Sleep abnormality detection method and apparatus, electronic device, and computer readable medium

Abstract

The application discloses a sleep anomaly detection method and device, electronic equipment and computer readable medium, relates to the technical field of health monitoring, and the method comprises the steps that an echo pulse signal is acquired, and corresponding distance gates are determined; body movement information corresponding to each distance gate at each preset time point is extracted, and a heat map is generated; boundary information corresponding to each distance gate in the heat map is determined based on the body movement information, and body movement parts corresponding to each distance gate are determined according to the boundary information; body movement intensity information corresponding to the boundary information is acquired, a target body movement part is determined from each body movement part, a target body movement time period is determined according to the body movement intensity information and the target body movement part; a body movement phase signal corresponding to the target body movement part is acquired, and an abnormal body movement phase signal in the body movement phase signal is determined according to the target body movement time period and the body movement phase signal. The intervention interference of other sound signals is avoided, and the accuracy of detecting the anomaly of a user in a preset time period is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health monitoring, and particularly relates to a sleep anomaly detection method and device, an electronic device and a computer readable medium. BACKGROUND

[0002] At present, with the continuous development and improvement of medical technology, modern people pay more and more attention to respiratory health problems that may occur at any time in their sleep. Coughing, as an abnormal respiratory state that may occur during sleep, is increasingly valued, especially in the health monitoring process of the elderly. The existing cough detection technology in sleep only records a single signal of sound, and then uses traditional analysis methods or artificial intelligence methods to detect the cough sound signal as an abnormal sound signal, which cannot protect the privacy of the user or patient; it is easily disturbed by external sounds, such as when coughing, other sound signals intervene, which greatly affects the accuracy.

[0003] In the process of implementing the present application, the inventors found that the method for detecting anomalies in the related art has low accuracy. SUMMARY

[0004] Therefore, the embodiments of the present application provide a sleep anomaly detection method and device, an electronic device and a computer readable medium, which can solve the problem of low accuracy of the existing method for detecting anomalies.

[0005] To achieve the above object, according to an aspect of an embodiment of the present application, a sleep anomaly detection method is provided, comprising:

[0006] An echo pulse signal is obtained, and then each distance gate corresponding to the echo pulse signal is determined;

[0007] Body movement information corresponding to each distance gate at each preset time point is extracted from the echo pulse signal, and then a heat map is generated;

[0008] Boundary information corresponding to each distance gate in the heat map is determined based on the body movement information, and a body movement part corresponding to each distance gate is determined according to the boundary information;

[0009] Body movement intensity information corresponding to the boundary information is obtained, a target body movement part is determined from each body movement part, and then a target body movement time period is determined according to the body movement intensity information and the target body movement part;

[0010] A body movement phase signal corresponding to the target body movement part is obtained, and then an abnormal body movement phase signal in the body movement phase signal is determined according to the target body movement time period and the body movement phase signal.

[0011] Optionally, the heat map is generated, comprising:

[0012] Taking each preset time point as the abscissa and each distance gate as the ordinate, a coordinate system is constructed;

[0013] The position of the body motion part corresponding to the body motion information corresponding to each distance gate is determined, and a heat map is generated in the coordinate system based on the positions of each body motion part.

[0014] Optionally, the body motion information corresponding to each distance gate at each preset time point is extracted from the echo pulse signal, including:

[0015] Based on the preset noise signal threshold, the echo pulse signal is denoised to obtain a denoised echo pulse signal;

[0016] The body motion information corresponding to each distance gate at each preset time point is extracted from the denoised echo pulse signal.

[0017] Optionally, the body motion part corresponding to each distance gate is determined according to the boundary information, including:

[0018] Based on the denoised heat map, the body motion energy value corresponding to each distance gate is obtained, the body motion energy value of each distance gate exceeding the preset body motion energy threshold is retained, and then the time integral of the body motion energy value corresponding to each distance gate is calculated;

[0019] According to the time integral, the distribution position of the distance gate corresponding to each body motion part in the target state is calculated;

[0020] The body motion part corresponding to each distance gate is determined according to the boundary information corresponding to the distribution position.

[0021] Optionally, the target body motion time period is determined, including:

[0022] The time period in which the body motion intensity corresponding to the body motion intensity information of the target body motion part exceeds the body motion intensity threshold and other body motion parts do not have corresponding body motion intensity information is determined as the target body motion time period.

[0023] Optionally, the body motion phase signal corresponding to the target body motion part is obtained, including:

[0024] The first body motion phase signal and the second body motion phase signal corresponding to the target body motion part are obtained;

[0025] The body motion phase signal is generated according to the first body motion phase signal and the second body motion phase signal.

