Alarm clock control method, radar and storage medium based on sleep stage prediction

Abstract

The present application provides an alarm control method, radar, and storage medium based on sleep stage prediction. The method includes: acquiring the echo signal obtained by radar detection of the surface area of the bed in real time, and extracting human sleep characteristics based on the echo signal; calculating the corresponding sleep stage index according to a preset cycle based on the human sleep characteristics; if it is monitored that the current time reaches the alarm timing, then based on the sleep stage index of the most recent N cycles, predicting the sleep stage index of the Mth cycle after the current cycle; determining the alarm ringing scheme based on the obtained sleep stage index, and controlling the alarm ringing based on the ringing scheme. The present application can use the radar detection method to calculate the sleep stage of a person, predict the sleep stage index of the user at the alarm timing time, and thus determine the corresponding alarm ringing scheme based on the sleep stage index, thereby reducing the discomfort caused to the human body by the alarm ringing.

Description

Technical Field

[0001] The present application relates to the field of radar technology, and in particular to an alarm control method based on sleep stage prediction, a radar, and a storage medium. Background Art

[0002] Most people set an alarm to wake themselves up when needed, and the alarm clock provides a wake-up service at the pre-set time. However, human sleep has a fixed pattern, and waking up naturally is in line with the body's circadian rhythm. However, being suddenly awakened from deep sleep can affect both psychologically and physiologically.

[0003] In order to develop an alarm clock that can wake up the user in a way that is consistent with the human body's biological clock, the existing technology usually analyzes the human body's sleep conditions based on brain waves, determines whether the person is in light sleep, and then controls the alarm clock to ring. However, this method requires the user to wear a brain wave detection instrument, which affects sleep quality. Summary of the Invention

[0004] The present application provides an alarm control method, radar, and storage medium based on sleep stage prediction to solve the problem of human discomfort caused by the alarm clock's scheduled wake-up service.

[0005] In a first aspect, the present application provides an alarm control method based on sleep stage prediction, comprising:

[0006] Acquire in real time the echo signal obtained by radar detection of the surface area of the bed, and extract the human sleep characteristics based on the echo signal;

[0007] Based on the human sleep characteristics, a corresponding sleep stage index is calculated according to a preset cycle;

[0008] If the current time reaches the alarm time, the sleep stage index of the Mth cycle after the current cycle is predicted based on the sleep stage index of the latest N cycles;

[0009] The ringing scheme of the alarm clock is determined according to the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle, and the ringing of the alarm clock is controlled based on the ringing scheme.

[0010] In a second aspect, the present application provides a radar comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in any possible implementation of the first aspect are implemented.

[0011] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method described in any possible implementation of the first aspect above.

[0012] The embodiment of the present application provides an alarm control method, radar, and storage medium based on sleep stage prediction. The method can obtain the echo signal obtained by the radar detecting the surface area of the bed in real time, and extract the human sleep characteristics based on the echo signal; based on the human sleep characteristics, calculate the corresponding sleep stage index according to the preset cycle; if it is monitored that the current time reaches the alarm timing time, then based on the sleep stage index of the most recent N cycles, predict the sleep stage index of the Mth cycle after the current cycle; according to the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle, determine the ringing scheme of the alarm clock, and control the ringing of the alarm clock based on the ringing scheme. Through the above method, this embodiment can use the radar detection method to calculate the sleep stage of a person, predict the sleep stage index of the user at the alarm timing time, and thus determine the corresponding alarm ringing scheme according to the sleep stage index, thereby reducing the discomfort caused to the human body by the alarm ringing. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0014] Figure 1 This is a flowchart of an implementation of an alarm clock control method based on sleep stage prediction provided by an embodiment of the present application;

[0015] Figure 2 Schematic diagram of the structure of an alarm clock control device based on sleep stage prediction provided by an embodiment of the present application;

[0016] Figure 3 Schematic diagram of the structure of the radar provided in the embodiment of the present application. DETAILED DESCRIPTION

[0017] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0018] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0019] See also Figure 1 , which shows a flowchart of an implementation of an alarm control method based on sleep stage prediction provided by an embodiment of the present application, as detailed below:

[0020] S101: Acquire in real time an echo signal obtained by radar detection of a bed surface area, and extract human sleep characteristics based on the echo signal.

