Rhythm adjustment illumination parameter control method and system

Abstract

The invention relates to the technical field of intelligent control, in particular to a rhythm adjustment illumination parameter control method and system. The system comprises the steps of collecting biological sign data and environment illumination data of a user through an intelligent wearable sensor, analyzing state differences in all biological rhythm modes according to the biological sign data, performing feature interaction on the environment illumination data and the state differences in the biological rhythm modes, generating illumination-mode state evaluation interaction feature data, and analyzing the illumination-mode state evaluation interaction feature data according to the illumination-mode state evaluation interaction feature data. Constructing an illumination demand mapping relation of the biological rhythm mode through a decision tree algorithm and the illumination-mode state evaluation interaction feature data, and performing learning optimization to generate an optimized rhythm mode illumination demand decision tree model; and transmitting the instant biological rhythm mode to the optimized rhythm mode illumination demand decision tree model to analyze the intelligent rhythm illumination demand data so as to execute rhythm adjustment illumination parameter control operation. According to the invention, dynamic intelligent illumination adjustment control based on the instant biological rhythm mode of the user is realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a method and system for controlling rhythmically regulated illumination parameters. Background Art

[0002] Biorhythm refers to the time regulation system within an organism that controls the periodic changes in physiological processes and behaviors, such as sleep, body temperature, and hormone secretion. These changes are usually coordinated with periodic factors in the external environment (such as the alternation of day and night). Light is a key factor affecting biorhythm, because light transmits signals through special receptors in the retina to regulate the biological clock in the brain. Biorhythm regulation of lighting uses specific lighting conditions, such as light intensity, spectrum, and time distribution, to influence or synchronize the internal rhythm of an organism. The rhythm-regulating lighting parameter control system dynamically adjusts parameters such as light intensity, color temperature, spectral composition, and duration to adapt to the circadian rhythm needs of an organism. It is usually based on the operating mechanism of the biological clock and uses artificial light sources to simulate changes in natural light to help regulate an individual's physiological rhythm. However, the existing rhythm-regulated lighting parameter control systems cannot effectively collect the user's biological sign data, such as heart rate, sleep status, etc., resulting in the disconnection of lighting regulation from the user's actual biological rhythm; lighting regulation is mostly based on preset schedules or fixed patterns, lacking in-depth analysis and prediction of the user's individual biological rhythms, and unable to achieve truly intelligent and personalized lighting control; and usually only adjusts the current biological rhythm pattern, lacking prediction of long-term biological rhythm trends and intelligent adjustment of future states, and unable to provide more precise intervention and improvement of the user's rhythm changes. Summary of the invention

[0003] Based on this, the present invention provides a method and system for controlling rhythmically regulated lighting parameters to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a rhythmic regulation lighting parameter control system includes the following modules:

[0005] A user perception data collection module, used to collect user perception data according to the smart wearable sensor and generate user perception data, wherein the user perception data includes ambient light data and biological sign data;

[0006] The biorhythm pattern analysis module is used to perform biorhythm time series identification analysis based on the biorhythm data to generate biorhythm time series data; perform biorhythm pattern analysis and processing based on the biorhythm time series data to generate biorhythm pattern data;

[0007] The biorhythm pattern state evaluation module is used to analyze the stable state of the biorhythm pattern based on the biorhythm pattern data to generate the biorhythm pattern stable state data; perform state evaluation processing of each biorhythm pattern based on the biorhythm pattern stable state data to generate the biorhythm pattern state evaluation data;

[0008] An interactive feature analysis module, used to perform interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data, and generate light-pattern state assessment interactive feature data;

[0009] The light demand model building module is used to establish a decision mapping relationship between the biological rhythm pattern and the light demand based on a preset decision tree algorithm, and generate an initial rhythm pattern light demand decision tree model; the initial personalized biological rhythm light demand model is optimized by multi-source decision tree pruning training using light-state interaction feature data, and an optimized rhythm pattern light demand decision tree model is generated;

[0010] The rhythm pattern trend model building module is used to analyze the periodic characteristics of the biological rhythm pattern on the biological sign time series data according to the biological rhythm pattern data, and generate the periodic characteristic data of the biological rhythm pattern; based on the periodic characteristic data of the biological rhythm pattern, the biological rhythm pattern change trend model is designed to generate the biological rhythm pattern change trend model;

[0011] The rhythm regulation lighting parameter control module is used to perform real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; perform real-time biorhythm pattern change trend analysis and processing on the real-time biorhythm pattern data based on the biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; transmit the real-time biorhythm pattern change trend data to the optimized rhythm pattern lighting demand decision tree model to perform intelligent analysis and processing of rhythm lighting demand to generate intelligent rhythm lighting demand data; and execute rhythm regulation lighting parameter control operations based on rhythm lighting intelligent regulation control parameters.

[0012] The present invention can accurately collect the user's biological sign data (such as heart rate, body temperature, sleep status, user behavior, etc.) and ambient light data through the real-time perception of the intelligent wearable device, ensuring that the system can monitor the user's physical condition and surrounding light conditions in real time. The collection of such data provides an accurate basis for subsequent analysis, helps to adjust the light more accurately, and improves the matching degree of light control with the actual needs of the user. By performing time series identification analysis on the biological sign data, the changing rules of the user's biological signs in different time periods can be accurately identified, and the biorhythm pattern data with time series characteristics can be extracted, ensuring that the analysis of the biorhythm pattern is closely related to the user's physiological state, providing a personalized basis for subsequent light adjustment, and making the light adjustment more synchronized with the user's biorhythm. Combined with the environmental light data and the user's biorhythm state assessment data, interactive feature analysis is performed to ensure that the light adjustment is highly correlated with the user's current state. Through this fine interactive analysis, the state of light feedback under each biorhythm mode is understood, and the light parameters can be dynamically adjusted, so that the light control is no longer a single-dimensional control, but fully considers the user's current biorhythm state and the environment in which it is located, and improves the effectiveness and accuracy of light adjustment. By using the decision tree algorithm combined with the biorhythm pattern data, the system can establish a mapping relationship between the lighting requirements of different biorhythm modes, so that the system can provide the most suitable lighting environment for users under different rhythm modes. By further using the light-state interaction feature data to train and optimize the decision tree model, the accuracy of the model is continuously improved. The optimization of the decision tree enables the system to adapt to the rhythm changes of users and gradually adjust the lighting parameters, thereby providing more personalized and intelligent lighting adjustment. The generated optimized rhythm mode lighting demand decision tree model can more accurately predict and meet the lighting needs of users under different biorhythm states, enhancing the system's ability to adapt to individual differences of users. The periodic characteristics of the biorhythm pattern are deeply analyzed to identify the long-term change rules and periodic characteristics of the user's biorhythm, and generate corresponding periodic feature data to design a model that reflects the trend of biorhythm changes. This trend model enables the system to have the ability to predict future changes in biorhythms, so that it can prepare and adjust in advance when adjusting lighting. Through data based on periodic characteristics, lighting control can better prevent rhythm disorders and provide users with a more continuous and dynamic lighting optimization solution. Real-time analysis of the user's biological sign data can update the user's biorhythm status in real time and generate real-time biorhythm pattern data, so that the system can monitor the user's rhythm status in a timely manner and ensure the real-time nature of the light adjustment plan. Combined with the biorhythm pattern change trend model, dynamic trend analysis of the real-time biorhythm status is performed, and the matching light demand is generated by optimizing the rhythm pattern light demand decision tree model. This intelligent analysis and processing based on the current state greatly improves the system's response speed and adjustment accuracy.The generation of intelligent rhythmic lighting demand data enables the system to intelligently adjust lighting parameters based on the user's current rhythmic state and future trend predictions. By performing lighting control operations based on real-time analysis, the lighting is effectively adjusted to adapt to the user's current biorhythm needs, ensuring the user's rhythmic balance and health, ensuring the dynamic, personalized and intelligent nature of lighting adjustment, and greatly improving the user experience.

[0013] This specification provides a rhythmic lighting parameter control method for executing the rhythmic lighting parameter control system as described above. The rhythmic lighting parameter control method includes:

[0014] Step S1: collecting user perception data according to the smart wearable sensor to generate user perception data, wherein the user perception data includes ambient light data and biological sign data;

[0015] Step S2: performing biological sign time series identification analysis based on the biological sign data to generate biological sign time series data; performing biological rhythm pattern analysis and processing based on the biological sign time series data to generate biological rhythm pattern data;

[0016] Step S3: performing a stable state analysis of the biorhythm pattern based on the biorhythm pattern data to generate stable state data of the biorhythm pattern; performing a state evaluation process of each biorhythm pattern based on the stable state data of the biorhythm pattern to generate state evaluation data of the biorhythm pattern;

[0017] Step S4: performing interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data to generate light-pattern state assessment interactive feature data;

[0018] Step S5: Design the mapping relationship of the light demand decision under each biological rhythm mode based on the preset decision tree algorithm and the biological rhythm mode data, and generate a rhythm mode light demand decision tree model; perform decision tree training optimization processing on the rhythm mode light demand decision tree model using the light-state interaction feature data, and generate an optimized rhythm mode light demand decision tree model;

[0019] Step S6: Analyze the periodic characteristics of the biorhythm pattern on the biological sign time series data according to the biorhythm pattern data to generate the periodic characteristic data of the biorhythm pattern; design a biorhythm pattern change trend model based on the periodic characteristic data of the biorhythm pattern to generate the biorhythm pattern change trend model;

[0020] Step S7: Performing real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; performing real-time biorhythm pattern change trend analysis and processing on the real-time biorhythm pattern data based on the biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; transmitting the real-time biorhythm pattern change trend data to the optimized rhythmic pattern lighting demand decision tree model to perform intelligent analysis and processing of rhythmic lighting demand to generate intelligent rhythmic lighting demand data; executing rhythmic lighting parameter control operations based on rhythmic lighting intelligent adjustment control parameters.