[0026] Optionally, the abnormal body motion phase signal in the body motion phase signal is determined, including:

[0027] The wave crest and the wave trough in the first body motion phase signal, and the wave crest time corresponding to the wave crest and the wave trough time corresponding to the wave trough are extracted;

[0028] a first difference value between the peak and the valley is calculated, and a second difference value between the peak time and the valley time is calculated;

[0029] the signal corresponding to the first difference value greater than the first threshold value and the second difference value less than the second threshold value in the first body motion phase signal is determined as the abnormal body motion phase signal.

[0030] In addition, the present application also provides a sleep abnormality detection device, comprising:

[0031] a signal acquisition unit configured to acquire an echo pulse signal, and determine each distance gate corresponding to the echo pulse signal;

[0032] a heat map generation unit configured to extract body motion information corresponding to each distance gate at each preset time point from the echo pulse signal, and generate a heat map;

[0033] a body motion part determination unit configured to determine boundary information corresponding to each distance gate in the heat map based on the body motion information, and determine a body motion part corresponding to each distance gate according to the boundary information;

[0034] a target body motion time period determination unit configured to acquire body motion intensity information corresponding to the boundary information, determine a target body motion part from each body motion part, and determine a target body motion time period according to the body motion intensity information and the target body motion part;

[0035] an abnormality detection unit configured to acquire a body motion phase signal corresponding to the target body motion part, and determine an abnormal body motion phase signal in the body motion phase signal according to the target body motion time period and the body motion phase signal.

[0036] Optionally, the heat map generation unit is further configured to:

[0037] construct a coordinate system with each preset time point as the horizontal coordinate and each distance gate as the vertical coordinate;

[0038] determine the position of the body motion part corresponding to the body motion information corresponding to each distance gate, and generate the heat map in the coordinate system based on the position of each body motion part.

[0039] Optionally, the heat map generation unit is further configured to:

[0040] perform denoising processing on the echo pulse signal based on a preset noise signal threshold to obtain a denoised echo pulse signal;

[0041] extract the body motion information corresponding to each distance gate at each preset time point from the denoised echo pulse signal.

[0042] Optionally, the body movement part determination unit is further configured to:

[0043] Based on the denoised heat map, the body movement energy values corresponding to each distance gate are obtained, the body movement energy values of each distance gate exceeding a preset body movement energy threshold are retained, and then the time integral of the body movement energy values corresponding to each distance gate is calculated;

[0044] According to the time integral, the distribution positions of the distance gates corresponding to each body movement part in the target state are calculated;

[0045] According to the boundary information corresponding to the distribution positions, the body movement parts corresponding to each distance gate are determined.

[0046] Optionally, the target body movement time period determination unit is further configured to:

[0047] The time period in which the body movement intensity corresponding to the target body movement part exceeds the body movement intensity threshold and other body movement parts do not have corresponding body movement intensity information is determined as the target body movement time period.

[0048] Optionally, the anomaly detection unit is further configured to:

[0049] Obtain the first body movement phase signal and the second body movement phase signal corresponding to the target body movement part;

[0050] Generate the body movement phase signal according to the first body movement phase signal and the second body movement phase signal.

[0051] Optionally, the anomaly detection unit is further configured to:

[0052] Extract the wave peaks and wave troughs in the first body movement phase signal, and the wave peak time corresponding to the wave peaks and the wave trough time corresponding to the wave troughs;

[0053] Calculate the first difference value between the wave peaks and the wave troughs, and calculate the second difference value between the wave peak time and the wave trough time;

[0054] Determine the signal in the first body movement phase signal corresponding to the first difference value greater than the first threshold and the second difference value less than the second threshold as the abnormal body movement phase signal.

[0055] In addition, the present application also provides a sleep anomaly detection electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the sleep anomaly detection method as described above.

[0056] In addition, the present application also provides a computer readable medium having a computer program stored thereon, the program being executed by a processor to implement the sleep anomaly detection method as described above.

[0057] One embodiment of the above application has the following advantages or benefits: the present application obtains echo pulse signals, and then determines each distance gate corresponding to the echo pulse signals; extracts body motion information corresponding to each distance gate at each preset time point from the echo pulse signals, and then generates a thermogram; determines boundary information corresponding to each distance gate in the thermogram based on the body motion information, and determines a body motion part corresponding to each distance gate according to the boundary information; obtains body motion intensity information corresponding to the boundary information, determines a target body motion part from each body motion part, and then determines a target body motion time period according to the body motion intensity information and the target body motion part; obtains a body motion phase signal corresponding to the target body motion part, and then determines an abnormal body motion phase signal in the body motion phase signal according to the target body motion time period and the body motion phase signal. The intervention interference of other sound signals is avoided, and the accuracy of detecting the abnormality of the user in the preset time period is effectively improved.

