Radar-based sleep staging method, terminal and storage medium

Abstract

This invention provides a radar-based sleep staging method, terminal, and storage medium. The method includes: acquiring human echo signals detected by radar over a preset monitoring area in real time, and calculating a sleep staging index corresponding to each calculation cycle during the sleep period based on the human echo signals; calculating a sleep staging threshold corresponding to the current calculation cycle based on the standard deviation of the sleep staging indices corresponding to multiple calculation cycles near the current calculation cycle; and determining the sleep staging result for the current calculation cycle based on the sleep staging index and the corresponding sleep staging threshold. This method can adaptively set the sleep staging threshold based on the user's own sleep patterns, thereby improving the accuracy of sleep staging calculations.

Description

Technical Field

[0001] This invention relates to the field of radar technology, and in particular to a radar-based sleep staging method, terminal, and storage medium. Background Technology

[0002] With the continuous development of radar technology, radar applications are becoming increasingly widespread. One application is in sleep monitoring, where radar is used to acquire information such as a person's breathing and heart rate throughout the night in a non-contact manner. This information is then processed to obtain sleep quality analysis results, such as wakefulness duration, deep sleep duration, and light sleep duration.

[0003] Traditional radar-based sleep staging methods calculate a sleep stage index for each moment in a person's sleep by analyzing information such as breathing, heart rate, body movement, and whether they are in bed throughout the night. The sleep stage index is then used to determine the sleep state at each moment. For example, if the sleep stage index at a given moment is greater than a threshold (thre1), the person is considered awake; otherwise, they are considered asleep. While this method is simple to calculate, its accuracy in determining sleep state is poor in practical applications because everyone's sleep patterns are different. Summary of the Invention

[0004] In view of this, the present invention provides a radar-based sleep staging method, terminal and storage medium, which can solve the problem of poor accuracy in sleep staging.

[0005] In a first aspect, embodiments of the present invention provide a radar-based sleep staging method, comprising:

[0006] The system acquires human echo signals detected by radar in a preset monitoring area in real time, and calculates the sleep stage index corresponding to each calculation cycle during the sleep period based on the human echo signals.

[0007] Based on the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle, calculate the sleep stage threshold corresponding to the current calculation cycle.

[0008] The sleep stage result for the current calculation period is determined based on the sleep stage index and the corresponding sleep stage threshold for the current calculation period.

[0009] In a second aspect, embodiments of the present invention provide a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any possible implementation of the first aspect above.

[0010] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method as described in any possible implementation of the first aspect above.

[0011] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0012] This invention acquires human echo signals detected by radar over a preset monitoring area in real time, and calculates the sleep stage index corresponding to each calculation cycle during the sleep period based on the human echo signals. Then, based on the standard deviation of the sleep stage indices corresponding to multiple calculation cycles near the current calculation cycle, it calculates the sleep stage threshold corresponding to the current calculation cycle. Finally, based on the sleep stage index and the corresponding sleep stage threshold of the current calculation cycle, it determines the sleep stage result of the current calculation cycle. This method can adaptively set the sleep stage threshold based on the user's own sleep patterns, thereby improving the accuracy of sleep stage calculation and enabling large-scale application of radar in the field of sleep monitoring. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating the implementation of the radar-based sleep staging method provided in this embodiment of the invention.

[0015] Figure 2 This is a schematic diagram of the radar-based sleep staging device provided in an embodiment of the present invention;

[0016] Figure 3 This is a schematic diagram of the terminal provided in an embodiment of the present invention. Detailed Implementation

[0017] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0018] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0019] See Figure 1 The flowchart illustrating the implementation of the radar-based sleep staging method provided in this embodiment of the invention is described in detail below:

[0020] S101: Real-time acquisition of human echo signals detected by radar in a preset monitoring area, and calculation of the sleep stage index corresponding to each calculation cycle of the human body during the sleep period based on the human echo signals.

