it indicates that the target has entered a sleep state; if the number of body movements per unit time is large, it indicates that the target has entered a waking state.

[0043] Furthermore, the respiratory phase signal during sleep is analyzed to confirm the respiratory depth of the target object. The respiratory depth can reflect whether the sleep state of the target object is stable. In this embodiment, sleep stages can be identified based on the respiratory depth, dividing the time range corresponding to the deep sleep period and the time range corresponding to the light sleep period during sleep.

[0044] Optionally, such as Figure 2 As shown, after acquiring sleep analysis data, the console 230 can send the sleep analysis data to the terminal device 240 via wireless communication.

[0045] In this embodiment, using non-contact devices to detect radar echo signals can improve the user experience. After acquiring the radar echo signals, the body movement information and respiratory phase signals of the target object are obtained based on the radar echo signals; sleep stage identification is performed based on the body movement information and respiratory phase signals to reflect changes in sleep depth, thereby obtaining sleep analysis data. This can avoid errors that may occur when making judgments based on a single piece of information, and improve the flexibility and accuracy of sleep analysis.

[0046] Figure 3 This is a flowchart of a sleep analysis method according to an embodiment of this application, as shown below. Figure 3 As shown, the method includes the following steps:

[0047] S301, acquire radar echo signal. The radar echo signal is the echo signal received after the radar equipment sends a radar signal to the target object.

[0048] S302 acquires the target's motion information and respiratory phase signal based on radar echo signals.

[0049] For a description of steps S301 to S302, please refer to the description in the above embodiments, which will not be repeated here.

[0050] S303, determine the resting state of the target object based on body movement information.

[0051] In some implementations, candidate positions in body motion information are clustered to estimate a distance interval in the radar detection range corresponding to the torso when the person is lying down. This allows for the determination of the distribution of candidate positions at different distances from the radar. Based on the clustered distribution of candidate positions, it can be determined which range interval the person is primarily located in in the radar detection range, thus identifying the target area where the target object is lying. In other words, the target area where the target object is lying is obtained based on the clustering results. Candidate positions within the target area are then identified as target positions, and the resting state of the target object is determined based on the target position and its corresponding target time.

[0052] Optionally, in this embodiment, the target time is traversed according to a preset time window to obtain a first target time belonging to the same time window and a first target position corresponding to the first target time. The number of body movements within the time window is determined based on the number of first target positions. The number of body movements is compared with a preset counting threshold. If the number of body movements is less than the counting threshold, the resting state of the target object is determined to be a transition from a waking state to a sleeping state. Optionally, the time without body movement can also be counted. If the number of body movements is less than the counting threshold, and the ratio of the time without body movement to the time window is greater than or equal to a preset proportion threshold, the resting state of the target object is determined to be a transition from a waking state to a sleeping state. Optionally, in this embodiment, the preset counting threshold can be 6 times, and the preset proportion threshold can be 80%.

[0053] Optionally, in response to the fact that the difference between any two adjacent target times in N consecutive target times is less than a preset time threshold, the resting state of the target object is determined to be a transition from sleep to wakefulness, where N is an integer greater than 2. Optionally, in this embodiment, the preset time threshold can be 5 minutes. Taking N as an example, if the difference between any two adjacent target times in 4 consecutive target times is less than 5 minutes, the resting state of the target object is determined to be a transition from sleep to wakefulness.

[0054] S304, in response to the target object's resting state being sleep state, obtain the target object's respiratory depth based on the respiratory phase signal.

[0055] In some implementations, the peaks and troughs in the respiratory phase signal are determined. The respiratory depth is then obtained based on the peaks and troughs.

[0056] Optionally, spline function interpolation is performed on the peak points to obtain the peak waveform, and spline function interpolation is performed on the trough points to obtain the trough waveform. The spline function can be transformed into a linear expression of the nodal function values, linearizing the parameters to be determined and obtaining the shape of the function in the optimal case. Optionally, the spline function can be of order zero, first, second, third, or higher. The breathing depth is obtained based on the difference between the peak waveform and the trough waveform; that is, the breathing depth is the difference between the peak waveform and the trough waveform.

