Intelligent sleep-aiding control system and method integrating phototherapy and biological rhythm

Abstract

The invention discloses an intelligent sleep-aiding control system and method integrating phototherapy and biological rhythm, and the system comprises a biological rhythm monitoring device which is used for collecting the biological rhythm data of a user, and transmitting the data to a computing terminal through a Bluetooth module; the computing terminal is used for analyzing the biological rhythm data through a sleep staging algorithm, judging the current sleep stage of the user, generating a corresponding control instruction and transmitting the control instruction to the intelligent sleep-aiding phototherapy pillow through the Bluetooth module; the intelligent sleep-aiding phototherapy pillow is used for adjusting the phototherapy function in real time according to the received control instruction so as to adapt to the current sleep stage of the user, and therefore automatic control and real-time adjustment of the sleep process of the user are achieved. By accurately simulating the change of natural light, adjusting the biological clock of the user, optimizing the sleep-aiding effect, improving the intelligent level, simplifying the system structure and reducing the cost, the requirements for an efficient and intelligent sleep-aiding system in modern life are met.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent wearable devices, and particularly relates to an intelligent sleep aid control system and method integrating light therapy and biological rhythm. Background Art

[0002] With the acceleration of the modern life rhythm, sleep disorders have become a health problem faced by more and more people. Existing sleep aid systems still have some deficiencies in terms of functional perfection, intelligent level, user experience, etc., which affect the sleep aid effect and market acceptance. For example, a sleep aid intelligent sofa with the publication number CN113995263B can promote users to fall asleep through physical means, but lacks comprehensive consideration of light therapy and biological rhythm regulation, and cannot simulate the light changes in the natural environment, affecting the comprehensiveness and persistence of the sleep aid effect. An intelligent sleep aid robot with the publication number CN111991672B combines various sleep aid means, but lacks precise regulation of individual biological rhythms and still cannot fully simulate the change law of natural light, affecting the personalization and scientific nature of the sleep aid effect. In addition, the robot system is relatively complex, with high costs, not easy to popularize, and there may be room for optimization in the collaborative work of some modules, and the user experience needs to be improved. Summary of the Invention

[0003] In view of the deficiencies of the prior art, the present invention proposes an intelligent sleep aid control system and method integrating light therapy and biological rhythm, which can adjust the user's biological clock by precisely simulating the changes of natural light, optimize the sleep aid effect, improve the intelligent level, simplify the system structure, reduce costs, and meet the requirements for an efficient and intelligent sleep aid system in modern life.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] An intelligent sleep aid control system integrating light therapy and biological rhythm, comprising: a biological rhythm monitoring device, a computing terminal, a Bluetooth module, and an intelligent sleep aid light therapy pillow;

[0006] The biological rhythm monitoring device is used to collect the biological rhythm data of the user and transmit the data to the computing terminal through the Bluetooth module;

[0007] The computing terminal is used to analyze the biological rhythm data through a sleep staging algorithm, determine the user's current sleep stage, generate corresponding control instructions, and transmit the control instructions to the intelligent sleep aid light therapy pillow through the Bluetooth module;

[0008] The intelligent sleep aid light therapy pillow is used to adjust the light therapy function in real time according to the received control instructions to adapt to the user's current sleep stage, thereby realizing the automatic control and real-time adjustment of the user's sleep process.

[0009] Preferably, the biological rhythm monitoring device is built-in with multiple sensors, including a body temperature sensor, a heart rate sensor, and a respiratory rate sensor;

[0010] The biological rhythm data includes but is not limited to: body temperature change rate, heart rate change rate, respiratory rate change rate, and electroencephalogram characteristics.