[0021] The beneficial effect of the present application is that the present invention collects the user's biological sign data through an intelligent wearable device, and performs biological sign time series identification analysis and biorhythm pattern analysis, generates the user's biorhythm pattern through multi-level data analysis and clustering methods, and performs accurate light adjustment based on each of the user's biorhythm patterns. This real-time perception and analysis based on the user's individual biological signs effectively solves the problem of being unable to accurately collect and analyze the user's biological sign data, ensuring that the light adjustment can accurately match the user's actual biorhythm needs. A mathematical model of the mapping relationship of light demand decisions is designed through a decision tree algorithm and biorhythm pattern data, and the model is trained and optimized to achieve intelligent decision analysis of light adjustment needs. Unlike a fixed mode or a preset schedule, it can dynamically adjust the light parameters according to the user's current biological signs and rhythmic state to achieve personalized and intelligent light control. This intelligent decision-making ability ensures that light adjustment is more in line with the user's actual needs and improves the user experience. Through the biorhythm pattern change trend model and the real-time update of the biorhythm pattern trend prediction, the user's biorhythm is analyzed for periodic characteristics and trend prediction. Not only can the current biorhythm be adjusted, but also the lighting parameters can be adjusted in advance based on future rhythm change trends to achieve adaptive lighting control. This solves the problem of only being able to make simple adjustments to the current state, and can provide users with more accurate rhythm management and health intervention, especially in long-term lighting regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of the module flow of a rhythm-regulated lighting parameter control system of the present invention;

[0023] Figure 2 for Figure 1 Detailed functional flow chart of the biorhythm pattern status assessment module;

[0024] Figure 3 for Figure 1 Detailed functional flow diagram of the lighting demand model building module;

[0025] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The technical method 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.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0029] To achieve this, please refer to Figures 1 to 3 The present invention provides a rhythmic regulation lighting parameter control system, comprising the following modules:

[0030] To achieve the above purpose, a rhythmic regulation lighting parameter control system includes the following modules:

[0031] A user perception data collection module, used to collect user perception data according to the smart wearable sensor and generate user perception data, wherein the user perception data includes ambient light data and biological sign data;

[0032] The biorhythm pattern analysis module is used to perform biorhythm time series identification analysis based on the biorhythm data to generate biorhythm time series data; perform biorhythm pattern analysis and processing based on the biorhythm time series data to generate biorhythm pattern data;

[0033] The biorhythm pattern state evaluation module is used to analyze the stable state of the biorhythm pattern based on the biorhythm pattern data to generate the biorhythm pattern stable state data; perform state evaluation processing of each biorhythm pattern based on the biorhythm pattern stable state data to generate the biorhythm pattern state evaluation data;

[0034] An interactive feature analysis module, used to perform interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data, and generate light-pattern state assessment interactive feature data;

[0035] The light demand model building module is used to establish a decision mapping relationship between the biological rhythm pattern and the light demand based on a preset decision tree algorithm, and generate an initial rhythm pattern light demand decision tree model; the initial personalized biological rhythm light demand model is optimized by multi-source decision tree pruning training using light-state interaction feature data, and an optimized rhythm pattern light demand decision tree model is generated;

[0036] The rhythm pattern trend model building module is used to analyze the periodic characteristics of the biological rhythm pattern on the biological sign time series data according to the biological rhythm pattern data, and generate the periodic characteristic data of the biological rhythm pattern; based on the periodic characteristic data of the biological rhythm pattern, the biological rhythm pattern change trend model is designed to generate the biological rhythm pattern change trend model;

[0037] The rhythm regulation lighting parameter control module is used to perform real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; perform real-time biorhythm pattern change trend analysis and processing on the real-time biorhythm pattern data based on the biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; transmit the real-time biorhythm pattern change trend data to the optimized rhythm pattern lighting demand decision tree model to perform intelligent analysis and processing of rhythm lighting demand to generate intelligent rhythm lighting demand data; and execute rhythm regulation lighting parameter control operations based on rhythm lighting intelligent regulation control parameters.

[0038] The present invention can accurately collect the user's biological sign data (such as heart rate, body temperature, sleep status, user behavior, etc.) and ambient light data through the real-time perception of the intelligent wearable device, ensuring that the system can monitor the user's physical condition and surrounding light conditions in real time. The collection of such data provides an accurate basis for subsequent analysis, helps to adjust the light more accurately, and improves the matching degree of light control with the actual needs of the user. By performing time series identification analysis on the biological sign data, the changing rules of the user's biological signs in different time periods can be accurately identified, and the biorhythm pattern data with time series characteristics can be extracted, ensuring that the analysis of the biorhythm pattern is closely related to the user's physiological state, providing a personalized basis for subsequent light adjustment, and making the light adjustment more synchronized with the user's biorhythm. Combined with the environmental light data and the user's biorhythm state assessment data, interactive feature analysis is performed to ensure that the light adjustment is highly correlated with the user's current state. Through this fine interactive analysis, the state of light feedback under each biorhythm mode is understood, and the light parameters can be dynamically adjusted, so that the light control is no longer a single-dimensional control, but fully considers the user's current biorhythm state and the environment in which it is located, and improves the effectiveness and accuracy of light adjustment. By using the decision tree algorithm combined with the biorhythm pattern data, the system can establish a mapping relationship between the lighting requirements of different biorhythm modes, so that the system can provide the most suitable lighting environment for users under different rhythm modes. By further using the light-state interaction feature data to train and optimize the decision tree model, the accuracy of the model is continuously improved. The optimization of the decision tree enables the system to adapt to the rhythm changes of users and gradually adjust the lighting parameters, thereby providing more personalized and intelligent lighting adjustment. The generated optimized rhythm mode lighting demand decision tree model can more accurately predict and meet the lighting needs of users under different biorhythm states, enhancing the system's ability to adapt to individual differences of users. The periodic characteristics of the biorhythm pattern are deeply analyzed to identify the long-term change rules and periodic characteristics of the user's biorhythm, and generate corresponding periodic feature data to design a model that reflects the trend of biorhythm changes. This trend model enables the system to have the ability to predict future changes in biorhythms, so that it can prepare and adjust in advance when adjusting lighting. Through data based on periodic characteristics, lighting control can better prevent rhythm disorders and provide users with a more continuous and dynamic lighting optimization solution. Real-time analysis of the user's biological sign data can update the user's biorhythm status in real time and generate real-time biorhythm pattern data, so that the system can monitor the user's rhythm status in a timely manner and ensure the real-time nature of the light adjustment plan. Combined with the biorhythm pattern change trend model, dynamic trend analysis of the real-time biorhythm status is performed, and the matching light demand is generated by optimizing the rhythm pattern light demand decision tree model. This intelligent analysis and processing based on the current state greatly improves the system's response speed and adjustment accuracy.The generation of intelligent rhythmic lighting demand data enables the system to intelligently adjust lighting parameters based on the user's current rhythmic state and future trend predictions. By performing lighting control operations based on real-time analysis, the lighting is effectively adjusted to adapt to the user's current biorhythm needs, ensuring the user's rhythmic balance and health, ensuring the dynamic, personalized and intelligent nature of lighting adjustment, and greatly improving the user experience.

[0039] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the module flow of a rhythm-regulated lighting parameter control system of the present invention. In this embodiment, the rhythm-regulated lighting parameter control system includes:

[0040] S1: a user perception data collection module, used to collect user perception data according to the smart wearable sensor and generate user perception data, wherein the user perception data includes ambient light data and biological sign data;

[0041] In an embodiment of the present invention, a smart wearable device having an ambient light sensor and a biometric sensor (such as a heart rate sensor, a skin temperature sensor, etc.) is worn on a user. Ensure that the device has sufficient contact with the user's skin to improve the accuracy of the data. Through the user interface or a preset schedule, the data acquisition module is triggered to start the acquisition process, and the acquisition interval is automatically set based on the user's daily schedule, or it can be triggered by manual input by the user. The ambient light sensor built into the smart wearable device continuously detects external light intensity, color temperature and other information to generate ambient light data. The light data should contain a timestamp so that it can be time-series associated with other data. The smart wearable device collects the user's biometric data (such as heart rate, body temperature, blood oxygen level, etc.) through sensors. These data are collected synchronously with the ambient light data and marked with the same timestamp to ensure the consistency of the time series data. The collected ambient light data and biometric data are transmitted to the background system or the cloud, and transmitted via a wireless connection (such as Wi-Fi or Bluetooth). The data is preprocessed (such as denoising, outlier detection) before uploading, and finally the user's processed ambient light data and biometric data are obtained.

