Intelligent intervention system for circadian rhythm disorder insomnia based on APP

Abstract

The invention relates to the technical field of sleep data processing, in particular to an intelligent intervention system for circadian rhythm disorder insomnia based on an APP. The system comprises a user day and night insomnia type marking and dividing module, a day and night insomnia user sleep parameter acquisition module, a day and night insomnia user disorder degree evaluation module and a day and night disorder insomnia user intelligent intervention execution module, and questionnaire survey and user day and night sleep parameter real-time acquisition can be performed through an APP on a wearable wristwatch. Obtaining a user day and night insomnia severity index and a user day and night sleep category measurement score, and performing day and night insomnia type virtual mark division to obtain various day and night insomnia types; the intelligent intervention work of the circadian rhythm disorder insomnia of the user is executed by monitoring the circadian sleep cycles and sleep quality scoring coefficients of the user corresponding to various users in real time and carrying out quantitative calculation of the rhythm disorder of the heart rate cycle and intelligent intervention pushing of the insomnia of the user. According to the invention, a customized insomnia intervention scheme can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep data processing, and in particular to an APP-based intelligent intervention system for circadian rhythm disorder insomnia. Background Art

[0002] Circadian Rhythm Sleep Disorders (CRSDs), also known as circadian rhythm sleep-wake disorders (CRSWD), are caused by long-term, repeated incoordination between lifestyle and endogenous circadian rhythm. They are more common in medical staff, police, security guards and other groups. Clinically, they can manifest as insomnia (difficulty falling asleep, difficulty maintaining sleep) and / or excessive sleepiness (increased daytime sleep) and other symptoms. In addition, studies have shown that circadian rhythm disorders are not only related to lifestyle, working hours and environmental factors, but may also lead to mental health problems such as anxiety and depression.

[0003] In recent years, with the rapid development of smart phones and mobile application technology, APP-based health intervention technology has gradually emerged, providing new ideas for the intelligent intervention management of circadian rhythm disorder insomnia. Through smart APPs, real-time monitoring and personalized intervention of different types of insomnia can be achieved, including sleep data collection, behavioral adjustment suggestions and psychological counseling. However, most sleep management apps on the market currently lack systematicity and scientificity, and often only provide basic sleep recording functions, and cannot effectively carry out comprehensive intervention for circadian rhythm disorders, thereby failing to improve users' sleep quality. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide an APP-based intelligent intervention system for circadian rhythm disorder insomnia to solve at least one of the above technical problems.

[0005] To achieve the above purpose, an APP-based intelligent intervention system for circadian rhythm disorder insomnia includes the following modules:

[0006] A user day and night insomnia type marking and classification module is used to collect the user's insomnia severity index scale and the morning type-evening type questionnaire in real time through the questionnaire function built into the APP software on the wearable watch, and collect the user's day and night sleep parameters in real time on the user's insomnia severity index scale and the morning type-evening type questionnaire to obtain the user's day and night insomnia severity index and the user's day and night sleep category measurement score; virtual marking and classification of day and night insomnia types are performed according to the user's day and night insomnia severity index and the user's day and night sleep category measurement score to obtain various day and night insomnia types;

[0007] The sleep parameter collection module for users with circadian insomnia is used to monitor the activity, sleep time, number of awakenings and heart rate of users with various types of circadian insomnia in real time during the same time period through a wearable watch, so as to obtain the circadian activity, circadian sleep time, number of awakenings and heart rate of users corresponding to various types of circadian insomnia; the sleep cycle of users is analyzed according to the circadian sleep time and number of awakenings corresponding to various types of circadian insomnia, so as to obtain the circadian sleep cycle of users corresponding to various types of circadian insomnia;

[0008] The module for evaluating the degree of disorder of circadian insomnia users is used to evaluate and analyze the circadian sleep quality of users corresponding to various types of circadian insomnia based on the circadian activity of users corresponding to various types of circadian insomnia, so as to obtain the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia; based on the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia and the circadian sleep cycles of users, the module for evaluating the degree of disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia is used to quantitatively calculate the disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia, so as to obtain the degree of disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia;

[0009] The circadian rhythm disorder insomnia user intelligent intervention execution module is used to push user insomnia intelligent intervention based on the degree of user circadian heart rate cycle rhythm disorder corresponding to various types of circadian insomnia using the APP software on the wearable watch, so as to execute the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

[0010] Furthermore, the user day and night insomnia type labeling and classification module includes the following functions:

[0011] The built-in questionnaire function of the wearable watch APP software collects users' Insomnia Severity Index Scale and Morningness-Eveningness Questionnaire in real time;

[0012] The user's daytime and nighttime insomnia severity index is collected in real time on the user's insomnia severity index scale to obtain the user's daytime and nighttime insomnia severity index, wherein the user's daytime and nighttime insomnia severity index can be divided into 0-7 points for no insomnia, 8-14 points for mild insomnia, 15-21 points for moderate insomnia, and 22-28 points for severe insomnia;

[0013] Performing a morning-night biological clock work-and-rest characteristic analysis on the user's morning-night type questionnaire to obtain the user's morning-night biological clock work-and-rest characteristic data;

[0014] The user's circadian sleep measurement is calculated based on the user's morning-night biological clock work and rest characteristic data to obtain the user's circadian sleep category measurement score, wherein the user's circadian sleep category measurement score can be divided into 16-30 points absolute night type, 31-41 points moderate night type, 42-58 points intermediate type, 59-69 points moderate morning type and 70-86 points absolute morning type;

[0015] Virtual marking and division of circadian insomnia types are performed according to the user's circadian insomnia severity index and the user's circadian sleep category measurement score to obtain various circadian insomnia types.

[0016] Further, the various types of circadian insomnia include:

[0017] Absolute night-no insomnia type, moderate night-no insomnia type, intermediate-no insomnia type, moderate morning-no insomnia type, absolute morning-no insomnia type, absolute night-mild insomnia type, moderate night-mild insomnia type, intermediate-mild insomnia type, moderate morning-mild insomnia type, absolute morning-mild insomnia type, absolute night-moderate insomnia type, moderate night-moderate insomnia type, intermediate-moderate insomnia type, moderate morning-moderate insomnia type, absolute morning-moderate insomnia type, absolute night-severe insomnia type, moderate night-severe insomnia type, intermediate-severe insomnia type, moderate morning-severe insomnia type and absolute morning-severe insomnia type.

[0018] Furthermore, the sleep parameter collection module for circadian insomnia users includes the following functions:

[0019] The wearable watch uses an acceleration sensor to monitor the user's activity during the day and night sleep period in real time during the same time period for various types of circadian insomnia, so as to obtain the user's circadian activity corresponding to various types of circadian insomnia;

[0020] Performing a circadian activity status analysis on the circadian activity amounts of the user corresponding to various circadian insomnia types to obtain the circadian activity status of the user corresponding to various circadian insomnia types; performing a circadian sleep stage judgment on the corresponding circadian activity amounts of the user according to the circadian activity status of the user corresponding to various circadian insomnia types to obtain the circadian sleep stage of the user corresponding to various circadian insomnia types, wherein the circadian sleep stage of the user includes a circadian deep sleep stage, a circadian light sleep stage, and a circadian wakefulness stage;

[0021] The sleep time sensor is used to monitor the sleep stage duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and night insomnia in real time, so as to obtain the sleep duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and night insomnia; the sleep duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and night insomnia are added together, so as to obtain the user's daytime and night sleep time corresponding to various types of daytime and night insomnia;

[0022] The suspected awakening frequency of the user is counted for the day and night awakening stages corresponding to various types of day and night insomnia, so as to obtain the suspected awakening frequency of the user during the day and night corresponding to various types of day and night insomnia; the user activity posture change data corresponding to various types of day and night insomnia are obtained by using a gyroscope sensor, and the number of awakening times is supplemented and corrected according to the user activity posture change data corresponding to various types of day and night insomnia and the suspected awakening frequency of the user during the day and night, so as to obtain the number of awakening times of the user during the day and night corresponding to various types of day and night insomnia;

[0023] The optical heart rate sensor on the wearable watch is used to obtain the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia, and the user's heart rate is calculated based on the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia, so as to obtain the user's circadian heart rate corresponding to various types of circadian insomnia;

[0024] The user's sleep cycle is analyzed according to the user's circadian sleep time and the number of times the user wakes up during the day and night corresponding to various types of circadian insomnia, so as to obtain the user's circadian sleep cycle corresponding to various types of circadian insomnia.

[0025] Furthermore, the auxiliary correction of the number of awakenings according to the user activity posture change data corresponding to various types of day and night insomnia and the user's suspected awakening frequency during the day and night includes:

[0026] Based on the suspected awakening frequencies of users corresponding to various types of circadian insomnia, the user activity posture change data corresponding to various types of circadian insomnia are matched and divided according to the suspected awakening frequencies, and the user activity posture change sub-data corresponding to each suspected awakening in various types of circadian insomnia are obtained;

[0027] Performing user activity trajectory recognition and analysis on the user activity posture change sub-data corresponding to each suspected awakening in various types of daytime and nighttime insomnia, and obtaining the user activity posture trajectory corresponding to each suspected awakening in various types of daytime and nighttime insomnia;

[0028] Performing activity trajectory behavior state analysis on the user activity posture trajectory corresponding to each suspected awakening in various types of day and night insomnia, and obtaining the user activity trajectory behavior state corresponding to each suspected awakening in various types of day and night insomnia;

[0029] Based on the user activity trajectory behavior state corresponding to each suspected wakefulness in various types of day and night insomnia, the corresponding user's suspected wakefulness during the day and night is compared and judged to assist in waking up. If it is judged that the user activity trajectory behavior state corresponding to the suspected wakefulness is a real wakefulness state, then the next user's suspected wakefulness during the day and night is compared and judged; if it is judged that the user activity trajectory behavior state corresponding to the suspected wakefulness is just a turning over state or a not really awake state, then the frequency of suspected wakefulness during the day and night of the user corresponding to various types of day and night insomnia is reduced by one, until all the user activity trajectory behavior states corresponding to the suspected wakefulness are compared and judged, so as to obtain the number of user wakeups during the day and night corresponding to various types of day and night insomnia.

[0030] Furthermore, the method of using the optical heart rate sensor on the wearable watch to obtain the user's photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia, and calculating the user's heart rate based on the user's photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia includes:

[0031] The optical heart rate sensor on the wearable watch is used to obtain the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia;

[0032] Performing low-pass environmental noise filtering on the user photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia to obtain low-pass environmental noise filtered fluctuation signals of the user pulse corresponding to various types of circadian insomnia; performing high-pass motion artifact elimination on the user pulse low-pass environmental noise filtered fluctuation signals corresponding to various types of circadian insomnia to obtain high-pass artifact eliminated fluctuation signals of the user pulse corresponding to various types of circadian insomnia;

[0033] Performing pulse fluctuation spectrum conversion on the user pulse high-pass artifact-eliminated fluctuation signal corresponding to various types of circadian insomnia to generate frequency domain graphs of the user pulse fluctuation signal corresponding to various types of circadian insomnia;

[0034] Perform pulse signal peak marking processing on the frequency domain spectra of the user pulse fluctuation signal corresponding to various types of day and night insomnia to obtain the peak points of the user pulse signal spectra corresponding to various types of day and night insomnia; perform peak interval calculation on the corresponding frequency domain spectra of the user pulse fluctuation signal based on the peak points of the user pulse signal spectra corresponding to various types of day and night insomnia to obtain the time interval between each pair of continuous peak points corresponding to various types of day and night insomnia;

[0035] According to the time interval between each pair of continuous peak points corresponding to various types of circadian insomnia, interval heart rate statistics are calculated to obtain the user's circadian heart rate sub-values ​​corresponding to each pair of continuous peak points of various types of circadian insomnia; the type heart rate arithmetic average calculation is performed on the user's circadian heart rate sub-values ​​corresponding to each pair of continuous peak points of various types of circadian insomnia to obtain the user's circadian heart rate corresponding to various types of circadian insomnia.

[0036] Further, the user sleep cycle analysis according to the user's daytime and nighttime sleep time corresponding to various types of daytime and nighttime insomnia and the number of times the user wakes up during the daytime and nighttime includes:

[0037] Determine the sleep start and end time points of the user's daytime and nighttime sleep time corresponding to various types of daytime and nighttime insomnia, and obtain the user's daytime and nighttime sleep start and end time points corresponding to various types of daytime and nighttime insomnia;

[0038] Based on the user's circadian sleep start time point and end time point corresponding to various types of circadian insomnia, the corresponding user's circadian sleep time is defined to generate a user's circadian sleep time range diagram corresponding to various types of circadian insomnia;

[0039] Based on the user's circadian sleep time range diagram corresponding to various types of circadian insomnia, the corresponding number of user's circadian awakening times is analyzed for interactive response, and the interactive response change curve between the circadian sleep duration and the number of awakening times corresponding to various types of circadian insomnia is obtained;

[0040] The user sleep cycle analysis is performed on the interactive response change curves between the user's circadian sleep duration and the number of awakenings corresponding to various types of circadian insomnia, and the user's circadian sleep cycles corresponding to various types of circadian insomnia are obtained.

