Sleep monitoring method and system, computer equipment and storage medium

Abstract

The invention relates to the technical field of sleep monitoring, in particular to a sleep monitoring method and system, computer equipment and a storage medium, and the sleep monitoring method comprises the following steps: monitoring the pressure change of the head and neck of a user through a miniature differential pressure sensor, collecting pressure data in real time, recording a respiratory cycle according to pressure fluctuation, and determining the sleep state of the user; and identifying high and low pressure peak values, and generating head pressure monitoring data. According to the invention, by monitoring the pressure change of the head and the neck in real time, the capturing capability of tiny breathing changes is improved, refined breathing cycle recording and high-precision pressure peak value recognition are realized, potential breathing abnormity can be found at the initial stage, timely response is ensured, and the breathing frequency and amplitude are comprehensively analyzed; the breathing modes are accurately classified, so that the recognition of the abnormal breathing state is quicker, more accurate and more detailed dynamic monitoring and data analysis are realized, the evaluation of the sleep depth and stage is enhanced, and the comprehensive evaluation of the sleep quality is more scientific.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep monitoring, and in particular to a sleep monitoring method, system, computer equipment and storage medium. Background Art

[0002] The field of sleep monitoring technology focuses on using various methods and systems to track and analyze individual sleep patterns and quality, combining physiological sensing technology, data analysis, machine learning, and human biology to obtain detailed information about sleep depth, duration, interruptions, and sleep cycles. Monitoring equipment includes mattress sensors, wearable devices, mobile applications, and other wireless technologies that can collect sleep-related physiological and motion data in real time. Through data analysis, it can help identify sleep disorders, assess sleep quality, and provide a scientific basis for improving personal health and quality of life.

[0003] Among them, the theme of sleep monitoring methods is to systematically collect and analyze sleep data through scientific and technological means to evaluate and improve sleep quality. The main uses include helping to identify various sleep disorders such as insomnia, sleep apnea or periodic limb movement disorder. In addition, it can monitor sleep health, provide decision support for medical professionals, and help ordinary users improve sleep quality by adjusting their living habits, such as sleeping environment and work and rest time, which helps to improve people's overall health and quality of life, especially in today's society, with the increasing number of sleep problems.

[0004] Existing technologies in sleep monitoring still have limitations in the detection and analysis of subtle physiological changes. Often, they can only provide limited data resolution, resulting in the neglect of subtle changes in breathing or movement, thus affecting the accurate assessment of sleep quality and stages. In addition, when processing large amounts of data, they often rely on more general analysis models and fail to fully consider the physiological differences between individuals, resulting in insufficient individualization of monitoring results. For example, for mild sleep apnea or subtle sleep movements, existing technologies may fail to identify and respond in a timely manner, thereby reducing the prevention and intervention effects of sleep disorders to a certain extent. These deficiencies may lead to a decline in user confidence in sleep monitoring technology in daily applications, especially for user groups that require precise monitoring. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a sleep monitoring method, system, computer device and storage medium.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a sleep monitoring method, comprising the following steps:

[0007] S1: Monitors the pressure changes of the user's head and neck through a micro differential pressure sensor, collects pressure data in real time, records the breathing cycle according to pressure fluctuations, identifies high and low pressure peaks, and generates head pressure monitoring data;

[0008] S2: Perform frequency and amplitude analysis on the head pressure monitoring data, identify normal breathing fluctuations and abnormal breathing fluctuations, convert the data into identification marks, and obtain breathing pattern analysis results;

[0009] S3: according to the breathing pattern analysis result, an alarm mechanism is set, an alarm signal is triggered when abnormal breathing is detected, a user is reminded through sound or light signal, the time point and frequency of alarm issuance are recorded, and a breathing abnormality alarm record is generated;

[0010] S4: Uses micro-kinetic sensors to monitor subtle head movements, evaluates the user's sleep stage through comparative analysis of movements and time, identifies the transition between deep sleep and light sleep, and generates head movement analysis results;

[0011] S5: Combine the abnormal breathing alarm record and the head movement analysis results to comprehensively evaluate the user's sleep quality, analyze the regularity of the sleep cycle and the distribution of abnormal sleep events, and output the user's comprehensive sleep monitoring record.