[0042] S2: a biorhythm pattern analysis module, which is used to perform biorhythm time series identification analysis based on biorhythm data to generate biorhythm time series data; and to perform biorhythm pattern analysis and processing based on biorhythm time series data to generate biorhythm pattern data;

[0043] In an embodiment of the present invention, the biological sign data is subjected to denoising, abnormal data cleaning and interpolation processing to ensure the continuity and validity of the data, and the biological sign time series identification is extracted based on the time series characteristics of the biological sign data using a time series analysis algorithm (such as a dynamic time warping algorithm DTW or a smoothing filter). The biological sign time series identification includes changes in key physiological indicators at specific moments (such as periodic fluctuations in heart rate) for subsequent analysis of biorhythms. By performing biorhythm pattern analysis on the biological sign time series data, a clustering algorithm is applied to regularize various types of biological sign time series data, and the rhythmic pattern of the biological sign is identified through a pre-set biorhythm pattern label, the generated biorhythm pattern data includes information such as the user's biorhythm peaks, troughs, and change cycles in different time periods, reflecting the user's daily physiological rhythm.

[0044] S3: a biorhythm pattern state evaluation module, which is used to analyze the stable state of the biorhythm pattern based on the biorhythm pattern data and generate the stable state data of the biorhythm pattern; and to perform state evaluation processing of each biorhythm pattern based on the stable state data of the biorhythm pattern and generate the biorhythm pattern state evaluation data;

[0045] In an embodiment of the present invention, the stability of the biorhythm is evaluated based on the biorhythm pattern data. Statistical analysis methods (such as coefficient of variation CV, mean and standard deviation calculation) are used to analyze the fluctuation range and frequency of the rhythm, and identify that the biorhythm is in a stable state. If the biorhythm fluctuation exceeds the normal range, it means that the user's biorhythm is disturbed by external factors (such as changes in light or irregular work and rest). According to the stable state data, combined with preset health assessment standards (such as biorhythm stability index, health standard range, etc.), a health assessment of the biorhythm pattern is performed, and a machine learning model is used to classify the data, such as a support vector machine (SVM) or a random forest classifier, to generate biorhythm pattern state assessment data, and evaluate the user's biorhythm state, including: normal, disordered, sub-healthy or abnormal, etc.

[0046] S4: an interactive feature analysis module, used to perform interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data, and generate light-pattern state assessment interactive feature data;

[0047] In the embodiment of the present invention, the collected ambient light data and the analyzed biorhythm pattern status assessment data are time-series aligned and preprocessed to ensure that the two types of data remain consistent in the time dimension. Then, correlation analysis and regression analysis techniques are used to analyze the relationship between light intensity, color temperature changes and biorhythm pattern status (such as stability or volatility), and extract key lighting parameters that affect biorhythms. Through this analysis, interactive feature data of ambient light and biorhythm pattern status are generated, revealing how lighting conditions affect the user's biorhythm status, and providing a basis for subsequent lighting adjustments.

[0048] S5: Lighting requirement model building module, used to establish a decision mapping relationship between biological rhythm patterns and lighting requirements based on a preset decision tree algorithm, and generate an initial rhythmic pattern lighting requirement decision tree model; use the light-state interaction feature data to perform multi-source decision tree pruning training optimization processing on the initial personalized biological rhythm lighting requirement model, and generate an optimized rhythmic pattern lighting requirement decision tree model;

[0049] In the embodiment of the present invention, based on the preset decision tree algorithm, the initial lighting demand decision tree model is established using the biorhythm pattern data and the historical lighting data. The model generates an initial rhythmic pattern lighting demand decision tree by analyzing the mapping relationship between the user's biorhythm characteristics and the lighting demand. Combined with the lighting-state interaction feature data generated by the interactive feature analysis module, the initial model is optimized for multi-source data, the redundant decision paths are reduced by the pruning algorithm, and the lighting demand under each biorhythm pattern is learned to improve the accuracy and efficiency of the model, and a personalized and optimized rhythmic pattern lighting demand decision tree model is generated.

[0050] S6: a rhythm pattern trend model building module, which is used to analyze the periodic characteristics of the biological rhythm pattern on the biological sign time series data according to the biological rhythm pattern data, and generate the periodic characteristic data of the biological rhythm pattern; based on the periodic characteristic data of the biological rhythm pattern, a biological rhythm pattern change trend model is designed to generate the biological rhythm pattern change trend model;

[0051] In an embodiment of the present invention, according to the biorhythm pattern data, a periodic analysis method (such as Fourier transform, period extraction algorithm) is applied to analyze the biological sign time series data, extract the rhythm periodic characteristics, and generate periodic characteristic data reflecting the long-term rhythm changes of the user. A change trend model of the biorhythm pattern is constructed based on the periodic characteristic data of the biorhythm pattern to predict the future trend of biorhythm changes. The model simulates the dynamic changes of biorhythms through time series analysis and machine learning methods (such as long short-term memory network LSTM), and provides a trend reference for the adjustment of personalized lighting needs.

[0052] S7: Rhythm regulation lighting parameter control module, used to perform real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; perform real-time biorhythm pattern change trend analysis and processing on real-time biorhythm pattern data based on biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; transmit the real-time biorhythm pattern change trend data to the optimized rhythm pattern lighting demand decision tree model to perform intelligent analysis and processing of rhythm lighting demand to generate intelligent rhythm lighting demand data; execute rhythm regulation lighting parameter control operation based on rhythm lighting intelligent adjustment control parameters.

[0053] In an embodiment of the present invention, based on the latest biological sign data, and by analyzing the correspondence between the first analyzed biological rhythm pattern data and the latest biological sign data, the user's current biological rhythm pattern is analyzed in real time to generate immediate biological rhythm pattern data. Based on the biological rhythm pattern change trend model constructed in the previous step, trend analysis is performed on the current data to predict the future change direction of the user's biological rhythm, and to generate immediate biological rhythm change trend data. The trend data is transmitted to the optimized rhythm pattern lighting demand decision tree model, and intelligent analysis and processing of the rhythmic lighting demand is performed to generate accurate intelligent rhythmic lighting demand data. Based on the intelligent rhythmic lighting demand data, the lighting parameters (such as light intensity and color temperature) are automatically adjusted, and rhythm-regulated lighting control is performed to ensure that the user's lighting environment matches their biological rhythm requirements.

[0054] Preferably, the biorhythm pattern analysis module includes the following functions:

[0055] Performing biological sign time series identification analysis according to the biological sign data to generate biological sign time series data;

[0056] Performing biological sign transient characteristic data analysis according to biological sign time series data to generate biological sign transient characteristic data;

[0057] Performing biological sign transient state clustering analysis on biological sign transient state feature data to generate biological sign transient state clustering data;

[0058] The biorhythm pattern analysis is performed based on the transient clustering data of biological signs to generate biorhythm pattern data.

[0059] The present invention performs time series identification analysis on biological sign data, extracts the changing trend of the user's physiological state in the time dimension, forms a series of time series feature data, ensures that the analysis of biological signs is not limited to the current state, and also identifies the physiological changes of the user at different times, providing a more timely and dynamic basis for the subsequent biorhythm pattern analysis, so that the light adjustment can be more accurately adjusted according to the user's real biorhythm changes. By performing transient state feature analysis on biological sign time series data, the physiological characteristics of the user at a specific moment, such as the transient state of heart rate, body temperature, blood pressure, etc., are captured. These transient state feature data reflect the user's immediate physiological condition at different time points, further understand the user's current health status and physiological rhythm changes, make the light adjustment more dynamic, and can quickly respond to the user's immediate needs. By performing cluster analysis on transient state feature data, the data is grouped according to the different physiological characteristics of the user, and meaningful cluster data is generated, which helps to identify the potential patterns and associations between the user's physiological characteristics, and provides data support for more in-depth biorhythm pattern analysis. Cluster analysis can effectively extract the physiological rhythm patterns of individual differences of users, so that light adjustment can not only be based on general patterns, but also be fine-tuned according to individual characteristics of users, further improving the personalization and intelligence level of light control. The biorhythm pattern analysis of transient clustering data can deduce the user's biorhythm pattern based on the user's transient clustering characteristics, identify the user's circadian rhythm state, and help the system understand whether the user's current physiological rhythm is normal or disordered. It provides specific data support based on the user's individual rhythm for subsequent light adjustment, ensuring that the light adjustment plan can accurately match the user's current rhythm state and help them restore and maintain the balance and stability of the rhythm.