[0021] Specifically, in this embodiment, the executing entity is a radar. The radar is used to detect the environment of a preset monitoring area, receive reflected human body echo signals, and extract the sleep stage index of the human body based on the human body echo signals. The preset monitoring area can be the surface area of ​​the bed, and the radar can be installed above the central axis of the bed or at a location such as a bedside table that can detect the entire surface area of ​​the bed.

[0022] Specifically, after the radar detects that the user is getting into bed, it begins to acquire human echo signals. After detecting that the user is getting out of bed, it stops acquiring human echo signals. When acquiring human echo signals, the radar extracts physiological characteristics that can represent the human sleep status from the human echo signals, and then calculates the sleep stage index based on the physiological characteristics. The sleep stage index is a measure used to define the characteristics of each sleep stage.

[0023] In one possible implementation, the specific implementation process of S101 includes:

[0024] S201: Extract respiratory stability index, heart rate stability index, body movement amplitude, and bed rest markers from the human body echo signal;

[0025] S202: Calculate the sleep stage index corresponding to each calculation cycle of the human body during the sleep period based on the respiratory stability index, the heart rate stability index, the body movement amplitude, and the bedside marker.

[0026] Specifically, the sleep period refers to the time between when a user goes to bed and when they get out of bed. The radar extracts respiratory stability index, heart rate stability index, body movement amplitude, and bed presence markers from the human body echo signal during the sleep period.

[0027] The respiratory stability index characterizes respiratory stability by measuring the speed and amplitude of body movements (micro-movements of the chest caused by breathing). A higher respiratory stability index indicates more unstable breathing and a higher probability that the person is currently in a light sleep stage; a lower respiratory stability index indicates more stable breathing and a higher probability that the person is currently in a deep sleep stage. Similarly, the heart rate stability index characterizes heart rate stability by measuring the speed and amplitude of body movements (micro-movements of the chest caused by heartbeat). A higher heart rate stability index indicates more unstable heart rate and a higher probability that the person is currently in a light sleep stage; a lower heart rate stability index indicates more stable heart rate and a higher probability that the person is currently in a deep sleep stage.

[0028] Body movement amplitude is used to represent the range of changes in the human body as a whole. The value of the bed indicator includes 0 and 1, where 0 indicates that the person is not in bed and 1 indicates that the person is in bed.

[0029] In one possible implementation, the specific implementation process of S201 includes:

[0030] Respiratory amplitude, respiratory rate, heart rate amplitude, and heart rate are extracted from the human body echo signal;

[0031] Based on formula

[0032]

[0033] Calculate the respiratory stability index;

[0034] Based on formula

[0035]

[0036] Calculate the heart rate stability index;

[0037] Where breathStability(n) represents the respiratory stability index corresponding to the nth calculation cycle, N represents the third preset value, std() represents the standard deviation calculation function, breathAmp() represents the array of respiratory amplitude, breathFreq() represents the array of respiratory frequency, heartStability(n) represents the heart rate stability index corresponding to the nth calculation cycle, heartAmp() represents the array of heart rate, heartFreq() represents the array of heart rate, and minNum represents the number of calculation cycles included in the sleep period.

[0038] Specifically, `heartFreq(1:N / 2)` represents an array of heart rate frequencies from the 1st to the N / 2nd calculation period, `heartFreq(nN / 2:n+N / 2-1)` represents an array of heart rate frequencies from the nN / 2th to the (n+N / 2-1)th calculation period, and `heartFreq(min Num-N / 2+1:min Num)` represents an array of heart rate frequencies from the min Num-N / 2+1th to the min Numth calculation period; `heartAmp(1:N / 2)` represents an array of heart rate amplitudes from the 1st to the N / 2nd calculation period, `heartAmp(nN / 2:n+N / 2-1)` represents an array of heart rate amplitudes from the nN / 2th to the (n+N / 2-1)th calculation period, and `heartAmp(min Num-N / 2+1:minNum)` represents an array of heart rate amplitudes from the min Num-N / 2+1th to the min Numth calculation period. An array of Num heartbeat amplitudes for each calculation cycle.