[0057] S305 identifies sleep stages based on breathing depth and obtains sleep analysis data.

[0058] In some implementations, respiratory depth data between two body movements are selected, and the short-time variance sequence of the derivative of respiratory depth is obtained. Variance can measure the dispersion of respiratory depth data, thereby determining whether respiratory depth is stable over a short period of time. Sleep stages are identified based on the sequence values ​​in the short-time variance sequence to obtain sleep analysis data.

[0059] Optionally, the sequence values ​​in the short-time variance sequence are compared with a preset depth threshold. The time of the sequence value that is greater than or equal to the depth threshold is determined as the stable time, and the time of the sequence value that is less than the depth threshold is determined as the non-stationary time. Optionally, in this embodiment, the preset depth threshold can be 0.0002.

[0060] Optionally, a first time range of continuous stable time is obtained, and the first time range greater than or equal to a preset first time range threshold is determined as the deep sleep period, and the first time range less than the first time range threshold or the second time range where the unstable time is located is determined as the light sleep period.

[0061] In this embodiment, the resting state of the target object is determined based on body movement information. Responding to the target object's resting state being a sleep state, the respiratory depth of the target object is obtained based on respiratory phase signals. Sleep stages are then identified based on the respiratory depth to obtain sleep analysis data. This embodiment can improve user experience by combining the stability of respiratory depth to determine deep sleep and light sleep stages, avoiding errors that may occur when determining based on a single piece of information. It also improves the flexibility of sleep analysis and the accuracy of detecting resting state, deep sleep period, and light sleep period, reflecting changes in sleep depth.

[0062] Figure 4 This is a flowchart of a sleep analysis method according to an embodiment of this application, as shown below. Figure 4 As shown, the method includes the following steps:

[0063] S401, acquire radar echo signal. The radar echo signal is the echo signal received after the radar equipment sends a radar signal to the target object.

[0064] For a description of step S401, please refer to the above embodiments; it will not be repeated here.

[0065] S402, acquires Doppler information of radar echo signals.

[0066] In this embodiment of the application, Doppler information of the radar echo signal is obtained. The Doppler information can reflect the time difference and / or frequency difference between the radar transmitted signal and the radar echo signal when the user moves, thereby obtaining information about the user's movement speed.

[0067] S403 generates motion information of the target object based on Doppler information and radar echo signals.

[0068] In this embodiment of the application, the motion information is obtained through signal energy analysis and calculation, and mainly reflects the energy of rapid motion. Optionally, the motion information includes the motion energy of the target object.

[0069] In some implementations, radar echo signals are divided into real and imaginary parts, and the absolute value of the sum of the squares of the real and imaginary parts is used as the signal energy, i.e., motion information.

[0070] In some implementations, the signal energy at each range gate of the radar echo is calculated using the chirp signal of the radar echo, and then the average signal energy over a short period is calculated to obtain the kinetic energy of rapid motion. This motion information can reflect the rapid kinetic energy of body movements other than large movements like breathing. Optionally, to improve the accuracy of the motion information, the kinetic energy can be corrected based on Doppler information.

[0071] S404, obtains body motion information based on motion information.

[0072] Body movement information includes candidate locations where the target object performs body movement and their corresponding candidate times.

[0073] To improve the accuracy of motion information, some implementations binarize the motion information based on a preset energy threshold. The portion below the energy threshold, mainly background noise, is set to 0, while the portion above the energy threshold is set to 1, thus obtaining candidate motion information above the energy threshold. Candidate motion information includes candidate motion energy of the target object's motion. There is a mapping relationship between motion energy and position. In this embodiment, the mapping relationship between motion energy and position is obtained, and the candidate position corresponding to the candidate motion energy is determined based on the mapping relationship. The candidate time corresponding to the candidate position is then obtained.

[0074] S405 acquires the phase signal based on the phase of the radar echo signal.

[0075] Phase information of radar echo signals is extracted to obtain phase signals.

[0076] S406 determines the phase signal in the chest distance dimension as the respiratory and heartbeat signal.

[0077] S407 performs bandpass filtering on the respiratory and heartbeat signals according to the preset first frequency band to obtain the respiratory phase signal.

