Sleep quality evaluation method and system based on non-contact UWB radar vital sign signals

Abstract

The invention discloses a sleep quality assessment method and system based on a non-contact UWB radar vital sign signal, and relates to the technical field of sleep quality assessment, and the method specifically comprises the following steps: S1, obtaining vital sign data; the method comprises the following steps: S1, acquiring vital sign data in a sleep process of a human body through a non-contact UWB radar, the vital sign data comprising a heart rate, a respiratory rate, a distance, body movement and body movement energy, S2, processing the vital sign data in S1; by setting a time judgment window T, clustering analysis and feature processing are carried out on the vital sign data in each T time from the starting point of a specified monitoring time interval, and a sequence of sleep states in each T time and a time-sharing sequence of the sleep states are obtained. The sleep mode is monitored continuously for a long time in a non-contact mode, sleep is not affected, privacy invasion is avoided, a personalized sleep health file is established for a user, the user can find related problems of sleep disorders in advance, and an effective reference basis is provided for subsequent treatment by doctors.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep quality assessment, and in particular to a sleep quality assessment method and system based on non-contact UWB radar vital sign signals. Background Art

[0002] With the rapid development of modern society, people's life pressure, work pressure, irritability and worries are getting greater and greater, and various insomnia, anxiety and depression follow. Sleep has become an important issue that affects the normal rhythm of life.

[0003] The demand for sleep statistics is indeed not hard, so if this not-so-hard demand is troublesome to achieve, people will have no motivation to persist. If there is a sleep monitoring device that does not require people to adjust the switch, and can automatically detect the human body's sleep status for a long time without feeling, it will be very convenient and intelligent for users to use. Therefore, non-contact tracking of changes in human body signs can understand what qualitative changes have occurred in people during sleep, and then automatically turn on the detection function, and finally give users complete sleep statistics and sleep quality assessments. In this way, you can know which indicators in your sleep process are abnormal, which can help you better manage your health, discover potential health problems, and take appropriate measures for prevention and treatment.

[0004] In the existing technology, contact-based and intermittent monitoring of sleep patterns can easily affect sleep and cause privacy violations. To this end, we propose a sleep quality assessment method and system based on non-contact UWB radar vital sign signals to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a sleep quality assessment method and system based on non-contact UWB radar vital sign signals to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for evaluating sleep quality based on non-contact UWB radar vital sign signals, specifically comprising the following steps:

[0007] S1. Obtaining vital sign data: Obtaining vital sign data of a human body during sleep through a non-contact UWB radar, the vital sign data including heart rate, respiratory rate, distance, body movement and body movement energy;

[0008] S2, processing the vital sign data in S1; by setting a time judgment window T, starting from the start point of the specified monitoring time interval, clustering analysis and feature processing are performed on the vital sign data within each T time, and the sequence of sleep states within each T time and the time-sharing sequence of sleep states are obtained;

[0009] S3, data correction: correcting the time-sharing sequence of the sleep state obtained in S2 to obtain a stage sequence of the complete sleep state;

[0010] S4, statistics of various indicators; statistics of various indicators related to sleep health in the stage sequence of sleep state in S3, including sleep stage statistics, sleep structure interpretation, heart rate statistics, respiratory rate statistics, and body movement statistics;

[0011] S5. Obtaining evaluation results: Based on various indicators collected during sleep, a comprehensive analysis is performed to obtain sleep quality evaluation results, which include sleep score and sleep score.