[0012] As a further solution of the present invention, the specific steps of monitoring the pressure changes of the user's head and neck by using a micro differential pressure sensor, collecting pressure data in real time, recording the breathing cycle according to the pressure fluctuation, identifying the high and low pressure peaks, and generating head pressure monitoring data are as follows:

[0013] S101: Based on the micro differential pressure sensor, perform equipment calibration, monitor and record the pressure changes of each detection point in real time, extract time series pressure data, and generate a head and neck pressure data set;

[0014] S102: Based on the head and neck pressure data set, data screening is performed to extract continuous pressure fluctuations, each respiratory cycle is defined by identifying peak values ​​and valley values, periodic data is classified, and a respiratory cycle record is generated;

[0015] S103: Based on the respiratory cycle record, data aggregation is performed to analyze the pressure data of the head and neck, and the overall trend of pressure changes is determined by calculating the average pressure value within the cycle to generate head pressure monitoring data.

[0016] As a further solution of the present invention, the specific steps of performing frequency and amplitude analysis on the head pressure monitoring data, identifying normal breathing fluctuations and abnormal breathing fluctuations, converting the data into identification marks, and obtaining the breathing pattern analysis results are as follows:

[0017] S201: Based on the head pressure monitoring data, accurately measure the fluctuation frequency, evaluate the amplitude of each fluctuation, extract the basic characteristics of each breath, and generate a basic breathing fluctuation feature set;

[0018] S202: Based on the basic respiratory fluctuation feature set, compare with the standard respiratory pattern, identify the frequency or amplitude that deviates from the normal parameters, mark the abnormal respiratory fluctuation, and generate an abnormal respiratory identification result;

[0019] S203: Based on the abnormal breathing identification result, classify and annotate the abnormal fluctuations, including snoring or apnea, and convert the annotations into breathing pattern recognition marks to generate breathing pattern analysis results.

[0020] As a further solution of the present invention, according to the breathing pattern analysis result, an alarm mechanism is set, an alarm signal is triggered when abnormal breathing is detected, a user is reminded through sound or light signal, and the time point and frequency of alarm issuance are recorded. The specific steps of generating abnormal breathing alarm record are:

[0021] S301: Based on the breathing pattern analysis result, define alarm triggering conditions, including thresholds of breathing frequency being lower or higher than normal values, set alarm parameters, and generate alarm triggering parameter setting results;

[0022] S302: Based on the alarm trigger parameter setting result, when the alarm is triggered, a corresponding sound or light signal is immediately issued, and the exact time point when the alarm information is issued is synchronously recorded to generate a real-time alarm issuance record;

[0023] S303: Based on the real-time alarm issuance record, the issuance time point and issuance frequency of each alarm are counted and summarized, an alarm response log is created, and a breathing abnormality alarm record is output.

[0024] As a further solution of the present invention, the micro-kinetic energy sensor is used to monitor the slight movement of the head, and the user's sleep stage is evaluated by comparing the movement and time, and the transition between deep sleep and light sleep is identified. The specific steps of generating the head movement analysis result are:

[0025] S401: Based on the micro-kinetic energy sensor, continuously monitor each tiny head movement of the user, record the timestamp and amplitude data of each movement action, and generate a head micro-movement data record;

[0026] S402: Based on the head micro-movement data record, analyzing the collected timestamps and head movement data, evaluating the frequency and duration of the movement, calculating the sleep stage index, distinguishing the changes in the sleep stages, and generating a sleep stage analysis result;

[0027] S403: Based on the sleep stage analysis result, identify the transition between deep sleep and light sleep, record the start and end time of the deep sleep period and the light sleep period, analyze the transition frequency, and generate a head movement analysis result.

[0028] As a further embodiment of the present invention, the sleep stage index is according to the formula:

[0029]

[0030] Calculate, where SSI represents the sleep stage index of time period i, f i is the head movement frequency of the ith record, d i is the corresponding duration, w i is the adaptive weight coefficient for each time period i, c i is the user's comfort score during sleep, v is the comfort weight coefficient, and T is the total observation time.

[0031] As a further solution of the present invention, the specific steps of comprehensively evaluating the user's sleep quality by combining the abnormal breathing alarm record and the head movement analysis result, analyzing the regularity of the sleep cycle and the distribution of abnormal sleep events, and outputting the user's comprehensive sleep monitoring record are as follows:

[0032] S501: Based on the abnormal breathing alarm record and the head movement analysis result, cross-comparison is performed on the abnormal breathing event and the head movement data at each time point, the time correspondence and frequency distribution in the entire sleep cycle are analyzed, and a cross-analysis record is generated;

[0033] S502: Based on the cross-analysis records, identifying abnormal sleep event patterns, analyzing the correlation between apnea and head movements, evaluating key factors affecting sleep quality, and generating key sleep quality factor analysis results;

[0034] S503: Based on the analysis results of the key sleep quality factors, comprehensively analyze the regularity of the sleep cycle and the distribution of abnormal events, evaluate the overall sleep quality, record and summarize the analysis results, and generate a comprehensive sleep monitoring record for the user.