[0078] In this embodiment, the phase signal resolved by the radar wave along the chest distance dimension contains phase information of two movements: breathing and heartbeat. Since breathing and heartbeat are at different frequencies, breathing and heartbeat information can be extracted separately by bandpass filtering of different frequency bands. In this embodiment, the first frequency band is the frequency band corresponding to breathing. Therefore, by bandpass filtering the breathing and heartbeat signals using the preset first frequency band, the breathing phase signal can be obtained.

[0079] S408 identifies sleep stages based on body movement information and respiratory phase signals, and obtains sleep analysis data.

[0080] For a description of step S408, please refer to the above embodiments; it will not be repeated here.

[0081] In this embodiment, motion information of the target object is generated based on Doppler information and radar echo signals, thereby obtaining body motion information. The phase signal in the chest distance dimension is determined as the respiratory and heartbeat signal. The respiratory and heartbeat signal is bandpass filtered according to a preset first frequency band to obtain the respiratory phase signal. This embodiment can improve user experience, determine deep sleep and light sleep stages, avoid errors that may occur when making judgments based on a single piece of information, improve the flexibility of sleep analysis, and enhance the accuracy of detecting rest state, deep sleep period, and light sleep period, reflecting changes in sleep depth.

[0082] Figure 5 This is a flowchart of a sleep analysis method according to an embodiment of this application, as shown below. Figure 5 As shown, after determining the phase signal in the chest distance dimension as the respiratory and heartbeat signal, the following steps are also included:

[0083] S501 performs bandpass filtering on the respiratory and heartbeat signals according to the preset second frequency band to obtain the heartbeat phase signal.

[0084] In this embodiment, the phase signal resolved by the radar wave along the chest distance dimension contains phase information of two movements: breathing and heartbeat. Since breathing and heartbeat are at different frequencies, breathing and heartbeat information can be extracted separately by bandpass filtering of different frequency bands. In this embodiment, the second frequency band is the frequency band corresponding to the heartbeat. Therefore, by bandpass filtering the breathing and heartbeat signals using the preset second frequency band, the heartbeat phase signal can be obtained.

[0085] S502 obtains the cardiopulmonary resonant energy spectrum based on the respiratory phase signal and the heartbeat phase signal.

[0086] In some implementations, consistency analysis is performed on respiratory phase signals and heartbeat phase signals to obtain correlation coefficients. Consistency analysis can assess the data quality of respiratory phase signals and heartbeat phase signals, thereby determining whether sleep analysis data conforms to consistency constraints in different datasets, i.e., in the information respiratory phase signals and heartbeat phase signals.

[0087] In some implementations, the cross-spectral amplitude between the respiratory phase signal and the heartbeat phase signal is obtained; the cross-spectral amplitude can also measure the correlation between the respiratory phase signal and the heartbeat phase signal. The cardiopulmonary resonant energy spectrum is obtained by multiplying the correlation coefficient and the cross-spectral amplitude.

[0088] S503, obtain the cardiopulmonary coupling degree based on the cardiopulmonary resonance energy spectrum.

[0089] In some implementations, multiple spectral peaks of the cardiopulmonary resonant energy spectrum in a preset third frequency band, as well as the first spectral area of ​​the cardiopulmonary resonant energy spectrum in the third frequency band, are extracted. Optionally, the preset third frequency band is the sleep breathing frequency band; in the embodiments of this application, the third frequency band can be selected as 0.2–0.4 Hz.

[0090] For any given spectral peak among multiple spectral peaks, obtain the second spectral area within a preset bandwidth range where the peak lies. Obtain the sum of the second spectral areas, and use the ratio of the sum of the second spectral areas to the first spectral area as the cardiopulmonary coupling degree value of the target object.

[0091] S504 generates micro-intervention instructions based on cardiopulmonary coupling and sends them to the intervention device. The micro-intervention instructions are used to instruct the intervention device to perform sleep intervention.

