Intelligent sleep monitoring system for three-dimensional multi-dimensional data
Through three-dimensional multi-dimensional data analysis, combined with sleep time, environment and status data, sleep quality characterization values are calculated, which solves the problem of inaccurate sleep quality analysis in the existing technology, and achieves more accurate sleep quality assessment and personalized feedback.
Patent Information
- Application Number
- CN202411047380.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing sleep data monitoring technology mainly focuses on single data analysis, and cannot comprehensively evaluate the various factors affecting sleep quality, resulting in inaccurate sleep quality analysis.
A three-dimensional multi-dimensional data intelligent sleep monitoring system is designed. By collecting and analyzing sleep time data, sleep environment data and sleep state data, sleep quality characterization values are calculated, and feedback tips are provided based on these values to help users understand and improve. Sleep.
The system can more accurately analyze sleep quality, identify influencing factors, provide personalized suggestions, improve the accuracy of sleep quality assessment and users' awareness of their own sleep.
Smart Images

Figure CN118948215A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to an intelligent sleep monitoring system for stereoscopic multi-dimensional data. Background Art
[0002] In the field of scientific research, monitoring and processing data during sleep helps to understand the impact of sleep on cognitive function and emotional regulation, thereby promoting progress in the field of sleep research. Sleep quality monitoring may be affected by environmental factors, resulting in inaccurate sleep quality assessment.
[0003] Prior art, such as a multimodal sleep quality analysis system and method based on data analysis, disclosed in the invention patent announcement with announcement number: CN115688186B, belongs to the technical field of multimodal sleep quality analysis. Through watermark encryption and decryption algorithms, the abnormality index and sleep index are calculated respectively with real-time monitored ECG signal data and sleeping posture data, and the abnormality index and sleep index are used as the strength of watermark encryption respectively, and then verified in combination with historical data, making it very difficult for malicious attackers to crack the data. Even if the first-level or second-level encryption is cracked, the first-level or second-level decryption needs to be verified through historical data. At the same time, the sleeping posture monitoring can be started only after the first-level decryption verification is passed. Even if the sleeping posture monitoring is started, the second-level encryption needs to be cracked and the second-level decryption verification needs to be performed; thus, the difficulty of attacking and tampering with the data of the subject is increased, and the analysis of sleep quality data is also made more accurate and effective.
[0004] Prior art, such as the invention patent announcement with announcement number: CN103632063B, discloses a method and system for obtaining user sleep quality level data, wherein the method includes the following steps: A. obtaining the user's motion data within a timing period through a sensor; B. obtaining the user's sleep state through the motion data, and determining whether the current time has reached the end time of the timing period; C. turning off the alarm when the current time has reached the end time of the current timing period and the user's sleep state is awake; D. obtaining the user's sleep quality level according to the number of times the current alarm rings. The invention obtains the user's motion data within a timing period through a sensor, obtains the user's sleep state based on the motion data, and obtains the user's sleep quality level data in combination with the alarm function, thereby knowing the user's sleep quality. In-depth services can be provided through the obtained sleep quality, such as reminding the user to rest early, adjust the schedule, etc.
[0005] Combining the above solutions, it is found that currently in the field of sleep data monitoring technology, usually only the user's behavioral data is analyzed in a single way, without targeted analysis of the user's sleep quality, and other factors that may affect the user's sleep quality cannot be analyzed, and the sleep quality analysis results are not accurate enough. Summary of the invention
[0006] In view of the deficiencies in the prior art, the present invention provides an intelligent sleep monitoring system with three-dimensional multi-dimensional data, which can effectively solve the problems involved in the above-mentioned background technology.
[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a three-dimensional multi-dimensional data intelligent sleep monitoring system, including a sleep data collection platform, which is used to collect the user's sleep time data, sleep environment data and sleep status data.
[0008] The sleep data analysis module is used to analyze the user's sleep time data, sleep environment data and sleep state data to obtain the user's sleep quality representation value.
[0009] The sleep quality analysis prompt module is used to provide feedback prompts based on the user's sleep quality representation value.
[0010] Furthermore, the sleep data analysis module specifically includes a user's sleep time monitoring unit, a user's sleep environment monitoring unit and a user's sleep state monitoring unit, wherein: the user's sleep time monitoring unit is used to analyze the user's sleep time data to obtain the user's sleep time representation value.
[0011] The user's sleeping environment monitoring unit is used to analyze the user's sleeping environment data to obtain the user's sleeping environment characterization value.
[0012] The user's sleep state monitoring unit is used to analyze the user's sleep state data to obtain the user's sleep state representation value.
[0013] Furthermore, the sleep time characterization value of the user is specifically analyzed in the following process: arranging a monitoring cycle, setting a number of monitoring time periods in the monitoring cycle, extracting the user's eye movement images in the sleep data collection platform, and analyzing to obtain the total duration of the user's rapid eye movement sleep in each monitoring time period.
[0014] The total sleep duration of the user in each monitoring time period is monitored, and the total REM sleep duration of the user in each monitoring time period is divided by the total sleep duration of the user in each monitoring time period as the REM sleep ratio of the user in each monitoring time period.
[0015] The sleeping sounds of the users in each monitoring time period are monitored and recorded, and analyzed to obtain the deep sleep duration of the users in each monitoring time period, and the ratio of the deep sleep duration of the users in each monitoring time period to the total sleep duration of the users in each monitoring time period is taken as the deep sleep proportion of the users in each monitoring time period.