[0012] A sleep quality assessment system based on non-contact UWB radar vital sign signals, comprising:

[0013] Data acquisition module; the data acquisition module is used to obtain vital signs data throughout the night;

[0014] Data analysis module: the data analysis module is used to obtain the whole night vital sign data set from the data acquisition module, and process the vital sign data set to obtain a sleep stage and time series;

[0015] An indicator statistics module; the indicator statistics module obtains the sleep stage time-sharing sequence in the data analysis module and processes the sleep stage time-sharing sequence;

[0016] Sleep quality assessment module: The sleep quality assessment module is used to score and assess the various results of the sleep stage and time sequence processing obtained by the indicator statistics module, and evaluate the sleep quality according to the final total score;

[0017] A microprocessor, the microprocessor is used to retrieve data from the data acquisition module, the data analysis module, the index statistics module and the sleep quality assessment module, and send control commands to the data acquisition module, the data analysis module, the index statistics module and the sleep quality assessment module;

[0018] The microprocessor is respectively connected to the radar data acquisition module, the data analysis module, the index statistics module, and the sleep quality assessment module.

[0019] Furthermore, the vital signs data acquired by the data acquisition module include human body movement, heart rate, respiratory rate, target distance and body movement energy rate. The radar echo containing physiological information is processed through clutter suppression technology and Doppler micro-motion signal adaptive algorithm to obtain the detected human vital signs data.

[0020] Furthermore, the acquired whole-night vital sign data set includes time-series data of five dimensions: heart rate, respiratory rate, target distance, body movement, and body movement energy. The data analysis module includes a sleep state recognition and staging unit and a sleep result correction unit; wherein the sleep state recognition and staging specifically includes the following processes:

[0021] A time judgment window T is set, and the vital signs data within each T time is extracted as the data sample to be classified. The clustering algorithm is used to obtain the cluster center. When the characteristics of the data sample are within the range of the cluster center, it is judged to be in the "sleep" state, otherwise, it is judged to be in the "non-sleep" state; a multi-feature optimization function is used as the weight when updating the cluster center to reduce the influence of outliers in the data sample on the accuracy of the cluster center, and further update the "sleep" and "non-sleep" state judgment rules; a step-by-step clustering processing method is designed according to the data set of the identified "sleep" state, and the feature judgment rules for different sleep stages of light sleep, rapid eye movement and deep sleep are obtained respectively; finally, the sleep state of the whole night sleep time series is staged.

[0022] Furthermore, the sleep result correction specifically includes the following process:

[0023] The stage from when a person lies down and changes from an unstable state of preparing to sleep to actually falling asleep is determined as "sleep onset latency"; the stage from a continuous stable state after waking up from sleep and getting out of bed to being awakened is determined as "wake-up latency"; the point where the "sleep onset latency" starts is defined as the "bedtime"; the point where the "sleep onset latency" ends is defined as the "sleep onset time"; the point where the "wake-up latency" starts is defined as the "wake-up time"; the point where the "wake-up latency" ends is defined as the "wake-up time", and the final complete sleep staging time-sharing sequence includes: bedtime, sleep onset time, wake-up time, wake-up time, sleep onset latency, wake-up latency, wake-up period, light sleep period, rapid eye movement period, deep sleep period; the sleep result correction corrects the result of the whole night sleep time series, the sleep staging result conforms to the actual law of sleep state change, and the final sleep staging time-sharing sequence is determined.

[0024] Further, the indicator statistics module includes a sleep staging indicator unit, a sleep structure indicator unit, a respiratory rate statistics unit, a heart rate statistics unit and a body movement statistics unit, the sleep staging indicator unit is used to count the sleep staging time-sharing sequence, the sleep structure indicator unit is used to divide the sleep staging time-sharing sequence, and the respiratory rate statistics unit, the heart rate statistics unit and the body movement statistics unit are used to count part of the vital sign data;

[0025] Among them: the statistical sleep stage time-sharing sequence specifically statistics the time points and time proportions of the sleep states in the sleep stage time-sharing sequence, and the time points and time proportions of the sleep states include: the time of falling asleep, the time of waking up, the time of going to bed, the time of getting up, the total number of awake times, the total duration of awake time, the proportion of light sleep, the proportion of rapid eye movement, and the proportion of deep sleep.