[0041] Furthermore, the module for assessing the degree of disorder of users suffering from circadian insomnia includes the following functions:

[0042] Performing a user activity intensity analysis on the user's circadian activity amounts corresponding to various types of circadian insomnia to obtain the user's circadian activity intensity corresponding to various types of circadian insomnia;

[0043] Based on the circadian activity intensity of the user corresponding to the various circadian insomnia types, the circadian activity-sleep cycle impact correlation analysis of the user circadian sleep cycle corresponding to the various circadian insomnia types is performed to obtain the user circadian activity-sleep cycle correlation factors corresponding to the various circadian insomnia types;

[0044] Based on the user's circadian activity-sleep cycle correlation factor corresponding to various types of circadian insomnia, the circadian sleep quality of the user's circadian sleep cycle corresponding to various types of circadian insomnia is evaluated and calculated using the sleep quality score calculation formula to obtain the user's circadian sleep quality score coefficient corresponding to various types of circadian insomnia;

[0045] The sleep quality score calculation formula is as follows:

[0046]

[0047] Where ξ is the user's circadian sleep quality score coefficient, T is the user's circadian sleep cycle, τ is the variable parameter of the sleep cycle time point, and Wτ is the correlation factor affecting the effectiveness of user circadian activity sleep at the sleep cycle time point τ, Q τ is the user's circadian activity sleep depth impact correlation factor at the sleep cycle time point τ, E τ is the user's circadian activity sleep environment impact correlation factor at the sleep cycle time point τ, R τ is the user's circadian activity sleep physiological impact correlation factor at the sleep cycle time point τ, and ε is the correction coefficient of the user's circadian sleep quality score coefficient;

[0048] Based on the circadian sleep cycles of the users corresponding to the various types of circadian insomnia, statistical analysis is performed on the circadian heart rates of the users corresponding to the various types of circadian insomnia to obtain characteristic data of the circadian heart rate cycles of the users corresponding to the various types of circadian insomnia;

[0049] Based on the user's daytime sleep quality score coefficient corresponding to various types of daytime insomnia, the heart rate rhythm disorder degree calculation formula is used to perform a quantitative calculation of the heart rate rhythm disorder on the user's daytime heart rate cycle rhythm change characteristic data corresponding to various types of daytime insomnia, so as to obtain the degree of user's daytime heart rate cycle rhythm disorder corresponding to various types of daytime insomnia.

[0050] Furthermore, the calculation formula for the degree of heart rate rhythm disorder is specifically:

[0051]

[0052] Where DHR is the degree of disorder of the user's circadian heart rate cycle rhythm, T is the user's circadian sleep cycle, t is the time variable parameter, HR(t) is the user's circadian heart rate at time point t, α is the influence weight factor of the user's circadian heart rate cycle rhythm, β is the user's circadian heart rate cycle rhythm attenuation coefficient, γ is the user's circadian heart rate cycle rhythm amplitude influence coefficient, ω is the user's circadian heart rate cycle rhythm amplitude change frequency, is the amplitude phase offset of the user's circadian heart rate cycle rhythm, ξ is the user's circadian sleep quality score coefficient, and η is the correction coefficient of the user's circadian heart rate cycle rhythm disorder degree.

[0053] Furthermore, the circadian disorder insomnia user intelligent intervention execution module includes the following functions:

[0054] Designing intelligent intervention strategies for circadian insomnia according to the degree of disorder of the circadian heart rate cycle rhythm of the user corresponding to various types of circadian insomnia, so as to generate intelligent intervention strategy solutions for circadian insomnia of the user corresponding to various types of circadian insomnia;

[0055] Use the APP software on the wearable watch to obtain the work and rest habits corresponding to the day and night insomnia type, and preset the insomnia intervention push time and frequency according to the work and rest habits of the corresponding day and night insomnia type, so as to obtain the insomnia intervention push time and insomnia intervention push frequency corresponding to various day and night insomnia types;

[0056] Based on the insomnia intervention push time and insomnia intervention push frequency corresponding to various types of circadian insomnia, the APP software on the wearable watch is used to push the corresponding user circadian insomnia intelligent intervention strategy plan to the user, so as to perform the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

[0057] Beneficial effects of the present invention:

[0058] The APP-based circadian rhythm disorder insomnia intelligent intervention system proposed by the present invention is composed of a user circadian insomnia type marking classification module, a circadian insomnia user sleep parameter collection module, a circadian insomnia user disorder degree assessment module, and a circadian disorder insomnia user intelligent intervention execution module. Compared with the prior art, the beneficial effect of the present application is that by using the built-in questionnaire survey function of the APP software on the wearable watch, the user's insomnia severity index and the morning type-night type questionnaire survey results can be collected in real time. This mechanism not only provides the convenience of data collection, but also enables users to participate in their own health management without additional burden. Real-time data collection means that the user's historical sleep status can be grasped in time, thereby improving the accuracy and timeliness of the data. By analyzing these data, the impact of insomnia on different users can be better understood, which is helpful to design personalized sleep intervention plans for different types of insomnia users in the subsequent process. By collecting the user's daytime and nighttime insomnia severity index in real time using the Insomnia Severity Index Scale, we can gain an in-depth understanding of the user's daytime and nighttime insomnia condition. The grading of this index (0-7 points for no insomnia, 8-14 points for mild insomnia, 15-21 points for moderate insomnia, and 22-28 points for severe insomnia) provides a clear quantitative standard for research and clinical intervention. Through this grading, professionals can quickly identify the user's degree of insomnia and take targeted measures. This comprehensive data accumulation is of great significance for improving sleep quality and formulating personalized intervention measures. At the same time, the user's daytime sleep category measurement score is calculated through the user's morning type-evening type questionnaire. The setting of this score (such as 16-30 points for absolute evening type, 31-41 points for moderate evening type, 42-58 points for intermediate type, 59-69 points for moderate morning type and 70-86 points for absolute morning type) provides researchers with a more detailed user classification, which can accurately identify the sleep patterns of different users. Through this classification, professionals can make more targeted adjustments to intervention measures to more effectively solve the user's insomnia problem, so that through this score, it can be understood whether the corresponding user is evening type or morning type, so as to adjust work and rest habits, optimize lifestyle, and provide basic data guarantee for subsequent processing. It also enables users to be accurately classified into different types of circadian insomnia by virtually marking and dividing the corresponding users according to their circadian insomnia severity index and sleep category measurement score. This provides corresponding insomnia users with a clearer self-awareness, allowing them to understand their own insomnia type and thus more effectively seek professional help or take self-regulation measures, thus enabling more effective intelligent intervention processes for different types of circadian rhythm disorders.Secondly, by using a wearable watch to monitor the activity corresponding to various types of circadian insomnia in real time using an accelerometer in the same time period, it is possible to effectively collect activity data of various types of circadian insomnia during circadian sleep. The key to this process is to capture the user's true activity level, including daily activities and small movements during sleep. This real-time data can help researchers identify the activity patterns of different types of insomnia, thereby providing basic data for further analysis. By analyzing the user's sleep time and number of wake-ups, we can have a clearer understanding of the integrity and stability of their sleep cycle. Insufficient sleep time and frequent night awakenings are usually the main manifestations of insomnia. By obtaining heart rate data, it can provide important data about the user's physiological state. The heart rate is closely related to sleep quality and can reflect the user's degree of relaxation and sleep depth. By analyzing the heart rate data of users with different types of insomnia, it can be revealed which physiological characteristics are directly related to insomnia. For example, fluctuations in heart rate may reflect the user's stress level and anxiety at night, thereby affecting the depth and continuity of their sleep, providing data support for the personalized intelligent intervention process. By analyzing the sleep cycle according to the user's daytime and nighttime sleep time and the number of times they wake up, the basic rules of the user's insomnia type can be revealed. This step not only helps to analyze the user's sleep structure by understanding the sleep cycle, but also identifies internal and external factors that affect sleep quality. By establishing a sleep cycle model, more scientific sleep management suggestions can be provided to users, such as how to optimize the sleep environment, adjust the work and rest time, etc., so as to improve their overall sleep quality and provide strong data support for subsequent processing. Then, based on the user's daytime and nighttime activity corresponding to various types of daytime and night insomnia, the sleep quality of the user's daytime and nighttime sleep cycle corresponding to various types of daytime and night insomnia is evaluated and calculated. The sleep quality score is a comprehensive indicator that not only considers the duration of sleep, but also includes multiple dimensions such as the depth, frequency, and number of times you wake up. Through quantitative analysis, the sleep quality score coefficients of different types of insomnia can be obtained. This evaluation process can provide a quantitative perspective for the subsequent processing process and help better understand the impact of insomnia. By quantifying the disturbance of the heart rate cycle rhythm of the user's circadian heart rate corresponding to various types of circadian insomnia based on the user's circadian sleep quality score coefficient corresponding to various types of circadian insomnia and the user's circadian sleep cycle, the rhythmic changes in heart rate are closely related to the individual's physiological state and mental health, especially in the context of insomnia, the heart rate may show obvious disorders. Therefore, by quantifying these changes, the degree and characteristics of heart rate disorders in different types of insomnia can be identified. This analysis not only provides a more personalized management plan for insomnia patients, but also provides an important theoretical basis for heart rate monitoring and management in clinical practice, which can provide comprehensive data support for subsequent comprehensive interventions for insomnia.Finally, by formulating personalized intelligent intervention strategies based on the user's circadian insomnia type and the degree of rhythm disorder of their heart rate cycle, and by deeply analyzing the relationship between different types of insomnia and heart rate variability, specific intervention needs can be identified. Through big data analysis and machine learning algorithms, a large amount of user data can be collected and processed to clarify which heart rate patterns are associated with specific types of insomnia. Personalized intervention is not just a superficial treatment of insomnia symptoms, but also a fundamental understanding of the user's physiological and psychological state, helping them improve their sleep quality, so as to better cope with the negative effects of circadian insomnia. In addition, by using the APP software on the wearable watch to push users' insomnia intelligent intervention, the corresponding insomnia intervention measures can be pushed to users. These intervention measures include customized meditation exercises, deep breathing exercises, and relaxing music before bedtime. According to user feedback and physiological data, the push content can be continuously optimized to ensure the real-time and adaptability of the intervention plan. The key to this step is to be able to transform scientific sleep intervention strategies into specific executable operations, which greatly improves the user experience and satisfaction. Through the real-time feedback mechanism, users can not only obtain personalized sleep suggestions, but also see the actual improvement effects during the application process. The implementation of such intelligent intervention helps to improve users' self-management capabilities, making them more confident and in control when facing insomnia problems. It can provide users with personalized, scientific and effective sleep solutions, thereby better improving the sleep quality of various types of insomnia. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0060] Figure 1 This is a module schematic diagram of the APP-based intelligent intervention system for circadian rhythm disorder insomnia of the present invention;

[0061] Figure 2 for Figure 1 Schematic diagram of the functional flow of the module for marking and dividing the types of circadian insomnia of users;

[0062] Figure 3 for Figure 1 Schematic diagram of the functional flow of the sleep parameter collection module for users with circadian insomnia. DETAILED DESCRIPTION

[0063] The technical system of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0064] To achieve this, please refer to Figures 1 to 3 The present invention provides an APP-based intelligent intervention system for circadian rhythm disorder insomnia, the system comprising the following modules:

[0065] A user day and night insomnia type marking and classification module is used to collect the user's insomnia severity index scale and the morning type-evening type questionnaire in real time through the questionnaire function built into the APP software on the wearable watch, and collect the user's day and night sleep parameters in real time on the user's insomnia severity index scale and the morning type-evening type questionnaire to obtain the user's day and night insomnia severity index and the user's day and night sleep category measurement score; virtual marking and classification of day and night insomnia types are performed according to the user's day and night insomnia severity index and the user's day and night sleep category measurement score to obtain various day and night insomnia types;

[0066] The sleep parameter collection module for users with circadian insomnia is used to monitor the activity, sleep time, number of awakenings and heart rate of users with various types of circadian insomnia in real time during the same time period through a wearable watch, so as to obtain the circadian activity, circadian sleep time, number of awakenings and heart rate of users corresponding to various types of circadian insomnia; the sleep cycle of users is analyzed according to the circadian sleep time and number of awakenings corresponding to various types of circadian insomnia, so as to obtain the circadian sleep cycle of users corresponding to various types of circadian insomnia;