[0058] Further effects of the above non-conventional optional mode will be described in the following in combination with the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0059] The accompanying drawings are used to better understand the present application, and do not constitute undue limitations on the present application. Among them:

[0060] Figure 1 is a schematic diagram of the main process of the sleep abnormality detection method according to an embodiment of the present application;

[0061] Figure 2 is a schematic diagram of the main process of the sleep abnormality detection method according to an embodiment of the present application;

[0062] Figure 3 is an algorithm flowchart of the sleep abnormality detection method according to an embodiment of the present application;

[0063] Figure 4 is a reinforced body motion index thermogram of a user of the sleep abnormality detection method according to an embodiment of the present application;

[0064] Figure 5 is a schematic diagram of the main unit of the sleep abnormality detection device according to an embodiment of the present application;

[0065] Figure 6 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0066] Figure 7 is a structural schematic diagram of a computer system of a terminal device or a server suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0067] Exemplary embodiments of the present application are described herein with reference to the accompanying drawings, which are cited by way of example. Various details of the embodiments of the present application are described herein in order to provide a thorough understanding thereof. It will be apparent, however, to those skilled in the art that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, the description set forth herein focuses on the principles of the present application. The description of known functions and constructions are omitted for clarity and conciseness. The acquisition, storage, use, processing, etc. of data in the technical solutions of the present application comply with relevant provisions of national laws and regulations.

[0068] Figure 1 is a schematic diagram of the main process of the sleep abnormality detection method according to an embodiment of the present application, as Figure 1 indicated, the sleep abnormality detection method comprises:

[0069] In step S101, an echo pulse signal is acquired, and then each distance gate corresponding to the echo pulse signal is determined.

[0070] In the present embodiment, the execution subject (for example, which can be a server) of the sleep abnormality detection method can acquire the echo pulse signal through wired connection or wireless connection. The echo pulse signal may, for example, be the echo pulse signal returned after detecting each body part of the user by using a millimeter wave radar. After acquiring the echo pulse signal, the execution subject can determine each distance gate corresponding to the echo pulse signal. The distance gate refers to a sampling point in the sampling data after pulse compression, and each sampling point has its own distance gate. Each sampling point may, for example, be each body part to be detected of the user. The distance gate can be used to define the distance span of each body part to be detected of the user and the millimeter wave radar.

[0071] In step S102, body movement information corresponding to each distance gate at each preset time point is extracted from the echo pulse signal, and then a heat map is generated.

[0072] The body movement in the present embodiment may, for example, refer to coughing, pulse jumping, or heart beating, etc. Each preset time point may, for example, be each detection time point in a whole night of a day, such as Figure 4 indicated, 02:37:44, 02:38:02, 02:39:05, and 02:40:08. The body movement information corresponding to each distance gate at each preset time point is extracted from the echo pulse signal, which specifically refers to the reinforced body movement index (RBMI) information of the body movement state of each body part to be detected of the user in the echo pulse signal, i.e. T represents the whole night monitoring time. The execution subject can determine each distance gate and the body movement information corresponding to each distance gate from the echo pulse signal, such asFigure 4 A1, A2, A3, and A4 in the figure are as follows Figure 4 The body motion information corresponding to the boundaries a, b, and c of the distance gate shown is used to generate the following: Figure 4 The heatmap shown can be in color or black and white; this embodiment does not specifically limit the color of the heatmap. In the generated heatmap, the horizontal axis represents the detection time, and the vertical axis represents each distance gate.

[0073] Specifically, the body motion information corresponding to each distance gate at each preset time point is extracted from the echo pulse signal, including:

[0074] Based on a preset noise threshold, the echo pulse signal is denoised to obtain a denoised echo pulse signal. For example, taking the detection of a user's cough as an example, the RBMI signal, representing body motion information extracted over a whole night of monitoring, is used. Thresholding is performed to remove useless noise information. The highest percentile of each distance gate detected by the millimeter-wave radar during the entire monitoring period is taken as the noise detection threshold for that corresponding distance gate, i.e., the preset noise signal threshold (here, the 90th percentile can be used as the preset noise signal threshold to achieve a better noise reduction effect). Locations exceeding this preset noise signal threshold (the areas enclosed by the horizontal and vertical axes in the heatmap correspond to the various body parts of the user to be detected) and time periods are assigned a value of 1, while the rest are assigned a value of 0, in order to binarize the heatmap.

[0075] Extract the body motion information corresponding to each distance gate at each preset time point from the denoised echo pulse signal.

[0076] Binarization can yield relatively clean user motion information. Extract body movement information of each door at each preset time point from relatively clean user body movement information.

[0077] Step S103: Determine the boundary information corresponding to each distance gate in the heat map based on the body motion information, and determine the body motion part corresponding to each distance gate based on the boundary information.

[0078] Specifically, determining the body movement parts corresponding to each distance gate based on boundary information includes: obtaining the body movement energy value corresponding to each distance gate based on the denoised heatmap, retaining the body movement energy values ​​of each distance gate that exceed a preset body movement energy threshold, and then calculating the time integral of the body movement energy value corresponding to each distance gate; calculating the distribution position of the distance gate corresponding to each body movement part in the target state based on the time integral; and determining the body movement parts corresponding to each distance gate based on the boundary information corresponding to the distribution position.