[0016] According to the user's rapid eye movement sleep ratio and the user's deep sleep ratio in each monitoring time period, the user's average sleep duration is counted and analyzed to obtain the user's sleep time representation value.
[0017] The user's sleep time characterization value represents a numerical quantification result obtained by analyzing the user's sleep time data, and is used to quantify the degree of influence of the user's deep sleep time on the user's sleep quality.
[0018] Furthermore, the specific analysis process of the user's sleep environment characterization value is as follows: monitor the temperature data in each monitoring time period, analyze and obtain the average temperature in each monitoring time period, and take the average value of the square of the difference between each temperature data in each monitoring time period and the average temperature in each monitoring time period as the variance value of the temperature in each monitoring time period.
[0019] The humidity data in each monitoring time period is monitored, and the average humidity in each monitoring time period is analyzed and obtained. The average value of the square of the difference between each humidity data in each monitoring time period and the average humidity in each monitoring time period is taken as the variance value of the humidity in each monitoring time period.
[0020] According to the variance value of temperature in each monitoring time period and the variance value of humidity in each monitoring time period, the light intensity and noise level values in each monitoring time period in the user's sleeping environment data are extracted, and the user's sleeping environment characterization value is obtained through analysis.
[0021] The user's sleep environment characterization value represents a numerical quantification result obtained by analyzing the user's sleep environment data, and is used to quantify the degree of influence of the user's sleep environment on the user's sleep quality.
[0022] Furthermore, the sleep state characterization value of the user is specifically analyzed in the following process: monitoring the number of body movements of the user in each monitoring time period, extracting the duration of each monitoring time period, and obtaining the body movement frequency of the user in each monitoring time period.
[0023] The user's breathing frequency in each monitoring time period is counted, and combined with the user's body movement frequency in each monitoring time period, the user's sleep state representation value is analyzed and obtained.
[0024] The user's sleep state characterization value represents a numerical quantification result obtained by analyzing the user's sleep state data, and is used to quantify the degree of influence of the user's sleep state on the user's sleep quality.
[0025] Furthermore, the sleep quality characterization value of the user is obtained by a specific analysis process of: obtaining the sleep quality characterization value of the user through comprehensive analysis based on the sleep time characterization value of the user, the sleep environment characterization value of the user and the sleep state characterization value of the user.
[0026] Furthermore, the sleep quality analysis and prompting module specifically includes a user's sleep quality analysis unit and a user's sleep quality prompting unit, wherein: the user's sleep quality analysis unit is used to analyze the user's sleep quality characterization value to obtain the user's sleep quality analysis result.
[0027] The user's sleep quality prompting unit is used to provide feedback prompts based on the user's sleep quality analysis results.
[0028] The sleep quality analysis result of the user includes whether the sleep quality of the user is qualified or not.
[0029] Furthermore, the sleep quality analysis result of the user is obtained, and the specific analysis process is: comparing the user's sleep quality characterization value with the set user's sleep quality characterization threshold value; if the user's sleep quality characterization value is higher than or equal to the set user's sleep quality characterization threshold value, then the user's sleep quality analysis result is that the user's sleep quality is qualified; if the user's sleep quality characterization value is lower than the set user's sleep quality characterization threshold value, then the user's sleep quality analysis result is that the user's sleep quality is unqualified.
[0030] Furthermore, the user's sleep quality is unqualified, including that the user's deep sleep time is unqualified, the user's sleeping environment is unqualified, and the user's sleeping state is unqualified.
[0031] If the user's sleep quality analysis result shows that the user's sleep quality is unqualified, the user's sleep time representation value will be compared with the set user's sleep time representation threshold. If the user's sleep time representation value is lower than the set user's sleep time representation threshold, the user's deep sleep time will be marked as unqualified, and the user's deep sleep time will be recorded as unqualified.
[0032] The user's sleep environment characterization value will be compared with the set user's sleep environment characterization threshold. If the user's sleep environment characterization value is lower than the set user's sleep environment characterization threshold, the user's sleep environment will be marked as unqualified and recorded as the user's sleep environment is unqualified.
[0033] The user's sleep state characterization value is compared with a set user's sleep state characterization threshold. If the user's sleep state characterization value is lower than the set user's sleep state characterization threshold, the user's sleep state is marked as unqualified and recorded as the user's sleep state unqualified.
[0034] Furthermore, the sleep quality characterization value of the user is specifically analyzed under the following conditions:
[0035] In the formula, α represents the user's sleep quality representation value, β represents the user's sleep time representation value, μ 1represents the weight factor corresponding to the set sleep time representation value, γ represents the user's sleep environment representation value, μ 2 represents the weight factor corresponding to the set sleep environment characterization value, δ represents the user's sleep state characterization value, μ 3 Indicates the weight factor corresponding to the set sleep state representation value.
[0036] The present invention has the following beneficial effects:
[0037] (1) The present invention provides a three-dimensional multi-dimensional data intelligent sleep monitoring system, which first collects the user's sleep time data, sleep environment data and sleep state data, and can more accurately analyze the user's sleep data. Then, the analysis obtains the user's sleep quality characterization value, which helps to improve the accuracy of the user's sleep quality data analysis. Finally, feedback prompts are given according to the user's sleep quality characterization value, and personalized feedback prompts can be provided to the user.