[0060] In an embodiment of the present invention, based on the biological sign data (such as heart rate, body temperature, respiratory rate, etc.) collected by the smart wearable device, the data is processed using a time series analysis method (such as a dynamic time warping algorithm DTW or a smoothing filter) to generate biological sign time series data. By time-marking and aligning these data, the law of biological sign changes over time is identified, and time series data that can reflect the dynamic changes of the user's physiological state over time is generated as the basis for subsequent analysis. Based on the biological sign time series data, the state of the biological sign at different time points is analyzed in a transient state. By extracting instantaneous feature indicators (such as instantaneous heart rate, temperature fluctuations, etc.), the biological sign characteristics of the user at a specific time point are analyzed using a data processing algorithm, and the biological sign transient state feature data is generated to describe the user's physiological state at each time point, and further capture the key feature changes in the biological rhythm. Clustering algorithms (such as K-means, DBSCAN, etc.) are applied to cluster the biological sign transient state feature data. By classifying similar transient state feature data, it is used to identify biological sign patterns under different states. Time points with similar physiological characteristics are grouped together to generate transient clustering data of biological signs. These clustering data can help analyze the changing trends of users' physiological states in different time periods. Based on the transient clustering data of biological signs, further biorhythm pattern analysis is performed to identify the biorhythm patterns corresponding to different clusters, and the patterns are classified through pre-set biorhythm pattern prescribed labels to generate biorhythm pattern data, which is used to describe various behavioral patterns of users' daily biorhythms, such as sleep, work, etc.

[0061] Preferably, the biorhythm pattern status assessment module includes the following functions:

[0062] Performing a biological sign transient state clustering baseline characteristic analysis based on the biological sign transient state clustering data to generate biological sign transient state clustering baseline characteristic data;

[0063] Perform a steady-state analysis of the biorhythm pattern on the transient clustering baseline characteristic data of biological signs according to the biorhythm pattern data to generate steady-state data of the biorhythm pattern;

[0064] Performing cluster subset deviation quantitative analysis on the transient state cluster data of biological signs to generate cluster subset deviation quantitative data of biological signs;

[0065] According to the stable state data of the biological rhythm pattern, the biological sign cluster subset deviation quantification data is processed for state evaluation of each biological rhythm pattern to generate biological rhythm pattern state evaluation data.

[0066] The present invention performs baseline feature analysis on the transient state clustering data of biological signs, extracts a stable physiological feature baseline from the transient state clustering, and these baseline feature data provide the physiological feature benchmark of the user in a normal state, which is helpful to identify the user's health level and rhythm balance state. This provides a reference for the subsequent rhythm pattern analysis, so that it can be judged whether the user is in a stable state of rhythm, and the corresponding light adjustment is adjusted according to the baseline features, thereby improving the accuracy and personalized adjustment ability of the system. Based on the biological rhythm pattern data, the transient state clustering baseline feature data is analyzed to evaluate whether the user's biological rhythm is in a stable state, and it can be identified whether the user's rhythm state is disturbed or fluctuates, and the stable state data of the rhythm pattern is generated, which provides a key basis for light control, so that the light adjustment can be optimized in real time according to the user's rhythm state, helping the user to maintain or restore rhythm stability, and improving health and comfort. By performing deviation quantification analysis on a subset of the transient state clustering data, the difference between the user's current physiological state and its normal baseline can be quantitatively evaluated. This deviation analysis can accurately identify the degree of abnormal changes or deviations in the user's biorhythm, thereby providing more refined data support for light adjustment, and providing corresponding light adjustment measures for different deviation amplitudes to ensure the accuracy and effectiveness of the adjustment. Combining the rhythm pattern stable state data and cluster subset deviation quantification data, a comprehensive assessment of the user's state under different rhythm modes is conducted to determine whether the user's biorhythm state is in different states such as normal, fluctuating, etc. This precise state assessment provides a highly personalized basis for subsequent light adjustment, allowing the light adjustment plan to be finely adjusted according to different rhythm states, thereby improving the adjustment effect and helping users maintain a healthy biorhythm.

[0067] As an example of the present invention, refer to Figure 2 As shown, Figure 1 The function flow diagram of the biorhythm pattern status evaluation module in this example includes:

[0068] S31: performing a biological sign transient state clustering baseline characteristic analysis based on the biological sign transient state clustering data to generate biological sign transient state clustering baseline characteristic data;

[0069] In the embodiment of the present invention, based on the transient state clustering data of biological signs, key features in the clustering data are extracted to perform baseline feature analysis. Baseline feature data are generated by calculating the center point or average value of each clustering group. These data are used to describe the typical state of each biological sign clustering group, ensuring that the generated baseline feature data can accurately represent the normal physiological state of the user and provide a basis for subsequent stability analysis.

[0070] S32: performing a stable state analysis of the biorhythm pattern on the transient state clustering baseline characteristic data of the biological signs according to the biorhythm pattern data to generate stable state data of the biorhythm pattern;

[0071] In the embodiment of the present invention, the biorhythm pattern data is used to perform stability analysis on the transient cluster baseline feature data of biological signs. By calculating the cluster baseline changes in each time period, the volatility and consistency of the biorhythm are evaluated, and the stable state data of the biorhythm pattern is generated. This analysis determines the fluctuation amplitude and time span of each cluster state to analyze whether the user's biorhythm pattern is in a stable state.

[0072] S33: performing cluster subset deviation quantitative analysis on the biological sign instantaneous state cluster data to generate biological sign cluster subset deviation quantitative data;

[0073] In the embodiment of the present invention, based on the transient state clustering data of biological signs, a deviation quantification analysis algorithm (such as mean square error or coefficient of variation) is applied to quantify the deviation of each cluster subset. By comparing the data of each subset with its corresponding baseline characteristics, the degree of deviation is calculated, and the deviation quantification data of the biological sign cluster subset is generated. These deviation data are used to evaluate whether each cluster subset is consistent with the baseline state or has significant deviations.

[0074] S34: performing state evaluation processing of each biorhythm pattern on the biological sign cluster subset deviation quantification data according to the biorhythm pattern stable state data to generate biorhythm pattern state evaluation data.

[0075] In the embodiment of the present invention, based on the stable state data of the biorhythm pattern, combined with the deviation quantification data of the biological sign cluster subset, the state evaluation processing of each type of biorhythm pattern is performed. In the specific operation, through multi-dimensional analysis, the stability and deviation degree of the biorhythm under each cluster state are calculated to generate the biorhythm pattern state evaluation data. This data provides an evaluation of the user's overall biorhythm state, such as whether the rhythm is normal, abnormal, or requires intervention.

[0076] Preferably, the interaction feature analysis module includes the following functions:

[0077] Performing data synchronization processing of the ambient light data and the biorhythm pattern state evaluation data according to the ambient light data and the biorhythm pattern state evaluation data to generate synchronized light-pattern state evaluation data;

[0078] An interactive feature analysis of ambient light and biorhythm pattern state assessment is performed based on the synchronized light-pattern state assessment data to generate light-pattern state assessment interactive feature data.

[0079] The present invention organically combines the lighting conditions in the current environment with the user's biorhythm state by synchronously processing the ambient lighting data and the biorhythm pattern state evaluation data. This synchronization process ensures that when adjusting the lighting in real time, not only the changes in ambient lighting are taken into account, but also the user's rhythmic state can be analyzed at the same time, and the ambient lighting conditions can be adaptively adjusted according to the user's current biorhythm needs. The lighting-mode state evaluation data generated by the synchronous processing provides integrated, multi-dimensional data support for subsequent analysis, which helps to improve the personalization and accuracy of lighting adjustment. By performing interactive feature analysis on the synchronized lighting-mode state evaluation data, the complex relationship between ambient lighting and the user's biorhythm pattern can be revealed. This interactive feature analysis not only helps the system understand how lighting changes affect the user's rhythmic state, but also identifies sensitive time nodes or parameters of lighting and rhythmic state. For example, different light intensities or color temperatures may have different effects on the user's physiological rhythm. By analyzing the interactive features, we can help find the lighting parameters that best suit the user's current rhythmic state. The generated interactive feature data provides more targeted guidance for lighting adjustment, ensuring that lighting adjustments are more in line with the user's immediate needs and maximizing the effectiveness of rhythm adjustment.

[0080] In an embodiment of the present invention, the ambient light data obtained from the ambient light sensor in the intelligent wearable device and the biorhythm pattern state evaluation data obtained by analysis are synchronously processed, and the light data and the biorhythm pattern data are aligned through the timestamp matching technology to ensure that the time series of the two are consistent, and synchronized light-mode state evaluation data is generated. This step is intended to provide an accurate data basis for subsequent interactive feature analysis. After the data synchronization processing is completed, interactive feature analysis is performed based on the synchronized light-mode state evaluation data, and algorithms such as multivariate regression analysis and correlation analysis are used to analyze the relationship between the lighting characteristics such as ambient light intensity and color temperature and the biorhythm pattern state, and extract key features that can reflect the interactive influence of the two, such as the state differences caused by various ambient lights under the same biorhythm mode, to generate light-mode state evaluation interactive feature data.