[0035] A sleep monitoring system, the system comprising:

[0036] The head pressure monitoring module is based on a micro differential pressure sensor, which monitors and records the pressure changes at each detection point in real time, identifies the peak and valley values ​​to define each breathing cycle, determines the overall trend of pressure changes, and generates head pressure monitoring data;

[0037] The respiratory fluctuation analysis module evaluates the amplitude of each fluctuation based on the head pressure monitoring data, extracts the basic characteristics of each breath, compares the standard breathing pattern, identifies the frequency or amplitude that deviates from the normal parameters, marks abnormal respiratory fluctuations, and generates abnormal breathing identification results;

[0038] The alarm setting module classifies and marks the abnormal fluctuations based on the abnormal breathing identification result, simultaneously defines the alarm triggering conditions, sets the alarm parameters, and generates the alarm triggering parameter setting results;

[0039] The alarm execution module is based on the alarm trigger parameter setting result, and when the alarm is triggered, the corresponding sound or light signal is immediately emitted, and the emission time and frequency of each alarm are counted and summarized, and the abnormal breathing alarm record is output;

[0040] The head movement monitoring module is based on a micro-kinetic energy sensor, which continuously monitors every tiny head movement of the user, evaluates the frequency and duration of the movement, calculates the sleep stage index, distinguishes the changes in sleep stages, identifies the transition between deep sleep and light sleep, and generates head movement analysis results;

[0041] Based on the abnormal breathing alarm records and head movement analysis results, the sleep quality assessment module cross-compares the data, identifies abnormal sleep event patterns, analyzes the correlation between apnea and head movements, evaluates key factors affecting sleep quality, evaluates overall sleep quality, and generates a comprehensive sleep monitoring record for the user.

[0042] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements a sleep monitoring system as described above when executing the computer program.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a sleep monitoring method as described above.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are:

[0045] In the present invention, by real-time monitoring of changes in head and neck pressure, the ability to capture tiny respiratory changes is improved, and refined respiratory cycle recording and high-precision pressure peak recognition are achieved. Potential respiratory abnormalities can be discovered at the initial stage to ensure timely response, and comprehensive analysis of respiratory frequency and amplitude can be performed to accurately classify respiratory patterns, making the identification of abnormal respiratory states faster and more accurate. Detailed dynamic monitoring and data analysis can enhance the assessment of sleep depth and stages, making the comprehensive assessment of sleep quality more scientific. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1It is a schematic diagram of the workflow of the present invention;

[0047] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0048] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0049] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0050] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0051] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0052] Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0055] See also Figure 1 , a sleep monitoring method, comprising the following steps:

[0056] S1: Monitors the pressure changes of the user's head and neck through a micro differential pressure sensor, collects pressure data in real time, records the breathing cycle according to pressure fluctuations, identifies high and low pressure peaks, and generates head pressure monitoring data;

[0057] S2: Perform frequency and amplitude analysis on the head pressure monitoring data, identify normal breathing fluctuations and abnormal breathing fluctuations, convert the data into identification marks, and obtain breathing pattern analysis results;

[0058] S3: according to the breathing pattern analysis results, an alarm mechanism is set, an alarm signal is triggered when abnormal breathing is detected, a user is reminded through sound or light signals, the time point and frequency of the alarm is recorded, and a record of abnormal breathing alarm is generated;

[0059] S4: Uses micro-kinetic sensors to monitor subtle head movements, evaluates the user's sleep stage through comparative analysis of movements and time, identifies the transition between deep sleep and light sleep, and generates head movement analysis results;

[0060] S5: Combine the abnormal breathing alarm records and head movement analysis results to comprehensively evaluate the user's sleep quality, analyze the regularity of the sleep cycle and the distribution of abnormal sleep events, and output the user's comprehensive sleep monitoring record.

[0061] Head pressure monitoring data includes breathing rate, pressure peak type and duration; breathing pattern analysis results include breathing stability analysis results and fluctuation abnormality analysis records; abnormal breathing alarm records include alarm trigger conditions, alarm type and alarm response results; head movement analysis results include sleep depth level, movement frequency and sleep stage duration; user comprehensive sleep monitoring records include sleep quality score, sleep pattern recognition results and abnormal sleep indicator records.