[0079] RBMI body movement information in the heat map after denoising and binarization processing The estimation of the distance gate where the body part is located is specifically: on the basis of the denoised RBMI signal, a higher body movement energy threshold is selected to retain information above a certain body movement intensity, and then time integration is performed on each distance gate to obtain the time integration of the body movement energy in the distance gate dimension, so that the approximate distribution range of the distance gate where the human body is located when sleeping on the bed can be estimated, that is, the distance gate where the head is located and the distance gate where the feet are located are estimated, and the distance gate where the position closest to the millimeter wave radar has body movement intensity is the distance gate where the head is located, and the distance gate where the farthest position has body movement intensity is the distance gate where the feet are located. By estimating the head distance gate and the foot distance gate position, the approximate positions of the chest, abdomen and knee of the human body are further estimated in combination with the structure proportion of the human body. For example Figure 4 The five different virtual-real boundaries a, b, c, d and e contained in the heat map are the boundaries of the positions of the five important body parts estimated to change over time (the boundaries can be polyline), wherein the a, b, c, d and e boundaries respectively represent the distance span changes of different distance gates with respect to the millimeter wave radar as time changes. Each of the a, b, c, d and e boundaries corresponds to a distance gate. As can be seen from the above, according to the boundary information, the body movement part corresponding to each distance gate can be determined, specifically: the a, b, c, d and e boundaries respectively represent the estimated positions of the head, chest, abdomen, knee and foot distance gates.

[0080] In step S104, the body movement intensity information corresponding to the boundary information is obtained, and a target body movement part is determined from the body movement parts, and then the target body movement time period is determined according to the body movement intensity information and the target body movement part.

[0081] For example, the body movement intensity information corresponding to the boundary information obtained can be the body movement intensity information located on the boundary or between two boundaries. The execution subject can determine a target body movement part from the body movement parts, for example, the execution subject can determine the target body movement part from the five body movement parts of the head, chest, abdomen, knee and feet, for example, the chest and abdomen. Then, the execution subject can screen the body movement intensity information corresponding to the vigorous movement of the chest and abdomen from the body movement intensity information corresponding to the boundary information, and then determine the time period corresponding to the vigorous movement of the chest and abdomen in the heat map as the target body movement time period. Taking the detection of the user's cough as an example, the target body movement time period is the time period corresponding to the vigorous cough in the heat map, for example Figure 4 the time period of 02:37:44-02:38:02 in the heat map.

[0082] Specifically, determining the target body movement time period includes:

[0083] The time period in which the body motion intensity information corresponding to the target body motion part exceeds the body motion intensity threshold and other body motion parts do not have corresponding body motion intensity information is determined as the target body motion time period.

[0084] For example, in the process of cough detection, the distance G at which the chest and abdomen of the user move violently is roughly located by the body part estimation technology. cough , and the time period t at which the cough occurs caugh The time period in which the body motion signal intensity between the chest and abdomen is strong but the body motion signal intensity between other parts is not strong is accurately located as the time period in which the cough is likely to occur, for example, the time period 02:37:44-02:38:02 in Figure 4 , which is taken as the target body motion time period.

[0085] In step S105, the body motion phase signal corresponding to the target body motion part is obtained, and then the abnormal body motion phase signal in the body motion phase signal is determined according to the target body motion time period and the body motion phase signal.

[0086] For example, the target body motion part can be the chest and abdomen, and the body motion phase signal corresponding to the target body motion part can be the breathing and heartbeat phase signal. Specifically, the breathing phase signal is obtained by calculating the phase information in the breathing and heartbeat signal. After the millimeter wave radar transmits a pulse signal, signals (including amplitude and phase information) at different positions (referred to as distance gates or distance dimensions) from far to near are obtained, the signal at the chest distance gate is found, which is called the breathing and heartbeat signal. At this time, the signal represents the movement of the chest position and contains low-frequency breathing movement and high-frequency heartbeat vibration, so it is called the breathing and heartbeat signal. The breathing phase signal is obtained by calculating the phase information of the signal and then performing band-pass filtering processing in the breathing frequency band.

[0087] The abnormal body motion phase signal, for example, one or more of the abnormal breathing phase signal or the abnormal heartbeat phase signal or the abnormal breathing and heartbeat phase signal, can be obtained by cutting out the signal corresponding to the target body motion time period in the body motion phase signal. The type and number of abnormal body motion phase signals are not limited in the embodiments of the present application.