[0067] The module for evaluating the degree of disorder of circadian insomnia users is used to evaluate and analyze the circadian sleep quality of users corresponding to various types of circadian insomnia based on the circadian activity of users corresponding to various types of circadian insomnia, so as to obtain the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia; based on the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia and the circadian sleep cycles of users, the module for evaluating the degree of disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia is used to quantitatively calculate the disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia, so as to obtain the degree of disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia;

[0068] The circadian rhythm disorder insomnia user intelligent intervention execution module is used to push user insomnia intelligent intervention based on the degree of user circadian heart rate cycle rhythm disorder corresponding to various types of circadian insomnia using the APP software on the wearable watch, so as to execute the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

[0069] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the modules of the APP-based intelligent intervention system for circadian rhythm disorder insomnia of the present invention. In this example, the APP-based intelligent intervention system for circadian rhythm disorder insomnia includes the following modules:

[0070] S1: A user day and night insomnia type marking and classification module, which is used to collect the user's insomnia severity index scale and the morning type-evening type questionnaire in real time through the questionnaire function built into the APP software on the wearable watch, and collect the user's day and night sleep parameters in real time on the user's insomnia severity index scale and the morning type-evening type questionnaire to obtain the user's day and night insomnia severity index and the user's day and night sleep category measurement score; perform virtual marking and classification of day and night insomnia types according to the user's day and night insomnia severity index and the user's day and night sleep category measurement score to obtain various day and night insomnia types;

[0071] In an embodiment of the present invention, the questionnaire survey results corresponding to the user are collected in real time by using the built-in questionnaire survey function of the APP software on the wearable watch, so as to guide the user to complete the insomnia severity index scale and the morning type-evening type questionnaire survey form through the user interface. The questionnaire survey form covers multiple dimensions, such as the time of falling asleep, the number of awakenings at night, and the feelings after waking up in the morning, etc., aiming to collect the user's insomnia situation in real time, and to collect the user's daytime and nighttime insomnia severity index scale in real time to adopt a standardized scoring method to quantitatively analyze the insomnia severity index scale filled in by the user. The analysis divides the results into four levels: 0 to 7 points represent no insomnia, 8 to 14 points represent mild insomnia, 15 to 21 points represent moderate insomnia, and 22 to 28 points represent severe insomnia, thereby obtaining the user's daytime and nighttime insomnia severity index. At the same time, a statistical analysis of the user's biological clock work and rest characteristics is performed on the morning type-evening type questionnaire obtained after previous users fill out the questionnaire, where the morning type-evening type questionnaire includes items such as morning and evening activity habits, emotional state, and daily routines. After the user completes the questionnaire, the APP background system automatically organizes and analyzes the specific data in the morning type-evening type questionnaire to obtain the user's biological clock work and rest characteristic data through statistical methods, and calculates the user's day and night sleep measurement score by using an algorithm in the APP background system. The scoring standard for the day and night sleep measurement score is divided into five categories: 16 to 30 points for absolute evening type, 31 to 41 points for moderate evening type, 42 to 58 points for intermediate type, 59 to 69 points for moderate morning type, and 70 to 86 points for absolute morning type. The calculation process combines the user's biological clock characteristics and uses a weighted algorithm to comprehensively evaluate the user's work and rest patterns, thereby calculating the user's day and night sleep category measurement score. Then, after obtaining the corresponding user's circadian insomnia severity index and circadian sleep category measurement score, the APP virtually marks and divides the user's insomnia type through the data analysis module. This process uses a decision tree model to divide the user into multiple circadian insomnia types according to the user's score range and biological clock characteristics, such as the absolute night type or absolute morning type and the distinction between insomnia severity, etc. The final marking and division results in various circadian insomnia types, including absolute night-no insomnia type, moderate night-no insomnia type, and intermediate-no insomnia type. Type, moderate morning-no insomnia type, absolute morning-no insomnia type, absolute night-mild insomnia type, moderate night-mild insomnia type, intermediate-mild insomnia type, moderate morning-mild insomnia type, absolute morning-mild insomnia type, absolute night-moderate insomnia type, moderate night-moderate insomnia type, intermediate-moderate insomnia type, moderate morning-moderate insomnia type, absolute morning-moderate insomnia type, absolute night-severe insomnia type, moderate night-severe insomnia type, intermediate-severe insomnia type, moderate morning-severe insomnia type, and absolute morning-severe insomnia type.

[0072] S2: a sleep parameter collection module for users with circadian insomnia, which is used to monitor the activity, sleep time, number of awakenings and heart rate of users with various types of circadian insomnia in real time during the same time period through a wearable watch, so as to obtain the circadian activity, circadian sleep time, number of awakenings and circadian heart rate of users corresponding to various types of circadian insomnia; perform a sleep cycle analysis on the circadian sleep time and number of awakenings corresponding to various types of circadian insomnia, and obtain the circadian sleep cycle of users corresponding to various types of circadian insomnia;

[0073] In an embodiment of the present invention, a wearable watch worn by a user uses a built-in acceleration sensor to monitor the activity of the user corresponding to various types of circadian insomnia during circadian sleep in real time within the same time period. The acceleration sensor can capture the movement data of the watch in three-dimensional space, classify the user's activities by setting thresholds, and divide them into static, light activity and intense activity, and record the activity data within this time period. The wearable watch sends the real-time collected data to the corresponding APP software through the built-in wireless transmission module, thereby obtaining the user's circadian activity corresponding to various types of circadian insomnia. By using a data analysis algorithm, a detailed activity state analysis is performed on the user's circadian activity corresponding to various types of circadian insomnia collected previously, so as to identify the user's circadian activity state, and by analyzing the user's circadian activity state obtained by the previous analysis, the circadian sleep stage of different types of insomnia is determined. According to the defined activity state, the user's activity is matched with the corresponding sleep stage (such as deep sleep, light sleep and wakefulness), and the user's circadian sleep state is determined as a deep sleep stage, a light sleep stage or a wakefulness stage, and by using a built-in sleep time sensor to analyze the various types of circadian insomnia determined by the previous analysis, the user's circadian activity state is determined as a deep sleep stage, a light sleep stage or a wakefulness stage. The sensors can collect physiological data by contacting the user's skin, analyze the user's heart rate changes, breathing patterns and brain wave signals in real time, and judge the user's actual sleep state. The monitoring data is transmitted to the APP via Bluetooth or Wi-Fi for processing. The algorithm embedded in the APP can automatically identify and distinguish the time periods of deep sleep and light sleep, and add the two values ​​of deep sleep stage duration and light sleep stage duration corresponding to users with different insomnia types obtained previously, so as to obtain the user's daytime and night sleep time corresponding to various daytime and night insomnia types. Secondly, by counting the frequency of awakening in the circadian wakefulness stages corresponding to the various types of circadian insomnia previously analyzed and judged, the built-in accelerometer and gyroscope of the wearable watch are used to monitor the user's activity status in real time, and the collected data is processed to identify the user's movement patterns, such as turning over, sitting up, etc., as indicators of suspected awakening. The preset thresholds and algorithms are used to analyze the awakening behaviors in specific circadian wakefulness stages, and these data are classified into corresponding circadian insomnia types to count the number of suspected awakenings of different types of users in different time periods (such as late night and dawn), and make auxiliary corrections. For example, if a user frequently turns over and has a high frequency of suspected awakening under a specific type of insomnia, it will be inferred that he is in a specific real awakening state, otherwise it is not a real awakening state, and the statistical results of the suspected awakening frequency will be adjusted accordingly, so as to obtain the number of user awakenings during the day and night corresponding to various types of circadian insomnia.Then, by using the optical heart rate sensor of the wearable watch, the user's photoelectric volume pulse fluctuation signal is obtained, which can reflect the user's heart rate changes in real time. The APP filters the collected pulse wave signal to remove noise and interference, and uses the time domain analysis method and Fourier transform to perform frequency domain analysis on the pulse wave signal to extract the heart rate information, thereby calculating the user's day and night heart rate corresponding to various types of day and night insomnia. Finally, by comprehensively analyzing the user's day and night sleep time and the number of times the user wakes up during the day and night corresponding to various types of day and night insomnia obtained by previous statistical analysis, the user's sleep cycle model is constructed and analyzed using algorithms (such as Kalman filtering) to extract regular sleep cycles, and statistical methods are used to analyze the changes in the user's sleep structure under different types of insomnia, such as the ratio of deep sleep to light sleep, the duration of each sleep stage, etc., thereby generating personalized sleep cycle analysis results to help users understand their own sleep status, and finally obtain the user's day and night sleep cycle corresponding to various types of day and night insomnia.

[0074] S3: A module for evaluating the degree of disorder of circadian insomnia users, which is used to evaluate and analyze the circadian sleep quality of users corresponding to various types of circadian insomnia based on the circadian activity of users corresponding to various types of circadian insomnia, so as to obtain the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia; based on the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia and the circadian sleep cycles of users, quantitatively calculate the circadian heart rate rhythm disorder of users corresponding to various types of circadian insomnia, so as to obtain the degree of disorder of the circadian heart rate rhythm of users corresponding to various types of circadian insomnia;

[0075] In an embodiment of the present invention, by collecting circadian activity data of users with various types of circadian insomnia, these data can be monitored in real time through the built-in sensors on the wearable watch, and the activity data includes the number of steps, exercise type, activity duration and intensity of the user in a day, and using data analysis tools (such as Pandas and NumPy libraries in Python), the collected activity data is cleaned and sorted, so as to statistically analyze the user's circadian activity amount corresponding to different circadian insomnia types (such as absolute night-no insomnia type, moderate night-no insomnia type, etc.) to obtain the user activity intensity under each category, and use the time series analysis method to analyze the corresponding user circadian sleep intensity by combining the user's circadian activity intensity obtained by the previous statistical analysis The corresponding impact correlation statistical analysis is performed on the cycle to extract the sleep start and end time according to the user's sleep record, and the sleep duration of each user is calculated. The correlation between activity intensity and sleep cycle is calculated by using statistical analysis tools (such as the correlation function in R language), and the activity-sleep cycle correlation factors corresponding to different types of circadian insomnia are identified. At the same time, a suitable calculation formula is formed by combining the user's circadian sleep cycle, the corresponding activity-sleep cycle correlation factors and related parameters to perform circadian sleep quality evaluation calculation, so as to quantify the calculation by combining these parameters with the related factors of circadian activity intensity, thereby calculating the user's circadian sleep quality score coefficients corresponding to various types of circadian insomnia. Then, by combining the user's circadian sleep cycle corresponding to the various types of circadian insomnia obtained by previous analysis with the corresponding statistically calculated user's circadian heart rate, the corresponding heart rate monitor in the wearable watch is used for real-time recording, and the heart rate data is analyzed using time domain and frequency domain analysis methods (such as FFT transformation) to extract the periodic change characteristics of the heart rate, including heart rate rhythm change characteristics such as average heart rate and heart rate variability. A suitable calculation formula is formed by combining the user's circadian sleep cycle, the user's circadian heart rate, the user's circadian sleep quality score coefficient and related parameters to quantitatively calculate the degree of heart rate cycle rhythm disorder, so as to quantify these indicators and the user's circadian sleep quality score coefficient, and obtain the degree of heart rate rhythm disorder corresponding to different types of circadian insomnia, and compare the differences in heart rate rhythm disorder between different types of insomnia by using corresponding statistical tests (such as ANOVA), and finally obtain the degree of user circadian heart rate cycle rhythm disorder corresponding to various types of circadian insomnia.

[0076] S4: Circadian rhythm disorder insomnia user intelligent intervention execution module is used to push user insomnia intelligent intervention based on the degree of user circadian heart rate cycle rhythm disorder corresponding to various types of circadian insomnia using the APP software on the wearable watch to execute the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

[0077] In an embodiment of the present invention, an intelligent intervention strategy for insomnia of different types of circadian insomnia is formulated based on the specific numerical values ​​of the degree of disorder of the circadian heart rate cycle rhythm of the user corresponding to various types of circadian insomnia obtained by quantitative calculation previously and in combination with the results of psychological and physiological research. For example, for users who have difficulty falling asleep at night or in the early morning, an intervention strategy based on relaxation training is designed, while for users who have difficulty maintaining sleep, the focus is on optimizing the sleep environment and adjusting pre-sleep activities. These strategies will form a comprehensive intelligent intervention plan, which specifically includes recommended relaxation music, meditation exercises, pre-sleep reading materials and other elements to meet the personalized needs of users with different types of circadian insomnia, and collect the work and rest habits of users determined to be corresponding to the types of circadian insomnia by using the corresponding APP software on the wearable watch, monitor the user's daily activities, sleep cycles and their changes through built-in sensors, record the user's daytime activity, sleep time, wake-up time, etc., and update the data to the APP in real time through wireless transmission, generating The report on the work and rest habits of the user is formed. At the same time, by setting specific intervention push time and frequency according to the work and rest habits of different types of circadian insomnia, for example, for users who wake up early, a gentle sound awakening is set between 3 and 4 in the morning, and for users who have difficulty falling asleep, it is recommended to push a reminder of relaxation exercises one hour before bedtime. These settings will be based on the user's personalized work and rest habits. Then, by combining the previously set insomnia intervention push time and push frequency corresponding to various types of circadian insomnia, the corresponding intervention strategy is implemented using the corresponding APP software on the wearable watch. The APP will regularly push personalized intervention content to users, such as meditation audio, breathing exercises or bedtime tips, and increase user attention through vibration or audio reminders. The wearable device will monitor the user's physiological responses to ensure that each user can obtain intervention measures that meet their needs and maximize the improvement of their circadian rhythm disorder insomnia, so that the corresponding user circadian rhythm disorder insomnia intelligent intervention work can be performed.