[0026] Furthermore, the scoring and evaluation includes the following process:

[0027] Refer to the Pittsburgh Sleep Quality Index and combine it with sleep health indicators to develop a sleep quality scoring standard, and then select 7 health indicators for scoring and evaluation;

[0028] Among them: each of the 7 health indicators is scored at different levels, and the accumulated scores of each health indicator are the sleep quality reduction points. The total score ranges from 0 to 50. The higher the score, the worse the sleep quality.

[0029] Furthermore, the sleep staging time-sharing sequence is divided into four structures, including early sleep, middle sleep, late sleep and sleep waking, and some of the vital signs data counted are the whole night heart rate, the whole night breathing rate and the whole night body movement.

[0030] Furthermore, the descriptions of the seven health indicators and the specific scoring methods are as follows:

[0031] (A) When falling asleep; "below 23:00" is scored as A1; "between 23:00 and 24:00" is scored as A2; "between 00:00 and 01:00" is scored as A3; "after 01:00" is scored as A4;

[0032] (B) Total sleep time; ">7 hours" is scored as B1; "6-7" is scored as B2; "5-6" is scored as B3; "<5 hours" is scored as B4;

[0033] (C) Percentage of deep sleep; "<10%" is scored as C1; "10-15%" is scored as C2; "15-20%" is scored as C3; ">20%" is scored as C4;

[0034] (D) Number of awake times; “0 times” was scored as D1; ​​“1-2 times” was scored as D2; “3-5 times” was scored as D3; “>5 times” was scored as D4;

[0035] (E) Sleep latency; “≤30 minutes” is scored as E1; ">30 minutes" is scored as E2;

[0036] (F) Abnormal sleep results; "Normal early sleep" is counted as F1; "Abnormal early sleep" is counted as F2; ​​"Normal mid-sleep" is counted as F3; "Abnormal mid-sleep" is counted as F4; "Normal late sleep" is counted as F5; "Abnormal late sleep" is counted as F6; "Normal waking up from sleep" is counted as F7; "Abnormal waking up from sleep" is counted as F8;

[0037] (G) Body movement; “≤6 times” is scored as G1; ">6 times" is scored as G2;

[0038] Total sleep score = 100-(component A + component B + component C + component D + component E + component F + component G score);

[0039] Sleep evaluation: "0-59 points" is poor; "60-69 points" is passing; "70-79 points" is fair; "80-89 points" is good; "90-100 points" is excellent.

[0040] Furthermore, the data acquisition module includes a transmitting antenna, a receiving antenna, an antenna controller and a signal processor, and the transmitting antenna, the receiving antenna, the antenna controller and the signal processor are connected in sequence, and the antenna controller is an antenna controller for the transmitting antenna and the receiving antenna.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. Non-contact, long-term uninterrupted monitoring of sleep patterns, without affecting sleep and privacy infringement, establishes personalized sleep health records for users, allowing users to detect sleep disorder-related problems early, making it easier for subsequent doctors to provide effective reference for treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a system diagram of a sleep quality assessment system based on non-contact UWB radar vital sign signals in the present invention;

[0044] Figure 2 It is a system diagram of a data acquisition module of a sleep quality assessment system based on non-contact UWB radar vital sign signals in the present invention;

[0045] Figure 3 It is a system diagram of a data analysis module of a sleep quality assessment system based on non-contact UWB radar vital sign signals in the present invention;

[0046] Figure 4 This is a system diagram of a data acquisition module of a sleep quality assessment system based on non-contact UWB radar vital sign signals in the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] A sleep quality assessment method based on non-contact UWB radar vital sign signals specifically comprises the following steps:

[0049] S1. Obtaining vital sign data: Obtaining vital sign data of a human body during sleep through a non-contact UWB radar, the vital sign data including heart rate, respiratory rate, distance, body movement and body movement energy;

[0050] S2, processing the vital sign data in S1; by setting a time judgment window T, starting from the start point of the specified monitoring time interval, clustering analysis and feature processing are performed on the vital sign data within each T time, and the sequence of sleep states within each T time and the time-sharing sequence of sleep states are obtained;

[0051] S3, data correction: correcting the time-sharing sequence of the sleep state obtained in S2 to obtain a stage sequence of the complete sleep state;

[0052] S4, statistics of various indicators; statistics of various indicators related to sleep health in the stage sequence of sleep state in S3, including sleep stage statistics, sleep structure interpretation, heart rate statistics, respiratory rate statistics, and body movement statistics;

[0053] S5. Obtaining evaluation results: Based on various indicators collected during sleep, a comprehensive analysis is performed to obtain sleep quality evaluation results, which include sleep score and sleep score.