[0038] (2) The present invention can effectively identify and quantify various factors that affect sleep quality by analyzing the user's sleep time data, sleep environment data and sleep status data. The sleep time data reflects the user's sleep duration and regularity, the sleep environment data indicates the degree of influence of environmental factors on sleep, and the sleep status data provides the user's sleep status information. Analyzing multi-dimensional data helps to more accurately evaluate the user's overall sleep performance.
[0039] (3) The present invention can improve the accuracy of the user's sleep quality assessment by analyzing the user's sleep quality characterization value, thereby more accurately identifying the user's sleep pattern and habits, improving the accuracy of the user's sleep data analysis, and providing data support for personalized sleep recommendations.
[0040] (4) By providing feedback based on the user's sleep quality characterization value, the present invention enables the system to more accurately analyze the user's sleep data, thereby improving the accuracy of the user's sleep data analysis, helping the user to understand the factors that affect sleep quality in a targeted manner, helping to enhance the user's understanding of their own sleep conditions, improving the accuracy of sleep quality assessment, and providing a data basis for the user's sleep quality optimization direction.
[0041] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 It is a schematic diagram of system module connection of the present invention.
[0043] Figure 2 Example image representing the value of a user's sleep state DETAILED DESCRIPTION
[0044] 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.
[0045] See also Figure 1 As shown, an embodiment of the present invention provides a technical solution: a three-dimensional multi-dimensional data intelligent sleep monitoring system, including a sleep data collection platform for collecting a user's sleep time data, sleep environment data and sleep status data.
[0046] It should be supplemented that the user's sleep time data includes: the user's total sleep time in each monitoring time period, the user's sleep sound in each monitoring time period and the user's average sleep time.
[0047] It should be supplemented that the user's sleeping environment data includes: temperature data in each monitoring time period, humidity data in each monitoring time period, and light intensity and noise level values in each monitoring time period.
[0048] It should be supplemented that the user's sleep state data includes: the number of body movements of the user in each monitoring time period and the breathing frequency of the user in each monitoring time period.
[0049] The sleep data analysis module is used to analyze the user's sleep time data, sleep environment data and sleep state data to obtain the user's sleep quality representation value.
[0050] The sleep quality analysis prompt module is used to provide feedback prompts based on the user's sleep quality representation value.
[0051] Specifically, the sleep data analysis module includes a user's sleep time monitoring unit, a user's sleep environment monitoring unit and a user's sleep state monitoring unit, wherein: the user's sleep time monitoring unit is used to analyze the user's sleep time data to obtain the user's sleep time representation value.
[0052] The user's sleeping environment monitoring unit is used to analyze the user's sleeping environment data to obtain the user's sleeping environment characterization value.
[0053] The user's sleep state monitoring unit is used to analyze the user's sleep state data to obtain the user's sleep state representation value.
[0054] Specifically, the user's sleep time characterization value, the specific analysis process is: arrange a monitoring cycle, set a number of monitoring time periods in the monitoring cycle, extract the user's eye movement images in the sleep data collection platform, and analyze to obtain the total duration of the user's rapid eye movement sleep in each monitoring time period.
[0055] It should be noted that the user's eye movement images in the sleep data collection platform are extracted and analyzed to obtain the total duration of the user's rapid eye movement sleep in each monitoring time period. The specific analysis process is: extract the time periods corresponding to the user's rapid and irregular eye movements in the user's eye movement images, and add up the time periods to obtain the total duration of the user's rapid eye movement sleep.
[0056] It should be added that the user's REM sleep is a stage in the sleep cycle. During REM sleep, the eyeballs will move rapidly. This phenomenon of rapid eye movement can usually be seen with the eyes closed. The REM sleep stage can be determined by detecting eye movements.
[0057] The total sleep duration of the user in each monitoring time period is monitored, and the total REM sleep duration of the user in each monitoring time period is divided by the total sleep duration of the user in each monitoring time period as the REM sleep ratio of the user in each monitoring time period.
[0058] The sleeping sounds of the users in each monitoring time period are monitored and recorded, and analyzed to obtain the deep sleep duration of the users in each monitoring time period, and the ratio of the deep sleep duration of the users in each monitoring time period to the total sleep duration of the users in each monitoring time period is taken as the deep sleep proportion of the users in each monitoring time period.
[0059] It should be noted that the sleeping sounds of the user in each monitoring time period are monitored and recorded and analyzed to obtain the deep sleep duration of the user in each monitoring time period. The specific analysis process is: use sleep monitoring equipment to record the sound signals of the user during sleep, use pattern recognition algorithm to classify the sound signals, determine the duration of each time period when the user is in deep sleep, calculate the total duration of the user's deep sleep in each time period, and record it as the deep sleep duration of the user in each monitoring time period.
[0060] According to the user's rapid eye movement sleep ratio and the user's deep sleep ratio in each monitoring time period, the user's average sleep duration is counted and analyzed to obtain the user's sleep time representation value.
[0061] It should be added that the user's average sleep duration usually refers to the user's average sleep duration per day during the monitoring period, which is usually obtained through sleep monitoring equipment.
[0062] In this embodiment, the sleep time characterization value of the user is obtained using the following analysis conditions, specifically:
[0063]
[0064] In the formula, β represents the user's sleep time representation value, a i represents the REM sleep ratio of the user in the i-th monitoring period, Δa represents the set reference REM sleep ratio, θ 1 represents the influence factor corresponding to the set REM sleep ratio, b i represents the deep sleep ratio of the user in the i-th monitoring period, Δb represents the defined deep sleep ratio, θ 2 represents the influencing factor corresponding to the set deep sleep ratio, c represents the average sleep duration of the user, Δc represents the set defined sleep duration, θ 3 It represents the influencing factor corresponding to the set sleep duration, i represents the number of each monitoring time period, i=1,2,3,…n, and n represents the total number of monitoring time periods.