[0088] Specifically, the body motion phase signal corresponding to the target body motion part is obtained, including:

[0089] Acquire a first body movement phase signal and a second body movement phase signal corresponding to the target body movement part; generate a body movement phase signal based on the first and second body movement phase signals. The first body movement phase signal may be, for example, a respiratory phase signal, and the second body movement phase signal may be, for example, a heartbeat phase signal. Combine the first and second body movement phase signals in a preset format to obtain the combined body movement phase signal, which contains information from both the first and second body movement phase signals.

[0090] Specifically, identifying abnormal body motion phase signals within the body motion phase signal includes:

[0091] Extract the peaks and troughs, as well as the peak times and trough times, from the first body motion phase signal. If the body motion phase signal is a respiratory-heartbeat phase signal, and the first body motion phase signal is a respiratory phase signal, then perform bandpass filtering on the respiratory band to extract the respiratory phase signal. Here, the selected respiratory bandpass filtering range can be 0.1–0.8 Hz. When the first body motion phase signal is a respiratory phase signal, the peaks and troughs, as well as the peak times and trough times, can be extracted within the target body motion time period (e.g., [missing information]). Figure 4 The peaks and troughs in the respiratory phase signal during the time period from 02:37:44 to 02:38:02, as well as the peak time corresponding to the peak and the trough time corresponding to the trough.

[0092] The first difference between the peak and the trough is calculated, and the second difference between the peak time and the trough time is calculated.

[0093] The signal in the first body motion phase signal whose first difference value is greater than the first threshold and whose second difference value is less than the second threshold is identified as an abnormal body motion phase signal.

[0094] For example, extract the peak P from the respiratory phase signal during the target body movement time period. i and wave valley V i And the time corresponding to the peak and trough respectively. and Calculate the absolute value of the difference between the corresponding peaks and troughs, denoted as ΔA. i =|P i -V i |, which is the first difference value, represents the user's breathing depth as detected by millimeter-wave radar at each monitoring point, and the corresponding time difference is calculated and denoted as . This is the second difference value, which represents the rate of exhalation or inhalation in each breath. ΔA is extracted from the respiratory phase signal. j Greater than the first threshold and ΔT iWhen the corresponding respiratory phase signal is less than the second threshold value, the respiratory phase signal is the respiratory phase signal when the cough (i.e., abnormal body movement) occurs, that is, the abnormal body movement phase signal.

[0095] The embodiment determines each distance gate corresponding to the echo pulse signal by obtaining the echo pulse signal; extracts body movement information corresponding to each distance gate at each preset time point from the echo pulse signal, and generates a thermogram; determines boundary information corresponding to each distance gate in the thermogram based on the body movement information, and determines a body movement part corresponding to each distance gate according to the boundary information; obtains body movement intensity information corresponding to the boundary information, determines a target body movement part from each body movement part, and then determines a target body movement time period according to the body movement intensity information and the target body movement part; obtains a body movement phase signal corresponding to the target body movement part, and then determines an abnormal body movement phase signal in the body movement phase signal according to the target body movement time period and the body movement phase signal. The interference of other sound signals is avoided, and the accuracy of detecting abnormalities of a user in a preset time period is effectively improved.

[0096] Figure 2 FIG. 1 is a main flowchart of a sleep abnormality detection method according to an embodiment of the present application, as shown in FIG. 1, the sleep abnormality detection method comprises the following steps. Figure 2

[0097] In step S201, an echo pulse signal is obtained, and then each distance gate corresponding to the echo pulse signal is determined.

[0098] The obtained echo pulse signal may be, for example, an echo pulse signal returned after each body part of a user is detected by a millimeter wave radar. After obtaining the echo pulse signal, the execution subject can determine each distance gate corresponding to the echo pulse signal. The distance gate refers to a sampling point in the sampling data after pulse compression, and each sampling point has its own distance gate. Each sampling point may be, for example, each body part of the user to be detected. The distance gate can be used to define the distance span of each body part of the user to be detected from the millimeter wave radar.

[0099] In step S202, body movement information corresponding to each distance gate at each preset time point is extracted from the echo pulse signal.

[0100] In step S203, a coordinate system is constructed with each preset time point as the horizontal coordinate and each distance gate as the vertical coordinate.

[0101] Each preset time point is a time point for detecting each body part of the user, which may be during the day or at night. The embodiment of the present application does not make specific limitations on each preset time point. The higher the vertical coordinate corresponding to each distance gate, the farther the position from the millimeter wave radar.

[0102] ​Step S204: Determine the position of the body movement part corresponding to the body movement information of each distance gate, and generate a heat map in the coordinate system based on the position of each body movement part.

[0103] Using each distance gate as the ordinate and the detection time as the abscissa, the position of the body part corresponding to the motion information of each distance gate is used as the drawing element (drawing element, for example...). Figure 4 Given A1, A2, A3, A4, B, and C, generate the following: Figure 4 The heatmap shown.

[0104] Step S205: Determine the boundary information corresponding to each distance gate in the heat map based on the body motion information, and determine the body motion part corresponding to each distance gate based on the boundary information.