[0011] Preferably, the computing terminal includes: a preprocessing unit and an analysis unit;

[0012] The preprocessing unit is used to preprocess the biological rhythm data, including filtering and smoothing to remove noise;

[0013] The analysis unit is used to integrate multiple preprocessed biological rhythm data by introducing a multi-modal fusion model, comprehensively monitor and analyze the user's sleep state, and determine the user's current sleep stage;

[0014] Among them, the multi-modal fusion model includes: an input branch, a feature extraction layer, a feature fusion layer, and a subsequent processing layer;

[0015] The input branch is used to design an independent input branch for each modality. Each branch is responsible for processing the data of one modality and extracting the features of that modality;

[0016] The feature extraction layer is used to extract features from the input data using neural network layers in each branch;

[0017] The feature fusion layer is used to fuse the features of different modalities at the intermediate layer after feature extraction;

[0018] The subsequent processing layer is used to generate the final prediction result based on the fused feature vector.

[0019] Preferably, the intelligent sleep-aiding light therapy pillow includes: a light intensity adjustment module, a light color adjustment module, and a sound effect playback module;

[0020] The light intensity adjustment module uses a dimming circuit to achieve light intensity adjustment from 0 to 1000 lux;

[0021] The light color adjustment module uses an RGB LED lamp to switch between warm yellow light and cold white light according to the control light color instruction;

[0022] The sound effect playback module uses a high-quality speaker to play sleep-aiding music or natural sound effects according to the control sound effect type instruction.

[0023] The present invention also provides an intelligent sleep aid control method integrating light therapy and biological rhythm, which is implemented by using the intelligent sleep aid control system integrating light therapy and biological rhythm according to any one of the above, and the sleep aid control method includes the following steps:

[0024] Collect the biological rhythm data of the user through a biological rhythm monitoring device;

[0025] Transmit the collected biological rhythm data to a computing terminal through a Bluetooth module;

[0026] The computing terminal preprocesses the received biological rhythm data to remove noise;

[0027] Analyze the preprocessed data through a multi-modal fusion model to determine the user's current sleep stage;

[0028] According to the determined sleep stage, generate corresponding control instructions through the computing terminal;

[0029] Send the control instructions to the intelligent sleep aid light therapy pillow through a Bluetooth module;

[0030] The intelligent sleep aid light therapy pillow adjusts the light therapy function in real time according to the received control instructions.

[0031] Preferably, the biological rhythm data includes but is not limited to: body temperature change rate, heart rate change rate, respiratory frequency change rate, and electroencephalogram characteristics.

[0032] Preferably, the multi-modal fusion model includes: an input branch, a feature extraction layer, a feature fusion layer, and a subsequent processing layer;

[0033] The input branch is used to design an independent input branch for each modality, and each branch is responsible for processing the data of one modality and extracting the features of that modality;

[0034] The feature extraction layer is used to extract features from the input data using neural network layers in each branch;

[0035] The feature fusion layer is used to fuse the features of different modalities at an intermediate layer after feature extraction;

[0036] The subsequent processing layer is used to generate a final prediction result based on the fused feature vector.

[0037] Preferably, the control instructions include a control light intensity instruction, a control light color instruction, a control sound effect type instruction, and a shutdown instruction.

[0038] The present invention also provides an electronic device, comprising: a memory and a processor, wherein a computer program run by the processor is stored on the memory, and the computer program, when run by the processor, executes any one of the intelligent sleep assistance control systems integrating light therapy and biological rhythm.

[0039] The present invention also provides a storage medium, on which a computer program is stored, and the computer program, when running, executes any one of the intelligent sleep assistance control systems integrating light therapy and biological rhythm.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] 1. By combining a biological rhythm monitoring device with a sleep assistance light therapy pillow, through monitoring and collecting the biological rhythm data of users, without manual intervention, the effect of fully automatic control can be achieved.

[0042] 2. Based on the data of the biological rhythm monitoring device for control, combining sleep stage detection and sleep onset point detection with the automatic control of the sleep assistance light therapy pillow, the effects of non-manual intervention, real-time adjustment, real-time control, and automatic control are achieved.

[0043] 3. The sleep staging algorithm adopting a multi-modal fusion model improves the accuracy and robustness of sleep staging and can better adapt to the sleep characteristics of different users.

[0044] 4. The system structure is simplified, the cost is reduced, and it has high market promotion value.