[0065] It should be noted that, in the present embodiment, the influencing factors corresponding to the preset rapid eye movement sleep ratio, the influencing factors corresponding to the deep sleep ratio and the influencing factors corresponding to the sleep duration are obtained from the sleep monitoring database, and the influencing factors corresponding to the rapid eye movement sleep ratio, the influencing factors corresponding to the deep sleep ratio and the influencing factors corresponding to the sleep duration are all numbers between 0 and 1.
[0066] In a specific embodiment, a fitting curve is obtained by fitting the relationship between the user's average sleep duration, the user's rapid eye movement sleep ratio in each monitoring time period, the user's deep sleep ratio in each monitoring time period, and the user's sleep time characterization value through historical data. The influencing factors corresponding to the rapid eye movement sleep ratio, the influencing factors corresponding to the deep sleep ratio, and the influencing factors corresponding to the sleep duration are determined according to the fitting curve. The real-time average sleep duration of the user, the user's rapid eye movement sleep ratio in each monitoring time period, and the user's deep sleep ratio in each monitoring time period are substituted into the fitting curve to obtain the corresponding influencing factors.
[0067] It should be explained that the analysis method of this embodiment obtains the user's sleep time characterization value by combining the user's average sleep duration, the user's rapid eye movement sleep ratio in each monitoring time period, and the user's deep sleep ratio in each monitoring time period for analysis, which helps to improve the accuracy of the user's sleep quality and sleep health status assessment, and thus provide data support for personalized sleep recommendations.
[0068] It should be added that the user's average sleep duration, the user's REM sleep ratio in each monitoring time period, and the user's deep sleep ratio in each monitoring time period in this formula are correlated and do not exist independently. For example, if the user has a longer average sleep duration, but if the user's REM sleep ratio is too high or the deep sleep ratio is too low, it may indicate that the user's sleep quality is poor. A comprehensive analysis of the user's average sleep duration, the user's REM sleep ratio in each monitoring time period, and the user's deep sleep ratio in each monitoring time period can more accurately evaluate the impact of the user's sleep time on the user's sleep quality.
[0069] In this implementation, the user's average sleep duration is analyzed to provide basic information about the user's overall sleeping habits, which can be used as a benchmark for sleep assessment. Analyzing the user's rapid eye movement sleep ratio in each monitoring time period helps to promptly identify possible sleep problems. Analyzing the user's deep sleep ratio in each monitoring time period helps to customize a personalized sleep optimization strategy. The sleep time representation value obtained by analysis can more comprehensively understand the user's sleep pattern and quality.
[0070] The user's sleep time characterization value represents a numerical quantification result obtained by analyzing the user's sleep time data, and is used to quantify the degree of influence of the user's deep sleep time on the user's sleep quality.
[0071] Specifically, the user's sleep environment characterization value, the specific analysis process is: monitor the temperature data in each monitoring time period, analyze to obtain the average temperature in each monitoring time period, and take the average value of the square of the difference between each temperature data in each monitoring time period and the average temperature in each monitoring time period as the variance value of the temperature in each monitoring time period.
[0072] The humidity data in each monitoring time period is monitored, and the average humidity in each monitoring time period is analyzed and obtained. The average value of the square of the difference between each humidity data in each monitoring time period and the average humidity in each monitoring time period is taken as the variance value of the humidity in each monitoring time period.
[0073] According to the variance value of temperature in each monitoring time period and the variance value of humidity in each monitoring time period, the light intensity and noise level values in each monitoring time period in the user's sleeping environment data are extracted, and the user's sleeping environment characterization value is obtained through analysis.
[0074] It should be added that the light intensity in each monitoring time period refers to the flow of light energy in the sleeping environment during the monitoring time period, which is usually measured by a light meter.
[0075] It should be added that the noise level value in each monitoring time period refers to the sound intensity or sound pressure level in the sleeping environment, which is usually measured by a sound meter.
[0076] In this embodiment, the sleep environment characterization value of the user is obtained using the following analysis conditions, specifically:
[0077]
[0078] In the formula, γ represents the user's sleep environment representation value, d i represents the variance value of the temperature in the i-th monitoring period, Δd represents the variance value of the set reference temperature, Indicates the influence factor corresponding to the variance value of the set temperature, f i represents the variance value of humidity in the i-th monitoring period, Δf represents the variance value of the set reference humidity, Indicates the influence factor corresponding to the set humidity variance value, g i represents the light intensity in the i-th monitoring time period, Δg represents the set reference light intensity, Indicates the influence factor corresponding to the set light intensity, h i represents the noise level value in the i-th monitoring period, Δh represents the set reference noise level value, It represents the impact factor corresponding to the set noise level value, i represents the number of each monitoring time period, i=1,2,3,…n, n represents the total number of monitoring time periods, and e represents a natural constant.
[0079] It should be noted that, in this embodiment, the influence factors corresponding to the preset temperature variance value, the influence factors corresponding to the humidity variance value, the influence factors corresponding to the light intensity, and the influence factors corresponding to the noise level value are obtained from the sleep monitoring database, and the influence factors corresponding to the temperature variance value, the influence factors corresponding to the humidity variance value, the influence factors corresponding to the light intensity, and the influence factors corresponding to the noise level value are all numbers between 0 and 1.