[0081] Preferably, the lighting demand model building module includes the following functions:

[0082] A decision-making mapping relationship between biological rhythm patterns and light requirements is established based on a preset decision tree algorithm to generate an initial rhythm pattern light requirement decision tree model;

[0083] Based on the biorhythm pattern data, the initial rhythm pattern light demand decision tree model is pruned for each biorhythm pattern to generate a rhythm pattern light demand decision tree model;

[0084] Performing a weighting process on the light-mode state evaluation interaction feature data for each biorhythm mode to generate weighted light-mode state evaluation interaction feature data;

[0085] Based on the weighted light-mode state evaluation interaction feature data, the rhythmic mode lighting demand decision tree model is trained and optimized to generate an optimized rhythmic mode lighting demand decision tree model.

[0086] The present invention establishes a mapping relationship of lighting requirements according to different biorhythm patterns through a preset decision tree algorithm, generates an initial rhythm pattern lighting requirement decision tree model, and clearly reflects the lighting conditions (such as light intensity, duration, etc.) required by the user under different biorhythm states. The model provides a basic framework for lighting regulation, ensuring that the system can effectively regulate lighting according to the rhythm pattern, laying the foundation for subsequent optimization and personalized adjustment. Decision tree pruning is a key step in optimizing the decision tree structure. Through pruning, redundant or unnecessary branches can be removed, and the decision model can be simplified. Pruning the initial decision tree model based on biorhythm pattern data can improve the efficiency and prediction accuracy of the model, respond to changes in rhythmic states more quickly, while maintaining the accuracy of decision-making, ensuring that the lighting regulation process is more efficient and smooth, and avoiding unnecessary complexity. The interactive feature data of light-mode state evaluation is weighted, and appropriate weights are assigned to each light parameter (such as intensity, color temperature, etc.) in different biorhythm modes. The light parameters can be more reasonably balanced and adjusted according to the user's current rhythmic state. The result of the weighted processing makes the light adjustment more flexible and accurate, and can give appropriate priority to different parameters according to actual needs, so as to achieve more accurate light regulation. By training and optimizing the model of the weighted interactive feature data, the adaptability and accuracy of the rhythmic mode light demand decision tree model can be improved. The optimized model better predicts the user's light demand under different rhythmic states and dynamically adjusts it according to the actual data. This optimization process makes the light control process more intelligent and adaptive, ensuring that the system can provide continuously optimized light solutions as the user's biorhythm changes.

[0087] As an example of the present invention, refer to Figure 3 As shown, Figure 1 Schematic diagram of the functional flow of the lighting demand model construction module in FIG. 1 . In this example, the functions of the lighting demand model construction module include:

[0088] S51: establishing a decision mapping relationship between the biological rhythm pattern and the light demand based on a preset decision tree algorithm, and generating an initial rhythm pattern light demand decision tree model;

[0089] In an embodiment of the present invention, a mapping relationship between a biological rhythm pattern and lighting requirements is established based on a preset decision tree algorithm. In specific implementation, the preset decision tree algorithm, as well as the collected biological rhythm pattern data (such as periodic changes in biological signs, peak and trough times, etc.) and historical lighting requirements data (such as light intensity, color temperature, etc.) are used to generate an initial rhythm pattern lighting requirements decision tree model. Through the branching structure in the decision tree, each node represents the lighting requirements of a specific biological rhythm pattern, thereby achieving a preliminary mapping of the biological rhythm pattern and the lighting requirements.

[0090] S52: performing decision tree pruning processing of each biological rhythm pattern on the initial rhythm pattern light demand decision tree model based on the biological rhythm pattern data to generate a rhythm pattern light demand decision tree model;

[0091] In an embodiment of the present invention, based on the biological rhythm pattern data, the initial rhythm pattern lighting demand decision tree model is pruned to optimize its complexity, and by analyzing the lighting demand characteristics under each biological rhythm pattern, it is determined whether certain branches contain redundant or irrelevant information. Through a pruning algorithm (such as a CART or ID3 pruning algorithm), nodes and branches that have little impact on the model prediction effect are deleted to reduce overfitting and generate a simplified rhythm pattern lighting demand decision tree model. The pruned model is more efficient, can reduce computing resource usage, and improve the generalization ability of the model.

[0092] S53: performing a weighting process on the light-mode state evaluation interaction feature data for each biorhythm mode to generate weighted light-mode state evaluation interaction feature data;

[0093] In the embodiment of the present invention, the illumination parameters of each biorhythm pattern are weighted based on the illumination-mode state evaluation interactive feature data, and the correlation between the illumination intensity, color temperature and other parameters and the biorhythm pattern state is analyzed, and a different weight value is assigned to each illumination parameter using the weighted average method or the information gain method. The size of the weight value is determined according to the degree of influence of the illumination parameter on the biorhythm pattern, and the weighted illumination-mode state evaluation interactive feature data is generated, including the ambient illumination corresponding to each biorhythm pattern state, and the weight information corresponding to each ambient illumination feature information, to ensure that the influence of different illumination parameters on each biorhythm pattern can be accurately captured in the subsequent model optimization process.

[0094] S54: Based on the weighted light-mode state evaluation interaction feature data, the rhythmic mode light demand decision tree model is trained and optimized to generate an optimized rhythmic mode light demand decision tree model.

[0095] In an embodiment of the present invention, the rhythmic pattern lighting demand decision tree model is trained and optimized based on the weighted lighting-mode state evaluation interaction feature data. The system adopts a supervised learning method, such as a gradient descent algorithm, and uses historical data for iterative model training to gradually adjust the weights and branch structures in the decision tree. By repeatedly optimizing the model parameters, it can better adapt to individualized lighting needs, and finally generate an optimized rhythmic pattern lighting demand decision tree model. The optimized model can more accurately predict the user's lighting needs under different biorhythm states, thereby improving the accuracy and responsiveness of the overall system.

[0096] Preferably, the step of weighting the illumination parameters of each biorhythm mode on the illumination-mode state assessment interaction feature data comprises:

[0097] Extracting time series data from the illumination-mode state evaluation interaction feature data to generate illumination-mode state evaluation interaction feature time series data;

[0098] Perform time-series light sensitivity factor analysis of each biorhythm mode based on the light-mode state evaluation interaction feature time-series data to generate time-series light sensitivity factor data;

[0099] Based on the time-series light sensitivity factor data, the light-mode state assessment interactive feature data is weighted by assigning the light parameters of each biorhythm mode to generate weighted light-mode state assessment interactive feature data.

[0100] The present invention extracts time series data from the interactive feature data of the light-mode state evaluation, identifies the time dependence between the light and the biorhythm mode, enables the system to analyze how the light conditions affect the rhythm changes of the user over time, and captures the dynamic characteristics of the light parameters. The generated time series data lays the foundation for subsequent analysis, ensuring that the system can make more accurate adjustments based on the changing laws of historical light and rhythm states, making the light adjustment scheme more timely. Through the analysis of time series light sensitivity factors, the user's sensitivity to specific light parameters under different biorhythm modes is identified, which helps to discover the influence of certain specific light conditions (such as intensity, color temperature, etc.) on various biorhythm modes at different times. The extraction of this sensitive factor enables more accurate light adjustment to be given to different biorhythm modes, so that the light adjustment is more targeted and more in line with the actual needs of the user, avoiding unnecessary intervention. Different light parameters are weighted according to the time series light sensitivity factor data, and the priority of each light parameter is dynamically adjusted under different biorhythm modes. The weighted processing ensures that the system can make corresponding weight adjustments for the lighting factors with greater influence when adjusting the lighting, improving the flexibility and accuracy of the adjustment. The generated weighted data makes the lighting adjustment more personalized and can fully adapt to the specific needs of users in different rhythmic states.

[0101] In the embodiment of the present invention, when processing the interactive characteristic data of light-mode state evaluation, it is necessary to extract the interactive characteristic data in time series, rearrange and segment the light data and the biorhythm pattern state data according to the time dimension, and generate the interactive characteristic time series data of light-mode state evaluation, which can capture the correlation between the light characteristics and the biorhythm pattern state that change over time, and ensure that the time series data can reflect the dynamic relationship between light and the biorhythm pattern. Time series data extraction is the basis for subsequent analysis, ensuring that the characteristic data is aligned and processed in time order. After generating the interactive characteristic time series data of light-mode state evaluation, the system will perform time series light sensitivity factor analysis of each biorhythm pattern based on these time series data. The system uses time series analysis methods (such as autocorrelation analysis, time series regression analysis) to identify the sensitivity factors between light parameters (such as light intensity, color temperature, light duration, etc.) and the biorhythm pattern state, and generates time series light sensitivity factor data by analyzing the influence of light parameters on biorhythms at different times. Each light sensitivity factor represents the degree of influence of a certain light parameter on a specific biorhythm pattern in a specific time period. These sensitivity factor data will serve as an important basis for subsequent weight assignment. After obtaining the time-series light sensitivity factor data, the light-mode state evaluation interactive feature data will be weighted for the light parameters based on these sensitivity factors. Different weights are assigned to each light parameter according to the size of the time-series light sensitivity factor. The weight value reflects the degree of influence of the light parameter on the specific biorhythm pattern. The weight assignment adopts a weighted analysis method, such as the information gain method or the weighted regression analysis method, to ensure that the weight of the light parameter is proportional to its sensitivity factor data. The generated weighted light-mode state evaluation interactive feature data contains the relative importance of different light parameters in each biorhythm mode, which can provide accurate input data for the subsequent optimization and training of the decision tree model, ensuring that the influence of the light parameters is accurately modeled to improve the model's ability to predict the light demand of individual biorhythms.