[0092] To further improve the user experience, some implementations obtain the average value of multiple preset second time periods of cardiopulmonary coupling. The average value is compared with a preset first coupling threshold. If the average value is less than the first coupling threshold, a micro-intervention command is generated and sent to the intervention device. In this embodiment, after obtaining the current cardiopulmonary coupling value, 10 historical cardiopulmonary coupling values ​​can be read to obtain the average value of 11 cardiopulmonary coupling values. The average value is compared with a preset first coupling threshold. If the average value is less than the first coupling threshold, meaning the target object is in a low cardiopulmonary coupling state, it indicates that the target object is in a sleep or light sleep stage. A command to begin micro-intervention can then be sent to the intervention device via the console.

[0093] In some implementations, when the average value is greater than or equal to the first coupling threshold, it indicates that the target object is in a high cardiopulmonary coupling state, which means that the target object is in a deep sleep stage. At this time, a micro-intervention stop command is generated and sent to the intervention device. The micro-intervention stop command is used to instruct the intervention device to stop the micro-intervention.

[0094] Optionally, the micro-interventions mentioned in the embodiments of this application include, but are not limited to, intervention methods such as sound (sleep-aid music, environmental white noise, etc.) and vibration. However, the degree of intervention must be guaranteed to be within the range that does not disturb or affect the user or the user's sleep perception, so as to achieve the effect of intervening in sleep while remaining outside the range that the user can perceive, i.e., micro-intervention.

[0095] S505, obtain the sending time of the micro-intervention command, and obtain the first cardiopulmonary coupling degree within a preset second time range threshold after the sending time and the second cardiopulmonary coupling degree within a second time range threshold before the sending time.

[0096] To further improve the accuracy of sleep analysis, in this embodiment, the sleep analysis data is corrected by cardiopulmonary coupling degree.

[0097] S506, obtain the coupling difference between the first cardiopulmonary coupling degree and the second cardiopulmonary coupling degree.

[0098] Based on whether the cardiopulmonary coupling degree changes before and after the micro-intervention event, it can be further determined whether the sleep stage has undergone a certain degree of change.

[0099] S507, in response to the coupling degree difference being greater than the preset second coupling degree threshold, and the second time range threshold after the transmission time being a light sleep period, the light sleep period is corrected to a deep sleep period.

[0100] In some implementations, a coupling degree difference less than or equal to a preset second coupling degree threshold indicates that the sleep stage has not changed significantly, meaning that the sleep stage should remain consistent before and after the micro-intervention event.

[0101] In some implementations, if the coupling difference is greater than the preset second coupling threshold, it indicates that a significant change has occurred in the sleep stage, and the sleep stage has changed to a certain extent. If the preset second time range threshold after the transmission time is a light sleep period, the light sleep period will be corrected to a deep sleep period.

[0102] This application embodiment can improve user experience through micro-intervention. Based on whether the cardiopulmonary coupling degree changes before and after the micro-intervention event, it can further determine whether the sleep stage has changed to a certain extent, thereby correcting the sleep stage, further improving the accuracy of sleep analysis, avoiding errors that may occur when judging based on a single piece of information, improving the flexibility of sleep analysis and the accuracy of detecting deep sleep and light sleep stages, and reflecting changes in sleep depth.

[0103] Figure 6 This is a flowchart of a sleep analysis method according to an embodiment of this application, as shown below. Figure 6 As shown, in some implementations, such as Figure 2 As shown, the radar device 210 and the control console 230 can communicate wirelessly. The user can trigger the activation of the radar device 210, for example, by pressing a power button. After activation, the radar device 210 can monitor whether the target object 220 is within the target area using millimeter-wave radar echo signals. If the target object is within the target area, it can send a radar echo signal to the control console 230. Upon receiving the radar echo signal, the control console 230 sends an audio or text prompt to the user, asking if they are ready to sleep, awaiting the user's feedback. If the user indicates they are not ready to sleep, the micro-intervention control process is not initiated. If the user indicates they are ready to sleep, the control console 230 initiates the real-time micro-intervention control process. The micro-intervention control process is described in steps S501 to S507.

[0104] The embodiments of this application can utilize non-contact devices to detect radar echo signals, which can improve user experience, reflect changes in sleep depth, and thus obtain sleep analysis data. This can avoid errors that may occur when making judgments based on a single piece of information, and improve the flexibility and accuracy of sleep analysis.