[0080] In a specific embodiment, through historical data, the relationship between the variance value of temperature in each monitoring time period, the variance value of humidity in each monitoring time period, the light intensity in each monitoring time period, the noise level value in each monitoring time period and the user's sleep environment characterization value is fitted to obtain a fitting curve, and the influencing factors corresponding to the variance value of temperature, the variance value of humidity, the light intensity and the noise level value are determined according to the fitting curve, and the real-time variance value of temperature in each monitoring time period, the variance value of humidity in each monitoring time period, the light intensity in each monitoring time period and the noise level value in each monitoring time period are substituted into the fitting curve to obtain the corresponding influencing factors.
[0081] It should be explained that the analysis method of this embodiment, by combining the variance value of temperature, the variance value of humidity, the light intensity and the noise level in each monitoring time period to obtain the user's sleep environment characterization value, helps to improve the accuracy of the user's sleep quality assessment and provide a data basis for personalized sleep environment optimization.
[0082] It should be added that the variance values of temperature, humidity, light intensity and noise level in each monitoring time period in this formula are correlated and do not exist independently. For example, if the variance values of temperature and humidity are large, combined with high noise level values and large fluctuations in light intensity, it may indicate that the sleeping environment is not stable and comfortable enough, which has a great impact on the user's sleep quality. Comprehensive analysis of the variance values of temperature, humidity, light intensity and noise level in each monitoring time period can more accurately evaluate the impact of the user's sleeping environment on the user's sleep quality.
[0083] In this implementation, analyzing the variance values of temperature in each monitoring time period can more accurately evaluate the impact of temperature on sleep quality. Analyzing the variance values of humidity and light intensity in each monitoring time period can help to optimize the sleep environment in a personalized manner, thereby improving the user's sleep quality. Analyzing the noise level values in each monitoring time period can more accurately evaluate the user's sleep environment quality. Analyzing the user's sleep environment characterization value can help to more accurately evaluate the user's sleep quality under different sleeping environment conditions.
[0084] The user's sleep environment characterization value represents a numerical quantification result obtained by analyzing the user's sleep environment data, and is used to quantify the degree of influence of the user's sleep environment on the user's sleep quality.
[0085] Specifically, the sleep state characterization value of the user is analyzed in the following steps: monitoring the number of body movements of the user in each monitoring time period, extracting the duration of each monitoring time period, and obtaining the body movement frequency of the user in each monitoring time period.
[0086] It should be added that the number of times the user's body movements occur in each monitoring time period is divided by the length of each monitoring time period to obtain the body movement frequency of the user in each monitoring time period.
[0087] The user's breathing frequency in each monitoring time period is counted, and combined with the user's body movement frequency in each monitoring time period, the user's sleep state representation value is analyzed and obtained.
[0088] It should be noted that the user's breathing frequency in each monitoring time period can be measured using a biosensor.
[0089] In this embodiment, the sleep state characterization value of the user is obtained using the following analysis conditions, specifically:
[0090]
[0091] In the formula, δ represents the user's sleep state representation value, K i represents the user's breathing frequency in the i-th monitoring period, ΔK represents the defined breathing frequency, ω 1 Represents the weight factor corresponding to the set respiratory rate, M i represents the user's body movement frequency in the i-th monitoring period, ΔM represents the set reference body movement frequency, ω 2 It represents the weight factor corresponding to the set body movement frequency, i represents the number of each monitoring time period, i=1,2,3,…n, and n represents the total number of monitoring time periods.
[0092] It needs to be explained that Figure 2 As shown, Figure 2 : is an example image of the user's sleep state characterization value, wherein the x-axis represents the user's breathing frequency, and the y-axis represents the user's sleep state characterization value. In this embodiment, the weight factor corresponding to the breathing frequency is 0.6, and the weight factor corresponding to the body movement frequency is 0.4. The breathing frequency is defined as 30 BPM, the reference body movement frequency is 3 times / hour, and the total number of monitoring time periods is 1. Three different groups of example parameters are defined in the figure, corresponding to different situations of the three curves, respectively represented by solid lines, dashed lines and dotted lines, and the corresponding curve labels are a, b, and c, respectively.
[0093] It needs to be explained that when the user's body movement frequency is 3 times / hour, the functional relationship image between the user's breathing frequency and the user's sleep state characterization value is shown in curve a, when the user's body movement frequency is 4 times / hour, the functional relationship image between the user's breathing frequency and the user's sleep state characterization value is shown in curve b, and when the user's body movement frequency is 5 times / hour, the functional relationship image between the user's breathing frequency and the user's sleep state characterization value is shown in curve c. The user's sleep state characterization value increases as the absolute value of the difference between the user's breathing frequency and the defined breathing frequency decreases, and when the user's body movement frequency increases, the user's sleep state characterization value decreases accordingly. The curve can be used to quickly and accurately obtain the user's sleep state characterization value, which solves the problem in the prior art that the user's sleep state characterization value cannot be accurately measured due to the lack of detailed analysis process, thereby achieving accurate measurement of the user's sleep quality.
[0094] It should be noted that, in this embodiment, the preset weight factor corresponding to the respiratory frequency and the weight factor corresponding to the body movement frequency are obtained from the sleep monitoring database, and the weight factor corresponding to the respiratory frequency and the weight factor corresponding to the body movement frequency are both numbers between 0 and 1.