[0054] A sleep quality assessment system based on non-contact UWB radar vital sign signals, comprising:

[0055] Data acquisition module 110; the data acquisition module 110 is used to obtain the vital signs data throughout the night; the data acquisition module 110 includes a transmitting antenna, a receiving antenna, an antenna controller and a signal processor, the transmitting antenna, the receiving antenna, the antenna controller and the signal processor are connected in sequence, and the antenna controller is an antenna controller for the transmitting antenna and the receiving antenna; the vital signs data obtained by the data acquisition module 110 include human body movement, heart rate, respiratory rate, target distance and body movement energy rate, and the radar echo containing physiological information is processed through the clutter suppression technology and the Doppler micro-motion signal adaptive algorithm to obtain the detected human vital signs data;

[0056] Data analysis module 120; the data analysis module 120 is used to obtain the whole night vital sign data set of the data acquisition module 110, and process the vital sign data set to obtain a sleep stage time series; the whole night vital sign data set obtained includes time series data of five dimensions: heart rate, respiratory rate, target distance, body movement and body movement energy. The data analysis module 120 includes a sleep state recognition and staging unit and a sleep result correction unit; wherein:

[0057] The sleep state identification and staging specifically includes the following processes: setting a time judgment window T, extracting vital sign data within each T time as the data sample to be classified, using a clustering algorithm to obtain the cluster center, and when the characteristics of the data sample are within the range of the cluster center, it is judged to be in a "sleep" state, otherwise, it is judged to be in a "non-sleep" state; using a multi-feature optimization function as the weight when updating the cluster center to reduce the influence of outliers in the data sample on the accuracy of the cluster center, and further updating the "sleep" and "non-sleep" state judgment rules; designing a step-by-step clustering processing method based on the data set of the identified "sleep" state, and respectively deriving the characteristic judgment rules for different sleep stages of light sleep, rapid eye movement and deep sleep; finally, staging the sleep state of the whole night sleep time series;

[0058] The correction of sleep results specifically includes the following processes: the stage from when a person lies down and changes from an unstable state of preparing to sleep to actually falling asleep is determined as the "sleep onset latency"; the previous continuous stable state after waking up from sleep and getting out of bed is transformed into the awakening stage and determined as the "wake-up latency"; the starting point of the "sleep onset latency" is defined as the "bedtime"; the end point of the "sleep onset latency" is defined as the "sleep onset time"; the starting point of the "wake-up latency" is defined as the "wake-up time"; the end point of the "wake-up latency" is defined as the "wake-up time", and the final complete sleep stage time-sharing sequence includes: bedtime, sleep onset time, wake-up time, wake-up time, sleep onset latency, wake-up latency, wake-up period, light sleep period, rapid eye movement period, deep sleep period; the sleep result correction corrects the results of the whole night sleep time series, the sleep staging results are in line with the actual law of changes in sleep state, and the final sleep staging time-sharing sequence is determined.