[0105] like Figure 7 As shown, based on the same concept, this application also provides a sleep analysis device 700, including:

[0106] The first acquisition module 710 is used to acquire radar echo signals, which are the echo signals received after the radar equipment sends radar signals to the target object.

[0107] The second acquisition module 720 is used to acquire the body movement information and respiratory phase signal of the target object based on the radar echo signal;

[0108] The sleep analysis module 730 is used to identify sleep stages based on body movement information and respiratory phase signals, and to obtain sleep analysis data.

[0109] In some implementations, the sleep analysis module 730 is also used to: determine the resting state of the target object based on body movement information; in response to the target object's resting state being a sleep state, obtain the target object's respiratory depth based on the respiratory phase signal, and perform sleep stage identification based on the respiratory depth to obtain sleep analysis data.

[0110] In some implementations, the sleep analysis module 730 is also used to: determine the peaks and troughs in the respiratory phase signal; and obtain the respiratory depth based on the peaks and troughs.

[0111] In some implementations, the sleep analysis module 730 is also used to: perform spline function interpolation on the peak points to obtain the peak waveform, perform spline function interpolation on the trough points to obtain the trough waveform, and obtain the respiratory depth based on the difference between the peak waveform and the trough waveform.

[0112] In some implementations, the sleep analysis module 730 is also used to: obtain a short-time variance sequence of the derivative of the breathing depth; identify sleep stages based on the sequence values ​​in the short-time variance sequence, and obtain sleep analysis data.

[0113] In some implementations, the sleep analysis module 730 is also used to: compare the sequence values ​​in the short-time variance sequence with a preset depth threshold, determine the time of the sequence values ​​that are greater than or equal to the depth threshold as stable time, and determine the time of the sequence values ​​that are less than the depth threshold as unstable time; obtain a first time range of continuous stable time, determine the first time range that is greater than or equal to a preset first time range threshold as deep sleep period, and determine the first time range that is less than the first time range threshold or the second time range of unstable time as light sleep period.

[0114] In some implementations, the sleep analysis module 730 is also used to: cluster candidate positions in body movement information, obtain the target area where the target object is lying based on the clustering results; determine the candidate positions within the target area as the target positions; and determine the resting state of the target object based on the target positions and their corresponding target times.

[0115] In some implementations, the sleep analysis module 730 is also used to: traverse the target time according to a preset time window, obtain the first target time belonging to the same time window and the first target position corresponding to the first target time; determine the number of body movements within the time window based on the number of first target positions; compare the number of body movements with a preset counting threshold, and determine the target object's rest state as transitioning from a waking state to a sleeping state if the number of body movements is less than the counting threshold; and determine the target object's rest state as transitioning from a sleeping state to a waking state if the difference between any two adjacent target times in N consecutive target times is less than the preset time threshold, where N is an integer greater than 2.

[0116] In some implementations, the second acquisition module 720 is also used to: acquire Doppler information of the radar echo signal; generate motion information of the target object based on the Doppler information and the radar echo signal; and acquire body motion information based on the motion information.

[0117] In some implementations, motion information includes the motion energy of the target object's motion, and body motion information includes the candidate positions where the target object's body motion occurs and their corresponding candidate times. The second acquisition module 720 is further configured to: perform binarization processing on the motion information according to a preset energy threshold to acquire candidate motion information higher than the energy threshold, the candidate motion information including the candidate motion energy of the target object's motion; acquire the mapping relationship between motion energy and position; determine the candidate position corresponding to the candidate motion energy according to the mapping relationship, and acquire the candidate time corresponding to the candidate position.

[0118] In some implementations, the second acquisition module 720 is also used to: acquire a phase signal based on the phase of the radar echo signal; determine the phase signal in the chest distance dimension as a respiratory and heartbeat signal; and perform bandpass filtering on the respiratory and heartbeat signal according to a preset first frequency band to acquire a respiratory phase signal.

[0119] In some implementations, the sleep analysis module 730 is also used to: perform bandpass filtering on the breathing and heartbeat signals according to a preset second frequency band to obtain the heartbeat phase signal; obtain the cardiopulmonary resonant energy spectrum based on the breathing phase signal and the heartbeat phase signal; obtain the cardiopulmonary coupling degree based on the cardiopulmonary resonant energy spectrum; generate micro-intervention instructions based on the cardiopulmonary coupling degree and send them to the intervention device, the micro-intervention instructions being used to instruct the intervention device to perform sleep intervention.