[0078] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 The function flow diagram of the user daytime and nighttime insomnia type marking classification module in this embodiment includes:

[0079] S11: Use the questionnaire function built into the APP software on the wearable watch to collect users' Insomnia Severity Index Scale and Morningness-Eveningness Questionnaire in real time;

[0080] In an embodiment of the present invention, the questionnaire survey results corresponding to the user are collected in real time by using the built-in questionnaire survey function of the APP software on the wearable watch, so as to guide the user to complete the insomnia severity index scale and the morning type-evening type questionnaire through the user interface. The questionnaire covers multiple dimensions, such as the time to fall asleep, the number of awakenings at night, and the feelings after waking up in the morning, etc., aiming to collect the user's insomnia situation in real time, and compare the user's selection with the preset standard through the data input interface to ensure the validity and accuracy of the questionnaire survey.

[0081] S12: collecting the user's daytime and nighttime insomnia severity index in real time from the user's insomnia severity index scale to obtain the user's daytime and nighttime insomnia severity index, wherein the user's daytime and nighttime insomnia severity index can be divided into 0-7 points for no insomnia, 8-14 points for mild insomnia, 15-21 points for moderate insomnia, and 22-28 points for severe insomnia;

[0082] In an embodiment of the present invention, the user's daytime insomnia severity index scale is collected in real time, and a standardized scoring method is used to perform a quantitative analysis on the insomnia severity index scale filled in by the user. The analysis divides the results into four levels: 0 to 7 points represent no insomnia, 8 to 14 points represent mild insomnia, 15 to 21 points represent moderate insomnia, and 22 to 28 points represent severe insomnia. This process is processed by the algorithm module of the APP background, and the result is generated into a user report, and finally the user's daytime insomnia severity index is obtained.

[0083] S13: analyzing the user's morning-night biological clock work and rest characteristics based on the user's morning-night type questionnaire to obtain the user's morning-night biological clock work and rest characteristic data;

[0084] In an embodiment of the present invention, a statistical analysis of the user's biological clock routine characteristics is performed on the morning type-evening type questionnaire obtained after previous user filling out, wherein the morning type-evening type questionnaire includes items such as morning and evening activity habits, emotional state, and daily routine. After the user completes the questionnaire, the APP background system automatically organizes and analyzes the specific data in the morning type-evening type questionnaire to obtain the user's biological clock routine characteristic data through statistical methods, and finally obtains the user's morning-evening biological clock routine characteristic data.

[0085] S14: performing a circadian sleep measurement calculation for the user according to the user's morning-night biological clock work and rest characteristic data to obtain a circadian sleep category measurement score for the user, wherein the circadian sleep category measurement score for the user can be divided into 16-30 points for an absolute night type, 31-41 points for a moderate night type, 42-58 points for an intermediate type, 59-69 points for a moderate morning type, and 70-86 points for an absolute morning type;

[0086] In an embodiment of the present invention, the user's circadian sleep measurement score is calculated by using an algorithm in the APP background system in combination with the user's morning-night biological clock work and rest characteristic data obtained by previous analysis. The scoring criteria for the circadian sleep measurement score are divided into five categories: 16 to 30 points for absolute night type, 31 to 41 points for moderate night type, 42 to 58 points for intermediate type, 59 to 69 points for moderate morning type, and 70 to 86 points for absolute morning type. The calculation process combines the user's biological clock characteristics and adopts a weighted algorithm to comprehensively evaluate the user's work and rest patterns to form a personalized sleep classification, and finally calculates the user's circadian sleep category measurement score.

[0087] S15: Virtually mark and divide the circadian insomnia types according to the user's circadian insomnia severity index and the user's circadian sleep category measurement score to obtain various circadian insomnia types.

[0088] In the embodiment of the present invention, after obtaining the circadian insomnia severity index and circadian sleep category measurement score of the corresponding user, the APP performs virtual labeling and classification of the user's insomnia type through the data analysis module. The process uses a decision tree model to classify the user into a variety of circadian insomnia types according to the user's score range and biological clock characteristics, such as the distinction between absolute night type or absolute morning type and insomnia severity, and finally the labeling and classification obtain various circadian insomnia types, including absolute night-no insomnia type, moderate night-no insomnia type, intermediate- No Insomnia Type, Moderate Morning-No Insomnia Type, Absolute Morning-No Insomnia Type, Absolute Night-Mild Insomnia Type, Moderate Night-Mild Insomnia Type, Intermediate-Mild Insomnia Type, Moderate Morning-Mild Insomnia Type, Absolute Morning-Mild Insomnia Type, Absolute Night-Moderate Insomnia Type, Moderate Night-Moderate Insomnia Type, Intermediate-Moderate Insomnia Type, Moderate Morning-Moderate Insomnia Type, Absolute Morning-Moderate Insomnia Type, Absolute Night-Severe Insomnia Type, Moderate Night-Severe Insomnia Type, Intermediate-Severe Insomnia Type, Moderate Morning-Severe Insomnia Type, and Absolute Morning-Severe Insomnia Type.

[0089] Further, the various types of circadian insomnia include:

[0090] Absolute night-no insomnia type, moderate night-no insomnia type, intermediate-no insomnia type, moderate morning-no insomnia type, absolute morning-no insomnia type, absolute night-mild insomnia type, moderate night-mild insomnia type, intermediate-mild insomnia type, moderate morning-mild insomnia type, absolute morning-mild insomnia type, absolute night-moderate insomnia type, moderate night-moderate insomnia type, intermediate-moderate insomnia type, moderate morning-moderate insomnia type, absolute morning-moderate insomnia type, absolute night-severe insomnia type, moderate night-severe insomnia type, intermediate-severe insomnia type, moderate morning-severe insomnia type and absolute morning-severe insomnia type.

[0091] In the embodiment of the present invention, the corresponding classification judgment is made according to the previously quantitatively calculated circadian insomnia severity index (such as 0 to 7 points representing no insomnia, 8 to 14 points representing mild insomnia, 15 to 21 points representing moderate insomnia, and 22 to 28 points representing severe insomnia) and the circadian sleep category measurement score (such as 16 to 30 points for absolute night type, 31 to 41 points for moderate night type, 42 to 58 points for intermediate type, 59 to 69 points for moderate early morning type, and 70 to 86 points for absolute early morning type). If the user's circadian insomnia severity index is 0 to 7 points and the user's circadian sleep category measurement score is 16 to 30 points, it is judged to be classified as absolute night-no insomnia. Type, and so on, so as to judge and divide the remaining moderate night-no insomnia type, middle-no insomnia type, moderate morning-no insomnia type, absolute morning-no insomnia type, absolute night-mild insomnia type, moderate night-mild insomnia type, middle-mild insomnia type, moderate morning-mild insomnia type, absolute morning-mild insomnia type, absolute night-moderate insomnia type, moderate night-moderate insomnia type, middle-moderate insomnia type, moderate morning-moderate insomnia type, absolute morning-moderate insomnia type, absolute night-severe insomnia type, moderate night-severe insomnia type, middle-severe insomnia type, moderate morning-severe insomnia type and absolute morning-severe insomnia type.

[0092] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 The function flow diagram of the sleep parameter collection module for day and night insomnia users is as follows. In this embodiment, the functions of the sleep parameter collection module for day and night insomnia users include:

[0093] S21: using a wearable wristwatch to monitor in real time the activity amounts of users corresponding to various types of circadian insomnia during circadian sleep using an acceleration sensor in the same time period, so as to obtain the circadian activity amounts of users corresponding to various types of circadian insomnia;

[0094] In an embodiment of the present invention, a wearable watch worn by a user uses a built-in accelerometer to monitor in real time the user's activity levels corresponding to various types of circadian insomnia during circadian sleep in the same time period. The accelerometer can capture the movement data of the watch in three-dimensional space, and classify the user's activities into stillness, light activity, and intense activity by setting thresholds, and record the activity data within this time period. The wearable watch sends the real-time collected data to the corresponding APP software through the built-in wireless transmission module, thereby obtaining the specific activity levels corresponding to different types of insomnia (such as absolute night-no insomnia type, moderate night-no insomnia type, etc.), and finally obtaining the user's circadian activity levels corresponding to various types of circadian insomnia.

[0095] S22: performing circadian activity state analysis on the circadian activity amounts of the user corresponding to the various circadian insomnia types to obtain the circadian activity states of the user corresponding to the various circadian insomnia types; performing circadian sleep stage judgment on the corresponding circadian activity amounts of the user according to the circadian activity states of the user corresponding to the various circadian insomnia types to obtain the circadian sleep stages of the user corresponding to the various circadian insomnia types, wherein the circadian sleep stages of the user include a circadian deep sleep stage, a circadian light sleep stage, and a circadian wakefulness stage;

[0096] In an embodiment of the present invention, a detailed activity status analysis is performed on the user's circadian activity amounts corresponding to various types of circadian insomnia previously collected by using a data analysis algorithm, so as to compare the acquired activity data with the standard circadian activity pattern and identify the user's circadian activity status. In a specific operation, the activity data is first preprocessed to remove noise and outliers, and then a statistical analysis method is applied to calculate the user's activity intensity and frequency in a specific time period. Through data mining technology, the activity patterns corresponding to various types of insomnia are identified. For example, a pattern of long-term stillness and lack of activity is related to difficulty falling asleep, while frequent changes are related to nighttime awakenings. These activity states are displayed in a graphical form, thereby obtaining the user's circadian activity status corresponding to various types of circadian insomnia. At the same time, the user's circadian activity status obtained by the previous analysis is analyzed to determine the circadian sleep stages of different insomnia types. According to the defined activity status, the user's activity amount is matched with the corresponding sleep stage (such as deep sleep, light sleep and wakefulness). In the specific implementation, a machine learning algorithm is used to train the model to identify the relationship between activity patterns and sleep stages. By classifying the real-time monitored activity data, the user's circadian sleep state is judged as a deep sleep stage, a light sleep stage or a wakefulness stage, and the duration of the user in each sleep stage is output in real time. These data are associated with different insomnia types, and finally the user's circadian sleep stages corresponding to various circadian insomnia types are obtained, where the user's circadian sleep stages include a circadian deep sleep stage, a circadian light sleep stage and a circadian wakefulness stage.

[0097] S23: using a sleep time sensor to monitor the sleep stage duration of the daytime deep sleep stage and the daytime light sleep stage corresponding to various types of daytime insomnia in real time, so as to obtain the sleep duration of the deep sleep stage and the sleep duration of the light sleep stage corresponding to various types of daytime insomnia; adding the sleep duration of the deep sleep stage and the sleep duration of the light sleep stage corresponding to various types of daytime insomnia, so as to obtain the daytime sleep time of the user corresponding to various types of daytime insomnia;

[0098] In an embodiment of the present invention, the sleep duration of the deep sleep stage and the light sleep stage corresponding to the various types of daytime and nighttime insomnia determined by the previous analysis is monitored in real time by using the built-in sleep time sensor. These sensors can collect physiological data by contacting the user's skin, analyze the user's heart rate changes, breathing patterns and brain wave signals in real time, and judge the user's actual sleep state. The monitoring data is transmitted to the APP via Bluetooth or Wi-Fi for processing. The algorithm embedded in the APP can automatically identify and distinguish the time periods of the deep sleep and light sleep stages, thereby monitoring the sleep duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and nighttime insomnia. At the same time, by adding the two values ​​of the deep sleep stage duration and the light sleep stage duration corresponding to the different types of insomnia users obtained by the previous monitoring, the total sleep time of the user is obtained. In the specific operation, the sleep duration of each type of insomnia is classified and summarized using the data analysis tool, and finally the daytime and night sleep time of the user corresponding to various types of daytime and nighttime insomnia is obtained.