[0045] 5. The setting of personalized sleep assistance solutions can meet the personalized needs of different users and further improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0047] Figure 1 It is a schematic diagram of an intelligent sleep assistance control system integrating light therapy and biological rhythm provided by an embodiment of the present invention;

[0048] Figure 2 It is a flowchart of an intelligent sleep assistance control method integrating light therapy and biological rhythm provided by an embodiment of the present invention;

[0049] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[0050] Description of the Drawings: 1 - Biological rhythm monitoring device, 2 - Computing terminal, 3 - Bluetooth module, 4 - Intelligent sleep - assisting light therapy pillow, 1010 - Processor; 1020 - Memory; 1030 - Input / output interface; 1040 - Communication interface; 1050 - Bus. Detailed Implementation Modes

[0051] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] To make the above - mentioned objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation modes.

[0053] Embodiment 1

[0054] As Figure 1 shown, the embodiment of the present invention discloses an intelligent sleep - assisting control system integrating light therapy and biological rhythm, including a biological rhythm monitoring device, a computing terminal, a Bluetooth module, and an intelligent sleep - assisting light therapy pillow.

[0055] The biological rhythm monitoring device is used to collect the biological rhythm data of the user, such as body temperature, heart rate, respiratory rate, etc., and transmit the data to the computing terminal through the Bluetooth module. The biological rhythm monitoring device is a wearable device, such as a smart bracelet, a smart watch, or a dedicated biological rhythm monitor, with multiple built - in sensors, including a body temperature sensor, a heart rate sensor, and a respiratory rate sensor. The accuracy of the sensors needs to reach the medical - grade standard. For example, the measurement accuracy of the body temperature sensor needs to reach ±0.1°C, the measurement accuracy of the heart rate sensor needs to reach ±1 beat per minute, and the measurement accuracy of the respiratory rate sensor needs to reach ±1 breath per minute.

[0056] The computing terminal includes: a pre - processing unit and an analysis unit; the computing terminal can be a PC terminal or a mobile terminal, such as a smart phone, a tablet computer, etc. After receiving the data from the biological rhythm monitoring device, the pre - processing unit first pre - processes the data, including filtering and smoothing to remove noise. The analysis unit inputs the pre - processed data into a sleep staging algorithm (multi - modal fusion model) for analysis. By introducing the multi - modal fusion model, integrating multiple biological rhythm data (such as the change rate of body temperature, the change rate of heart rate, the change rate of respiratory rate), the comprehensive monitoring and analysis of the user's sleep state are realized, the current sleep stage of the user is determined, and corresponding control instructions are generated. The specific implementation method of the multi - modal fusion model:

[0057] I. Input Branches: Independent input branches are designed for each modality to process single-modal data and extract features. The body temperature model takes the body temperature change rate as the input, the heart rate model takes the heart rate change rate as the input, and the respiratory rate model takes the respiratory rate change rate as the input. LSTM models are trained respectively. The electroencephalogram model takes electroencephalogram features as the input and trains a CNN model.

[0058] II. Feature Extraction Layers: For the characteristics of different-modal data, a heterogeneous hybrid neural network combination based on physiological signal characteristics is designed in the present invention:

[0059] 1: Heterogeneous Network Design:

[0060] Processing of Body Temperature, Heart Rate, and Respiratory Rate (Bidirectional LSTM):

[0061] Input: Sequences of temperature, heart rate, and respiratory rate sampled once per minute.

[0062] Network Structure: Bidirectional LSTM layer (hidden layer dimension 128) to capture forward and backward temporal dependencies respectively.

[0063] Dropout layer (ratio 0.3) to prevent overfitting.

[0064] Output: 128-dimensional feature vectors at each time point.

[0065] Processing of Electroencephalogram (Improved 1D-CNN):

[0066] Input: Raw electroencephalogram signals (sampling rate 256Hz), framed into 30-second segments.

[0067] Network Structure: Convolutional layer 1: 64 filters, size 5, stride 1, activation function ReLU to extract time-domain features. Adaptive pooling layer: Dynamically adjust the pooling window size to retain key frequency bands (such as δ wave 1 - 4Hz).