[0120] In some implementations, the sleep analysis module 730 is also used to: perform consistency analysis on the respiratory phase signal and the heartbeat phase signal, obtain the correlation coefficient, and obtain the cross-spectral amplitude between the respiratory phase signal and the heartbeat phase signal; and obtain the cardiopulmonary resonant energy spectrum based on the product of the correlation coefficient and the cross-spectral amplitude.

[0121] In some implementations, the sleep analysis module 730 is also used to: extract multiple spectral peaks of the cardiopulmonary resonant energy spectrum in a preset third frequency band, and the first spectral area of ​​the cardiopulmonary resonant energy spectrum in the third frequency band; for any one of the multiple spectral peaks, obtain the second spectral area of ​​the preset bandwidth range where the spectral peak is located; and obtain the cardiopulmonary coupling degree based on the ratio of the sum of the second spectral areas to the first spectral area.

[0122] In some implementations, the sleep analysis module 730 is also used to: obtain the average value of cardiopulmonary coupling for multiple preset second time periods; compare the average value with a preset first coupling threshold; and generate a micro-intervention instruction and send it to the intervention device in response to the average value being less than the first coupling threshold.

[0123] In some implementations, the sleep analysis module 730 is also used to: generate a micro-intervention stop command and send it to the intervention device in response to an average value being greater than or equal to a first coupling degree threshold. The micro-intervention stop command is used to instruct the intervention device to stop the micro-intervention.

[0124] In some implementations, the sleep analysis module 730 is also used to: obtain the sending time of the micro-intervention command, and obtain the first cardiopulmonary coupling degree within a preset second time range threshold after the sending time and the second cardiopulmonary coupling degree within a second time range threshold before the sending time; obtain the coupling degree difference between the first cardiopulmonary coupling degree and the second cardiopulmonary coupling degree; and, in response to the coupling degree difference being greater than the preset second coupling degree threshold, and the preset second time range threshold after the sending time being a light sleep period, correct the light sleep period to a deep sleep period.

[0125] This application embodiment utilizes non-contact devices to detect radar echo signals, which can improve user experience, reflect changes in sleep depth, and thus obtain sleep analysis data. This can avoid errors that may occur when making judgments based on a single piece of information, and improve the flexibility and accuracy of sleep analysis.

[0126] Based on the same concept, embodiments of this application also provide an electronic device.

[0127] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 8 As shown, the electronic device 800 includes a memory 810, a processor 820, and a computer program product stored in the memory 810 and executable on the processor 820. When the processor executes the computer program, it implements the aforementioned sleep analysis method.

[0128] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0130] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0131] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0132] Based on the same concept, embodiments of this application also provide a computer-readable storage medium storing computer instructions thereon, wherein the computer instructions are used to cause a computer to execute the sleep analysis method in the above embodiments.

[0133] Based on the same concept, embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, represents the sleep analysis method described in the above embodiments.