[0059] The indicator statistics module 130; the indicator statistics module 130 obtains the sleep staging time-sharing sequence in the data analysis module 120, and processes the sleep staging time-sharing sequence; the indicator statistics module 130 includes a sleep staging indicator unit, a sleep structure indicator unit, a respiratory rate statistics unit, a heart rate statistics unit and a body movement statistics unit, the sleep staging indicator unit is used to count the sleep staging time-sharing sequence, the sleep structure indicator unit is used to divide the sleep staging time-sharing sequence, the respiratory rate statistics unit, the heart rate statistics unit and the body movement statistics unit are used to count part of the vital sign data; wherein:

[0060] The statistical sleep stage time series specifically includes the statistical time points and time proportions of the sleep states in the sleep stage time series. The time points and time proportions of the sleep states include: the time of falling asleep, the time of waking up, the time of going to bed, the time of waking up, the total number of awake times, the total duration of awake time, the proportion of light sleep, the proportion of rapid eye movement, and the proportion of deep sleep;

[0061] The sleep stage time series is divided into four structures, including the early sleep stage, the middle sleep stage, the late sleep stage and the sleep awakening stage. Some of the vital signs data collected are the heart rate, respiratory rate and body movement throughout the night. Among them:

[0062] The pre-sleep stage is divided into 6 categories: 1. Easy to fall asleep; in the first third of the whole night sleep stage time-sharing sequence, when the "sleep onset latency" does not exceed 30 minutes and there is no "awakening", it means "easy to fall asleep"; 2. Easy to fall asleep, but easy to wake up in the middle of the night; in the first third of the whole night sleep stage time-sharing sequence, when the "sleep onset latency" does not exceed 30 minutes and there is "awakening", it means "easy to fall asleep, but easy to wake up in the middle of the night"; 3. Easy to fall asleep, but difficult to maintain sleep; in the first third of the whole night sleep stage time-sharing sequence, when the "sleep onset latency" does not exceed 30 minutes and there are multiple "awakenings", it means "easy to fall asleep, but difficult to maintain sleep"; 4. It is easy to fall asleep, but it takes a little longer to enter deep sleep. In the first third of the time-sharing sequence of the whole night's sleep stages, when the "sleep onset latency" does not exceed 30 minutes and there is no "awake", and the "deep sleep" accounts for a small proportion, it means "it is easy to fall asleep, but it takes a little longer to enter deep sleep"; 5. It is easy to fall asleep, but the sleep is very shallow. In the first third of the time-sharing sequence of the whole night's sleep stages, when the "sleep onset latency" does not exceed 30 minutes and there is no "awake", and there is no "deep sleep", it means "it is easy to fall asleep, but the sleep is very shallow"; 6. Difficulty falling asleep. In the first third of the time-sharing sequence of the whole night's sleep stages, when the "sleep onset latency" exceeds 30 minutes, it means "difficulty falling asleep";

[0063] Mid-sleep is divided into 4 categories: 1. Normal and sufficient sleep. In the middle one-third of the time-sharing sequence of the whole night's sleep stages, when the proportion of "deep sleep" is normal and there is no "awake", it means "normal and sufficient sleep"; 2. Very shallow sleep. In the middle one-third of the time-sharing sequence of the whole night's sleep stages, when there is no "deep sleep" and no "awake", it means "very shallow sleep"; 3. Easy to wake up, but fall asleep again quickly. In the middle one-third of the time-sharing sequence of the whole night's sleep stages, there is only one "awake", which means "easy to wake up, but fall asleep again quickly"; 4. Easy to wake up in the middle of sleep, and it is difficult to fall asleep again. In the middle one-third of the time-sharing sequence of the whole night's sleep stages, there are multiple "awakes", which means "easy to wake up in the middle of sleep, and it is difficult to fall asleep again";

[0064] The late stage of sleep is divided into two categories: 1. Restful sleep. In the last third of the whole night's sleep stage, when the "deep sleep" ratio is normal and there is no "awakening", it means "restful sleep"; 2. Easy to sleep and unable to wake up. In the last third of the whole night's sleep stage, when there are many "awakenings", it means "easy to sleep and unable to wake up";

[0065] There are two types of awakening during sleep: 1. Natural awakening, which means "natural awakening" in the state before the "latency to wake up" of the whole night sleep stage, when the state is not "deep sleep"; 2. Sudden awakening, which means "sudden awakening" in the state before the "latency to wake up" of the whole night sleep stage, when the state is "deep sleep";

[0066] Heart rate throughout the night: with minutes as the granularity unit and taking the average value, record the heart rate value and statistical indicators from bedtime to waking time throughout the night, and the statistical indicators include the time-sharing sequence of heart rate values, minimum heart rate, average heart rate, and maximum heart rate;

[0067] Respiratory rate throughout the night: with minutes as the granularity unit and taking the average value, record the respiratory rate value and statistical indicators from bedtime to waking time throughout the night, and the statistical indicators include the time-sharing series of respiratory rate values, minimum respiratory rate, average respiratory rate, and maximum respiratory rate.