[0068] Convolutional layer 2: 32 filters, size 3, stride 1, to further extract time-frequency joint features.

[0069] Output: 64-dimensional feature vectors for each segment.

[0070] 2: Parameter Quantity Optimization

[0071] Parameter quantity of the traditional full LSTM model: Approximately 2.1M (bidirectional LSTM layer × 3).

[0072] Parameter quantity of the heterogeneous network in this solution: 1.7M (LSTM 1.2M + CNN 0.5M), a reduction of 18%.

[0073] II. Feature Fusion Layer: The present invention designs a dynamic spatio-temporal attention mechanism. This mechanism dynamically adjusts the weights of different modal features according to the time series characteristics (such as the periodic changes in body temperature and heart rate) and cross-modal correlations of biological rhythm data. Specifically, it includes:

[0074] 1: Design of Attention in the Time Dimension

[0075] Input Processing: Segment the time series data of each modality (such as heart rate and body temperature), with each segment having a length of 10 minutes (covering a complete sleep cycle segment).

[0076] LSTM Time Series Modeling: Use a bidirectional LSTM network to process the data of each modality separately. The forward LSTM captures historical dependencies, and the backward LSTM predicts future trends.

[0077] Generation of Attention Weights: Calculate the attention scores at each time point through a fully connected layer:

[0078] α t = Softmax(W·h t + b);

[0079] where h t is the hidden state of the LSTM at time point t, and W and b are learnable parameters.

[0080] Weight the time series features according to α t and sum them up to highlight key time points (such as the sharp drop in body temperature corresponding to the falling asleep period).

[0081] 2: Design of Cross-Modal Attention

[0082] Cross-Attention Module:

[0083] Generation of Query-Key-Value: The electroencephalogram features are used as Query (Q), and the heart rate and respiratory rate features are used as Key (K) and Value (V). Calculate the similarity matrix between Q and K and normalize it to obtain the attention weights:

[0084]

[0085] where d k is the dimensionality scaling factor.

[0086] Information Fusion: Dynamically map the heart rate and respiratory features to the electroencephalogram feature space through the attention weights to enhance complementarity.

[0087] Dynamic Weight Allocation: According to the current sleep stage (such as the REM stage), adaptively adjust the contribution weights of different modalities. For example, in the REM stage, the theta wave activity of the electroencephalogram is more critical, and its weight is increased to 70%.

[0088] III. Subsequent Processing Layer: The fused feature vectors will be input into subsequent processing layers, such as the Dense Layer, to generate the final prediction results. The specific prediction process is as follows:

[0089] 1. Structure and Parameter Design of the Dense Layer

[0090] Input Layer: Receives the fused feature vectors from the feature fusion layer, with a dimension of 256 (for example, the result of concatenating the 128-dimensional temporal features output by the bidirectional LSTM and the 128-dimensional time-frequency features output by the 1D-CNN).

[0091] Hidden Layer Design:

[0092] The First Dense Layer (FC1): 128 neurons, using the ReLU activation function, with the formula:

[0093] FC1 Output = ReLU(W 1 ·X fused +b 1 );

[0094] Where W 1 is a 128×256 weight matrix, and b 1 is a bias vector.

[0095] The Second Dense Layer (FC2): 64 neurons, using the ReLU activation function, with the formula:

[0096] FC2 Output = ReLU(W 2 ·FC1 Output + b 2 );

[0097] Where W 2 is a 128×256 weight matrix, and b 2 is a bias vector.

[0098] Dropout Layer: Add a Dropout layer (dropout rate 0.3) between FC1 and FC2 to randomly mask 30% of the neurons to prevent overfitting.

[0099] Output Layer:

[0100] Softmax Classification Layer: 4 neurons, corresponding to the four classifications of sleep stages (wakefulness, light sleep, deep sleep, REM sleep), with the formula:

[0101]

[0102] Where W 0 is a 4×64 weight matrix, and b 0 is a bias vector, P(yi ) represents the probability of the i-th sleep stage.