[0099] S24: performing statistics on the suspected awakening frequency of the user in the day and night awakening stages corresponding to various types of day and night insomnia to obtain the suspected awakening frequency of the user in the day and night corresponding to various types of day and night insomnia; using a gyroscope sensor to obtain the user activity posture change data corresponding to various types of day and night insomnia, and performing auxiliary correction of the number of awakenings according to the user activity posture change data corresponding to various types of day and night insomnia and the suspected awakening frequency of the user in the day and night to obtain the number of awakenings of the user in the day and night corresponding to various types of day and night insomnia;

[0100] In an embodiment of the present invention, the awakening frequencies of the circadian wakefulness stages corresponding to the various types of circadian insomnia previously analyzed and determined are counted, so as to utilize the built-in accelerometer and gyroscope of the wearable watch to monitor the user's activity status in real time, and process the collected data to identify the user's movement patterns, such as turning over, sitting up, etc., as indicators of suspected awakening, and utilize preset thresholds and algorithms to analyze the awakening behaviors in specific circadian wakefulness stages, and classify these data into corresponding circadian insomnia types, so as to count the suspected awakening frequencies of different types of users in different time periods (e.g., late night, dawn), thereby obtaining the suspected awakening frequencies of users corresponding to various types of circadian insomnia during the day and night. At the same time, by using the built-in gyroscope sensor to monitor the user's activity posture change data during sleep in real time, through data collection, record the user's turning angle, turning frequency and other dynamic parameters, so as to form the user's activity posture change data corresponding to various types of day and night insomnia, and through combining the suspected awakening frequency obtained by previous statistical analysis, auxiliary correction is performed. For example, if the user frequently turns over and has a high frequency of suspected awakening under a specific type of insomnia, it will be inferred that it is a specific real awake state, otherwise it is not a real awake state, and the statistical results of the suspected awakening frequency will be adjusted accordingly to obtain the real number of awakenings, and finally the number of user awakenings during the day and night corresponding to various types of day and night insomnia is obtained.

[0101] S25: using the optical heart rate sensor on the wearable watch to obtain the user's photoelectric volume pulse fluctuation signals corresponding to the various types of circadian insomnia, and calculating the user's heart rate based on the user's photoelectric volume pulse fluctuation signals corresponding to the various types of circadian insomnia, so as to obtain the user's circadian heart rate corresponding to the various types of circadian insomnia;

[0102] In an embodiment of the present invention, the optical heart rate sensor of a wearable watch is used to obtain the user's photoelectric volume pulse fluctuation signal, which can reflect the user's heart rate changes in real time. The APP filters the collected pulse wave signal to remove noise and interference, and performs frequency domain analysis on the pulse wave signal by using a time domain analysis method and Fourier transform to extract the heart rate information, thereby generating circadian heart rate data for users with different types of circadian insomnia, and finally obtaining the circadian heart rate of users corresponding to various types of circadian insomnia.

[0103] S26: Analyze the user's sleep cycle according to the user's circadian sleep time and the number of times the user wakes up during the day and night corresponding to the various types of circadian insomnia, and obtain the user's circadian sleep cycle corresponding to the various types of circadian insomnia.

[0104] In an embodiment of the present invention, a comprehensive analysis is performed on the user's daytime and nighttime sleep time and the number of times the user wakes up during the day and night corresponding to various types of daytime and night insomnia obtained through previous statistical analysis, so as to construct a sleep cycle model of the user and use an algorithm (such as Kalman filtering) for analysis to extract regular sleep cycles, and use statistical methods to analyze the changes in the user's sleep structure under different types of insomnia, such as the ratio of deep sleep to light sleep, the duration of each sleep stage, etc., so as to generate personalized sleep cycle analysis results, help users understand their own sleep status, and finally obtain the user's daytime and night sleep cycles corresponding to various types of daytime and night insomnia.

[0105] Furthermore, the auxiliary correction of the number of awakenings according to the user activity posture change data corresponding to various types of day and night insomnia and the user's suspected awakening frequency during the day and night includes:

[0106] Based on the suspected awakening frequencies of users corresponding to various types of circadian insomnia, the user activity posture change data corresponding to various types of circadian insomnia are matched and divided according to the suspected awakening frequencies, and the user activity posture change sub-data corresponding to each suspected awakening in various types of circadian insomnia are obtained;

[0107] In an embodiment of the present invention, by combining the user's suspected daytime and nighttime awakening frequencies corresponding to various types of diurnal insomnia obtained by previous statistical analysis, these data include every possible awakening moment recorded by the user through the APP, and according to the user's input and the sensor monitoring results, the awakening frequencies are matched with various types of diurnal insomnia. For example, for insomnia types A, B and C, the awakening frequency data of users in different time periods are respectively counted, and the activity posture change data of users of the corresponding types are matched and extracted by using data analysis tools (such as Python's Pandas library). By setting a specific algorithm to identify the activity posture changes corresponding to the suspected awakening time points, and by comparing the user's activity status before and after waking up, the posture change data that meets the specific pattern is screened out and classified into the respective insomnia types to form a direct correlation between wakefulness and posture changes, and finally the user's activity posture change sub-data corresponding to each suspected awakening in various types of diurnal insomnia are obtained.

[0108] Preferably, the user activity trajectory recognition analysis is performed on the user activity posture change sub-data corresponding to each suspected awakening in various types of daytime and nighttime insomnia, so as to obtain the user activity posture trajectory corresponding to each suspected awakening in various types of daytime and nighttime insomnia;

[0109] In an embodiment of the present invention, the user activity trajectory is identified and analyzed by analyzing the user activity posture change sub-data corresponding to each suspected awake state in various types of circadian insomnia previously screened out, so as to use a machine learning algorithm (such as a decision tree or a support vector machine) to perform feature extraction on the time series data of the user activity posture change, and identify the characteristic activity trajectory of the user in the awake state. For example, common trajectories of the user in the awake state include sitting up, standing up or moving, etc. At this time, the activity trajectory is visualized by a graphical data analysis tool (such as Matplotlib or Seaborn) to help intuitively understand the user's activity performance in the suspected awake state. At the same time, the identified activity trajectory is matched with a predefined behavior model to ensure that the activity trajectory of each awake time point is accurately classified into the corresponding circadian insomnia type, and finally the user activity posture trajectory corresponding to each suspected awake state in various types of circadian insomnia is obtained.

[0110] Preferably, the activity trajectory behavior state analysis is performed on the user activity posture trajectory corresponding to each suspected awakening in various types of daytime and nighttime insomnia, so as to obtain the user activity trajectory behavior state corresponding to each suspected awakening in various types of daytime and nighttime insomnia;

[0111] In an embodiment of the present invention, a detailed behavioral state analysis is performed on the user's activity posture trajectory corresponding to each suspected awake state in various types of circadian insomnia obtained by previous identification and analysis, so as to determine whether the user's behavioral state is awake, turning over or sleeping by setting a series of state analysis indicators, such as duration, activity intensity and its transition frequency, and cluster analysis is performed on the feature data of the activity trajectory with the help of data mining technology (such as K-means clustering) to distinguish different behavioral states. For the user's activity trajectory under different types of insomnia, a rule-based analysis method is adopted to set a clear threshold to determine whether the activity trajectory meets the state of "really awake". For example, if the activity trajectory shows that the user has not returned to the sleeping state within a certain period of time and continues to show high-intensity activity, it can be determined as really awake, so as to list the behavioral state corresponding to each suspected awake state, and finally obtain the user's activity trajectory behavioral state corresponding to each suspected awake state in various types of circadian insomnia.

[0112] Preferably, based on the user activity trajectory behavior state corresponding to each suspected wakefulness in various types of day and night insomnia, the corresponding user's suspected wakefulness during the day and night is compared and judged to assist in waking up. If it is judged that the user activity trajectory behavior state corresponding to the suspected wakefulness is a real wakefulness state, then the comparison and judgment of the next user's suspected wakefulness during the day and night is continued; if it is judged that the user activity trajectory behavior state corresponding to the suspected wakefulness is just a turning over state or a not really awake state, then the frequency of suspected wakefulness during the day and night of the user corresponding to various types of day and night insomnia is reduced by one, until all the user activity trajectory behavior states corresponding to the suspected wakefulness are compared and judged, so as to obtain the number of user wakeups during the day and night corresponding to various types of day and night insomnia.

[0113] In an embodiment of the present invention, a comprehensive judgment is made on the user activity trajectory behavior state corresponding to each suspected wakefulness according to the analysis results of the previous behavior state, so as to establish a judgment mechanism and evaluate the suspected wakefulness state using a logistic regression model. If the model determines that the behavior state is truly awake, the record of the suspected wakefulness will be retained; if it is determined to be just turning over or not really waking up, the number of wakefulness corresponding to the state will be automatically reduced. The specific operation includes comparing the wakefulness state of each user with his or her activity state. If it is determined to be a truly awake state, the next suspected wakefulness state of the user during the day and night will be compared and judged; if it is determined to be a non-awake state, the user's suspected wakefulness frequency will be reduced by one until all the activity trajectory behavior states corresponding to the suspected wakefulness are judged. Through these operations, the number of user wakefulness during the day and night corresponding to various types of day and night insomnia is finally obtained, thereby providing users with personalized sleep intervention suggestions.

[0114] Furthermore, the method of using the optical heart rate sensor on the wearable watch to obtain the user's photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia, and calculating the user's heart rate based on the user's photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia includes:

[0115] The optical heart rate sensor on the wearable watch is used to obtain the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia;

[0116] In an embodiment of the present invention, an optical heart rate sensor is embedded in a wearable watch, and the skin surface is illuminated by an LED light source. The blood changes in the blood vessels in the skin are measured by utilizing the principle of light reflection, so that the data of the heart rate sensor is continuously collected, and the photoelectric volume accumulation pulse fluctuation signal at each moment is stored in a data cache, ensuring that the frequency of signal acquisition reaches at least 50 Hz, so as to obtain sufficient resolution in the subsequent processing stage, accurately reflect the user's heart rate changes and circadian insomnia types, and finally obtain the user's photoelectric volume accumulation pulse fluctuation signal corresponding to various circadian insomnia types.

[0117] Preferably, low-pass environmental noise filtering is performed on the user photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia to obtain low-pass environmental noise filtered fluctuation signals of the user pulse corresponding to various types of circadian insomnia; high-pass motion artifact elimination is performed on the user pulse low-pass environmental noise filtered fluctuation signals corresponding to various types of circadian insomnia to obtain high-pass artifact eliminated fluctuation signals of the user pulse corresponding to various types of circadian insomnia;

[0118] In an embodiment of the present invention, a low-pass environmental noise digital filtering process is performed on the user photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia previously collected, and a Butterworth low-pass filter is used to set the cutoff frequency to 4 Hz to eliminate the high-frequency environmental noise in the signal. The specific operation includes designing the transfer function of the filter, and using the fast Fourier transform (FFT) method to convert the signal into the frequency domain. In the frequency domain, the frequency components below 4 Hz are retained, and the high-frequency noise part is attenuated to near zero. The filtered pulse fluctuation signal is obtained by inverse transformation, thereby obtaining the user pulse low-pass environmental noise filtered fluctuation signal corresponding to various types of circadian insomnia. At the same time, by applying high-pass filtering technology to the obtained low-pass environmental noise filtered fluctuation signal, the low-frequency artifacts generated by the user's movement are removed, and a high-pass filter with a cut-off frequency of 0.5Hz is selected to ensure that the heart rate fluctuations are retained in the signal while the signal changes caused by slow movement are filtered out. This process also uses FFT to perform frequency domain processing on the signal to eliminate frequency components below 0.5Hz, and uses inverse FFT to obtain the pulse fluctuation signal after high-pass filtering, thereby purifying the heart rate signals of various types of circadian insomnia, and finally obtaining the user's pulse high-pass artifact-eliminated fluctuation signal corresponding to various types of circadian insomnia.

[0119] Preferably, the pulse high-pass artifact-eliminated fluctuation signal of the user's pulse corresponding to various types of circadian insomnia is converted into a pulse fluctuation spectrum to generate a frequency domain spectrum of the user's pulse fluctuation signal corresponding to various types of circadian insomnia;

[0120] In an embodiment of the present invention, the user pulse high-pass artifact eliminated fluctuation signal corresponding to various types of circadian insomnia obtained after high-pass artifact elimination is input into the FFT module, converted into a frequency domain signal, and the amplitude and phase information of the signal is extracted through spectrum analysis to generate a corresponding frequency domain spectrum. This step includes setting the FFT sampling window and overlapping strategy to ensure the continuity and resolution of the spectrum, and storing and marking the frequency domain spectrum of each user according to different types of circadian insomnia, and finally generating a frequency domain spectrum of the user pulse fluctuation signal corresponding to various types of circadian insomnia.