[0021] Specifically, the execution subject of this embodiment is a radar, which includes a conventional radar detection module for detecting targets and determining their spatial positions using radio methods, and an alarm clock, and the radar detection module is communicatively connected to the alarm clock.

[0022] Specifically, the radar detection module is installed above the central axis of the bed, and is used to detect the environment of the surface area of the bed downward, receive the reflected echo signal, and extract the human body's sleep characteristics based on the echo signal.

[0023] Human sleep characteristics include, but are not limited to, respiratory rate, heart rate, bed presence flag, and body movement flag. Respiratory rate indicates the number of breaths per minute, measured in breaths / minute, with a typical value of 0 to 30. Heart rate indicates the number of heartbeats per minute, measured in beats / minute, with a typical value of 50 to 120. The bed presence flag indicates whether a human body is detected on the bed surface, with a typical value of 0 or 1, where 0 indicates the person is not in bed and 1 indicates the person is in bed. The body movement flag indicates whether the person changes motion, with a typical value of 0 or 1, where 0 indicates no motion and 1 indicates motion.

[0024] S102: Calculating a corresponding sleep stage index according to a preset cycle based on the human sleep characteristics.

[0025] In one possible implementation, the human sleep characteristics include respiratory rate, heart rate, bedtime sign, and body movement sign; the specific implementation process of S102 includes:

[0026] S201: determining whether there is anyone in the bed surface area in the current cycle based on the bed occupancy flag of the current cycle;

[0027] S202: If there is a person in the bed surface area in the current cycle, then based on the respiratory rate, the heart rate and the body movement marker at each sampling moment in the latest K cycles, calculate the sleep stage index of the current cycle;

[0028] S203: If there is no person in the bed surface area during the current cycle, the sleep stage index of the current cycle is set to a first preset value.

[0029] In this embodiment, the radar detection module acquires echo signals from the bed surface area at a preset sampling interval. After receiving the echo signals, the preset sampling interval may be 1 minute. After acquiring the sleep characteristics, the radar detection module calculates the sleep stage index for each cycle at a preset interval. For example, if the preset interval is 5 minutes, the radar detection module calculates the sleep stage index every five minutes.

[0030] Specifically, at each preset period, the presence of a person within the bed surface area is determined based on the bed occupancy indicator at any sampling moment within that period. If a person is present within the bed surface area during the current period, the sleep stage index for the current period is calculated based on the respiratory rate, heart rate, and body movement indicators at each sampling moment within the last K periods.

[0031] Among them, K can be 1, 2, 3 or 4, etc., and can be determined according to the preset cycle length and the actual sleep cycle.

[0032] In one possible implementation, after S101, the method provided in this embodiment further includes:

[0033] Determine whether there are remaining storage locations in a current sliding window array for storing human sleep characteristics. If there are no remaining storage locations in the current sliding window array, delete the human sleep characteristics earliest stored in the current sliding window array, and store the human sleep characteristics corresponding to the current sampling moment in the current sliding window array.

[0034] In this embodiment, after calculating the human sleep characteristics, the radar detection module stores the human sleep characteristics in a sliding window array. The sliding window array is used to store the human sleep characteristics of the most recent K cycles. Every time a new human sleep characteristic that needs to be stored is added, the earliest human sleep characteristic stored in the current sliding window array is deleted, and the latest human sleep characteristic is stored in the current sliding window array. In this way, a smaller storage space can be used to implement an alarm control method based on sleep stage prediction.

[0035] Specifically, the sliding window array includes arrays corresponding to the respiratory rate, heart rate, bed sign, and body movement sign, and the radar detection module stores various human sleep characteristics in the corresponding arrays based on the above storage method.