[0103] 2. Result determination: Select the category with the highest probability as the current sleep stage. For example:

[0104] If P(deep sleep stage) > 0.7, it is determined as the deep sleep stage;

[0105] If the probabilities of multiple categories are close (such as the maximum probability difference < 0.1), smooth processing is performed by combining the prediction results of the previous time period to avoid frequent jumps.

[0106] IV. Model output: The present invention adopts a closed-loop feedback light therapy control strategy, which not only outputs the sleep stage classification result but also generates a dynamic adjustment curve of light therapy parameters in combination with historical data. For example: When the model predicts that the user is about to enter the deep sleep stage, the light intensity is gradually decreased (instead of suddenly changing) 10 minutes in advance to avoid disturbing the sleep continuity. According to the user's personalized data (such as historical sleep cycles), the light therapy color switching threshold is adaptively adjusted.

[0107] 1: Generation of dynamic curve of light therapy parameters

[0108] Input: The current sleep stage (such as the light sleep stage) and historical data (such as the user's average sleep onset time, deep sleep duration).

[0109] Prediction model: Use a time series prediction algorithm (such as ARIMA) to predict the sleep stage change in the next 30 minutes based on the sleep data of the past 3 days.

[0110] Control strategy: Gradual light reduction: If it is predicted that the user will enter the deep sleep stage in 10 minutes, the light intensity is linearly reduced from 500 lux to 50 lux at a rate of 5 lux / second instead of suddenly dropping to 0. Personalized threshold: Adjust the light therapy color switching threshold according to the user's historical data. For example, for a "night owl" user, the time to switch from warm yellow light to cold white light is postponed by 1 hour.

[0111] 2: Real-time feedback adjustment

[0112] Closed-loop control logic: Receive the update of biological rhythm data every 5 minutes. If the deviation between the actual sleep stage and the prediction exceeds 10% (such as predicting deep sleep but actually being REM), immediately trigger the control instruction correction. Correction strategy: Dynamically adjust the light intensity change rate based on the PID controller.

[0113] The specific method for designing the PID controller is as follows:

[0114] 1. Error definition: The actual sleep stage S a and the deviation e(t) from the predicted stage S p is weighted and calculated according to the stage importance:

[0115] e(t) = ω s ·|S p - S a |;

[0116] Wherein, the weight ω s is: 1.2 for the deep sleep stage, 1.0 for the REM stage, and 0.8 for the light sleep stage.

[0117] 2. Control formula: The PID output adjustment amount ΔS(t) is:

[0118]

[0119] (The proportional coefficient K p = 0.8: Quickly respond to the current deviation; the integral coefficient K i = 0.2: Eliminate the long-term cumulative error; the differential coefficient K d = 0.1: Suppress overshoot and enhance stability.)

[0120] 3. Rate adjustment:

[0121] The original rate S0 is set according to the sleep stage mapping table, and the corrected rate:

[0122] S new = S 0 + ΔS(t);

[0123] Range limit: 0.5 ≤ S new ≤ 5 lux / second.

[0124] Implementation steps:

[0125] 1. Real-time monitoring: Update the biological rhythm data every 5 minutes and calculate e(t);

[0126] 2. Dynamic correction: Based on the PID output, adjust the rate Snew;

[0127] 3. Instruction issuance: Send Snew to the light therapy pillow through the Bluetooth module to perform a gradual adjustment.

[0128] The calculation terminal generates corresponding control instructions according to the determined sleep stage, including control instructions for light intensity, control instructions for light color, control instructions for sound effect types, and shutdown instructions, etc.

[0129] The intelligent sleep-aid light therapy pillow is internally integrated with multiple functional modules, including a light intensity adjustment module, a light color adjustment module, and a sound effect playback module. The light intensity adjustment module uses a dimming circuit and can achieve light intensity adjustment from 0 to 1000 lux; the light color adjustment module uses RGB LED lights and can switch between warm yellow light and cold white light according to the control light color instruction; the sound effect playback module uses high-quality speakers and can play sleep-aid music or natural sound effects according to the control sound effect type instruction. After receiving the control instructions transmitted by the computing terminal, the corresponding functional modules of the intelligent sleep-aid light therapy pillow will adjust their functions in real time to adapt to the user's current sleep stage.