[0102] Preferably, the model training optimization processing of the rhythmic mode lighting demand decision tree model based on the weighted lighting-mode state evaluation interaction feature data includes:

[0103] The weighted light-mode state assessment interaction feature data is transmitted to the rhythmic pattern light demand decision tree model. In the rhythmic pattern light demand decision tree model, the weighted light-mode state assessment interaction feature data is used to learn the optimal light demand nodes of each biological rhythm pattern through the gradient descent algorithm to generate an optimized rhythmic pattern light demand decision tree model.

[0104] The present invention transmits the weighted light-mode state evaluation interactive feature data to the decision tree model, comprehensively considers the weight information of different light parameters, so that the decision tree model can make more accurate light demand predictions according to each weighted parameter, ensures that the light regulation model reasonably distributes the importance of each light parameter in the decision-making process, and improves the responsiveness and pertinence of the decision tree model, so that the light regulation is more accurate and personalized. Through the gradient descent algorithm, the decision tree model learns based on the weighted light-mode state evaluation data, finds the best light demand node adapted to different biorhythm modes, and the application of the gradient descent algorithm enables the model to continuously optimize its light demand prediction, quickly converges to the optimal solution, improves the accuracy and adaptability of the decision tree model, enables the system to better adjust the light parameters according to the individual differences and dynamic changes of users, and provides a more accurate light regulation scheme. After learning and optimizing the gradient descent algorithm, the generated optimized rhythmic mode light demand decision tree model can more accurately predict the best light demand under different biorhythm modes, making the light regulation process more intelligent and personalized, and can better meet the actual needs of users under different biorhythm states.

[0105] In an embodiment of the present invention, during the model training optimization process, the weighted light-mode state evaluation interactive feature data processed by weight assignment is transmitted to the rhythmic mode lighting demand decision tree model, and these data are loaded into the model according to a predefined input format, including the weight information of different lighting parameters (such as light intensity, color temperature, duration, etc.) under each biological rhythm mode state. The decision tree model corresponding to each type of biological rhythm mode receives these weighted data to further learn the lighting demand node during the training process. The transmission of data must ensure consistent format and time series alignment to ensure that the associated information of different biological rhythm modes and lighting conditions is accurately input into the decision tree model. After receiving the weighted light-mode state evaluation interactive feature data, the decision tree model enters the training optimization stage, and the gradient descent algorithm is used to learn the model nodes. The gradient descent algorithm calculates the error between the prediction result output by the model and the actual lighting demand data (usually calculated by the loss function), and adjusts the parameters of the decision tree inversely according to the gradient of the error, and gradually updates the weight and decision path of each node. Through the iterative learning process, the optimal lighting demand node under each biorhythm mode is found at each branch of the tree, and the model gradually approaches the optimal decision path, so that the model can more accurately predict the user's lighting needs under a specific biorhythm state. After the gradient descent algorithm completes multiple iterative updates, each node of the model has been fully learned, and an optimized rhythmic pattern lighting demand decision tree model is generated based on the learning results. This optimization model has adjusted the lighting demand under different biorhythm pattern states through the node learning process to ensure that each node can accurately reflect the relationship between lighting parameters and rhythmic patterns. The final generated optimized rhythmic pattern lighting demand decision tree model has a more accurate and efficient prediction capability, and can provide users with more personalized and dynamic lighting demand recommendations.

[0106] Preferably, the rhythm pattern trend model building module includes the following functions:

[0107] Extracting biorhythm pattern time series features from biological sign time series data according to the biorhythm pattern data to generate biorhythm pattern time series feature data;

[0108] Performing periodic characteristic analysis of the biorhythm pattern on the biorhythm pattern time series characteristic data to generate periodic characteristic data of the biorhythm pattern;

[0109] Based on the periodic characteristic data of the biorhythm pattern, a biorhythm pattern change trend model is designed to generate a biorhythm pattern change trend model.

[0110] The present invention combines and analyzes the biorhythm pattern data with the biological sign time series data, extracts the time series characteristic data of the user's biorhythm pattern, reflects the changing trend of the user's physiological state at different time points, enables the system to capture the dynamic changing law of the user's biorhythm, provides a more comprehensive time dimension basis for subsequent light adjustment, makes the light adjustment more adaptable to the user's actual rhythm fluctuation, and improves the accuracy of adjustment. The periodic characteristic analysis of the time series characteristic data can identify the periodic law of the user's biorhythm pattern, understand the changing trend of the user's biorhythm in different time periods, and predict the pattern of the user's physiological state changing over time, ensuring that the light adjustment can be adjusted in advance according to the user's periodic rhythm needs, making the light adjustment more accurate and forward-looking. Using the periodic characteristic data of the biorhythm pattern, a trend model reflecting the changes in the user's biorhythm is designed to predict the changing trend of the user's future biorhythm, and provide advance strategic guidance for light adjustment. The design of this trend model enables the user's rhythm changes to be foreseen and corresponding adjustments to be made, improves the intelligence and adaptability of the light system, and makes the light adjustment more predictable and accurate.

[0111] In the embodiment of the present invention, the biological sign time series data is extracted based on the biological rhythm pattern data, and the key change patterns in the biological sign data, such as the fluctuation trend of heart rate, body temperature, etc. over time, are identified through time series analysis technology (such as autocorrelation analysis, fast Fourier transform FFT, etc.), and these biological sign time series data are preprocessed, including denoising, smoothing and normalization operations, to ensure the continuity and accuracy of the data. Afterwards, the key feature points in the biological rhythm pattern, such as peak period, trough period, cycle starting point, etc., are identified through feature extraction algorithms (such as peak detection, local extreme value analysis, etc.) and biological rhythm pattern data, so as to generate biological rhythm pattern time series feature data, which reflects the periodic change law of the user's physiological rhythm at different times, as the basis for subsequent periodic analysis. The biological rhythm pattern time series feature data is subjected to periodic feature analysis, and the periodic change characteristics in the biological rhythm pattern are identified by using a period detection algorithm (such as periodogram analysis, discrete wavelet transform DWT, etc.). By analyzing the repeated fluctuations of biological signs over time, the main period length and frequency of each biological rhythm pattern are determined, and its inherent periodic structure is identified. The generated periodic characteristic data of the biorhythm pattern contains the cycle length, phase and amplitude information of different physiological states (such as sleep, activity, rest, etc.), and further understands how the user's biorhythm cycle changes over time. These periodic characteristic data are used to model the long-term change trend of the biorhythm. Based on the periodic characteristic data of the biorhythm pattern, the biorhythm pattern change trend model is designed, and the periodic characteristic data is analyzed using time series prediction algorithms (such as ARIMA model, long short-term memory network LSTM, etc.) to predict the future change trend of the biorhythm. By learning the change trajectory of the past biorhythm pattern, a trend model that can predict future rhythm changes is constructed. The trend model captures the long-term change signals in the biorhythm pattern, such as the lengthening, shortening or phase shift of the cycle, and finally generates a biorhythm pattern change trend model.

[0112] Preferably, the rhythm regulation lighting parameter control module includes the following functions:

[0113] Performing real-time biorhythm pattern analysis and processing according to biological sign data to generate real-time biorhythm pattern data;

[0114] Transmitting the instant biorhythm pattern data to the biorhythm pattern change trend model for biorhythm pattern change trend prediction processing to generate biorhythm pattern change trend data;

[0115] Performing biorhythm pattern change feature extraction processing on the biorhythm pattern time series feature data to generate biorhythm pattern change feature data; performing instant update time period design for each biorhythm pattern based on the biorhythm pattern change feature data to generate biorhythm pattern instant update time period data;

[0116] Based on the biorhythm pattern instant update time period data, the biorhythm pattern change trend data is updated in real time to generate the real-time biorhythm pattern change trend data;

[0117] The real-time biorhythm pattern change trend data is transmitted to the optimized rhythm pattern lighting demand decision tree model for intelligent analysis and processing of rhythm lighting demand to generate intelligent rhythm lighting demand data;

[0118] Design intelligent rhythmic lighting control parameters according to intelligent rhythmic lighting demand data and generate intelligent rhythmic lighting control parameters;

[0119] Perform rhythmic adjustment lighting parameter control operations based on intelligent rhythmic lighting control parameters.