[0105] Step S206: Obtain the body movement intensity information corresponding to the boundary information, determine the target body movement part from each body movement part, and then determine the target body movement time period based on the body movement intensity information and the target body movement part.

[0106] Step S207: Obtain the body movement phase signal corresponding to the target body movement part, and then determine the abnormal body movement phase signal in the body movement phase signal based on the target body movement time period and body movement phase signal.

[0107] This application embodiment realizes contactless cough target detection in cough detection scenarios without relying on audio recording, effectively protecting the privacy of users and patients, avoiding privacy protection issues caused by sound recording, and false detection caused by external noise interference. It not only strengthens the privacy protection of users and patients, but also effectively improves the accuracy of cough detection.

[0108] Figure 3 This is a schematic diagram illustrating an application scenario of a sleep abnormality detection method according to an embodiment of this application. The sleep abnormality detection method of this application embodiment can be applied to scenarios involving the detection of coughing during sleep. Figure 3 As shown, when detecting a user's cough during sleep, the system first acquires radar echo pulse signals to obtain RBMI (Radio Resonance Body Movement Information) body movement information. Then, the body movement location is estimated, and based on the RBMI body movement information, a segment of the quasi-cough location (i.e., the target body movement time period) is determined. Next, respiratory and heart rate phase signals are acquired, and respiratory phase signals are extracted from these signals. Finally, based on the respiratory phase signals and the quasi-cough location segment, the cough segment is precisely located and analyzed to identify and output abnormal respiratory phase signals. This avoids privacy issues caused by sound recording and false detections caused by external noise interference, thus strengthening the privacy protection of users and patients while effectively improving the accuracy of cough detection.

[0109] Figure 5 is a schematic diagram of main units of a sleep anomaly detection apparatus according to an embodiment of the present application. As shown in Figure 5 the sleep anomaly detection apparatus 500 includes a signal acquisition unit 501, a thermogram generation unit 502, a body movement part determination unit 503, a target body movement time period determination unit 504, and an anomaly detection unit 505.

[0110] The signal acquisition unit 501 is configured to acquire echo pulse signals, and determine respective distance gates corresponding to the echo pulse signals.

[0111] The thermogram generation unit 502 is configured to extract body movement information corresponding to respective distance gates at respective preset time points from the echo pulse signals, and generate a thermogram.

[0112] The body movement part determination unit 503 is configured to determine boundary information corresponding to respective distance gates in the thermogram based on the body movement information, and determine body movement parts corresponding to respective distance gates according to the boundary information.

[0113] The target body movement time period determination unit 504 is configured to acquire body movement intensity information corresponding to the boundary information, determine target body movement parts from the body movement parts, and determine a target body movement time period according to the body movement intensity information and the target body movement parts.

[0114] The anomaly detection unit 505 is configured to acquire body movement phase signals corresponding to the target body movement parts, and determine abnormal body movement phase signals in the body movement phase signals according to the target body movement time period and the body movement phase signals.

[0115] In some embodiments, the thermogram generation unit 502 is further configured to: construct a coordinate system with respective preset time points as abscissas and respective distance gates as ordinates; and determine positions of the body movement parts corresponding to the body movement information of respective distance gates, and generate the thermogram in the coordinate system based on the positions of the respective body movement parts.

[0116] In some embodiments, the thermogram generation unit 502 is further configured to: perform denoising processing on the echo pulse signals based on a preset noise signal threshold to obtain denoised echo pulse signals; and extract the body movement information corresponding to respective distance gates at respective preset time points from the denoised echo pulse signals.

[0117] In some embodiments, the body movement part determination unit 503 is further configured to: based on the denoised heat map, obtain body movement energy values corresponding to each distance gate, retain body movement energy values of each distance gate exceeding a preset body movement energy threshold, and then calculate time integrals of the body movement energy values corresponding to each distance gate; and according to the time integrals, calculate distribution positions of the distance gates corresponding to each body movement part in the target state; and according to the boundary information corresponding to the distribution positions, determine the body movement parts corresponding to each distance gate.

[0118] In some embodiments, the target body movement time period determination unit 504 is further configured to: determine a time period in which the body movement intensity of the target body movement part corresponding to the body movement intensity information exceeds the body movement intensity threshold and other body movement parts do not have corresponding body movement intensity information as the target body movement time period.

[0119] In some embodiments, the anomaly detection unit 505 is further configured to: obtain a first body movement phase signal and a second body movement phase signal corresponding to the target body movement part; and generate a body movement phase signal according to the first body movement phase signal and the second body movement phase signal.

[0120] In some embodiments, the anomaly detection unit 505 is further configured to: extract a wave peak and a wave trough in the first body movement phase signal, and a wave peak time corresponding to the wave peak and a wave trough time corresponding to the wave trough; calculate a first difference value between the wave peak and the wave trough, and a second difference value between the wave peak time and the wave trough time; and determine a signal in the first body movement phase signal corresponding to a first difference value greater than a first threshold and a second difference value less than a second threshold as an abnormal body movement phase signal.