[0095] In a specific embodiment, through historical data, the relationship between the user's breathing frequency in each monitoring time period, the user's body movement frequency in each monitoring time period and the user's sleep state characterization value is fitted to obtain a fitting curve, and the weight factor corresponding to the breathing frequency and the weight factor corresponding to the body movement frequency are determined according to the fitting curve, and the real-time breathing frequency of the user in each monitoring time period and the body movement frequency of the user in each monitoring time period are substituted into the fitting curve to obtain the corresponding weight factor.
[0096] It should be explained that the analysis method of this embodiment obtains the user's sleep state characterization value by combining the user's breathing frequency in each monitoring time period and the user's body movement frequency in each monitoring time period, which helps to accurately evaluate the user's sleep state and the impact of the sleep state on sleep quality, thereby improving the accuracy of sleep quality assessment.
[0097] It should be added that the breathing frequency of the user in each monitoring time period and the body movement frequency of the user in each monitoring time period in this formula are correlated and do not exist independently. For example, the breathing frequency is relatively stable during deep sleep, while the body movement frequency is relatively low. During light sleep or wakefulness, the breathing frequency may be faster and the body movement frequency is higher. A comprehensive analysis of the breathing frequency of the user in each monitoring time period and the body movement frequency of the user in each monitoring time period can more accurately evaluate the impact of the user's sleep state on the user's sleep quality.
[0098] In this implementation, analyzing the user's breathing frequency in each monitoring time period can more accurately identify whether the user is in a deep sleep stage, thereby more accurately evaluating the proportion and quality of the user's deep sleep. Analyzing the user's body movement frequency in each monitoring time period helps to identify the instability of the user's sleep. Analyzing the user's sleep state characterization value helps to improve the accuracy of sleep quality assessment.
[0099] The user's sleep state characterization value represents a numerical quantification result obtained by analyzing the user's sleep state data, and is used to quantify the degree of influence of the user's sleep state on the user's sleep quality.
[0100] Specifically, the sleep quality characterization value of the user is obtained, and the specific analysis process is: according to the sleep time characterization value of the user, the sleep environment characterization value of the user and the sleep state characterization value of the user, a comprehensive analysis is performed to obtain the sleep quality characterization value of the user.
[0101] Specifically, the sleep quality analysis and prompting module includes a user's sleep quality analysis unit and a user's sleep quality prompting unit, wherein: the user's sleep quality analysis unit is used to analyze the user's sleep quality characterization value to obtain the user's sleep quality analysis result.
[0102] The user's sleep quality prompting unit is used to provide feedback prompts based on the user's sleep quality analysis results.
[0103] It should be added that feedback is provided based on the user's sleep quality analysis results. The specific process is that if the user's sleep quality analysis result is that the user's sleep quality is unqualified, a message is sent to the user indicating that the user's sleep quality is unqualified, and detailed feedback is provided to prompt the user's specific reasons for the unqualified quality, among which the specific reasons include that the user's deep sleep time is unqualified, the user's sleeping environment is unqualified, and the user's sleep state is unqualified.
[0104] The sleep quality analysis result of the user includes whether the sleep quality of the user is qualified or not.
[0105] Specifically, the user's sleep quality analysis result is obtained, and the specific analysis process is: comparing the user's sleep quality characterization value with the set user's sleep quality characterization threshold. If the user's sleep quality characterization value is higher than or equal to the set user's sleep quality characterization threshold, then the user's sleep quality analysis result is that the user's sleep quality is qualified; if the user's sleep quality characterization value is lower than the set user's sleep quality characterization threshold, then the user's sleep quality analysis result is that the user's sleep quality is unqualified.
[0106] Specifically, the user's sleep quality is unqualified, including that the user's deep sleep time is unqualified, the user's sleeping environment is unqualified, and the user's sleeping state is unqualified.
[0107] If the user's sleep quality analysis result shows that the user's sleep quality is unqualified, the user's sleep time representation value will be compared with the set user's sleep time representation threshold. If the user's sleep time representation value is lower than the set user's sleep time representation threshold, the user's deep sleep time will be marked as unqualified, and the user's deep sleep time will be recorded as unqualified.
[0108] The user's sleep environment characterization value will be compared with the set user's sleep environment characterization threshold. If the user's sleep environment characterization value is lower than the set user's sleep environment characterization threshold, the user's sleep environment will be marked as unqualified and recorded as the user's sleep environment is unqualified.
[0109] The user's sleep state characterization value is compared with a set user's sleep state characterization threshold. If the user's sleep state characterization value is lower than the set user's sleep state characterization threshold, the user's sleep state is marked as unqualified and recorded as the user's sleep state unqualified.
[0110] Specifically, the sleep quality characterization value of the user, the specific analysis conditions are:
[0111]
[0112] In the formula, α represents the user's sleep quality representation value, β represents the user's sleep time representation value, μ 1 represents the weight factor corresponding to the set sleep time representation value, γ represents the user's sleep environment representation value, μ 2 represents the weight factor corresponding to the set sleep environment characterization value, δ represents the user's sleep state characterization value, μ 3 Indicates the weight factor corresponding to the set sleep state representation value.
[0113] In a specific embodiment, Table 1 shows the sleep quality characterization values corresponding to different sleep time characterization values, sleep environment characterization values and sleep state characterization values. In this embodiment, the weight factor corresponding to the sleep time characterization value is 0.2, the weight factor corresponding to the sleep environment characterization value is 0.4, and the weight factor corresponding to the sleep state characterization value is 0.4.