[0121] Preferably, the pulse signal peak marking process is performed on the frequency domain spectra of the user pulse fluctuation signal corresponding to various types of day and night insomnia to obtain the peak points of the user pulse signal spectra corresponding to various types of day and night insomnia; based on the peak points of the user pulse signal spectra corresponding to various types of day and night insomnia, the peak interval calculation is performed on the corresponding frequency domain spectra of the user pulse fluctuation signal to obtain the time interval between each pair of continuous peak points corresponding to various types of day and night insomnia;

[0122] In an embodiment of the present invention, after obtaining the frequency domain spectrum of the user's pulse fluctuation signal corresponding to various types of circadian insomnia, the corresponding peak detection processing is performed, and a threshold-based method is adopted to set a specific amplitude threshold to identify significant peaks in the spectrum. This process uses an algorithm to analyze the derivative of the signal, identify the local maximum value, and extract the peak points of the user's pulse signal spectrum corresponding to each type of circadian insomnia. The processing results will be displayed graphically in the APP interface, and the user can intuitively view the fluctuation of his pulse signal, thereby obtaining the peak points of the user's pulse signal spectrum corresponding to various types of circadian insomnia. At the same time, the time intervals between the peak points are calculated according to the peak points of the user pulse signal spectrum corresponding to the various types of circadian insomnia determined previously, so as to extract the time coordinates of each peak point in the corresponding user pulse fluctuation signal frequency domain spectrum to form a time series, and calculate the time difference between adjacent peak points to generate a time interval list. In terms of implementation method, a programming language (such as Python) is used for array operations, and loops or vectorized calculations are used to efficiently extract peak intervals, thereby revealing the pulse fluctuation laws corresponding to different types of circadian insomnia, and finally obtaining the time intervals between each pair of continuous peak points corresponding to various types of circadian insomnia.

[0123] Preferably, interval heart rate statistics are calculated based on the time interval between each pair of consecutive peak points corresponding to various types of circadian insomnia to obtain user circadian heart rate sub-values ​​corresponding to each pair of consecutive peak point intervals for various types of circadian insomnia; type heart rate arithmetic average calculation is performed on the user circadian heart rate sub-values ​​corresponding to each pair of consecutive peak point intervals for various types of circadian insomnia to obtain the user circadian heart rate corresponding to various types of circadian insomnia.

[0124] In the embodiment of the present invention, by using the previously calculated time intervals between each pair of continuous wave peak points corresponding to various types of day and night insomnia, the heart rate can be calculated by the formula "heart rate (bpm) = 60 / time interval (seconds)". In specific implementation, all intervals need to be converted into seconds, and then the corresponding heart rate values ​​are calculated one by one by applying the above formula to form a set of circadian heart rate sub-values ​​of the user. This process needs to ensure the accuracy of the algorithm to ensure that the statistical results reflect the true heart rate fluctuation characteristics, thereby obtaining the user's circadian heart rate sub-values ​​corresponding to each pair of continuous wave peak points of various types of day and night insomnia. At the same time, after obtaining all the user's circadian heart rate sub-values, these values ​​are arithmetic averaged to obtain the user's circadian heart rate corresponding to each type of day and night insomnia. This step is implemented by programming. First, all the heart rate sub-values ​​corresponding to the corresponding circadian insomnia type are added, and then divided by the total amount of valid heart rate values ​​to obtain the average heart rate value, and finally the user's circadian heart rate corresponding to various types of day and night insomnia is obtained.

[0125] Further, the user sleep cycle analysis according to the user's daytime and nighttime sleep time corresponding to various types of daytime and nighttime insomnia and the number of times the user wakes up during the daytime and nighttime includes:

[0126] Determine the sleep start and end time points of the user's daytime and nighttime sleep time corresponding to various types of daytime and nighttime insomnia, and obtain the user's daytime and nighttime sleep start and end time points corresponding to various types of daytime and nighttime insomnia;

[0127] In an embodiment of the present invention, the circadian sleep time of the user corresponding to the various types of circadian insomnia previously collected can be achieved through the built-in sleep tracking function in the APP. This function can automatically record the user's sleeping and waking time through the sleep plan set by the user on the mobile phone or by using sensors. Specifically, the APP will record the user's dynamic data, including the activity status captured by the accelerometer and gyroscope. When the user's activity level in a quiet state at night is lower than a preset threshold, the APP will mark this time as the user's bedtime. On the contrary, when the user's activity level returns to normal levels in the morning, or shows a wake-up state, it will be marked as waking up time. After a certain period of data collection, the APP will generate the user's sleep time pattern, clarify the start and end time points corresponding to different types of circadian insomnia, and finally obtain the user's circadian sleep start and end time points corresponding to various types of circadian insomnia.

[0128] Preferably, based on the user's daytime sleep start time point and end time point corresponding to various types of daytime insomnia, the corresponding user's daytime sleep time is defined for the daytime sleep time range, so as to generate a user's daytime sleep time range diagram corresponding to various types of daytime insomnia;

[0129] In an embodiment of the present invention, the range of the corresponding user's daytime and night sleep time is defined by combining the user's daytime and night sleep start time points and end time points corresponding to the various types of daytime and night insomnia determined previously. The specific operation includes organizing the collected time data to form a time distribution diagram of each type of daytime and night insomnia, and determining the duration of each type of sleep through data analysis. In combination with the user's personal sleep cycle characteristics, a sleep time range for different types of insomnia is formulated. For example, for users with night or early morning insomnia, the sleep time range is from 11 pm to 2 am; and for users with early awakening, the sleep time range is from 10 pm to 5 am. The APP will generate a visual user daytime and night sleep time range diagram, and finally generate a user daytime and night sleep time range diagram corresponding to various types of daytime and night insomnia.

[0130] Preferably, based on the user's daytime and nighttime sleep time range diagram corresponding to various types of daytime and nighttime insomnia, the corresponding number of user's daytime and nighttime awakening times is subjected to sleep awakening times interactive response analysis, so as to obtain interactive response change curves between the user's daytime and nighttime sleep duration and the number of awakening times corresponding to various types of daytime and nighttime insomnia;

[0131] In an embodiment of the present invention, the interactive response between the number of daytime and night awakenings of the user and the sleep duration is analyzed by combining the user's daytime and night sleep time range diagram corresponding to the various types of daytime and night insomnia defined previously, and the user's daytime and night awakening times corresponding to this range are analyzed. The specific operation is that the APP will record the user's awakening events in each sleep cycle, and calculate the number of awakenings corresponding to each type of daytime and night insomnia, and combine the user's sleep duration data, using statistical analysis methods such as linear regression or time series analysis to explore the relationship between the specific range of the user's sleep time and the number of awakenings, and present the interactive response change curve in a graphical form. The APP can intuitively display the changing trend of sleep duration and awakening times in a specific type of insomnia. This trend chart can help users understand how sleep quality changes over time, and finally obtain the interactive response change curve between the user's daytime and night sleep duration and the number of awakenings corresponding to various types of daytime and night insomnia.

[0132] Preferably, the user sleep cycle analysis is performed on the interactive response change curves between the user's daytime and nighttime sleep duration and the number of awakenings corresponding to various types of daytime and night insomnia to obtain the user's daytime and nighttime sleep cycles corresponding to various types of daytime and night insomnia.

[0133] In an embodiment of the present invention, by using the interactive response change curve obtained from the previous analysis to conduct an in-depth analysis of the sleep cycle of the corresponding user, the APP will use signal processing technologies such as Fourier transform to convert the interactive response change data between the user's daytime and nighttime sleep duration and the number of times they wake up into a periodic analysis model. Specifically, by performing frequency domain analysis on the interactive response change data between the user's daytime and nighttime sleep duration and the number of times they wake up obtained through response analysis, the user's natural sleep cycle and its regularity can be identified, such as statistical indicators such as the average sleep duration of each cycle and the standard deviation of the number of wake-ups. The analysis results will generate user sleep cycles for different types of daytime and night insomnia, and ultimately obtain user daytime and night sleep cycles corresponding to various types of daytime and night insomnia.

[0134] Furthermore, the module for assessing the degree of disorder of users suffering from circadian insomnia includes the following functions:

[0135] Performing a user activity intensity analysis on the user's circadian activity amounts corresponding to various types of circadian insomnia to obtain the user's circadian activity intensity corresponding to various types of circadian insomnia;

[0136] In an embodiment of the present invention, by collecting circadian activity data of users with various types of circadian insomnia, these data can be monitored in real time through built-in sensors on wearable watches. The activity data include the number of steps, exercise type, activity duration and intensity of the user in a day, and use data analysis tools (such as Pandas and NumPy libraries in Python) to clean and organize the collected activity data to ensure the accuracy of the data. According to the circadian activity amount of users corresponding to different circadian insomnia types (such as absolute night-no insomnia type, moderate night-no insomnia type, etc.), the user activity intensity under each category is statistically analyzed, and finally the user circadian activity intensity corresponding to various circadian insomnia types is obtained.

[0137] Preferably, based on the circadian activity intensity of the user corresponding to the various types of circadian insomnia, the circadian activity-sleep cycle impact correlation analysis of the user circadian sleep cycle corresponding to the various types of circadian insomnia is performed to obtain the user circadian activity-sleep cycle correlation factors corresponding to the various types of circadian insomnia;

[0138] In an embodiment of the present invention, a time series analysis method is used to perform corresponding impact correlation statistical analysis on the corresponding user's circadian sleep cycle by combining the user's circadian activity intensity corresponding to various circadian insomnia types obtained by previous statistical analysis, so as to extract the sleep start and end time according to the user's sleep record, and calculate the sleep duration of each user, and calculate the correlation between the activity intensity and the sleep cycle by using a statistical analysis tool (such as the correlation function in the R language), and identify the activity-sleep cycle correlation factors corresponding to different circadian insomnia types. In this process, ensure that appropriate statistical methods (such as Pearson or Spearman correlation analysis) are used to verify the specific effects of different activity intensities on the sleep cycle, thereby revealing the potential causes of circadian rhythm disorders, including sleep effectiveness influencing correlation factors, sleep depth influencing correlation factors, sleep environment influencing correlation factors, and sleep physiology influencing correlation factors, etc., and finally obtain the user's circadian activity-sleep cycle correlation factors corresponding to various circadian insomnia types.

[0139] Preferably, based on the user's circadian activity-sleep cycle correlation factor corresponding to various types of circadian insomnia, a circadian sleep quality evaluation calculation is performed on the user's circadian sleep cycle corresponding to various types of circadian insomnia using a sleep quality score calculation formula to obtain the user's circadian sleep quality score coefficient corresponding to various types of circadian insomnia;

[0140] In an embodiment of the present invention, a suitable sleep quality score calculation formula is formed by combining the user's circadian sleep cycle, sleep cycle time point variable parameters, user's circadian activity sleep effectiveness influencing correlation factors, user's circadian activity sleep depth influencing correlation factors, user's circadian activity sleep environment influencing correlation factors, user's circadian activity sleep physiological influencing correlation factors and related parameters to perform circadian sleep quality assessment calculation on the user's circadian sleep cycle corresponding to various types of circadian insomnia, so as to quantify and calculate these parameters in combination with related factors of circadian activity intensity, and finally obtain the user's circadian sleep quality score coefficient corresponding to various types of circadian insomnia.

[0141] The specific calculation formula for sleep quality score is:

[0142]

[0143] Where ξ is the user's circadian sleep quality score coefficient, T is the user's circadian sleep cycle, τ is the variable parameter of the sleep cycle time point, and W τ is the correlation factor affecting the effectiveness of user circadian activity sleep at the sleep cycle time point τ, Q τ is the user's circadian activity sleep depth impact correlation factor at the sleep cycle time point τ, E τis the user's circadian activity sleep environment impact correlation factor at the sleep cycle time point τ, R τ is the user's circadian activity sleep physiological impact correlation factor at the sleep cycle time point τ, and ε is the correction coefficient of the user's circadian sleep quality score coefficient;

[0144] The present invention obtains a sleep quality score calculation formula by using a specific mathematical model and verifying it, which is used to evaluate and calculate the circadian sleep quality of the user's circadian sleep cycle corresponding to various types of circadian insomnia. The sleep quality score calculation formula combines multiple influencing factors (effectiveness, depth, environment and physiology), which can comprehensively reflect the user's sleep condition. This multi-dimensional consideration helps to identify the root cause of sleep quality problems. By taking into account the time variable in an integral manner, the formula can dynamically capture the user's sleep state at different time points. This dynamic nature helps to observe changes in the user's sleep pattern. This formula can provide a quantitative evaluation method by calculating the sleep quality score, so that the user's sleep quality can be compared and analyzed through numerical values, thereby providing a basis for clinical research or personal health management. In addition, each factor in the formula (such as W τ , Q τ 、E τ , R τ ) can be specifically quantified through data collection, thereby improving the accuracy and credibility of sleep quality scores. Through the application of this formula, the sleep quality of users with different types of circadian insomnia can be systematically evaluated, and accurate suggestions and improvement measures can be provided. This not only helps users improve their sleep quality, but also provides data support and scientific basis for health management. Overall, the sleep quality score calculation formula plays a key role in the entire analysis process and can provide an effective framework for understanding the complex relationship between users' circadian activities and sleep quality. In summary, this formula fully considers the user's circadian sleep quality score coefficient ξ, the user's circadian sleep cycle T, the variable parameter τ at the sleep cycle time point, and the user's circadian activity sleep effectiveness influencing correlation factor W at the sleep cycle time point τ. τ , the user's circadian activity sleep depth impact correlation factor Q at the sleep cycle time point τ τ , the user's circadian activity sleep environment impact correlation factor E at the sleep cycle time point τ τ , the user's circadian activity sleep physiological impact correlation factor R at the sleep cycle time point τ τ , the correction coefficient ε of the user's daytime and nighttime sleep quality score coefficient, and a functional relationship is formed according to the mutual correlation between the user's daytime and nighttime sleep quality score coefficient ξ and the above parameters This formula can realize the calculation process of circadian sleep quality evaluation of the user's circadian sleep cycle corresponding to various types of circadian insomnia. At the same time, by introducing the correction coefficient ε of the user's circadian sleep quality score coefficient, it can be adjusted according to the errors occurring in the calculation process, thereby improving the accuracy and applicability of the sleep quality score calculation formula.