[0036] Accordingly, the specific implementation process of S202 includes:

[0037] The sleep stage index of the current cycle is calculated based on the respiratory frequency, the heart rate and the body movement marker at each sampling moment in the current sliding window array.

[0038] In one possible implementation, the specific implementation process of S202 further includes:

[0039] Calculate the standard deviation of the respiratory rate at each sampling moment in the current sliding window array, the standard deviation of the heart rate at each sampling moment, and the mean of the body movement marker at each sampling moment;

[0040] Calculate the sleep stage index of the current cycle based on the sleep stage index calculation formula;

[0041] The sleep stage index calculation formula is:

[0042] sleepFactor=k1·breathStd+k2·heartStd+k3·moveFlagMean;

[0043] Among them, sleepFactor represents the sleep stage index, breathStd represents the standard deviation of the breathing rate, heartStd represents the standard deviation of the heart rate, moveFlagMean represents the mean of the body movement flag, and k1, k2, and k3 are preset coefficients respectively.

[0044] In some embodiments, k1 = 0.3, k2 = 0.3, and k3 = 5. Of course, in other embodiments, k1, k2, and k3 may also have other values.

[0045] In this embodiment, if the value of the bed presence flag is 0, the first preset value is -1.

[0046] In one embodiment, after the sleep stage index of each cycle is calculated, the sleep stage indexes of the most recent N cycles are saved in the index storage array sleepFactorWin. That is, each time the sleep stage index of a new cycle is calculated, the earliest sleep stage index stored in the index storage array sleepFactorWin is deleted, and the most recently calculated sleep stage index is stored in the index storage array sleepFactorWin.

[0047] S103: If it is monitored that the current time reaches the alarm time, the sleep stage index of the Mth cycle after the current cycle is predicted based on the sleep stage indexes of the latest N cycles.

[0048] In one possible implementation, the specific implementation process of S103 includes:

[0049] Perform polynomial fitting on the sleep stage index of the latest N cycles to obtain the fitting formula;

[0050] The Mth cycle after the current cycle is substituted into the fitting formula to obtain the sleep stage index of the Mth cycle after the current cycle.

[0051] In this embodiment, a communication connection is established between the radar detection module and the alarm clock. Specifically, the radar and alarm clock can be connected via Bluetooth or a network connection. When the alarm clock reaches the set time, it sends a control instruction to the radar detection module. Upon detecting the alarm clock's control instruction, the radar detection module predicts the sleep stage index for the Mth cycle after the current cycle based on the sleep stage indexes of the most recent N cycles.

[0052] Exemplarily, N can be 18, and M can be 3. Taking the preset period of 5 minutes as an example, the radar detection module predicts the sleep stage index 15 minutes after the timing time based on the sleep stage index 90 minutes before the timing time.

[0053] Specifically, the specific implementation process of S103 further includes:

[0054] Perform quadratic curve fitting on the sleep stage index of the latest N cycles, and the fitting formula is as follows:

[0055] y=ax 2 +bx+c;

[0056] In the fitting formula, x represents the serial number of the cycle to be predicted, and y represents the sleep stage index.

[0057] The serial number of the Mth cycle after the current cycle is substituted into the fitting formula to obtain the sleep stage index of the Mth cycle after the current cycle.

[0058] As another specific embodiment, this embodiment can also take the serial numbers and corresponding sleep stage indexes of M+N consecutive cycles as a training sample, obtain multiple training samples to train the neural network model, and after the neural network model completes training, input the sleep stage index and serial numbers of the N cycles before the current cycle into the neural network model, and output the sleep stage index of the Mth cycle after the current cycle.

[0059] S104: Determine a ringing scheme for the alarm clock according to the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle, and control the ringing of the alarm clock based on the ringing scheme.