[0062] See also Figure 2 , the specific steps of S1 are:

[0063] S101: Based on the micro differential pressure sensor, perform equipment calibration, monitor and record the pressure changes of each detection point in real time, extract time series pressure data, and generate a head and neck pressure data set;

[0064] Initialize the differential pressure sensor, and perform sensitivity and baseline calibration to ensure measurement accuracy. During the calibration phase, select the standard pressure value and adjust the sensor output to match the standard pressure value. The calibration process is repeated three times to ensure data consistency and repeatability. Subsequently, the sensor is set to collect pressure at multiple detection points on the head and neck, and the sampling frequency is set to 100Hz to capture rapid pressure changes. The data of each detection point is converted into a digital signal after noise filtering and signal amplification, and organized into a time series by the data acquisition system. Finally, the head and neck pressure dataset is generated based on the timestamp and pressure value, and the storage format is a CSV file, including the timestamp, detection point number, and the corresponding pressure value.

[0065] S102: Based on the head and neck pressure data set, data screening is performed to extract continuous pressure fluctuations, each respiratory cycle is defined by identifying peak values ​​and valley values, the periodic data is classified, and a respiratory cycle record is generated;

[0066] The data screening process first eliminates abnormal pressure data that is not within the physiological range (for example, exceeding the maximum or minimum pressure value that the human body can withstand) based on the physical threshold. Then, the local extreme value detection method is used to detect each data point in the data set to identify all peaks (pressure surge points) and valleys (pressure drop points), which mark the beginning and end of the respiratory cycle. Next, the data between each pair of peak and valley values ​​is timestamped, and these cycles are arranged in chronological order to form a clearly classified respiratory cycle record. This record includes the start and end time of each respiratory cycle, and the peak and valley pressure values ​​for subsequent analysis and research.

[0067] S103: Based on the respiratory cycle record, data aggregation is performed to analyze the pressure data of the head and neck, and the overall trend of pressure changes is determined by calculating the average pressure value within the cycle to generate head pressure monitoring data;

[0068] First, each cycle in the respiratory cycle record is iterated, and the arithmetic mean of all pressure values ​​in the cycle is calculated to estimate the average pressure level of the cycle. In addition, in order to more accurately describe the trend of pressure changes, the pressure change rate of each cycle is calculated (the difference between the peak pressure and the peak pressure of the previous cycle divided by the time interval). Through calculation, a comprehensive data set containing the average pressure of the cycle and its changing trend is formed. Finally, the data is integrated and a chart is generated for visual analysis of pressure trends, which helps to better understand the pressure performance of the head and neck in continuous monitoring.

[0069] See also Figure 3 , the specific steps of S2 are:

[0070] S201: Based on the head pressure monitoring data, accurately measure the fluctuation frequency, evaluate the amplitude of each fluctuation, extract the basic characteristics of each breath, and generate a basic breathing fluctuation feature set;

[0071] Using the time series data in the head pressure monitoring dataset, the Fourier transform analysis method was applied to extract frequency information and determine the main frequency and harmonic components of each fluctuation. Subsequently, the amplitude of each data point was evaluated, and the amplitude of each fluctuation was obtained by calculating the difference between adjacent peaks and valleys. The frequency and amplitude information were associated with the timestamp to identify the start and end points of each breath, as well as the duration and intensity of the breath. The basic characteristics of each breath, such as frequency, amplitude, and duration, were summarized to form a structured respiratory fluctuation feature set as the basis for subsequent analysis.

[0072] S202: Based on the basic respiratory fluctuation feature set, compare with the standard respiratory pattern, identify the frequency or amplitude that deviates from the normal parameters, mark the abnormal respiratory fluctuation, and generate an abnormal respiratory identification result;

[0073] By setting thresholds for standardized comparison of respiratory rate and amplitude, data points that differ significantly from normal breathing patterns are identified. The standard breathing pattern is set at a respiratory rate of 12 to 20 times per minute and a certain amplitude range, and respiratory events that exceed or fall below this range are marked as abnormal. In addition, statistical analysis methods such as standard deviation and skewness analysis are used to further confirm irregularities or abnormalities in the breathing pattern. Finally, all respiratory events identified as abnormal are compiled into the abnormal breathing identification results.