[0039] `breathFreq(1:N / 2)` represents an array of respiratory frequencies from the 1st to the N / 2nd calculation period; `breathFreq(nN / 2:n+N / 2-1)` represents an array of respiratory frequencies from the nN / 2nd to the (n+N / 2-1)th calculation period; `breathFreq(min Num-N / 2+1:min Num)` represents an array of respiratory frequencies from the min Num-N / 2+1th to the min Numth calculation period; `breathAmp(1:N / 2)` represents an array of respiratory amplitudes from the 1st to the N / 2nd calculation period; `breathAmp(nN / 2:n+N / 2-1)` represents an array of respiratory amplitudes from the nN / 2nd to the (n+N / 2-1)th calculation period; `breathAmp(min Num-N / 2+1:minNum)` represents an array of respiratory amplitudes from the min Num-N / 2+1th to the min Numth calculation period. An array of Num calculation cycles representing respiratory amplitude.

[0040] For example, the calculation cycle can be 1 minute, that is, a sleep stage index is obtained every minute. N can be set by the user, and a typical value can be 30.

[0041] In one possible implementation, the specific implementation process of S202 includes:

[0042] Based on the "in-bed" indicator, determine whether the person is in bed during the current calculation period;

[0043] If the person is in bed during the current calculation period, the sleep stage index corresponding to each calculation period during the sleep period is calculated based on the formula sleepSta(n)=weight1*breathStability(n)+weight2*heartStability(n)+weight3*moveValue(n). Wherein, sleepSta(n) represents the sleep stage index corresponding to the nth calculation period, breathStability(n) represents the breathing stability index corresponding to the nth calculation period, heartStability(n) represents the heart rate stability index corresponding to the nth calculation period, moveValue(n) represents the body movement amplitude corresponding to the nth calculation period, weight1 represents the fourth weight, weight2 represents the fifth weight, and weight3 represents the sixth weight.

[0044] If the person is not in bed during the current calculation period, the sleep stage index corresponding to the current calculation period will be set to the default value.

[0045] Specifically, the default value can be -1. When the sleep stage index is -1, it means that the person is not in bed.

[0046] The above method can comprehensively reflect the stability of human respiration by calculating the product of the standard deviations of respiratory frequency and respiratory amplitude in multiple calculation cycles near the current calculation cycle. Similarly, it can comprehensively reflect the stability of human heartbeat by calculating the product of the standard deviations of heart rate and heartbeat amplitude in multiple calculation cycles near the current calculation cycle.

[0047] It should be noted that since respiration has a greater impact on body movement than heartbeat, the respiratory stability index calculated based on radar information is more accurate than the heartbeat stability index. Therefore, in practical applications, the respiratory stability index has a greater weight than the heartbeat stability index. Of course, the final weighting can be determined through extensive testing and verification with a large amount of data to find the most accurate weighting method.

[0048] S102: Calculate the sleep stage threshold corresponding to the current calculation cycle based on the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle.

[0049] In one possible implementation, the sleep stage threshold includes a light sleep threshold; the specific implementation process of S102 includes:

[0050] S201: Calculate the average value of the sleep stage index corresponding to all calculation cycles during the sleep period to obtain the total average value;

[0051] S202: Calculate the standard deviation of the sleep stage index for multiple calculation cycles near the current calculation cycle;

[0052] S203: Based on the total average value and the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle, calculate the light sleep threshold corresponding to the current calculation cycle.

[0053] In one possible implementation, the specific implementation process of S203 includes:

[0054] Based on formula

[0055]

[0056] Calculate the light sleep threshold corresponding to the current calculation cycle;

[0057] Wherein, lightThre(n) represents the light sleep threshold of the nth calculation cycle within the sleep period, sleepStaMean represents the total average value, sleepSta() represents the array of sleep stage indices, minNum represents the number of calculation cycles included in the sleep period, std() represents the standard deviation calculation function, M represents the first preset value, and weight4 represents the first weight.