[0121] It should be noted that the sleep anomaly detection method and the sleep anomaly detection device of the present application have a corresponding relationship in the specific implementation content, and therefore repeated content will not be described.

[0122] Figure 6 An exemplary system architecture 600 to which the sleep anomaly detection method or the sleep anomaly detection device of the embodiments of the present application can be applied is shown.

[0123] As shown in Figure 6 , the system architecture 600 can include terminal devices 601, 602, 603, a network 604, and a server 605. The network 604 is used to provide a medium for communication links between the terminal devices 601, 602, 603 and the server 605. The network 604 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0124] The user can use the terminal devices 601, 602, and 603 to interact with the server 605 through the network 604 to receive or send messages, and the like. Various communication client applications can be installed on the terminal devices 601, 602, and 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, and the like (only as examples).

[0125] The terminal devices 601, 602, and 603 can be various electronic devices with sleep anomaly detection processing screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0126] The server 605 can be a server providing various services, such as a background management server providing support for the user to obtain echo pulse signals using the terminal devices 601, 602, and 603 (only as an example). The background management server can obtain the echo pulse signals, and then determine various distance gates corresponding to the echo pulse signals; extract body motion information corresponding to each distance gate at each preset time point from the echo pulse signals, and then generate a heat map; determine boundary information corresponding to each distance gate in the heat map based on the body motion information, determine a body motion part corresponding to each distance gate according to the boundary information; obtain body motion intensity information corresponding to the boundary information, determine a target body motion part from each body motion part, and then determine a target body motion time period according to the body motion intensity information and the target body motion part; obtain a body motion phase signal corresponding to the target body motion part, and then determine an abnormal body motion phase signal in the body motion phase signal according to the target body motion time period and the body motion phase signal. The intervention interference of other sound signals is avoided, and the accuracy of detecting the anomaly of the user within the preset time period is effectively improved.

[0127] It should be noted that the sleep anomaly detection method provided in the embodiments of the present application is generally executed by the server 605, and correspondingly, the sleep anomaly detection apparatus is generally arranged in the server 605.

[0128] It should be understood that Figure 6 The number of terminal devices, networks, and servers in the above description is only illustrative. Any number of terminal devices, networks, and servers can be provided according to the needs of implementation.

[0129] Reference will be made to Figure 7 which shows a structural schematic diagram of a computer system 700 of a terminal device suitable for use to implement the embodiments of the present application. Figure 7 The terminal device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0130] As Figure 7As shown, the computer system 700 includes a central processing unit (CPU) 701 which can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 702 or loaded into a random access memory (RAM) 703 from a storage section 708. In the RAM 703, various programs and data required for the operation of the computer system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0131] Connected to the I / O interface 705 are an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a display device such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as necessary. A removable recording medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read therefrom is installed into the storage section 708 as necessary.

[0132] In particular, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 709, and / or installed from the removable recording medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-described functions defined in the system of the present application are executed.

[0133] It should be noted that computer-readable media in this disclosure can be computer-readable storage media, or computer-readable signal media, or any combination thereof. Computer-readable storage media can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this disclosure, computer-readable storage media can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a computer-readable storage medium, or any computer-readable medium that can transmit or propagate code in the form of computer-readable instructions or program code, or any combination of the above. The computer-readable medium can be transmitted in baseband or as part of a carrier wave over a transmission medium, including a wired medium, or a wireless medium, or any suitable combination of the above. Computer-readable media can also be any medium that can be used to store or transfer a program for use by or in connection with an instruction execution system, apparatus, or device.

[0134] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functional processes, and operations that can be implemented in systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0135] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware. The described units can also be arranged in a processor, for example, a processor can be described as including a signal acquisition unit, a heat map generation unit, a body movement part determination unit, a target body movement time period determination unit, and an anomaly detection unit. In some cases, the names of these units do not constitute a limitation on the units themselves.

[0136] As another aspect, the present application also provides a computer readable medium, which can be included in the device described in the above embodiments, or can exist independently without being assembled into the device. The computer readable medium carries one or more programs, which, when executed by the device, cause the device to acquire an echo pulse signal, and then determine each distance gate corresponding to the echo pulse signal; extract body movement information corresponding to each distance gate at each preset time point from the echo pulse signal, and then generate a heat map; determine boundary information corresponding to each distance gate in the heat map based on the body movement information, determine a body movement part corresponding to each distance gate according to the boundary information; acquire body movement intensity information corresponding to the boundary information, determine a target body movement part from each body movement part, and then determine a target body movement time period according to the body movement intensity information and the target body movement part; acquire a body movement phase signal corresponding to the target body movement part, and then determine an abnormal body movement phase signal in the body movement phase signal according to the target body movement time period and the body movement phase signal.