[0060] In one possible implementation, the specific implementation process of S104 includes:

[0061] S301: Determine the sleep staging result of the current cycle according to the sleep staging index of the current cycle; the sleep staging result includes deep sleep period, light sleep period and awake period;

[0062] S302: Determine a sleep staging result of the Mth cycle after the current cycle based on the sleep staging index of the Mth cycle after the current cycle;

[0063] S303: Determine the alarm ringing scheme according to the sleep staging result of the current cycle and the sleep staging result of the Mth cycle after the current cycle; the alarm ringing scheme includes ringing immediately and ringing at the arrival time of the Mth cycle after the current cycle.

[0064] In one possible implementation, the specific implementation process of S303 includes:

[0065] If the sleep stage result corresponding to the current cycle is a light sleep period or a wakeful period, the alarm clock is controlled to ring immediately;

[0066] If the sleep staging result corresponding to the current cycle is a deep sleep period, and the sleep staging result of the Mth cycle after the current cycle is a deep sleep period, controlling the alarm clock to ring immediately;

[0067] If the sleep staging result corresponding to the current cycle is deep sleep, and the sleep staging result of the Mth cycle after the current cycle is light sleep or awake, the alarm clock is controlled to ring at the time when the Mth cycle after the current cycle arrives.

[0068] In one possible implementation, the specific implementation process of S301 includes:

[0069] If the sleep stage index of the current cycle is greater than the first preset threshold, the sleep stage result of the current cycle is determined to be the awake period;

[0070] If the sleep stage index of the current cycle is less than or equal to the first preset threshold and greater than the second preset threshold, the sleep stage result of the current cycle is determined to be light sleep; the first preset threshold is greater than the second preset threshold;

[0071] If the sleep stage index of the current cycle is not greater than the second preset threshold, the sleep stage result of the current cycle is determined to be a deep sleep stage.

[0072] It can be seen from the above embodiments that the present application can control the alarm clock to ring at the most appropriate time based on the human body's sleep staging results through the above method, minimize the discomfort caused by the alarm clock to the human body, and help the human body quickly enter a better state. In addition, the present embodiment uses a sliding window array to save the human body's sleep characteristics and sleep staging index, which can reduce storage space. At the same time, a linear fitting method is used to predict the sleep staging index. The calculation method is simple and can reduce the amount of calculation, so that the method can be implemented inside the radar. There is no need to send a whole night of data to the cloud platform to complete the sleep staging, which improves the real-time performance of the sleep staging prediction, thereby improving the accuracy of the alarm clock control. At the same time, it can reduce the amount of communication data between the radar and the cloud platform, saving bandwidth.

[0073] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0074] The following are device embodiments of the present application. For details not fully described therein, please refer to the corresponding method embodiments described above.

[0075] Figure 2 A schematic diagram of the structure of an alarm clock control device based on sleep stage prediction provided by an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown, which are detailed as follows:

[0076] like Figure 2 As shown, the alarm control device 100 based on sleep stage prediction includes:

[0077] The sleep feature extraction module 110 is used to obtain the echo signal obtained by the radar detecting the surface area of the bed in real time, and extract the sleep features of the human body based on the echo signal;

[0078] A sleep stage index calculation module 120 is configured to calculate a corresponding sleep stage index according to a preset cycle based on the human sleep characteristics;

[0079] The sleep stage index prediction module 130 is configured to predict the sleep stage index of the Mth cycle after the current cycle based on the sleep stage indexes of the most recent N cycles if the current time reaches the alarm time;

[0080] The ringing control module 140 is configured to determine a ringing scheme for the alarm clock according to the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle, and control the alarm clock to ring based on the ringing scheme.

[0081] In one possible embodiment, the human sleep characteristics include respiratory rate, heart rate, bed sign, and body movement sign; the sleep stage index calculation module 120 includes:

[0082] a bed occupancy determination unit, configured to determine whether there is a person in the bed surface area in the current cycle based on the bed occupancy flag of the current cycle;

[0083] a first sleep stage index calculation unit, configured to calculate the sleep stage index of the current cycle based on the respiratory rate, the heart rate, and the body movement marker at each sampling moment in the most recent K cycles, if there is a person in the bed surface area in the current cycle;

[0084] The second sleep stage index calculation unit is configured to set the sleep stage index of the current cycle to a first preset value if no one is present in the surface area of the bed during the current cycle.