[0058] Specifically, the mean of each person's sleep stage index during a sleep period reflects the average sleep quality of that individual during that sleep cycle, while the weighted average of the standard deviations of the sleep stage index over a period around the current calculation period reflects the individual's sleep quality over that period. If a person was awake for a period of time, the standard deviation of the sleep stage index will be relatively large. In this case, the light sleep threshold is lower, and the sleep stage index needs to be relatively low to be classified as light sleep; otherwise, it will be classified as awake. If a person was in a light sleep or deep sleep period of time, the standard deviation of the sleep stage index will be relatively small. In this case, the light sleep threshold is higher, and the sleep stage index needs to be relatively high to be classified as awake; otherwise, it will be classified as light sleep or deep sleep.

[0059] For example, M can be set by the user, with a typical value of 60.

[0060] The above method combines the average sleep duration of a user's current sleep session with the standard deviation of sleep duration over the current time period. It can effectively adjust the sleep threshold adaptively based on the individual's actual sleep situation. When a user is in the current sleep stage, a significant change in the sleep stage index is required before entering another sleep stage. This improves the accuracy of sleep stage determination and makes the sleep stage method applicable to everyone, thus expanding its application.

[0061] In one possible implementation, the sleep stage threshold includes a deep sleep threshold; the specific implementation process of S102 includes:

[0062] Based on formula

[0063]

[0064] Calculate the deep sleep threshold corresponding to the current calculation cycle;

[0065] Wherein, deepThre(n) represents the deep sleep threshold of the nth calculation cycle within the sleep period, mean() represents the average value calculation function, sleepSta() represents the array of sleep stage indices, minNum represents the number of calculation cycles included in the sleep period, std() represents the standard deviation calculation function, K represents the second preset value, weight5 represents the second weight, and weight6 represents the third weight.

[0066] Specifically, the radar calculates the deep sleep threshold by subtracting the weighted average of the standard deviations of the sleep stage index over a period of time around the current calculation cycle from the mean of the sleep stage index over the same period. Thus, if a person was awake for a period of time, the weighted average of the sleep stage index minus the standard deviation will be smaller, indicating a lower deep sleep threshold; a relatively low sleep stage index is needed to determine if the person is in deep sleep. Conversely, if a person was in deep sleep for a period of time, the weighted average of the sleep stage index minus the standard deviation will be larger, indicating a higher deep sleep threshold. The sleep stage index can easily determine if the user is in deep sleep, requiring a significant increase to indicate the user has entered a light sleep stage.

[0067] For example, K can be set by the user, with a typical value of 30.

[0068] The above method combines the average sleep duration of a user's current sleep session with the standard deviation of sleep duration over the current time period. It can effectively adjust the sleep threshold according to the individual's actual sleep situation, thereby improving the accuracy of sleep staging results.

[0069] S103: Determine the sleep stage result for the current calculation period based on the sleep stage index and the corresponding sleep stage threshold for the current calculation period.

[0070] In one possible implementation, the sleep stage threshold includes a deep sleep threshold and a light sleep threshold; and the deep sleep threshold is less than the light sleep threshold; the specific implementation process of S103 includes:

[0071] If the sleep stage index of the current calculation cycle is greater than or equal to the light sleep threshold, then the sleep stage result of the current calculation cycle is determined to be the waking period;

[0072] If the sleep stage index of the current calculation period is less than the light sleep threshold and greater than or equal to the deep sleep threshold, then the sleep stage result of the current calculation period is determined to be light sleep.

[0073] If the sleep stage index of the current calculation period is less than the deep sleep threshold, then the sleep stage result of the current calculation period is determined to be deep sleep.

[0074] It should be noted that the above restriction that the deep sleep threshold is less than the light sleep threshold is a limitation on the size of the two sleep stage thresholds for the same person. The size of the deep sleep threshold and light sleep threshold for different people is not subject to the above restriction.