[0145] Preferably, based on the circadian sleep cycles of the users corresponding to the various types of circadian insomnia, a statistical analysis of the circadian heart rates of the users corresponding to the various types of circadian insomnia is performed to obtain characteristic data of the circadian heart rate cycles and rhythmic changes of the users corresponding to the various types of circadian insomnia;

[0146] In an embodiment of the present invention, a statistical analysis of the heart rate rhythm changes of the user's circadian heart rate obtained by corresponding statistical calculation is performed by combining the user's circadian sleep cycles corresponding to various types of circadian insomnia obtained by previous analysis, so that the corresponding heart rate monitor in the wearable watch is used to record the data in real time, and the heart rate data is analyzed using time domain and frequency domain analysis methods (such as FFT transformation) to extract the periodic change characteristics of the heart rate, including indicators such as the average heart rate and heart rate variability. Cluster analysis is performed using statistical software to identify the heart rate rhythm change characteristics of users with different types of circadian insomnia, and finally the circadian heart rate periodic rhythm change characteristic data of users corresponding to various types of circadian insomnia are obtained.

[0147] Preferably, based on the user's daytime sleep quality score coefficients corresponding to various types of daytime insomnia, a heart rate rhythm disorder degree calculation formula is used to perform a quantitative calculation of the heart rate rhythm disorder on the user's daytime heart rate cycle rhythm change characteristic data corresponding to various types of daytime insomnia, so as to obtain the degree of user's daytime heart rate cycle rhythm disorder corresponding to various types of daytime insomnia.

[0148] In an embodiment of the present invention, a suitable heart rate rhythm disorder degree calculation formula is formed by combining the user's circadian sleep cycle, time variable parameters, the user's circadian heart rate, the user's circadian heart rate cycle rhythm influence weight factor, the user's circadian heart rate cycle rhythm attenuation coefficient, the user's circadian heart rate cycle rhythm amplitude influence coefficient, the user's circadian heart rate cycle rhythm amplitude change frequency, the user's circadian heart rate cycle rhythm amplitude phase offset, the user's circadian sleep quality score coefficient and related parameters to perform quantitative calculation of the heart rate rhythm disorder degree, so as to quantify these indicators and the user's circadian sleep quality score coefficient to obtain the degree of heart rate rhythm disorder corresponding to different types of circadian insomnia, and compare the differences in heart rate rhythm disorders between different types of insomnia by using corresponding statistical tests (such as ANOVA), and finally obtain the degree of user's circadian heart rate cycle rhythm disorder corresponding to various types of circadian insomnia.

[0149] Furthermore, the calculation formula for the degree of heart rate rhythm disorder is specifically:

[0150]

[0151] Where DHR is the degree of disorder of the user's circadian heart rate cycle rhythm, T is the user's circadian sleep cycle, t is the time variable parameter, HR(t) is the user's circadian heart rate at time point t, α is the influence weight factor of the user's circadian heart rate cycle rhythm, β is the user's circadian heart rate cycle rhythm attenuation coefficient, γ is the user's circadian heart rate cycle rhythm amplitude influence coefficient, ω is the user's circadian heart rate cycle rhythm amplitude change frequency, is the amplitude phase offset of the user's circadian heart rate cycle rhythm, ξ is the user's circadian sleep quality score coefficient, and η is the correction coefficient of the user's circadian heart rate cycle rhythm disorder degree.

[0152] The present invention obtains a formula for calculating the degree of heart rate rhythm disorder by using a specific mathematical model and verifying that the formula is used to quantitatively calculate the heart rate rhythm disorder of the user's circadian heart rate cycle rhythm change characteristic data corresponding to various types of circadian insomnia. The formula for calculating the degree of heart rate rhythm disorder can comprehensively reflect the changing characteristics of the user's heart rate by integrating multiple parameters. This comprehensiveness helps to deeply understand the complex relationship between heart rate rhythm and sleep quality. The application of integral form allows the analysis of heart rate data at different time points, reveals the trend of heart rate changes over time, and helps to study the dynamic relationship between heart rate and sleep cycle. Through the calculation of the degree of rhythm disorder, a quantitative indicator can be provided for the subsequent intelligent intervention process, which makes it possible to more clearly identify the abnormal situation of heart rate rhythm, so as to intervene more targetedly. Secondly, the parameters such as weight factor and attenuation coefficient in the formula can be adjusted according to the heart rate characteristics of different individuals, and a personalized health management plan is provided, which means that users can adjust their lifestyles or intelligent intervention plans based on their own heart rate data. By combining the data from wearable devices, real-time monitoring of the degree of rhythm disorder can be achieved, which can provide users and medical professionals with instant feedback, thereby helping users understand their health status and make timely adjustments. In summary, this formula fully considers the user's circadian heart rate cycle rhythm disorder degree DHR, the user's circadian sleep cycle T, the time variable parameter t, the user's circadian heart rate HR(t) at time point t, the user's circadian heart rate cycle rhythm influence weight factor α, the user's circadian heart rate cycle rhythm attenuation coefficient β, the user's circadian heart rate cycle rhythm amplitude influence coefficient γ, the user's circadian heart rate cycle rhythm amplitude change frequency ω, the user's circadian heart rate cycle rhythm amplitude phase offset The user's circadian sleep quality score coefficient ξ, the user's circadian heart rate cycle rhythm disorder degree correction coefficient η, according to the user's circadian heart rate cycle rhythm disorder degree DHR and the mutual correlation between the above parameters constitute a functional relationship This formula can realize the quantitative calculation process of heart rate rhythm disorder of the user's circadian heart rate rhythm change characteristic data corresponding to various types of circadian insomnia. At the same time, by introducing the correction coefficient η of the user's circadian heart rate rhythm disorder degree, it can be adjusted according to the error occurring in the calculation process, thereby improving the accuracy and applicability of the heart rate rhythm disorder degree calculation formula.

[0153] Furthermore, the circadian disorder insomnia user intelligent intervention execution module includes the following functions:

[0154] Designing intelligent intervention strategies for circadian insomnia according to the degree of disorder of the circadian heart rate cycle rhythm of the user corresponding to various types of circadian insomnia, so as to generate intelligent intervention strategy solutions for circadian insomnia of the user corresponding to various types of circadian insomnia;

[0155] In an embodiment of the present invention, intelligent intervention strategies for insomnia are formulated for different types of circadian insomnia based on the specific numerical values ​​of the degree of disorder of the user's circadian heart rate cycle corresponding to various types of circadian insomnia obtained by previous quantitative calculation and in combination with the results of psychological and physiological research. For example, for users who have difficulty falling asleep at night or in the early morning, an intervention strategy based on relaxation training is designed, while for users who have difficulty maintaining sleep, the focus is on optimizing the sleep environment and adjusting pre-sleep activities. These strategies will form a comprehensive intelligent intervention plan, which specifically includes recommended relaxation music, meditation exercises, bedtime reading materials and other elements to meet the personalized needs of users with different types of circadian insomnia, and finally a design is generated for user circadian insomnia intelligent intervention strategy plans corresponding to various types of circadian insomnia.

[0156] Preferably, the APP software on the wearable watch is used to obtain the work and rest habits corresponding to the day and night insomnia type, and the insomnia intervention push time and frequency are preset according to the work and rest habits corresponding to the day and night insomnia type, so as to obtain the insomnia intervention push time and insomnia intervention push frequency corresponding to various day and night insomnia types;

[0157] In an embodiment of the present invention, the work and rest habits of users determined to have corresponding circadian insomnia types are collected by using the corresponding APP software on the wearable watch. The wearable device monitors the user's daily activities, sleep cycles and their changes through built-in sensors, and records the user's daytime activity, sleep time, wake-up time, etc. The data is updated to the APP in real time through wireless transmission to generate an analysis report on the user's work and rest habits. At the same time, according to the work and rest habits of different circadian insomnia types, specific intervention push times and frequencies are set. For example, for users who wake up early, a gentle sound awakening is set between 3 and 4 in the morning, and for users who have difficulty falling asleep, it is recommended to push a reminder for relaxation exercises one hour before bedtime. These settings will ensure that the intervention measures are pushed within the most effective time according to the user's personalized work and rest habits, and finally the insomnia intervention push times and insomnia intervention push frequencies corresponding to various circadian insomnia types are obtained.

[0158] Preferably, based on the insomnia intervention push time and insomnia intervention push frequency corresponding to various types of circadian insomnia, the APP software on the wearable watch is used to push the corresponding user circadian insomnia intelligent intervention strategy plan to the user, so as to execute the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

[0159] In an embodiment of the present invention, by combining the previously set insomnia intervention push time and push frequency corresponding to various types of circadian insomnia, the corresponding intervention strategy is implemented using the corresponding APP software on the wearable watch. The APP will regularly push personalized intervention content to the user, such as meditation audio, breathing exercises or bedtime tips, and increase the user's attention through vibration or audio reminders. The wearable device will monitor the user's physiological reactions, such as heart rate and activity level, to evaluate the intervention effect. When the user feedback is that the intervention effect is not good, the APP background system will automatically adjust the intervention strategy and further optimize the push content and frequency. Through such a dynamic feedback mechanism, it is ensured that each user can obtain intervention measures that meet their needs and maximize the improvement of their circadian rhythm disorder insomnia, so that the corresponding user circadian rhythm disorder insomnia intelligent intervention work can be performed.

[0160] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An APP-based intelligent intervention system for circadian rhythm disorder insomnia, characterized in that: Includes the following modules: A user day and night insomnia type labeling and classification module is used to collect the user's insomnia severity index scale and the morning type-evening type questionnaire in real time through the questionnaire function built into the APP software on the wearable watch, and collect the user's day and night sleep parameters in real time on the user's insomnia severity index scale and the morning type-evening type questionnaire, so as to obtain the user's day and night insomnia severity index and the user's day and night sleep category measurement score; Virtually marking and dividing the circadian insomnia types according to the user's circadian insomnia severity index and the user's circadian sleep category measurement score to obtain various circadian insomnia types; The sleep parameter collection module for users with circadian insomnia is used to monitor the activity, sleep time, number of awakenings and heart rate of users with various types of circadian insomnia in real time during the same time period through a wearable watch, so as to obtain the circadian activity, circadian sleep time, number of awakenings and circadian heart rate of users corresponding to various types of circadian insomnia; Perform a sleep cycle analysis on the user based on the user's circadian sleep time and the number of times the user wakes up during the day and night corresponding to various types of circadian insomnia, and obtain the user's circadian sleep cycle corresponding to various types of circadian insomnia; The module for evaluating the degree of disorder of circadian insomnia users is used to evaluate and analyze the circadian sleep quality of users corresponding to various types of circadian insomnia based on the circadian activity of users corresponding to various types of circadian insomnia, so as to obtain the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia; based on the circadian sleep quality score coefficients of users corresponding to various types of circadian insomnia and the circadian sleep cycles of users, the module for evaluating the degree of disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia is used to quantitatively calculate the disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia, so as to obtain the degree of disorder of the circadian heart rate cycle of users corresponding to various types of circadian insomnia; The circadian rhythm disorder insomnia user intelligent intervention execution module is used to push user insomnia intelligent intervention based on the degree of user circadian heart rate cycle rhythm disorder corresponding to various types of circadian insomnia using the APP software on the wearable watch, so as to execute the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

2. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 1 is characterized in that: The user day and night insomnia type marking classification module includes the following functions: The built-in questionnaire function of the wearable watch APP software collects users' Insomnia Severity Index Scale and Morningness-Eveningness Questionnaire in real time; The user's daytime and nighttime insomnia severity index is collected in real time on the user's insomnia severity index scale to obtain the user's daytime and nighttime insomnia severity index, wherein the user's daytime and nighttime insomnia severity index can be divided into 0-7 points for no insomnia, 8-14 points for mild insomnia, 15-21 points for moderate insomnia, and 22-28 points for severe insomnia; Performing a morning-night biological clock work-and-rest characteristic analysis on the user's morning-night type questionnaire to obtain the user's morning-night biological clock work-and-rest characteristic data; The user's circadian sleep measurement is calculated based on the user's morning-night biological clock work and rest characteristic data to obtain the user's circadian sleep category measurement score, wherein the user's circadian sleep category measurement score can be divided into 16-30 points absolute night type, 31-41 points moderate night type, 42-58 points intermediate type, 59-69 points moderate morning type and 70-86 points absolute morning type; Virtual marking and division of circadian insomnia types are performed according to the user's circadian insomnia severity index and the user's circadian sleep category measurement score to obtain various circadian insomnia types.

3. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 2 is characterized in that: The various types of circadian insomnia include: Absolute night-no insomnia type, moderate night-no insomnia type, intermediate-no insomnia type, moderate morning-no insomnia type, absolute morning-no insomnia type, absolute night-mild insomnia type, moderate night-mild insomnia type, intermediate-mild insomnia type, moderate morning-mild insomnia type, absolute morning-mild insomnia type, absolute night-moderate insomnia type, moderate night-moderate insomnia type, intermediate-moderate insomnia type, moderate morning-moderate insomnia type, absolute morning-moderate insomnia type, absolute night-severe insomnia type, moderate night-severe insomnia type, intermediate-severe insomnia type, moderate morning-severe insomnia type and absolute morning-severe insomnia type.

4. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 1 is characterized in that: The sleep parameter collection module for circadian insomnia users includes the following functions: The wearable watch uses an acceleration sensor to monitor the user's activity during the day and night sleep period in real time during the same time period for various types of circadian insomnia, so as to obtain the user's circadian activity corresponding to various types of circadian insomnia; Performing a circadian activity status analysis on the circadian activity amounts of the user corresponding to various circadian insomnia types to obtain the circadian activity status of the user corresponding to various circadian insomnia types; performing a circadian sleep stage judgment on the corresponding circadian activity amounts of the user according to the circadian activity status of the user corresponding to various circadian insomnia types to obtain the circadian sleep stage of the user corresponding to various circadian insomnia types, wherein the circadian sleep stage of the user includes a circadian deep sleep stage, a circadian light sleep stage, and a circadian wakefulness stage; The sleep time sensor is used to monitor the sleep stage duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and night insomnia in real time, so as to obtain the sleep duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and night insomnia; the sleep duration of the deep sleep stage and the light sleep stage corresponding to various types of daytime and night insomnia are added together, so as to obtain the user's daytime and night sleep time corresponding to various types of daytime and night insomnia; The suspected awakening frequency of the user is counted for the day and night awakening stages corresponding to various types of day and night insomnia, so as to obtain the suspected awakening frequency of the user during the day and night corresponding to various types of day and night insomnia; the user activity posture change data corresponding to various types of day and night insomnia are obtained by using a gyroscope sensor, and the number of awakening times is supplemented and corrected according to the user activity posture change data corresponding to various types of day and night insomnia and the suspected awakening frequency of the user during the day and night, so as to obtain the number of awakening times of the user during the day and night corresponding to various types of day and night insomnia; The optical heart rate sensor on the wearable watch is used to obtain the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia, and the user's heart rate is calculated based on the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia, so as to obtain the user's circadian heart rate corresponding to various types of circadian insomnia; The user's sleep cycle is analyzed according to the user's circadian sleep time and the number of times the user wakes up during the day and night corresponding to various types of circadian insomnia, so as to obtain the user's circadian sleep cycle corresponding to various types of circadian insomnia.

5. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 4 is characterized in that: The auxiliary correction of the number of awakenings according to the user activity posture change data corresponding to various types of day and night insomnia and the user's suspected awakening frequency during the day and night includes: Based on the suspected awakening frequencies of users corresponding to various types of circadian insomnia, the user activity posture change data corresponding to various types of circadian insomnia are matched and divided according to the suspected awakening frequencies, and the user activity posture change sub-data corresponding to each suspected awakening in various types of circadian insomnia are obtained; Performing user activity trajectory recognition and analysis on the user activity posture change sub-data corresponding to each suspected awakening in various types of daytime and nighttime insomnia, and obtaining the user activity posture trajectory corresponding to each suspected awakening in various types of daytime and nighttime insomnia; Performing activity trajectory behavior state analysis on the user activity posture trajectory corresponding to each suspected awakening in various types of day and night insomnia, and obtaining the user activity trajectory behavior state corresponding to each suspected awakening in various types of day and night insomnia; Based on the user activity trajectory behavior state corresponding to each suspected wakefulness in various types of day and night insomnia, the corresponding user's suspected wakefulness during the day and night is compared and judged to assist in waking up. If it is judged that the user activity trajectory behavior state corresponding to the suspected wakefulness is a real wakefulness state, then the next user's suspected wakefulness during the day and night is compared and judged; if it is judged that the user activity trajectory behavior state corresponding to the suspected wakefulness is just a turning over state or a not really awake state, then the frequency of suspected wakefulness during the day and night of the user corresponding to various types of day and night insomnia is reduced by one, until all the user activity trajectory behavior states corresponding to the suspected wakefulness are compared and judged, so as to obtain the number of user wakeups during the day and night corresponding to various types of day and night insomnia.

6. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 4 is characterized in that: The method of using the optical heart rate sensor on the wearable watch to obtain the user's photoelectric volume pulse fluctuation signals corresponding to various types of day and night insomnia, and calculating the user's heart rate based on the user's photoelectric volume pulse fluctuation signals corresponding to various types of day and night insomnia includes: The optical heart rate sensor on the wearable watch is used to obtain the user's photoelectric volume pulse fluctuation signal corresponding to various types of circadian insomnia; Performing low-pass environmental noise filtering on the user photoelectric volume pulse fluctuation signals corresponding to various types of circadian insomnia to obtain low-pass environmental noise filtered fluctuation signals of the user pulse corresponding to various types of circadian insomnia; performing high-pass motion artifact elimination on the user pulse low-pass environmental noise filtered fluctuation signals corresponding to various types of circadian insomnia to obtain high-pass artifact eliminated fluctuation signals of the user pulse corresponding to various types of circadian insomnia; Performing pulse fluctuation spectrum conversion on the user pulse high-pass artifact-eliminated fluctuation signal corresponding to various types of circadian insomnia to generate frequency domain graphs of the user pulse fluctuation signal corresponding to various types of circadian insomnia; Perform pulse signal peak marking processing on the frequency domain spectra of the user pulse fluctuation signal corresponding to various types of day and night insomnia to obtain the peak points of the user pulse signal spectra corresponding to various types of day and night insomnia; perform peak interval calculation on the corresponding frequency domain spectra of the user pulse fluctuation signal based on the peak points of the user pulse signal spectra corresponding to various types of day and night insomnia to obtain the time interval between each pair of continuous peak points corresponding to various types of day and night insomnia; According to the time interval between each pair of continuous peak points corresponding to various types of circadian insomnia, interval heart rate statistics are calculated to obtain the user's circadian heart rate sub-values ​​corresponding to each pair of continuous peak points of various types of circadian insomnia; the type heart rate arithmetic average calculation is performed on the user's circadian heart rate sub-values ​​corresponding to each pair of continuous peak points of various types of circadian insomnia to obtain the user's circadian heart rate corresponding to various types of circadian insomnia.

7. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 4 is characterized in that: The analysis of the user's sleep cycle according to the user's daytime and nighttime sleep time corresponding to various types of daytime and nighttime insomnia and the number of times the user wakes up during the daytime and nighttime includes: Determine the sleep start and end time points of the user's daytime and nighttime sleep time corresponding to various types of daytime and nighttime insomnia, and obtain the user's daytime and nighttime sleep start and end time points corresponding to various types of daytime and nighttime insomnia; Based on the user's circadian sleep start time point and end time point corresponding to various types of circadian insomnia, the corresponding user's circadian sleep time is defined to generate a user's circadian sleep time range diagram corresponding to various types of circadian insomnia; Based on the user's circadian sleep time range diagram corresponding to various types of circadian insomnia, the corresponding number of user's circadian awakening times is analyzed for interactive response, and the interactive response change curve between the circadian sleep duration and the number of awakening times corresponding to various types of circadian insomnia is obtained; The user sleep cycle analysis is performed on the interactive response change curves between the user's circadian sleep duration and the number of awakenings corresponding to various types of circadian insomnia, and the user's circadian sleep cycles corresponding to various types of circadian insomnia are obtained.

8. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 1 is characterized in that: The module for assessing the degree of disorder of circadian insomnia users includes the following functions: Performing a user activity intensity analysis on the user's circadian activity amounts corresponding to various types of circadian insomnia to obtain the user's circadian activity intensity corresponding to various types of circadian insomnia; Based on the circadian activity intensity of the user corresponding to the various circadian insomnia types, the circadian activity-sleep cycle impact correlation analysis of the user circadian sleep cycle corresponding to the various circadian insomnia types is performed to obtain the user circadian activity-sleep cycle correlation factors corresponding to the various circadian insomnia types; Based on the user's circadian activity-sleep cycle correlation factor corresponding to various types of circadian insomnia, the circadian sleep quality of the user's circadian sleep cycle corresponding to various types of circadian insomnia is evaluated and calculated using the sleep quality score calculation formula to obtain the user's circadian sleep quality score coefficient corresponding to various types of circadian insomnia; The specific calculation formula for sleep quality score is: Where ξ is the user's circadian sleep quality score coefficient, T is the user's circadian sleep cycle, τ is the variable parameter of the sleep cycle time point, and W τ is the correlation factor affecting the effectiveness of user circadian activity sleep at the sleep cycle time point τ, Q τ is the user's circadian activity sleep depth impact correlation factor at the sleep cycle time point τ, E τ is the user's circadian activity sleep environment impact correlation factor at the sleep cycle time point τ, R τ is the user's circadian activity sleep physiological impact correlation factor at the sleep cycle time point τ, and ε is the correction coefficient of the user's circadian sleep quality score coefficient; Based on the circadian sleep cycles of the users corresponding to the various types of circadian insomnia, statistical analysis is performed on the circadian heart rates of the users corresponding to the various types of circadian insomnia to obtain characteristic data of the circadian heart rate cycles of the users corresponding to the various types of circadian insomnia; Based on the user's daytime sleep quality score coefficient corresponding to various types of daytime insomnia, the heart rate rhythm disorder degree calculation formula is used to perform a quantitative calculation of the heart rate rhythm disorder on the user's daytime heart rate cycle rhythm change characteristic data corresponding to various types of daytime insomnia, so as to obtain the degree of user's daytime heart rate cycle rhythm disorder corresponding to various types of daytime insomnia.

9. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 8 is characterized in that: The calculation formula for the degree of heart rate rhythm disorder is specifically: Where DHR is the degree of disorder of the user's circadian heart rate cycle rhythm, T is the user's circadian sleep cycle, t is the time variable parameter, HR(t) is the user's circadian heart rate at time point t, α is the influence weight factor of the user's circadian heart rate cycle rhythm, β is the user's circadian heart rate cycle rhythm attenuation coefficient, γ is the user's circadian heart rate cycle rhythm amplitude influence coefficient, ω is the user's circadian heart rate cycle rhythm amplitude change frequency, is the amplitude phase offset of the user's circadian heart rate cycle rhythm, ξ is the user's circadian sleep quality score coefficient, and η is the correction coefficient of the user's circadian heart rate cycle rhythm disorder degree.

10. The APP-based intelligent intervention system for circadian rhythm disorder insomnia according to claim 1 is characterized in that: The circadian disorder insomnia user intelligent intervention execution module includes the following functions: Designing intelligent intervention strategies for circadian insomnia according to the degree of disorder of the circadian heart rate cycle rhythm of the user corresponding to various types of circadian insomnia, so as to generate intelligent intervention strategy solutions for circadian insomnia of the user corresponding to various types of circadian insomnia; Use the APP software on the wearable watch to obtain the work and rest habits corresponding to the day and night insomnia type, and preset the insomnia intervention push time and frequency according to the work and rest habits of the corresponding day and night insomnia type, so as to obtain the insomnia intervention push time and insomnia intervention push frequency corresponding to various day and night insomnia types; Based on the insomnia intervention push time and insomnia intervention push frequency corresponding to various types of circadian insomnia, the APP software on the wearable watch is used to push the corresponding user circadian insomnia intelligent intervention strategy plan to the user, so as to perform the corresponding user circadian rhythm disorder insomnia intelligent intervention work.

Images