[0068] Body movement throughout the night: with minutes as the granularity unit and taking the average value, record the body movement and statistical indicators from bedtime to waking time throughout the night, and the statistical indicators include the time series of body movement index, body movement duration, body movement frequency, and limb movement index. The limb movement index is the ratio of body movement frequency to total sleep duration.

[0069] Sleep quality assessment module 140: The sleep quality assessment module 140 is used to score and assess the various results of the sleep stage and time sequence processing obtained by the indicator statistics module 130, and assess the sleep quality according to the final total score; the scoring and assessment includes the following processes:

[0070] With reference to the Pittsburgh Sleep Quality Index, the sleep quality scoring standard was formulated in combination with the sleep health index, and then 7 health indicators were selected for scoring and evaluation; among them: the 7 health indicators include 32 items, each of the 7 health indicators is scored at different levels, and the accumulated scores of each health indicator are sleep quality reduction points. The total score ranges from 0 to 50. The higher the score, the worse the sleep quality. The description of the 7 health indicators and the specific scoring method are as follows:

[0071] (A) When falling asleep; "below 23:00" is scored as A1; "between 23:00 and 24:00" is scored as A2; "between 00:00 and 01:00" is scored as A3; "after 01:00" is scored as A4;

[0072] (B) Total sleep time; ">7 hours" is scored as B1; "6-7" is scored as B2; "5-6" is scored as B3; "<5 hours" is scored as B4;

[0073] (C) Percentage of deep sleep; "<10%" is scored as C1; "10-15%" is scored as C2; "15-20%" is scored as C3; ">20%" is scored as C4;

[0074] (D) Number of awake times; “0 times” was scored as D1; ​​“1-2 times” was scored as D2; “3-5 times” was scored as D3; “>5 times” was scored as D4;

[0075] (E) Sleep latency; “≤30 minutes” is scored as E1; ">30 minutes" is scored as E2;

[0076] (F) Abnormal sleep results; "Normal early sleep" is counted as F1; "Abnormal early sleep" is counted as F2; ​​"Normal mid-sleep" is counted as F3; "Abnormal mid-sleep" is counted as F4; "Normal late sleep" is counted as F5; "Abnormal late sleep" is counted as F6; "Normal waking up from sleep" is counted as F7; "Abnormal waking up from sleep" is counted as F8;

[0077] (G) Body movement; “≤6 times” is scored as G1; ">6 times" is scored as G2;

[0078] Total sleep score = 100-(component A + component B + component C + component D + component E + component F + component G score);

[0079] Sleep evaluation: "0-59 points" is poor; "60-69 points" is passing; "70-79 points" is fair; "80-89 points" is good; "90-100 points" is excellent.

[0080] The microprocessor 150 is used to retrieve data from the data acquisition module 110, the data analysis module 120, the index statistics module 130 and the sleep quality assessment module 140, and send control commands to the data acquisition module 110, the data analysis module 120, the index statistics module 130 and the sleep quality assessment module 140;

[0081] The microprocessor 150 is respectively connected to the radar data acquisition module 110 , the data analysis module 120 , the index statistics module 130 , and the sleep quality assessment module 140 .

[0082] It monitors sleep patterns non-contactly and continuously for a long time without affecting sleep or infringing privacy. It builds personalized sleep health records for users, allowing them to detect problems related to sleep disorders early, making it easier for doctors to provide effective reference for treatment.