[0075] This invention can analyze the sleep stage index based on human sleep characteristics and obtain an adaptive sleep stage threshold. Based on this sleep stage threshold, the sleep stage results can be obtained more accurately.

[0076] It should be understood that the sequence number of each step in the above embodiments does not imply 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 the present invention.

[0077] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0078] Figure 2 A schematic diagram of a radar-based sleep staging device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0079] like Figure 2 As shown, the radar-based sleep staging device 100 includes:

[0080] The sleep stage index calculation module 110 is used to acquire human body echo signals detected by radar in a preset monitoring area in real time, and calculate the sleep stage index corresponding to each calculation cycle of the human body during the sleep period based on the human body echo signals.

[0081] The sleep stage threshold calculation module 120 is used to calculate the sleep stage threshold corresponding to the current calculation cycle based on the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle.

[0082] The sleep staging module 130 is used to determine the sleep staging result for the current calculation period based on the sleep staging index and the corresponding sleep staging threshold for the current calculation period.

[0083] In one possible implementation, the sleep stage threshold includes a light sleep threshold; the sleep stage threshold calculation module 120 includes:

[0084] The total average calculation unit is used to calculate the average value of the sleep stage index corresponding to all calculation cycles during the sleep period, and obtain the total average value.

[0085] The standard deviation calculation unit is used to calculate the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle.

[0086] The light sleep threshold calculation unit is used to calculate the light sleep threshold corresponding to the current calculation cycle based on the total average value and the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle.

[0087] In one possible implementation, the light sleep threshold calculation unit includes:

[0088] Based on formula

[0089]

[0090] Calculate the light sleep threshold corresponding to the current calculation cycle;

[0091] Wherein, lightThre(n) represents the light sleep threshold of the nth calculation cycle within the sleep period, sleepStaMean represents the total average value, sleepSta() represents the array of sleep stage indices, minNum represents the number of calculation cycles included in the sleep period, std() represents the standard deviation calculation function, M represents the first preset value, and weight4 represents the first weight.

[0092] In one possible implementation, the sleep stage threshold includes a deep sleep threshold; the sleep stage threshold calculation module 120 further includes:

[0093] Based on formula

[0094]

[0095] Calculate the deep sleep threshold corresponding to the current calculation cycle;

[0096] Wherein, deepThre(n) represents the deep sleep threshold of the nth calculation cycle within the sleep period, mean() represents the average value calculation function, sleepSta() represents the array of sleep stage indices, minNum represents the number of calculation cycles included in the sleep period, std() represents the standard deviation calculation function, K represents the second preset value, weight5 represents the second weight, and weight6 represents the third weight.

[0097] In one possible implementation, the sleep staging threshold includes a deep sleep threshold and a light sleep threshold; and the deep sleep threshold is less than the light sleep threshold; the sleep staging module 130 includes:

[0098] If the sleep stage index of the current calculation cycle is greater than or equal to the light sleep threshold, then the sleep stage result of the current calculation cycle is determined to be the waking period;

[0099] If the sleep stage index of the current calculation period is less than the light sleep threshold and greater than or equal to the deep sleep threshold, then the sleep stage result of the current calculation period is determined to be light sleep.

[0100] If the sleep stage index of the current calculation period is less than the deep sleep threshold, then the sleep stage result of the current calculation period is determined to be deep sleep.

[0101] In one possible implementation, the sleep staging index calculation module 110 includes:

[0102] The feature extraction unit is used to extract respiratory stability index, heart rate stability index, body movement amplitude, and bed rest markers from the human body echo signal.

[0103] The sleep stage index calculation unit is used to calculate the sleep stage index corresponding to each calculation cycle of the human body during the sleep period based on the respiratory stability index, the heart rate stability index, the body movement amplitude, and the bedside marker.