[0074] S203: Based on the abnormal breathing identification result, classify and annotate the abnormal fluctuations, including snoring or apnea, and convert the annotations into breathing pattern recognition tags to generate breathing pattern analysis results;

[0075] Based on the analysis of the marked abnormal breathing data, abnormal classification is performed to identify representative abnormal types, such as snoring and apnea. Snoring is usually manifested as continuous noise accompanied by irregular pressure fluctuations, while apnea is manifested as a complete pause in pressure fluctuations. Each abnormal event is assigned a specific classification tag, and the time of its occurrence and the duration period are recorded. After the data is sorted, it is converted into easy-to-understand breathing pattern recognition tags, such as statistics on snoring frequency and apnea events. In this way, the generated breathing pattern analysis results provide an intuitive way to assist in a deeper analysis and diagnosis of the user's respiratory health status.

[0076] See also Figure 4 , the specific steps of S3 are:

[0077] S301: Based on the breathing pattern analysis result, define alarm triggering conditions, including thresholds of breathing frequency being lower or higher than normal values, set alarm parameters, and generate alarm triggering parameter setting results;

[0078] By analyzing and summarizing the respiratory rate data collected in the early stage, the normal respiratory rate range is set to 12 to 20 times per minute. Combined with clinical experience and the specific conditions of the patient, the upper and lower thresholds for alarm triggering are set. For example, the alarm is triggered when the frequency is higher than 25 times or lower than 10 times per minute. The alarm parameters are further set, including the volume, type (sound or light signal), duration and stop conditions of the alarm. These parameters are stored in the configuration file of the monitoring system so that a quick response can be made when the trigger conditions are met. Finally, a document containing all alarm trigger conditions and parameters is generated for subsequent reference and adjustment.

[0079] S302: Based on the alarm trigger parameter setting result, when the alarm is triggered, a corresponding sound or light signal is immediately issued, and the exact time point of the alarm information being issued is synchronously recorded to generate a real-time alarm issuance record;

[0080] In actual operation, the patient's breathing rate is continuously detected and compared with the set alarm trigger conditions. Once the breathing rate is detected to exceed the set threshold, the preset alarm signal is immediately activated, whether it is an audio or optical signal, adjusted according to the set parameters. At the same time, the exact time point when the alarm is issued is recorded, including year, month, day, hour, minute and second. The information is automatically recorded in the database, forming a real-time alarm issuance record for subsequent inspection and analysis.

[0081] S303: Based on the real-time alarm issuance record, count and summarize the issuance time and issuance frequency of each alarm, create an alarm response log, and output the abnormal breathing alarm record;

[0082] Through detailed statistical analysis of alarm issuance records, we can identify the time periods or conditions under which alarms occur more frequently, so as to conduct further etiology analysis and system adjustments. Statistical software is used to sort and classify the collected data, such as summarizing the alarm frequency by daily, weekly, and monthly. In addition, the alarm response log also records the rapidity and effectiveness of the response to each alarm, which is crucial for evaluating system performance and medical response speed. The resulting abnormal breathing alarm record not only reflects the real-time and frequency of the alarm, but also provides a basis for improving the system and treatment strategies.

[0083] See also Figure 5 , the specific steps of S4 are:

[0084] S401: Based on the micro-kinetic energy sensor, continuously monitor each tiny head movement of the user, record the timestamp and amplitude data of each movement action, and generate head micro-movement data records;

[0085] A high-precision micro-kinetic energy sensor is used to monitor every head movement of the user during sleep. No matter how small, it is captured by the sensor and converted into an electrical signal. After the signal is processed by an amplifier and filter, it is converted into digital data, recording the exact time and relative amplitude of each movement. The data acquisition system is set to detect once every 10 milliseconds to ensure the continuity and accuracy of the record. Each recorded data is timestamped to ensure the time accuracy of subsequent analysis. Finally, a comprehensive head micro-movement data record file is formed, and each record lists the time and amplitude of the movement in detail, which is convenient for further data analysis and sleep quality assessment.

[0086] S402: Based on the head micro-movement data record, analyzing the collected timestamps and head movement data, evaluating the frequency and duration of the movement, calculating the sleep stage index, distinguishing the changes in the sleep stages, and generating a sleep stage analysis result;

[0087] Sleep stage index, according to the formula:

[0088]

[0089] Calculate, where SSI represents the sleep stage index of time period i, f i is the head movement frequency of the ith record, d i is the corresponding duration, w i is the adaptive weight coefficient for each time period i, c i is the user's comfort score during sleep, v is the comfort weight coefficient, and T is the total observation time.