[0120] The present invention instantly analyzes the biological sign data, captures the user's current biorhythm state in real time, quickly adapts to the user's immediate needs, ensures that the light adjustment can accurately respond to the user's current rhythmic situation, and the generation of instant biorhythm pattern data provides real-time data support for subsequent light adjustment, improving the dynamics and flexibility of the adjustment. The instant biorhythm pattern data is transmitted to the trend model to predict the future change trend of the user's biorhythm, so that the light adjustment is no longer a passive response to the current state, but has forward-looking, and can adjust the light in advance to cope with the user's upcoming biorhythm changes, improving the system's predictability and adjustment effect. Extract the change characteristics of the biorhythm pattern, identify the potential change trend of the user's biorhythm, and timely adjust the understanding of the user's biorhythm, and reasonably design the instant update time period of each biorhythm pattern according to the change characteristics, and adjust it in the appropriate time period according to the user's latest state, further improving the accuracy and timeliness of light adjustment. By updating the data of the time period in real time, the trend data of the biorhythm pattern is dynamically corrected to ensure that the prediction is closer to the user's current actual state. This real-time update process enables rapid response to changes in biorhythms and adjusts the lighting requirements according to the latest trend forecasts to ensure the real-time and forward-looking nature of lighting adjustment. The change trend data is transmitted to the optimized decision tree model, which can be intelligently analyzed according to the user's current state and trend forecasts. Combined with historical data and real-time trends, it provides highly accurate guidance for the lighting adjustment plan, ensuring that the prediction of lighting requirements is more in line with the user's personalized rhythm changes and improving the accuracy and intelligence of the lighting adjustment plan. Designing lighting control parameters based on the results of intelligent analysis can generate the lighting adjustment plan that best suits the user's current biorhythm state. Intelligent parameter design ensures high personalization and accuracy of lighting adjustment, and can quickly adjust lighting parameters to ensure that users obtain the best lighting environment, thereby improving user comfort and experience. The system performs adjustment operations based on the intelligently designed lighting control parameters, ensuring the effective implementation of the lighting adjustment plan, enabling the lighting environment to adapt to the user's biorhythm needs in real time, further improving the response speed and accuracy of lighting control, and helping users better adapt to the environment.

[0121] In an embodiment of the present invention, by collecting real-time biological sign data (such as heart rate, respiratory rate, body temperature, etc.), combined with the existing biorhythm pattern analysis method, an immediate biorhythm pattern analysis process is performed, the current biorhythm pattern is extracted from the real-time data, and the immediate biorhythm pattern data is generated. This data is used to reflect the user's current physiological state and ensure that the light adjustment can be adjusted based on the user's immediate rhythm needs. The generated immediate biorhythm pattern data is transmitted to the biorhythm pattern change trend model, and the biorhythm pattern change trend prediction process is performed. According to the previously designed trend model (such as ARIMA or LSTM model), the immediate rhythm pattern data is trend predicted, and the direction and amplitude of the biorhythm change in the future period of time are calculated, and the biorhythm pattern change trend data is generated to help the system predict the possible future change trend of the user's biorhythm, and provide a forward-looking guidance basis for subsequent light adjustment. The biorhythm pattern change feature extraction is performed on the existing biorhythm pattern time series feature data. By analyzing the key nodes in the biorhythm time series (such as cycle peaks, troughs, turning points, etc.), combined with the prediction results of the trend model, the key feature data reflecting the characteristics of biorhythm changes are extracted to generate biorhythm pattern change feature data. This feature data is used to reveal the significant changes that may occur in the user's biorhythm in the future, providing a basis for further design of lighting control strategies. After obtaining the biorhythm pattern change feature data, the system will design the instant update time period for each biorhythm pattern based on these features. According to the periodicity and current state of the rhythm, the key time period suitable for rhythm regulation is designed. These time periods usually include the turning points of the biorhythm or the positions with the largest fluctuations, and the biorhythm pattern instant update time period data is generated. This data determines the optimal time window for light regulation to ensure that light intervention can effectively affect the user's biorhythm. After obtaining the real-time update time period data of the biorhythm pattern, the system will update the previously generated biorhythm pattern change trend data based on these time periods, recalculate the real-time impact of lighting parameters on biorhythms, and dynamically adjust the prediction model to generate real-time biorhythm pattern change trend data. This update process ensures that the model can timely reflect the user's current biorhythm changes and provide the latest rhythm trend information for subsequent lighting demand analysis. The real-time biorhythm pattern change trend data is transmitted to the optimized rhythm pattern lighting demand decision tree model for intelligent analysis of rhythm lighting demand. The model intelligently analyzes the user's lighting demand parameters (such as light intensity, duration, color temperature, etc.) under different rhythmic states based on the current rhythm pattern change trend and historical data, and generates intelligent rhythm lighting demand data to ensure that users can obtain the best lighting environment at different time periods and different biorhythm states.According to the intelligent rhythmic lighting demand data, specific intelligent rhythmic lighting control parameters are designed. According to the parameters in the lighting demand data (such as light intensity, color temperature, time, etc.), combined with the lighting conditions of the user's current environment, the lighting control strategy is dynamically adjusted to generate intelligent rhythmic lighting control parameters to ensure that the lighting adjustment matches the user's current biorhythm needs. After the intelligent rhythmic lighting control parameters are determined, the rhythmic adjustment lighting parameter control operation is finally executed. By controlling the lighting equipment (such as adjusting the brightness and color temperature of the lamps), the ambient lighting conditions are automatically adjusted to match the user's current biorhythm state, the lighting effects are regularly monitored, and the lighting parameters are continuously adjusted according to real-time feedback to ensure that the adjustment effect is as expected and help users maintain a healthy biorhythm.

[0122] This specification provides a rhythmic lighting parameter control method for executing the rhythmic lighting parameter control system as described above. The rhythmic lighting parameter control method includes:

[0123] Step S1: collecting user perception data according to the smart wearable sensor to generate user perception data, wherein the user perception data includes ambient light data and biological sign data;

[0124] Step S2: performing biological sign time series identification analysis based on the biological sign data to generate biological sign time series data; performing biological rhythm pattern analysis and processing based on the biological sign time series data to generate biological rhythm pattern data;

[0125] Step S3: performing a stable state analysis of the biorhythm pattern based on the biorhythm pattern data to generate stable state data of the biorhythm pattern; performing a state evaluation process of each biorhythm pattern based on the stable state data of the biorhythm pattern to generate state evaluation data of the biorhythm pattern;

[0126] Step S4: performing interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data to generate light-pattern state assessment interactive feature data;

[0127] Step S5: Design the mapping relationship of the light demand decision under each biological rhythm mode based on the preset decision tree algorithm and the biological rhythm mode data, and generate a rhythm mode light demand decision tree model; perform decision tree training optimization processing on the rhythm mode light demand decision tree model using the light-state interaction feature data, and generate an optimized rhythm mode light demand decision tree model;

[0128] Step S6: Analyze the periodic characteristics of the biorhythm pattern on the biological sign time series data according to the biorhythm pattern data to generate the periodic characteristic data of the biorhythm pattern; design a biorhythm pattern change trend model based on the periodic characteristic data of the biorhythm pattern to generate the biorhythm pattern change trend model;

[0129] Step S7: Performing real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; performing real-time biorhythm pattern change trend analysis and processing on the real-time biorhythm pattern data based on the biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; transmitting the real-time biorhythm pattern change trend data to the optimized rhythmic pattern lighting demand decision tree model to perform intelligent analysis and processing of rhythmic lighting demand to generate intelligent rhythmic lighting demand data; executing rhythmic lighting parameter control operations based on rhythmic lighting intelligent adjustment control parameters.

[0130] The beneficial effect of the present application is that the present invention collects the user's biological sign data through an intelligent wearable device, and performs biological sign time series identification analysis and biorhythm pattern analysis, generates the user's biorhythm pattern through multi-level data analysis and clustering methods, and performs accurate light adjustment based on each of the user's biorhythm patterns. This real-time perception and analysis based on the user's individual biological signs effectively solves the problem of being unable to accurately collect and analyze the user's biological sign data, ensuring that the light adjustment can accurately match the user's actual biorhythm needs. A mathematical model of the mapping relationship of light demand decisions is designed through a decision tree algorithm and biorhythm pattern data, and the model is trained and optimized to achieve intelligent decision analysis of light adjustment needs. Unlike a fixed mode or a preset schedule, it can dynamically adjust the light parameters according to the user's current biological signs and rhythmic state to achieve personalized and intelligent light control. This intelligent decision-making ability ensures that light adjustment is more in line with the user's actual needs and improves the user experience. Through the biorhythm pattern change trend model and the real-time update of the biorhythm pattern trend prediction, the user's biorhythm is analyzed for periodic characteristics and trend prediction. Not only can the current biorhythm be adjusted, but also the lighting parameters can be adjusted in advance based on future rhythm change trends to achieve adaptive lighting control. This solves the problem of only being able to make simple adjustments to the current state, and can provide users with more accurate rhythm management and health intervention, especially in long-term lighting regulation.