[0104] In one possible implementation, the feature extraction unit includes:

[0105] Respiratory amplitude, respiratory rate, heart rate amplitude, and heart rate are extracted from the human echo signal; based on the formula

[0106]

[0107] Calculate the respiratory stability index;

[0108] Based on formula

[0109]

[0110] Calculate the heart rate stability index;

[0111] Where breathStability(n) represents the respiratory stability index corresponding to the nth calculation cycle, N represents the third preset value, std() represents the standard deviation calculation function, breathAmp() represents the array of respiratory amplitude, breathFreq() represents the array of respiratory frequency, heartStability(n) represents the heart rate stability index corresponding to the nth calculation cycle, heartAmp() represents the array of heart rate, heartFreq() represents the array of heart rate, and minNum represents the number of calculation cycles included in the sleep period.

[0112] In one possible implementation, the sleep staging index calculation unit includes:

[0113] Based on the "in-bed" indicator, determine whether the person is in bed during the current calculation period;

[0114] If the person is in bed during the current calculation period, the sleep stage index corresponding to each calculation period during the sleep period is calculated based on the formula sleepSta(n)=weight1*breathStability(n)+weight2*heartStability(n)+weight3*moveValue(n). Wherein, sleepSta(n) represents the sleep stage index corresponding to the nth calculation period, breathStability(n) represents the breathing stability index corresponding to the nth calculation period, heartStability(n) represents the heart rate stability index corresponding to the nth calculation period, moveValue(n) represents the body movement amplitude corresponding to the nth calculation period, weight1 represents the fourth weight, weight2 represents the fifth weight, and weight3 represents the sixth weight.

[0115] If the person is not in bed during the current calculation period, the sleep stage index corresponding to the current calculation period will be set to the default value.

[0116] The radar-based sleep staging device provided in this embodiment can be used to execute the radar-based sleep staging method embodiment described above. Its implementation principle and technical effect are similar, and will not be repeated here.

[0117] Figure 3 This is a schematic diagram of a terminal provided in an embodiment of the present invention. For example... Figure 3 As shown, the terminal 3 in 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, it implements the steps in the various radar-based sleep staging method embodiments described above, for example... Figure 1Steps S101 to S103 are shown. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of modules 110 to 130 are shown.

[0118] For example, the computer program 32 can be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 32 in the terminal 3.

[0119] The terminal 3 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal 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 merely an example of terminal 3 and does not constitute a limitation on terminal 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal may also include input / output devices, network access devices, buses, etc.

[0120] The processor 30 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0121] The memory 31 can be an internal storage unit of the terminal 3, such as a hard disk or memory of the terminal 3. The memory 31 can also be an external storage device of the terminal 3, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal 3. Furthermore, the memory 31 can include both internal storage units and external storage devices of the terminal 3. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to 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 embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0124] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0125] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0128] If the integrated module / unit is implemented as 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, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various radar-based sleep staging method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0129] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A radar-based sleep staging method, characterized by, include: The system acquires human echo signals detected by radar in a preset monitoring area in real time, and calculates the sleep stage index corresponding to each calculation cycle during the sleep period based on the human echo signals. Based on the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle, calculate the sleep stage threshold corresponding to the current calculation cycle. Based on the sleep stage index and the corresponding sleep stage threshold of the current calculation period, the sleep stage result of the current calculation period is determined; The sleep stage thresholds include the light sleep threshold; The calculation of the sleep stage threshold corresponding to the current calculation cycle based on the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle includes: Calculate the average value of the sleep stage index corresponding to all calculation cycles within the sleep period to obtain the overall average value; Calculate the standard deviation of the sleep stage index for multiple calculation cycles near the current calculation cycle; Based on the total average value and the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle, the light sleep threshold corresponding to the current calculation cycle is calculated. The calculation of the light sleep threshold corresponding to the current calculation cycle based on the total average and the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle includes: Based on formula ， Calculate the light sleep threshold corresponding to the current calculation cycle; wherein, represents a light sleep threshold for a computation period of the sleep session, n represents the total average value, represents an array of sleep stage indices, represents a number of computation periods included in the sleep session, represents a standard deviation computation function, M represents a first preset value, represents a first weight.​ 2. The radar-based sleep staging method according to claim 1, characterized in that, The sleep stage thresholds include the deep sleep threshold; The calculation of the sleep stage threshold corresponding to the current calculation cycle based on the standard deviation of the sleep stage index corresponding to multiple calculation cycles near the current calculation cycle includes: Based on formula Calculate the deep sleep threshold corresponding to the current calculation cycle; in, Indicates the first [number]th ... n The deep sleep threshold for each calculation cycle. This represents the function for calculating the average value. An array representing the sleep stage index, This indicates the number of calculation cycles included in the sleep period. This represents the function for calculating standard deviation. K This indicates the second preset value. Indicates the second weight. This indicates the third weight.