[0114] Table 1 Sleep quality characterization values corresponding to different sleep time characterization values, sleep environment characterization values and sleep state characterization values
[0115] Sleep time characterization value Sleep environment characterization value Sleep state characterization value Sleep quality characterization value 1.5 1.6 0.7 0.8987 1.7 1.6 0.7 0.9125 1.5 1.8 0.7 0.9263 1.5 1.6 1.0 0.9399
[0116] It needs to be explained that in Table 1, as the sleep time characterization value, the sleep environment characterization value and the sleep state characterization value increase, the sleep quality characterization value increases accordingly. Table 1 lists the values of 4 different sleep time characterization values, sleep environment characterization values and sleep state characterization values, and the corresponding sleep quality characterization values are obtained by the formula. These sleep quality characterization values provide the degree of influence of different sleep time characterization values, sleep environment characterization values and sleep state characterization values on the sleep quality characterization value. The sleep quality characterization value comprehensively considers the user's sleep time characterization value, sleep environment characterization value and sleep state characterization value, provides data support for the user's sleep quality evaluation, and improves the accuracy of sleep quality evaluation.
[0117] It should be noted that, in this embodiment, the weight factor corresponding to the preset sleep time characterization value, the weight factor corresponding to the sleep environment characterization value, and the weight factor corresponding to the sleep state characterization value are obtained from the sleep monitoring database, and the weight factor corresponding to the sleep time characterization value, the weight factor corresponding to the sleep environment characterization value, and the weight factor corresponding to the sleep state characterization value are all numbers between 0 and 1.
[0118] In a specific embodiment, through historical data, the relationship between the user's sleep time characterization value, the user's sleep environment characterization value, the user's sleep state characterization value and the user's sleep quality characterization value is fitted to obtain a fitting curve, and the weight factor corresponding to the sleep time characterization value, the weight factor corresponding to the sleep environment characterization value and the weight factor corresponding to the sleep state characterization value are determined according to the fitting curve, and the real-time user's sleep time characterization value, the user's sleep environment characterization value and the user's sleep state characterization value are substituted into the fitting curve to obtain the corresponding weight factor.
[0119] It should be explained that the analysis method of this embodiment, by combining the user's sleep time characterization value, the user's sleep environment characterization value and the user's sleep state characterization value for analysis, obtains the user's sleep quality characterization value, which helps to timely discover potential sleep problems and further understand the user's overall sleep quality more accurately.
[0120] It should be added that the user's sleep time representation value, the user's sleep environment representation value and the user's sleep state representation value in this formula are correlated and do not exist independently. For example, long-term sleep but uneven sleep state distribution may also lead to poor sleep quality, thereby affecting the overall sleep quality. Comprehensive analysis of the user's sleep time representation value, the user's sleep environment representation value and the user's sleep state representation value can more accurately evaluate the impact of the user's sleep time, environment and state on the user's sleep quality.
[0121] It should be noted that an intelligent sleep monitoring system for three-dimensional multi-dimensional data also includes a sleep monitoring database, which is used to store the reference rapid eye movement sleep ratio, the defined deep sleep ratio, the defined sleep duration, the influencing factors corresponding to the rapid eye movement sleep ratio, the influencing factors corresponding to the deep sleep ratio, the influencing factors corresponding to the sleep duration, the variance value of the reference temperature, the variance value of the reference humidity, the reference light intensity, the reference noise level value, the influencing factors corresponding to the variance value of the temperature, the influencing factors corresponding to the variance value of the humidity, the influencing factors corresponding to the light intensity, the influencing factors corresponding to the noise level value, the defined breathing frequency, the reference body movement frequency, the weight factor corresponding to the breathing frequency, the weight factor corresponding to the body movement frequency, the weight factor corresponding to the sleep time representation value, the weight factor corresponding to the sleep environment representation value and the weight factor corresponding to the sleep state representation value.
[0122] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0123] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. A three-dimensional multi-dimensional data intelligent sleep monitoring system, characterized in that: include: Sleep data collection platform, used to collect users' sleep time data, sleep environment data and sleep status data; A sleep data analysis module is used to analyze the user's sleep time data, sleep environment data and sleep state data to obtain the user's sleep quality representation value; The sleep quality analysis prompt module is used to provide feedback prompts based on the user's sleep quality representation value.
2. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 1, characterized in that: The sleep data analysis module specifically includes a user's sleep time monitoring unit, a user's sleep environment monitoring unit, and a user's sleep state monitoring unit, wherein: The user's sleep time monitoring unit is used to analyze the user's sleep time data to obtain the user's sleep time representation value; The user's sleep environment monitoring unit is used to analyze the user's sleep environment data to obtain the user's sleep environment representation value; The user's sleep state monitoring unit is used to analyze the user's sleep state data to obtain the user's sleep state representation value.
3. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 2, characterized in that: The sleep time characterization value of the user, the specific analysis process is as follows: Arrange a monitoring cycle, set a number of monitoring time periods in the monitoring cycle, extract the user's eye movement images in the sleep data collection platform, and analyze to obtain the total duration of the user's rapid eye movement sleep in each monitoring time period; Monitor the total sleep duration of the user in each monitoring time period, and divide the total REM sleep duration of the user in each monitoring time period by the total sleep duration of the user in each monitoring time period as the REM sleep ratio of the user in each monitoring time period; Monitor and record the sleep sounds of the user in each monitoring time period and analyze them to obtain the deep sleep duration of the user in each monitoring time period, and use the ratio of the deep sleep duration of the user in each monitoring time period to the total sleep duration of the user in each monitoring time period as the deep sleep ratio of the user in each monitoring time period; According to the user's rapid eye movement sleep ratio and the user's deep sleep ratio in each monitoring time period, the user's average sleep duration is calculated, and the user's sleep time representation value is obtained through analysis; The user's sleep time characterization value represents a numerical quantification result obtained by analyzing the user's sleep time data, and is used to quantify the degree of influence of the user's deep sleep time on the user's sleep quality.
4. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 2, characterized in that: The specific analysis process of the user's sleeping environment characterization value is as follows: Monitor the temperature data in each monitoring time period, analyze and obtain the average temperature in each monitoring time period, and take the average value of the square of the difference between each temperature data in each monitoring time period and the average temperature in each monitoring time period as the variance value of the temperature in each monitoring time period; Monitor the humidity data in each monitoring time period, analyze and obtain the average humidity in each monitoring time period, and take the average value of the square of the difference between each humidity data in each monitoring time period and the average humidity in each monitoring time period as the variance value of the humidity in each monitoring time period; According to the variance value of temperature in each monitoring time period and the variance value of humidity in each monitoring time period, the light intensity and noise level values in each monitoring time period in the user's sleeping environment data are extracted, and the sleeping environment characterization value of the user is obtained by analysis; The user's sleep environment characterization value represents a numerical quantification result obtained by analyzing the user's sleep environment data, and is used to quantify the degree of influence of the user's sleep environment on the user's sleep quality.
5. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 2, characterized in that: The sleep state characterization value of the user, the specific analysis process is: Monitor the number of body movements of the user in each monitoring time period, extract the duration of each monitoring time period, and obtain the body movement frequency of the user in each monitoring time period; The user's breathing frequency in each monitoring period is counted, and combined with the user's body movement frequency in each monitoring period, the user's sleep state representation value is analyzed; The user's sleep state characterization value represents a numerical quantification result obtained by analyzing the user's sleep state data, and is used to quantify the degree of influence of the user's sleep state on the user's sleep quality.
6. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 1, characterized in that: The specific analysis process of obtaining the sleep quality characterization value of the user is as follows: The user's sleep quality characterization value is obtained through comprehensive analysis based on the user's sleep time characterization value, the user's sleep environment characterization value and the user's sleep state characterization value.
7. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 1, characterized in that: The sleep quality analysis and prompting module specifically includes a user's sleep quality analysis unit and a user's sleep quality prompting unit, wherein: The user's sleep quality analysis unit is used to analyze the user's sleep quality representation value to obtain the user's sleep quality analysis result; The user's sleep quality prompting unit is used to provide feedback prompts based on the user's sleep quality analysis results; The sleep quality analysis result of the user includes whether the sleep quality of the user is qualified or not.
8. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 7, characterized in that: The sleep quality analysis result of the user is obtained, and the specific analysis process is as follows: The user's sleep quality characterization value is compared with the set user's sleep quality characterization threshold. If the user's sleep quality characterization value is higher than or equal to the set user's sleep quality characterization threshold, the user's sleep quality analysis result is that the user's sleep quality is qualified. If the user's sleep quality characterization value is lower than the set user's sleep quality characterization threshold, the user's sleep quality analysis result is that the user's sleep quality is unqualified.
9. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 8, characterized in that: The user's sleep quality is unqualified, including the user's deep sleep time is unqualified, the user's sleeping environment is unqualified, and the user's sleeping state is unqualified; If the sleep quality analysis result of the user is that the sleep quality of the user is unqualified, the sleep time characterization value of the user is compared with the set sleep time characterization threshold of the user. If the sleep time characterization value of the user is lower than the set sleep time characterization threshold of the user, the deep sleep time of the user is marked as unqualified, and the deep sleep time of the user is recorded as unqualified; The user's sleep environment characterization value is compared with a set user's sleep environment characterization threshold. If the user's sleep environment characterization value is lower than the set user's sleep environment characterization threshold, the user's sleep environment is marked as unqualified and recorded as the user's sleep environment is unqualified; The user's sleep state characterization value is compared with a set user's sleep state characterization threshold. If the user's sleep state characterization value is lower than the set user's sleep state characterization threshold, the user's sleep state is marked as unqualified and recorded as the user's sleep state unqualified.
10. The intelligent sleep monitoring system of three-dimensional multi-dimensional data according to claim 6, characterized in that: The sleep quality characterization value of the user, the specific analysis conditions are: Wherein, α represents the user's sleep quality representation value, β represents the user's sleep time representation value, μ1 represents the weight factor corresponding to the set sleep time representation value, γ represents the user's sleep environment representation value, μ2 represents the weight factor corresponding to the set sleep environment representation value, δ represents the user's sleep state representation value, and μ3 represents the weight factor corresponding to the set sleep state representation value.
Citation Information
Patent Citations
Human body sleep analysis method and device based on environment monitoring and storage medium
CN114403808A
Healthy sleep management system and method
CN116269230A
Multi-dimensional human body data monitoring system based on big data real-time analysis
CN118319245A
Sleep and environment control method and system
US20050143617A1
Sleep monitoring device
US20160270721A1
Cited By
Sleep quality evaluation method and system based on sleep activity recognition
CN120052829A
Sleep Quality Assessment Method and System Based on Sleep Activity Recognition
CN120052829B
Sleep quality monitoring system and method based on multi-source data fusion
CN120732357A