[0134] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. This application can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0135] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0136] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0137] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A sleep analysis method, characterized in that, include: Acquire radar echo signals, wherein the radar echo signals are the echo signals received after the radar equipment sends radar signals to the target object; The target object's motion information and respiratory phase signal are obtained based on the radar echo signal; Sleep stages are identified based on the body movement information and the respiratory phase signal to obtain sleep analysis data; The step of identifying sleep stages based on the body movement information and the respiratory phase signal to obtain sleep analysis data includes: The resting state of the target object is determined based on the body movement information; In response to the target object's resting state being a sleep state, the respiratory depth of the target object is obtained based on the respiratory phase signal; Sleep stages are identified based on the breathing depth to obtain sleep analysis data; The process of acquiring the respiratory phase signal of the target object based on the radar echo signal includes: The phase signal is obtained based on the phase of the radar echo signal; The phase signal in the chest distance dimension is determined as the respiratory and heartbeat signal; The respiratory and heartbeat signals are bandpass filtered according to a preset first frequency band to obtain a respiratory phase signal; After determining the phase signal in the chest distance dimension as a respiratory and heartbeat signal, the method further includes: The respiratory and heartbeat signals are bandpass filtered according to a preset second frequency band to obtain the heartbeat phase signal; The cardiopulmonary resonant energy spectrum is obtained based on the respiratory phase signal and the heartbeat phase signal; The cardiopulmonary coupling degree is obtained based on the cardiopulmonary resonance energy spectrum. Micro-intervention instructions are generated based on the cardiopulmonary coupling degree and sent to the intervention device. The micro-intervention instructions are used to instruct the intervention device to perform sleep intervention. After identifying sleep stages based on the breathing depth and obtaining sleep analysis data, the process further includes: Obtain the sending time of the micro-intervention command, and obtain the first cardiopulmonary coupling degree within a preset second time range threshold after the sending time and the second cardiopulmonary coupling degree within the second time range threshold before the sending time; Obtain the coupling difference between the first cardiopulmonary coupling degree and the second cardiopulmonary coupling degree; In response to the coupling difference being greater than a preset second coupling threshold, and the second time range threshold after the transmission time being a light sleep period, the light sleep period is corrected to a deep sleep period.

2. The method according to claim 1, characterized in that, The step of obtaining the respiratory depth of the target object based on the respiratory phase signal includes: Determine the peak and trough points in the respiratory phase signal; The breathing depth is obtained based on the peak and trough points.

3. The method according to claim 2, characterized in that, The step of obtaining the breathing depth based on the peak and trough points includes: Spline function interpolation is performed on the peak points to obtain the peak waveform, and spline function interpolation is performed on the trough points to obtain the trough waveform; The breathing depth is obtained based on the difference between the peak waveform and the trough waveform.

4. The method according to claim 1, characterized in that, The step of identifying sleep stages based on the breathing depth and obtaining sleep analysis data includes: Obtain the short-time variance sequence of the derivative of the breathing depth; Sleep stages are identified based on the sequence values ​​in the short-time variance sequence to obtain sleep analysis data.

5. The method according to claim 4, characterized in that, The step of identifying sleep stages based on sequence values ​​in the short-time variance sequence and obtaining sleep analysis data includes: The sequence values ​​in the short-time variance sequence are compared with a preset depth threshold. The time of the sequence value that is greater than or equal to the depth threshold is determined as the stable time, and the time of the sequence value that is less than the depth threshold is determined as the non-stable time. A first time range of continuous stable time is obtained, and the first time range that is greater than or equal to a preset first time range threshold is determined as a deep sleep period, and the first time range that is less than the first time range threshold or the second time range in which the unstable time is located is determined as a light sleep period.

6. The method according to claim 1, characterized in that, Determining the resting state of the target object based on the body movement information includes: The candidate locations in the body movement information are clustered, and the target area where the target object is lying is obtained based on the clustering results; The candidate locations within the target area are determined as the target locations; The resting state of the target object is determined based on the target location and its corresponding target time.

7. The method according to claim 6, characterized in that, Determining the resting state of the target object based on the target location and its corresponding target time includes: The target time is traversed according to a preset time window to obtain the first target time belonging to the same time window and the first target position corresponding to the first target time. The number of body movements within the time window is determined based on the number of the first target locations; Based on the comparison between the number of body movements and a preset counting threshold, in response to the number of body movements being less than the counting threshold, the resting state of the target object is determined to be transitioning from a waking state to a sleeping state; In response to N consecutive target times, if the difference between any two adjacent target times is less than a preset time threshold, the resting state of the target object is determined to be transitioning from a sleep state to a wakeful state, where N is an integer greater than 2.

8. The method according to claim 1, characterized in that, The step of obtaining the motion information of the target object based on the radar echo signal includes: Obtain the Doppler information of the radar echo signal; The motion information of the target object is generated based on the Doppler information and the radar echo signal; The body movement information is obtained based on the motion information.