[0131] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0132] 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. A rhythmic lighting parameter control system, characterized in that: Includes the following modules: A user perception data collection module, used to collect user perception data according to the smart wearable sensor and generate user perception data, wherein the user perception data includes ambient light data and biological sign data; The biorhythm pattern analysis module is used to perform biorhythm time series identification analysis based on the biorhythm data to generate biorhythm time series data; perform biorhythm pattern analysis and processing based on the biorhythm time series data to generate biorhythm pattern data; The biorhythm pattern state evaluation module is used to analyze the stable state of the biorhythm pattern based on the biorhythm pattern data to generate the biorhythm pattern stable state data; perform state evaluation processing of each biorhythm pattern based on the biorhythm pattern stable state data to generate the biorhythm pattern state evaluation data; An interactive feature analysis module, used to perform interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data, and generate light-pattern state assessment interactive feature data; The light demand model building module is used to establish a decision mapping relationship between the biological rhythm pattern and the light demand based on a preset decision tree algorithm, and generate an initial rhythm pattern light demand decision tree model; the initial personalized biological rhythm light demand model is optimized by multi-source decision tree pruning training using light-state interaction feature data, and an optimized rhythm pattern light demand decision tree model is generated; A rhythm pattern trend model building module is used to analyze the periodic characteristics of the biological rhythm pattern on the biological sign time series data according to the biological rhythm pattern data, and generate the periodic characteristic data of the biological rhythm pattern; Design a biorhythm pattern change trend model based on the periodic characteristic data of the biorhythm pattern, and generate a biorhythm pattern change trend model; A rhythm-regulated illumination parameter control module is used to perform real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; Performing real-time biorhythm pattern change trend analysis and processing on the real-time biorhythm pattern data based on the biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; The real-time biorhythm pattern change trend data is transmitted to the optimized rhythm pattern lighting demand decision tree model for intelligent analysis and processing of rhythm lighting demand to generate intelligent rhythm lighting demand data; Based on the rhythmic lighting intelligent adjustment control parameters, the rhythmic lighting parameter control operation is performed.

2. The rhythm-regulated illumination parameter control system according to claim 1, characterized in that: The biorhythm pattern analysis module has the following functions: Performing biological sign time series identification analysis according to the biological sign data to generate biological sign time series data; Performing biological sign transient characteristic data analysis according to biological sign time series data to generate biological sign transient characteristic data; Performing biological sign transient state clustering analysis on biological sign transient state feature data to generate biological sign transient state clustering data; The biorhythm pattern analysis is performed based on the transient clustering data of biological signs to generate biorhythm pattern data.

3. The rhythm-regulated illumination parameter control system according to claim 2, characterized in that: The biorhythm pattern status assessment module includes the following functions: Performing a biological sign transient state clustering baseline characteristic analysis based on the biological sign transient state clustering data to generate biological sign transient state clustering baseline characteristic data; Perform a steady-state analysis of the biorhythm pattern on the transient clustering baseline characteristic data of biological signs according to the biorhythm pattern data to generate steady-state data of the biorhythm pattern; Performing cluster subset deviation quantitative analysis on the transient state cluster data of biological signs to generate cluster subset deviation quantitative data of biological signs; According to the stable state data of the biological rhythm pattern, the biological sign cluster subset deviation quantification data is processed for state evaluation of each biological rhythm pattern to generate biological rhythm pattern state evaluation data.

4. The rhythm-regulated illumination parameter control system according to claim 1, characterized in that: The interactive feature analysis module includes the following functions: Performing data synchronization processing of the ambient light data and the biorhythm pattern state evaluation data according to the ambient light data and the biorhythm pattern state evaluation data to generate synchronized light-pattern state evaluation data; An interactive feature analysis of ambient light and biorhythm pattern state assessment is performed based on the synchronized light-pattern state assessment data to generate light-pattern state assessment interactive feature data.

5. The rhythmic lighting parameter control system according to claim 1, characterized in that: The lighting demand model building module includes the following functions: A decision-making mapping relationship between biological rhythm patterns and light requirements is established based on a preset decision tree algorithm to generate an initial rhythm pattern light requirement decision tree model; Based on the biorhythm pattern data, the initial rhythm pattern light demand decision tree model is pruned for each biorhythm pattern to generate a rhythm pattern light demand decision tree model; Performing a weighting process on the light-mode state evaluation interaction feature data for each biorhythm mode to generate weighted light-mode state evaluation interaction feature data; Based on the weighted light-mode state evaluation interaction feature data, the rhythmic mode lighting demand decision tree model is trained and optimized to generate an optimized rhythmic mode lighting demand decision tree model.

6. The rhythm-regulated illumination parameter control system according to claim 5, characterized in that: The step of weighting the illumination parameters of each biorhythm mode on the illumination-mode state evaluation interaction feature data comprises: Extracting time series data from the illumination-mode state evaluation interaction feature data to generate illumination-mode state evaluation interaction feature time series data; Perform time-series light sensitivity factor analysis of each biorhythm mode based on the light-mode state evaluation interaction feature time-series data to generate time-series light sensitivity factor data; Based on the time-series light sensitivity factor data, the light-mode state assessment interactive feature data is weighted by assigning the light parameters of each biorhythm mode to generate weighted light-mode state assessment interactive feature data.

7. The rhythm-regulated illumination parameter control system according to claim 5, characterized in that: The model training optimization processing of the rhythmic mode lighting demand decision tree model based on the weighted lighting-mode state evaluation interaction feature data includes: The weighted light-mode state assessment interaction feature data is transmitted to the rhythmic pattern light demand decision tree model. In the rhythmic pattern light demand decision tree model, the weighted light-mode state assessment interaction feature data is used to learn the optimal light demand nodes of each biological rhythm pattern through the gradient descent algorithm to generate an optimized rhythmic pattern light demand decision tree model.

8. The rhythm-regulated illumination parameter control system according to claim 1, characterized in that: The rhythm pattern trend model building module includes the following functions: Extracting biorhythm pattern time series features from biological sign time series data according to the biorhythm pattern data to generate biorhythm pattern time series feature data; Performing periodic characteristic analysis of the biorhythm pattern on the biorhythm pattern time series characteristic data to generate periodic characteristic data of the biorhythm pattern; Based on the periodic characteristic data of the biorhythm pattern, a biorhythm pattern change trend model is designed to generate a biorhythm pattern change trend model.

9. The rhythm-regulated illumination parameter control system according to claim 1, characterized in that: The rhythm regulation lighting parameter control module includes the following functions: Performing real-time biorhythm pattern analysis and processing according to biological sign data to generate real-time biorhythm pattern data; Transmitting the instant biorhythm pattern data to the biorhythm pattern change trend model for biorhythm pattern change trend prediction processing to generate biorhythm pattern change trend data; Performing biorhythm pattern change feature extraction processing on the biorhythm pattern time series feature data to generate biorhythm pattern change feature data; Design the instant update time period of each biorhythm pattern according to the biorhythm pattern change characteristic data, and generate the biorhythm pattern instant update time period data; Based on the biorhythm pattern instant update time period data, the biorhythm pattern change trend data is updated in real time to generate the real-time biorhythm pattern change trend data; The real-time biorhythm pattern change trend data is transmitted to the optimized rhythm pattern lighting demand decision tree model for intelligent analysis and processing of rhythm lighting demand to generate intelligent rhythm lighting demand data; Design intelligent rhythmic lighting control parameters according to intelligent rhythmic lighting demand data and generate intelligent rhythmic lighting control parameters; Perform rhythmic adjustment lighting parameter control operations based on intelligent rhythmic lighting control parameters.

10. A method for controlling rhythmic illumination parameters, characterized in that: Used to execute the rhythm-regulated lighting parameter control system as claimed in claim 1, the rhythm-regulated lighting parameter control method comprising: Step S1: collecting user perception data according to the smart wearable sensor to generate user perception data, wherein the user perception data includes ambient light data and biological sign data; Step S2: performing biological sign time series identification analysis based on the biological sign data to generate biological sign time series data; performing biological rhythm pattern analysis and processing based on the biological sign time series data to generate biological rhythm pattern data; Step S3: performing a stable state analysis of the biorhythm pattern based on the biorhythm pattern data to generate stable state data of the biorhythm pattern; performing a state evaluation process of each biorhythm pattern based on the stable state data of the biorhythm pattern to generate state evaluation data of the biorhythm pattern; Step S4: performing interactive feature analysis of ambient light and biorhythm pattern state assessment based on ambient light data and biorhythm pattern state assessment data to generate light-pattern state assessment interactive feature data; Step S5: Design the mapping relationship of the light demand decision under each biological rhythm mode based on the preset decision tree algorithm and the biological rhythm mode data, and generate a rhythm mode light demand decision tree model; perform decision tree training optimization processing on the rhythm mode light demand decision tree model using the light-state interaction feature data, and generate an optimized rhythm mode light demand decision tree model; Step S6: Analyze the periodic characteristics of the biorhythm pattern on the biological sign time series data according to the biorhythm pattern data to generate the periodic characteristic data of the biorhythm pattern; design a biorhythm pattern change trend model based on the periodic characteristic data of the biorhythm pattern to generate the biorhythm pattern change trend model; Step S7: Performing real-time biorhythm pattern analysis and processing based on biological sign data to generate real-time biorhythm pattern data; performing real-time biorhythm pattern change trend analysis and processing on the real-time biorhythm pattern data based on the biorhythm pattern change trend model to generate real-time biorhythm pattern change trend data; transmitting the real-time biorhythm pattern change trend data to the optimized rhythmic pattern lighting demand decision tree model to perform intelligent analysis and processing of rhythmic lighting demand to generate intelligent rhythmic lighting demand data; executing rhythmic lighting parameter control operations based on rhythmic lighting intelligent adjustment control parameters.

Images