[0090] The execution process is as follows:

[0091] First, collect and calculate the head movement frequency f for each record i and duration d i , then, determine an adaptive weight w for each record i , based on the irregularity of movement and its predicted impact on sleep quality, w is determined by analyzing historical data i , then collect the user comfort score c i , and set a comfort weight v, which is obtained through correlation analysis with the user's sleep quality. Finally, all weighted f i ×d i Value and v×c i The sum is divided by the total observation time T to obtain the sleep stage index SSI.

[0092] S403: Based on the sleep stage analysis results, identify the transition between deep sleep and light sleep, record the start and end time of the deep sleep period and the light sleep period, analyze the transition frequency, and generate a head movement analysis result;

[0093] By analyzing the time series changes of the sleep stage index, the boundaries between deep sleep and light sleep stages are determined. Threshold segmentation technology is used to distinguish the depth of sleep. When the SSI is lower than a certain set threshold, it is marked as a deep sleep period, and when it is higher than another threshold, it is marked as a light sleep period. The start and end time of each sleep stage is recorded. In order to accurately track changes in sleep patterns, the conversion frequency from light sleep to deep sleep and from deep sleep to light sleep is calculated. These data are integrated into the head movement analysis results, which not only show the dynamic changes in sleep quality, but also provide important information for sleep research and user health management.

[0094] See also Figure 6 , the specific steps of S5 are:

[0095] S501: Based on the abnormal breathing alarm record and the head movement analysis results, cross-comparison is performed on the abnormal breathing events and head movement data at each time point, the time correspondence and frequency distribution in the entire sleep cycle are analyzed, and a cross-analysis record is generated;

[0096] By synchronizing the timestamps of the two data sets, we can ensure that the time of each record corresponds accurately. We match the timestamps of abnormal breathing events and find head movement records that are close or overlapping in time. In this way, we can determine whether abnormal breathing events are associated with specific head movements. Next, we analyze the frequency distribution of abnormal breathing and head movements, and count the frequency and pattern of their occurrence in different sleep stages. We use statistical analysis software to generate cross-distribution graphs and correlation analysis reports, and the data will be integrated into cross-analysis records to provide basic data for subsequent sleep quality analysis.

[0097] S502: Based on the cross-analysis records, identify abnormal sleep event patterns, analyze the correlation between apnea and head movements, evaluate key factors affecting sleep quality, and generate key sleep quality factor analysis results;

[0098] Use advanced data analysis techniques, such as regression analysis and pattern recognition, to determine the statistical correlation between apnea events and specific head movements. Analyze whether the correlation indicates the presence of a sleep disorder, such as snoring or sleep apnea syndrome. In addition, explore other factors that may affect sleep quality, such as sleeping environment, time duration, etc. Aggregate and analyze the data of all influencing factors to generate a comprehensive report containing key factors. This report describes in detail how each factor affects sleep quality alone or together, providing accurate diagnostic support.

[0099] S503: Based on the analysis results of key sleep quality factors, comprehensively analyze the regularity of sleep cycles and the distribution of abnormal events, evaluate the overall sleep quality, record and summarize the analysis results, and generate a comprehensive sleep monitoring record for the user;

[0100] All analysis data are integrated to form a comprehensive sleep quality assessment report. This includes regularity analysis of sleep cycles, statistical distribution of abnormal events, and assessment of how they affect overall sleep quality. Considering the importance of regularity of sleep cycles, special analysis is made on the ratio of deep sleep to light sleep, as well as the impact of frequent awakening events on sleep continuity. The analysis results are presented using charts and visualization tools, allowing users to intuitively understand multiple aspects of sleep quality. The resulting comprehensive monitoring record provides a systematic way to assess a user's sleep health and provides a scientific basis for improving sleep quality.

[0101] See also Figure 7 , a sleep monitoring system, comprising:

[0102] The head pressure monitoring module is based on a micro differential pressure sensor, which monitors and records the pressure changes at each detection point in real time, identifies the peak and valley values ​​to define each breathing cycle, determines the overall trend of pressure changes, and generates head pressure monitoring data;

[0103] The respiratory fluctuation analysis module evaluates the amplitude of each fluctuation based on the head pressure monitoring data, extracts the basic characteristics of each breath, compares it with the standard breathing pattern, identifies the frequency or amplitude that deviates from the normal parameters, marks abnormal respiratory fluctuations, and generates abnormal breathing identification results;

[0104] The alarm setting module classifies and marks abnormal fluctuations based on the abnormal breathing identification results, simultaneously defines alarm triggering conditions, sets alarm parameters, and generates alarm triggering parameter setting results;