[0085] In one possible implementation, the alarm control device based on sleep stage prediction provided in this embodiment further includes:

[0086] a sliding window storage module, configured to determine whether there are any remaining storage locations in a current sliding window array for storing human sleep characteristics; if there are no remaining storage locations in the current sliding window array, deleting the human sleep characteristics earliest stored in the current sliding window array, and storing the human sleep characteristics corresponding to the current sampling moment in the current sliding window array;

[0087] Accordingly, the first sleep stage index calculation unit includes:

[0088] The sleep stage index of the current cycle is calculated based on the respiratory frequency, the heart rate and the body movement marker at each sampling moment in the current sliding window array.

[0089] In one possible implementation, the first sleep stage index calculation unit further includes:

[0090] Calculate the standard deviation of the respiratory rate at each sampling moment in the current sliding window array, the standard deviation of the heart rate at each sampling moment, and the mean of the body movement marker at each sampling moment;

[0091] Calculate the sleep stage index of the current cycle based on the sleep stage index calculation formula;

[0092] The sleep stage index calculation formula is:

[0093] sleepFactor=k1·breathStd+k2·heartStd+k3·moveFlagMean;

[0094] Among them, sleepFactor represents the sleep stage index, breathStd represents the standard deviation of the breathing rate, heartStd represents the standard deviation of the heart rate, moveFlagMean represents the mean of the body movement flag, and k1, k2, and k3 are preset coefficients respectively.

[0095] In one possible implementation, the sleep stage index prediction module 130 includes:

[0096] Perform polynomial fitting on the sleep stage index of the latest N cycles to obtain the fitting formula;

[0097] The Mth cycle after the current cycle is substituted into the fitting formula to obtain the sleep stage index of the Mth cycle after the current cycle.

[0098] In one possible implementation, the ring control module 140 includes:

[0099] A current stage result determination unit, configured to determine the sleep stage result of the current cycle according to the sleep stage index of the current cycle; the sleep stage result includes deep sleep period, light sleep period and wakefulness period;

[0100] a sleep staging result prediction unit, configured to determine a sleep staging result of the Mth cycle after the current cycle based on the sleep staging index of the Mth cycle after the current cycle;

[0101] The ringing scheme determining unit is used to determine the ringing scheme of the alarm clock according to the sleep staging result of the current cycle and the sleep staging result of the Mth cycle after the current cycle; the ringing scheme of the alarm clock includes ringing immediately and ringing at the arrival time of the Mth cycle after the current cycle.

[0102] In one possible implementation, the ringing scheme determining unit includes:

[0103] If the sleep stage result corresponding to the current cycle is a light sleep period or a wakeful period, the alarm clock is controlled to ring immediately;

[0104] If the sleep staging result corresponding to the current cycle is a deep sleep period, and the sleep staging result of the Mth cycle after the current cycle is a deep sleep period, controlling the alarm clock to ring immediately;

[0105] If the sleep staging result corresponding to the current cycle is deep sleep, and the sleep staging result of the Mth cycle after the current cycle is light sleep or awake, the alarm clock is controlled to ring at the time when the Mth cycle after the current cycle arrives.

[0106] In one possible implementation, the current staging result determination unit includes:

[0107] If the sleep stage index of the current cycle is greater than the first preset threshold, the sleep stage result of the current cycle is determined to be the awake period;

[0108] If the sleep stage index of the current cycle is less than or equal to the first preset threshold and greater than the second preset threshold, the sleep stage result of the current cycle is determined to be light sleep; the first preset threshold is greater than the second preset threshold;

[0109] If the sleep stage index of the current cycle is not greater than the second preset threshold, the sleep stage result of the current cycle is determined to be a deep sleep stage.