9. The method according to claim 8, characterized in that, The motion information includes the motion energy of the target object's motion, and the body movement information includes candidate positions where the target object's body movement occurs and their corresponding candidate times. Obtaining the body movement information based on the motion information includes: The motion information is binarized according to a preset energy threshold to obtain candidate motion information that is higher than the energy threshold. The candidate motion information includes candidate motion energy of the target object's motion. To obtain the mapping relationship between kinetic energy and position; Based on the mapping relationship, the candidate positions corresponding to the candidate motion energies are determined, and the candidate times corresponding to the candidate positions are obtained.

10. The method according to claim 1, characterized in that, The step of obtaining the cardiopulmonary resonant energy spectrum based on the respiratory phase signal and the heartbeat phase signal includes: Consistency analysis is performed on the respiratory phase signal and the heartbeat phase signal to obtain the correlation coefficient, and the cross-spectral amplitude between the respiratory phase signal and the heartbeat phase signal is obtained. The cardiopulmonary resonant energy spectrum is obtained by multiplying the correlation coefficient and the cross spectrum amplitude.

11. The method according to claim 1, characterized in that, The step of obtaining the cardiopulmonary coupling degree based on the cardiopulmonary resonance energy spectrum includes: Extract multiple spectral peaks of the cardiopulmonary resonant energy spectrum in a preset third frequency band, and the first spectral area of ​​the cardiopulmonary resonant energy spectrum in the third frequency band; For any one of the multiple spectral peaks, obtain the second spectral area of ​​the preset bandwidth range in which the spectral peak is located; The cardiopulmonary coupling degree is obtained by the ratio of the sum of the second spectral areas to the first spectral area.

12. The method according to claim 1, characterized in that, The step of generating micro-intervention instructions based on the cardiopulmonary coupling degree and sending them to the intervention device includes: Obtain the average cardiopulmonary coupling degree of multiple preset second time periods; The average value is compared with a preset first coupling threshold. If the average value is less than the first coupling threshold, the micro-intervention instruction is generated and sent to the intervention device.

13. The method according to claim 12, characterized in that, Also includes: In response to the average value being greater than or equal to the first coupling degree threshold, a micro-intervention stop instruction is generated and sent to the intervention device, the micro-intervention stop instruction being used to instruct the intervention device to stop the micro-intervention.

14. A sleep analysis device, characterized in that, include: The first acquisition module is used to acquire radar echo signals, which are echo signals received after the radar equipment sends radar signals to the target object. The second acquisition module is used to acquire the body movement information and respiratory phase signal of the target object based on the radar echo signal; The sleep analysis module is used to identify sleep stages based on the body movement information and the respiratory phase signal, and to obtain sleep analysis data. The sleep analysis module is further configured to determine the resting state of the target object based on the body movement information; in response to the target object's resting state being a sleep state, to obtain the target object's respiratory depth based on the respiratory phase signal; and to perform sleep stage identification based on the respiratory depth to obtain sleep analysis data. The second acquisition module is further configured to acquire a phase signal based on the phase of the radar echo signal; determine the phase signal in the chest distance dimension as a respiratory and heartbeat signal; and perform bandpass filtering on the respiratory and heartbeat signal according to a preset first frequency band to acquire a respiratory phase signal. The sleep analysis module is further configured to perform bandpass filtering on the breathing and heartbeat signals according to a preset second frequency band to obtain a heartbeat phase signal; obtain a cardiopulmonary resonant energy spectrum based on the breathing phase signal and the heartbeat phase signal; obtain a cardiopulmonary coupling degree based on the cardiopulmonary resonant energy spectrum; generate a micro-intervention command based on the cardiopulmonary coupling degree and send it to the intervention device, wherein the micro-intervention command is used to instruct the intervention device to perform sleep intervention; The sleep analysis module is further configured to obtain the sending time of the micro-intervention command, and obtain the first cardiopulmonary coupling degree within a preset second time range threshold after the sending time and the second cardiopulmonary coupling degree within the second time range threshold before the sending time; and obtain the coupling degree difference between the first cardiopulmonary coupling degree and the second cardiopulmonary coupling degree. In response to the coupling difference being greater than a preset second coupling threshold, and the second time range threshold after the transmission time being a light sleep period, the light sleep period is corrected to a deep sleep period.

15. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-13.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-13.

17. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-13.

Images