[0105] The alarm execution module is based on the alarm trigger parameter setting results. When the alarm is triggered, the corresponding sound or light signal is immediately issued, and the issuance time and frequency of each alarm are counted and summarized, and the abnormal breathing alarm record is output;

[0106] The head movement monitoring module is based on a micro-kinetic energy sensor, which continuously monitors every tiny head movement of the user, evaluates the frequency and duration of the movement, calculates the sleep stage index, distinguishes the changes in sleep stages, identifies the transition between deep sleep and light sleep, and generates head movement analysis results;

[0107] The sleep quality assessment module cross-compares the data based on the abnormal breathing alarm records and head movement analysis results, identifies abnormal sleep event patterns, analyzes the correlation between apnea and head movements, evaluates key factors affecting sleep quality, evaluates overall sleep quality, and generates comprehensive sleep monitoring records for users.

[0108] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A sleep monitoring method, characterized in that: The following steps are involved: Through the micro differential pressure sensor, the pressure changes of the user's head and neck are monitored, the pressure data is collected in real time, the breathing cycle is recorded according to the pressure fluctuation, the high and low pressure peaks are identified, and the head pressure monitoring data is generated; Performing frequency and amplitude analysis on the head pressure monitoring data, identifying normal breathing fluctuations and abnormal breathing fluctuations, converting the data into identification marks, and obtaining breathing pattern analysis results; According to the breathing pattern analysis result, an alarm mechanism is set up, and an alarm signal is triggered when abnormal breathing is detected, the user is reminded through sound or light signals, the time point and frequency of the alarm are recorded, and a breathing abnormality alarm record is generated; Use micro-kinetic sensors to monitor subtle head movements, evaluate the user's sleep stage through comparative analysis of movements and time, identify the transition between deep sleep and light sleep, and generate head movement analysis results; Combined with the abnormal breathing alarm record and the head movement analysis results, a comprehensive assessment of the user's sleep quality is performed, the regularity of the sleep cycle and the distribution of abnormal sleep events are analyzed, and the user's comprehensive sleep monitoring record is output.

2. The sleep monitoring method according to claim 1, characterized in that: The micro differential pressure sensor is used to monitor the pressure changes in the user's head and neck, collect pressure data in real time, record the breathing cycle according to the pressure fluctuations, identify the high and low pressure peaks, and generate the head pressure monitoring data in the following specific steps: Based on the micro differential pressure sensor, the equipment is calibrated, the pressure changes of each detection point are monitored and recorded in real time, the time series pressure data is extracted, and the head and neck pressure data set is generated; Based on the head and neck pressure data set, data screening is performed to extract continuous pressure fluctuations, each respiratory cycle is defined by identifying peak values ​​and valley values, and periodic data is classified to generate a respiratory cycle record; Based on the respiratory cycle record, data aggregation is performed to analyze the pressure data of the head and neck, and the overall trend of pressure changes is determined by calculating the average pressure value within the cycle to generate head pressure monitoring data.

3. The sleep monitoring method according to claim 1, characterized in that: The specific steps of performing frequency and amplitude analysis on the head pressure monitoring data, identifying normal breathing fluctuations and abnormal breathing fluctuations, converting the data into identification marks, and obtaining the breathing pattern analysis results are as follows: Based on the head pressure monitoring data, the fluctuation frequency is accurately measured, and the amplitude of each fluctuation is evaluated, the basic characteristics of each breath are extracted, and a basic breathing fluctuation feature set is generated; Based on the basic respiratory fluctuation feature set, comparing with the standard respiratory pattern, identifying the frequency or amplitude that deviates from the normal parameters, marking the abnormal respiratory fluctuation, and generating an abnormal respiratory identification result; Based on the abnormal breathing identification result, the abnormal fluctuations are classified and labeled, including snoring or apnea, and the labels are converted into breathing pattern recognition marks to generate breathing pattern analysis results.

4. The sleep monitoring method according to claim 1, characterized in that: According to the breathing pattern analysis result, an alarm mechanism is set, an alarm signal is triggered when abnormal breathing is detected, a user is reminded through sound or light signal, and the time point and frequency of the alarm are recorded. The specific steps of generating abnormal breathing alarm records are: Based on the breathing pattern analysis result, define alarm triggering conditions, including thresholds of breathing frequency being lower or higher than normal values, and set alarm parameters to generate alarm triggering parameter setting results; Based on the alarm trigger parameter setting result, when the alarm is triggered, a corresponding sound or light signal is immediately issued, and the exact time point when the alarm information is issued is synchronously recorded to generate a real-time alarm issuance record; Based on the real-time alarm issuance record, the issuance time point and issuance frequency of each alarm are counted and summarized, an alarm response log is created, and a breathing abnormality alarm record is output.