[0110] An embodiment of the present application provides an alarm control device based on sleep stage prediction. The device can obtain echo signals obtained by radar detection of the surface area of the bed in real time, and extract human sleep characteristics based on the echo signals; based on the human sleep characteristics, calculate the corresponding sleep stage index according to a preset cycle; if it is monitored that the current time reaches the alarm timing, the sleep stage index of the Mth cycle after the current cycle is predicted based on the sleep stage index of the most recent N cycles; based on the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle, determine the alarm ringing scheme, and control the alarm ringing based on the ringing scheme. This embodiment can use a radar detection method to calculate the sleep stage of a person, predict the sleep stage index of the user at the alarm timing, and thus determine the corresponding alarm ringing scheme based on the sleep stage index, thereby reducing the discomfort caused to the human body by the alarm ringing.

[0111] Figure 3 Schematic diagram of the radar provided in the embodiment of the present application. Figure 3 As shown, the radar 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps of the above-mentioned various embodiments of the alarm control method based on sleep stage prediction are implemented, such as Figure 1 Alternatively, when the processor 30 executes the computer program 32, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 2 The functions of the modules 110 to 140 are shown.

[0112] For example, the computer program 32 may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to implement the solution provided by the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the radar 3.

[0113] The radar 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that Figure 3 This is only an example of radar 3 and does not constitute a limitation of radar 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the radar may also include input and output devices, network access devices, buses, etc.

[0114] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0115] The memory 31 can be an internal storage unit of the radar 3, such as the radar 3's hard drive or memory. Alternatively, the memory 31 can be an external storage device of the radar 3, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 31 can include both the radar 3's internal storage unit and an external storage device. The memory 31 is used to store the computer program and other programs and data required by the radar. The memory 31 can also be used to temporarily store data that has been output or is about to be output.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0117] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0118] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0119] In the embodiments provided herein, it should be understood that the disclosed devices / radars and methods can be implemented in other ways. For example, the device / radar embodiments described above are merely illustrative. For example, the division of modules or units is merely a logical functional division. In actual implementation, other divisions may be employed, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interface, or the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other.

[0120] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0121] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0122] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various embodiments of the alarm control method based on sleep stage prediction. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0123] In addition, the embodiments shown in the drawings of the present application or the features of the various embodiments mentioned in this specification are not necessarily to be understood as independent embodiments. Rather, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.

[0124] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An alarm clock control method based on sleep stage prediction, characterized in that: include: Acquire in real time the echo signal obtained by radar detection of the surface area of the bed, and extract the human sleep characteristics based on the echo signal; Based on the human sleep characteristics, a corresponding sleep stage index is calculated according to a preset cycle; If the current time reaches the alarm time, the sleep stage index of the Mth cycle after the current cycle is predicted based on the sleep stage index of the latest N cycles; The ringing scheme of the alarm clock is determined according to the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle, and the ringing of the alarm clock is controlled based on the ringing scheme.

2. The alarm control method based on sleep stage prediction according to claim 1, characterized in that: The human sleep characteristics include respiratory rate, heart rate, bed sign, and body movement sign; The step of calculating the corresponding sleep stage index based on the human sleep characteristics according to a preset cycle includes: determining whether there is anyone in the bed surface area in the current cycle based on the occupancy flag of the current cycle; If there is someone in the bed surface area in the current cycle, then calculating the sleep stage index of the current cycle based on the respiratory rate, the heart rate and the body movement marker at each sampling moment in the latest K cycles; If there is no person in the surface area of the bed during the current cycle, the sleep stage index of the current cycle is set to a first preset value.

3. The alarm control method based on sleep stage prediction according to claim 2, characterized in that: After extracting the human sleep characteristics based on the echo signal, the method further includes: Determining whether there are any remaining storage locations in a current sliding window array for storing human sleep characteristics; if there are no remaining storage locations in the current sliding window array, deleting the human sleep characteristics earliest stored in the current sliding window array, and storing the human sleep characteristics corresponding to the current sampling moment in the current sliding window array; Accordingly, the calculation of the sleep stage index of the current cycle based on the respiratory frequency, the heart rate, and the body movement marker at each sampling moment in the latest K cycles includes: The sleep stage index of the current cycle is calculated based on the respiratory frequency, the heart rate and the body movement marker at each sampling moment in the current sliding window array.