[0137] According to the technical solutions of the embodiments of the present application, the intervention of other sound signals is avoided, and the accuracy of detecting the anomaly of the user within the preset time period is effectively improved.

[0138] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A sleep abnormality detection method characterized by comprising: The method comprises: acquiring echo pulse signals, and determining each distance gate corresponding to the echo pulse signals; extracting body motion information corresponding to each distance gate at each preset time point from the echo pulse signals, and generating a thermogram; the generating of the thermogram comprises: taking each preset time point as the horizontal coordinate and each distance gate as the vertical coordinate to construct a coordinate system; determining the positions of body motion parts corresponding to the body motion information of each distance gate; and generating a thermogram based on the positions of each body motion part in the coordinate system; determining boundary information corresponding to each distance gate in the thermogram based on the body motion information, and determining the body motion parts corresponding to each distance gate according to the boundary information; acquiring body motion intensity information corresponding to the boundary information, determining a target body motion part from each body motion part, and determining a target body motion time period according to the body motion intensity information and the target body motion part; acquiring a body motion phase signal corresponding to the target body motion part, and determining an abnormal body motion phase signal in the body motion phase signal according to the target body motion time period and the body motion phase signal.

2. The method of claim 1, wherein, The extracting of the body motion information corresponding to each distance gate at each preset time point from the echo pulse signals comprises: performing denoising processing on the echo pulse signals based on a preset noise signal threshold to obtain denoised echo pulse signals; extracting the body motion information corresponding to each distance gate at each preset time point from the denoised echo pulse signals.

3. The method of claim 2, wherein, The determining of the body motion parts corresponding to each distance gate according to the boundary information comprises: acquiring body motion energy values corresponding to each distance gate based on the denoised thermogram, retaining the body motion energy values of each distance gate that exceed a preset body motion energy threshold, and calculating a time integral of the body motion energy values corresponding to each distance gate; calculating the distribution positions of the distance gates corresponding to each body motion part in a target state according to the time integral; determining the body motion parts corresponding to each distance gate according to the boundary information corresponding to the distribution positions.

4. The method of claim 1, wherein, The determining of the target body motion time period comprises: determining a time period in which the body motion intensity information corresponding to the target body motion part exceeds a body motion intensity threshold and in which no body motion intensity information corresponding to other body motion parts exists as the target body motion time period.

5. The method of claim 1, wherein, The acquiring of the body motion phase signal corresponding to the target body motion part comprises: acquiring a first body motion phase signal and a second body motion phase signal corresponding to the target body motion part; generating a body motion phase signal according to the first body motion phase signal and the second body motion phase signal.

6. The method of claim 5, wherein, The determining of the abnormal body motion phase signal in the body motion phase signal comprises: extracting a wave crest and a wave trough in the first body motion phase signal, a wave crest time corresponding to the wave crest, and a wave trough time corresponding to the wave trough; calculating a first difference value between the wave crest and the wave trough, and a second difference value between the wave crest time and the wave trough time; The first body motion phase signal corresponding to the first difference value greater than the first threshold value and the second difference value less than the second threshold value in the first body motion phase signal is determined as an abnormal body motion phase signal.

7. A sleep abnormality detection device characterized by comprising: The method comprises: a signal acquisition unit configured to acquire an echo pulse signal, and determine each distance gate corresponding to the echo pulse signal; a heat map generation unit configured to extract body motion information corresponding to each distance gate at each preset time point from the echo pulse signal, and generate a heat map; the heat map generation unit is further configured to: construct a coordinate system with each preset time point as the horizontal coordinate and each distance gate as the vertical coordinate; determine the positions of body motion parts corresponding to the body motion information corresponding to each distance gate, and generate a heat map based on the positions of each body motion part in the coordinate system; a body motion part determination unit configured to determine boundary information corresponding to each distance gate in the heat map based on the body motion information, and determine body motion parts corresponding to each distance gate according to the boundary information; a target body motion time period determination unit configured to acquire body motion intensity information corresponding to the boundary information, determine a target body motion part from each body motion part, and determine a target body motion time period according to the body motion intensity information and the target body motion part; an anomaly detection unit configured to acquire a body motion phase signal corresponding to the target body motion part, and determine an abnormal body motion phase signal in the body motion phase signal according to the target body motion time period and the body motion phase signal.

8. The apparatus of claim 7, wherein, The heat map generation unit is further configured to: perform denoising processing on the echo pulse signal based on a preset noise signal threshold to obtain a denoised echo pulse signal; extract body motion information corresponding to each distance gate at each preset time point from the denoised echo pulse signal. 9.A sleep abnormality detection electronic device, comprising: The method comprises: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-6.

10. A computer readable medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the method according to any one of claims 1-6.

Images