[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A sleep quality assessment method based on non-contact UWB radar vital sign signals, characterized in that: The specific steps include: S1. Obtaining vital sign data: Obtaining vital sign data of a human body during sleep through a non-contact UWB radar, the vital sign data including heart rate, respiratory rate, distance, body movement and body movement energy; S2, processing the vital sign data in S1; by setting a time judgment window T, starting from the start point of the specified monitoring time interval, clustering analysis and feature processing are performed on the vital sign data within each T time, and the sequence of sleep states within each T time and the time-sharing sequence of sleep states are obtained; S3, data correction: correcting the time-sharing sequence of the sleep state obtained in S2 to obtain a stage sequence of the complete sleep state; S4, statistics of various indicators; statistics of various indicators related to sleep health in the stage sequence of sleep state in S3, including sleep stage statistics, sleep structure interpretation, heart rate statistics, respiratory rate statistics, and body movement statistics; S5. Obtaining evaluation results: Based on various indicators collected during sleep, a comprehensive analysis is performed to obtain sleep quality evaluation results, which include sleep score and sleep score.

2. A sleep quality assessment system based on a non-contact UWB radar vital sign signal according to any one of claim 1, characterized in that: include: Data acquisition module; The data acquisition module is used to obtain vital sign data throughout the night; Data analysis module; The data analysis module is used to obtain the whole night vital sign data set from the data acquisition module, and process the vital sign data set to obtain a sleep stage and time sequence; An indicator statistics module; the indicator statistics module obtains the sleep stage time-sharing sequence in the data analysis module and processes the sleep stage time-sharing sequence; Sleep quality assessment module: The sleep quality assessment module is used to score and assess the various results of the sleep stage and time sequence processing obtained by the indicator statistics module, and evaluate the sleep quality according to the final total score; A microprocessor, the microprocessor is used to retrieve data from the data acquisition module, the data analysis module, the index statistics module and the sleep quality assessment module, and send control commands to the data acquisition module, the data analysis module, the index statistics module and the sleep quality assessment module; The microprocessor is respectively connected to the radar data acquisition module, the data analysis module, the index statistics module, and the sleep quality assessment module.

3. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 2, characterized in that: The vital signs data acquired by the data acquisition module include human body movement, heart rate, respiratory rate, target distance and body movement energy rate. The radar echo containing physiological information is processed through clutter suppression technology and Doppler micro-motion signal adaptive algorithm to acquire the detected human vital signs data.

4. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 2, characterized in that: The acquired whole-night vital sign data set includes time-series data of five dimensions: heart rate, respiratory rate, target distance, body movement and body movement energy. The data analysis module includes a sleep state recognition and staging unit and a sleep result correction unit. The sleep state recognition and staging specifically includes the following processes: A time judgment window T is set, and the vital signs data within each T time is extracted as the data sample to be classified. The clustering algorithm is used to obtain the cluster center. When the characteristics of the data sample are within the range of the cluster center, it is judged as a "sleep" state, otherwise, it is judged as a "non-sleep" state; a multi-feature optimization function is used as the weight when updating the cluster center to reduce the influence of outliers in the data sample on the accuracy of the cluster center, and further update the "sleep" and "non-sleep" state judgment rules; a step-by-step clustering processing method is designed based on the data set of the identified "sleep" state, and the feature judgment rules for different sleep stages of light sleep, rapid eye movement and deep sleep are obtained respectively; finally, the sleep state of the whole night sleep time series is staged.

5. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 4, characterized in that: The sleep result correction specifically includes the following process: The stage from the unstable state of preparing for sleep to the stage of falling asleep is defined as "sleep onset latency"; the stage from the continuous stable state after waking up from sleep and leaving the bed to the stage of being awakened is defined as "wake-up latency"; the starting point of "sleep onset latency" is defined as "bedtime"; the ending point of "sleep onset latency" is defined as "sleep onset time"; the starting point of "wake-up latency" is defined as "wake-up time"; The point where the "awake latency" ends is defined as the "awake time point", and the final complete time sleep staging time-sharing sequence includes: bedtime point, sleep onset time point, waking up time point, wake-up time point, sleep onset latency, wake-up latency, wakefulness, light sleep, rapid eye movement, and deep sleep; the sleep result correction corrects the result of the whole night sleep time series, the sleep staging result conforms to the actual law of sleep state changes, and determines the final sleep staging time-sharing sequence.

6. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 2, characterized in that: The indicator statistics module includes a sleep staging indicator unit, a sleep structure indicator unit, a respiratory rate statistics unit, a heart rate statistics unit and a body movement statistics unit. The sleep staging indicator unit is used to count the sleep staging time-sharing sequence, the sleep structure indicator unit is used to divide the sleep staging time-sharing sequence, and the respiratory rate statistics unit, the heart rate statistics unit and the body movement statistics unit are used to count part of the vital sign data; Among them: the statistical sleep stage time-sharing sequence specifically statistics the time points and time proportions of the sleep states in the sleep stage time-sharing sequence, and the time points and time proportions of the sleep states include: the time of falling asleep, the time of waking up, the time of going to bed, the time of getting up, the total number of awake times, the total duration of awake time, the proportion of light sleep, the proportion of rapid eye movement, and the proportion of deep sleep.

7. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 2, characterized in that: The scoring process includes the following steps: Refer to the Pittsburgh Sleep Quality Index and combine it with sleep health indicators to develop a sleep quality scoring standard, and then select 7 health indicators for scoring and evaluation; Among them: each of the 7 health indicators is scored at different levels, and the accumulated scores of each health indicator are the sleep quality reduction points. The total score ranges from 0 to 50. The higher the score, the worse the sleep quality.

8. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 6, characterized in that: The sleep stage time-sharing sequence is divided into four structures, wherein the four structures include early sleep stage, middle sleep stage, late sleep stage and sleep awakening. Some of the vital sign data that are counted include the heart rate, respiratory rate and body movement throughout the night.

9. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 7, characterized in that: The descriptions of the 7 health indicators and the specific scoring methods are as follows: (A) When falling asleep: "<23:00" is scored as A1; "23-24:00" is scored as A2; "00-01:00" is scored as A3; "after 01:00" is scored as A4; (B) Total sleep time; ">7 hours" is scored as B1; "6-7" is scored as B2; "5-6" is scored as B3; "<5 hours" is scored as B4; (C) Deep sleep percentage; "<10%" is scored as C1; "10-15%" is scored as C2; "15-20%" is scored as C3; ">20% is scored as C4; (D) Number of awake times; "0 times" was scored as D1; ​​"1-2 times" was scored as D2; "3-5 times" was scored as D3; ">5 times" was scored as D4; (E) Sleep latency; "≤30 minutes" is scored as E1; ">30 minutes" is scored as E2; (F) Abnormal sleep results; "normal early sleep" is counted as F1; "abnormal early sleep" is counted as F2; ​​"normal mid-sleep" is counted as F3; "abnormal mid-sleep" is counted as F4; "normal late sleep" is counted as F5; "abnormal late sleep" is counted as F6; "normal waking up from sleep" is counted as F7; "abnormal waking up from sleep" is counted as F8; (G) Body movement; "≤6 times" is scored as G1; ">6 times" is scored as G2; Total sleep score = 100-(component A + component B + component C + component D + component E + component F + component G score); Sleep evaluation: "0-59 points" is poor; "60-69 points" is passing; "70-79 points" is fair; "80-89 points" is good; "90-100 points" is excellent.

10. The sleep quality assessment system based on non-contact UWB radar vital sign signals according to claim 8, characterized in that: The data acquisition module includes a transmitting antenna, a receiving antenna, an antenna controller and a signal processor, and the transmitting antenna, the receiving antenna, the antenna controller and the signal processor are connected in sequence, and the antenna controller is an antenna controller for the transmitting antenna and the receiving antenna.

Images