5. The sleep monitoring method according to claim 1, characterized in that: The micro-kinetic energy sensor is used to monitor the slight movement of the head. By comparing the movement and time, the user's sleep stage is evaluated and the transition between deep sleep and light sleep is identified. The specific steps to generate the head movement analysis results are as follows: Based on the micro-kinetic energy sensor, continuously monitor each tiny head movement of the user, record the timestamp and amplitude data of each movement action, and generate head micro-movement data records; Based on the head micro-movement data record, analyzing the collected timestamps and head movement data, evaluating the frequency and duration of the movement, calculating the sleep stage index, distinguishing the changes in the sleep stages, and generating a sleep stage analysis result; Based on the sleep stage analysis results, the transition between deep sleep and light sleep is identified, the start and end times of the deep sleep period and the light sleep period are recorded, the transition frequency is analyzed, and the head movement analysis results are generated.

6. The sleep monitoring method according to claim 5, characterized in that: The sleep stage index is according to the formula: Calculate, where SSI represents the sleep stage index of time period i, f i is the head movement frequency of the ith record, d i is the corresponding duration, w i is the adaptive weight coefficient for each time period i, c i is the user's comfort score during sleep, v is the comfort weight coefficient, and T is the total observation time.

7. The sleep monitoring method according to claim 1, characterized in that: Combined with the abnormal breathing alarm record and the head movement analysis results, the user's sleep quality is comprehensively evaluated, the regularity of the sleep cycle and the distribution of abnormal sleep events are analyzed, and the specific steps of outputting the user's comprehensive sleep monitoring record are as follows: Based on the abnormal breathing alarm record and the head movement analysis results, cross-comparison is performed on the abnormal breathing events and head movement data at each time point, the time correspondence and frequency distribution in the entire sleep cycle are analyzed, and a cross-analysis record is generated; Based on the cross-analysis records, identifying abnormal sleep event patterns, analyzing the correlation between apnea and head movements, evaluating key factors affecting sleep quality, and generating key sleep quality factor analysis results; Based on the analysis results of the key sleep quality factors, the regularity of the sleep cycle and the distribution of abnormal events are comprehensively analyzed to evaluate the overall sleep quality, and the analysis results are recorded and summarized to generate a comprehensive sleep monitoring record for the user.

8. A sleep monitoring system, characterized in that: The sleep monitoring system is used to execute the sleep monitoring method according to any one of claims 1 to 7, and the sleep monitoring system comprises: The head pressure monitoring module is based on a micro differential pressure sensor, which monitors and records the pressure changes at each detection point in real time, identifies the peak and valley values ​​to define each breathing cycle, determines the overall trend of pressure changes, and generates head pressure monitoring data; The respiratory fluctuation analysis module evaluates the amplitude of each fluctuation based on the head pressure monitoring data, extracts the basic characteristics of each breath, compares the standard breathing pattern, identifies the frequency or amplitude that deviates from the normal parameters, marks abnormal respiratory fluctuations, and generates abnormal breathing identification results; The alarm setting module classifies and marks the abnormal fluctuations based on the abnormal breathing identification result, simultaneously defines the alarm triggering conditions, sets the alarm parameters, and generates the alarm triggering parameter setting results; The alarm execution module is based on the alarm trigger parameter setting result, and when the alarm is triggered, the corresponding sound or light signal is immediately emitted, and the emission time and frequency of each alarm are counted and summarized, and the abnormal breathing alarm record is output; The head movement monitoring module is based on a micro-kinetic energy sensor, which continuously monitors every tiny head movement of the user, evaluates the frequency and duration of the movement, calculates the sleep stage index, distinguishes the changes in sleep stages, identifies the transition between deep sleep and light sleep, and generates head movement analysis results; Based on the abnormal breathing alarm records and head movement analysis results, the sleep quality assessment module cross-compares the data, identifies abnormal sleep event patterns, analyzes the correlation between apnea and head movements, evaluates key factors affecting sleep quality, evaluates overall sleep quality, and generates a comprehensive sleep monitoring record for the user.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor implements the sleep monitoring system of claim 8 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the sleep monitoring method according to any one of claims 1 to 7 are implemented.

Images