3. The radar-based sleep staging method according to claim 1, characterized in that, The sleep stage thresholds include a deep sleep threshold and a light sleep threshold; and the deep sleep threshold is less than the light sleep threshold. The step of determining the sleep stage result for the current calculation period based on the sleep stage index and the corresponding sleep stage threshold for the current calculation period includes: If the sleep stage index of the current calculation cycle is greater than or equal to the light sleep threshold, then the sleep stage result of the current calculation cycle is determined to be the waking period; If the sleep stage index of the current calculation period is less than the light sleep threshold and greater than or equal to the deep sleep threshold, then the sleep stage result of the current calculation period is determined to be light sleep. If the sleep stage index of the current calculation period is less than the deep sleep threshold, then the sleep stage result of the current calculation period is determined to be deep sleep.

4. The radar-based sleep staging method according to claim 1, characterized in that, The calculation of the sleep stage index corresponding to each calculation cycle during the sleep period based on the human body echo signal includes: Respiratory stability index, heart rate stability index, body movement amplitude, and bed rest markers are extracted from the human body echo signal. Based on the respiratory stability index, the heart rate stability index, the body movement amplitude, and the bedside markers, the sleep stage index corresponding to each calculation cycle during the sleep period is calculated.

5. The radar-based sleep staging method according to claim 4, characterized in that, The extraction of respiratory stability index and heart rate stability index from the human body echo signal includes: Respiratory amplitude, respiratory rate, heart rate amplitude, and heart rate are extracted from the human body echo signal; Based on formula Calculate the respiratory stability index; Based on formula Calculate the heart rate stability index; in, Indicates the first n The respiratory stability index corresponding to each calculation cycle. N This represents the third preset value. This represents the function for calculating standard deviation. An array representing the amplitude of breathing. An array representing respiratory rate. Indicates the first n The heart rate stability index corresponding to each calculation cycle. An array representing the amplitude of the heartbeat. An array representing heart rate. This indicates the number of calculation cycles included in the sleep period.

6. The radar-based sleep staging method according to claim 4, characterized in that, The calculation of the sleep stage index corresponding to each calculation cycle during the sleep period based on the respiratory stability index, the heart rate stability index, the body movement amplitude, and the bedside markers includes: Based on the "in-bed" indicator, determine whether the person is in bed during the current calculation period; If the person is in bed during the current calculation period, then based on the formula... Calculate the sleep stage index corresponding to each calculation cycle during the sleep period; among which, This represents the sleep stage index corresponding to the nth calculation period. Indicates the first n The respiratory stability index corresponding to each calculation cycle. Indicates the first n The heart rate stability index corresponding to each calculation cycle. Indicates the first n The amplitude of body movement corresponding to each calculation cycle Indicates the fourth weight. Indicates the fifth weight. Indicates the sixth weight; If the person is not in bed during the current calculation period, the sleep stage index corresponding to the current calculation period will be set to the default value.

7. A terminal, characterized in that, It includes a processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to perform the method as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6 above.

Images