4. The alarm control method based on sleep stage prediction according to claim 3, characterized in that: The step of calculating the sleep stage index of the current cycle based on the respiratory frequency, the heart rate, and the body movement marker at each sampling moment in the current sliding window array includes: Calculate the standard deviation of the respiratory rate at each sampling moment in the current sliding window array, the standard deviation of the heart rate at each sampling moment, and the mean of the body movement marker at each sampling moment; Calculate the sleep stage index of the current cycle based on the sleep stage index calculation formula; The sleep stage index calculation formula is: sleepFactor=k1·breathStd+k2·heartStd+k3·moveFlagMean; Among them, sleepFactor represents the sleep stage index, breathStd represents the standard deviation of the breathing rate, heartStd represents the standard deviation of the heart rate, moveFlagMean represents the mean of the body movement flag, and k1, k2, and k3 are preset coefficients respectively.

5. The alarm control method based on sleep stage prediction according to claim 1, characterized in that: The step of predicting the sleep stage index of the Mth cycle after the current cycle based on the sleep stage indexes of the most recent N cycles includes: Perform polynomial fitting on the sleep stage index of the latest N cycles to obtain a fitting formula; The Mth cycle after the current cycle is substituted into the fitting formula to obtain the sleep stage index of the Mth cycle after the current cycle.

6. The alarm clock control method based on sleep stage prediction according to claim 1, characterized in that: The step of determining the alarm ringing scheme according to the sleep stage index of the current cycle and the sleep stage index of the Mth cycle after the current cycle includes: Determining the sleep staging result of the current cycle according to the sleep staging index of the current cycle; the sleep staging result includes deep sleep period, light sleep period and wakefulness period; determining a sleep staging result of the Mth cycle after the current cycle according to the sleep staging index of the Mth cycle after the current cycle; The alarm clock ringing scheme is determined according to the sleep staging result of the current cycle and the sleep staging result of the Mth cycle after the current cycle; the alarm clock ringing scheme includes ringing immediately and ringing at the arrival time of the Mth cycle after the current cycle.

7. The alarm control method based on sleep stage prediction according to claim 6, characterized in that: The step of determining the alarm ringing scheme according to the sleep staging result of the current cycle and the sleep staging result of the Mth cycle after the current cycle includes: If the sleep stage result corresponding to the current cycle is a light sleep period or a wakeful period, the alarm clock is controlled to ring immediately; If the sleep staging result corresponding to the current cycle is a deep sleep period, and the sleep staging result of the Mth cycle after the current cycle is a deep sleep period, controlling the alarm clock to ring immediately; If the sleep staging result corresponding to the current cycle is deep sleep, and the sleep staging result of the Mth cycle after the current cycle is light sleep or awake, the alarm clock is controlled to ring at the time when the Mth cycle after the current cycle arrives.

8. The alarm control method based on sleep stage prediction according to claim 6, characterized in that: Determining the sleep staging result of the current cycle according to the sleep staging index of the current cycle includes: If the sleep stage index of the current cycle is greater than the first preset threshold, the sleep stage result of the current cycle is determined to be the awake period; If the sleep stage index of the current cycle is less than or equal to the first preset threshold and greater than the second preset threshold, the sleep stage result of the current cycle is determined to be light sleep; the first preset threshold is greater than the second preset threshold; If the sleep stage index of the current cycle is not greater than the second preset threshold, the sleep stage result of the current cycle is determined to be a deep sleep stage.

9. A radar comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the alarm control method based on sleep stage prediction as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the alarm control method based on sleep stage prediction as described in any one of claims 1 to 8 are implemented.

Images