[0130] To further improve the accuracy and reliability of the system, the biological rhythm monitoring device 1 and the intelligent sleep-aid light therapy pillow 4 can be provided with multiple redundant sensors and functional modules. For example, the biological rhythm monitoring device 1 can be provided with two body temperature sensors to ensure that when one sensor fails, the other sensor can still work normally. The intelligent sleep-aid light therapy pillow 4 can be provided with multiple RGB LED lights to ensure the smoothness and uniformity of light color adjustment.

[0131] The computing terminal can also set personalized sleep-aid solutions. Users can input their personal sleep habits, preferences, and needs through the user interface of the computing terminal. The computing terminal generates corresponding control instructions according to the personalized needs of the users and sends them to the intelligent sleep-aid light therapy pillow.

[0132] In summary, the present invention provides an intelligent sleep-aid control system integrating light therapy and biological rhythm. The biological rhythm monitoring device collects the user's biological rhythm data, and the computing terminal analyzes the data through a sleep staging algorithm, generates corresponding control instructions, and transmits them to the intelligent sleep-aid light therapy pillow in real time through the Bluetooth module. The intelligent sleep-aid light therapy pillow adjusts its light therapy and sound effect functions in real time according to the received instructions to help users improve their sleep quality. This system has the characteristics of no need for manual intervention, real-time control, and self-regulation, and has broad application prospects and practical value.

[0133] Specific implementation process:

[0134] Suppose the user uses the sleep aid system at 10 p.m. The biological rhythm monitoring device collects the user's body temperature, heart rate, and respiratory rate data before the user goes to sleep and transmits the data to the computing terminal through the Bluetooth module. After receiving the data, the computing terminal first performs filtering and denoising processing to ensure the accuracy of the data. Then, the computing terminal inputs the processed data into the sleep staging algorithm to determine that the user is in the light sleep stage. The computing terminal generates an instruction to reduce the light intensity and sends it to the intelligent sleep aid light therapy pillow through the Bluetooth module. After receiving the instruction, the light intensity adjustment module of the intelligent sleep aid light therapy pillow gradually reduces the light intensity from 500 lux to 100 lux to help the user better enter the light sleep stage. As the user gradually falls asleep, the biological rhythm monitoring device continues to collect data and transmits it to the computing terminal in real time. The computing terminal determines that the user has entered the REM stage through the sleep staging multimodal fusion model algorithm, generates an instruction to switch the light color from warm yellow light to cold white light, and sends it to the intelligent sleep aid light therapy pillow through the Bluetooth module. After receiving the instruction, the light color adjustment module of the intelligent sleep aid light therapy pillow smoothly switches the light from warm yellow light to cold white light to meet the requirements of the REM stage. When the user enters the deep sleep stage, the biological rhythm monitoring device continues to collect data. The computing terminal determines that the user is in the deep sleep stage through the sleep staging algorithm, generates a shutdown instruction, and sends it to the intelligent sleep aid light therapy pillow through the Bluetooth module. After receiving the shutdown instruction, all functional modules of the intelligent sleep aid light therapy pillow stop working to ensure that the user is not disturbed during the deep sleep stage.

[0135] Embodiment 2

[0136] As Figure 2 shown, the present invention also provides an intelligent sleep aid control method integrating light therapy and biological rhythm, which is implemented by using the intelligent sleep aid control system integrating light therapy and biological rhythm described in any one of the above, and the control method includes the following steps:

[0137] Collect the user's biological rhythm data through a biological rhythm monitoring device;

[0138] Transmit the collected biological rhythm data to the computing terminal through the Bluetooth module;

[0139] The computing terminal preprocesses the received biological rhythm data to remove noise;

[0140] Analyze the preprocessed data through a multimodal fusion model to determine the user's current sleep stage;

[0141] Generate corresponding control instructions through the computing terminal according to the determined sleep stage;

[0142] Send the control instructions to the intelligent sleep aid light therapy pillow through the Bluetooth module;

[0143] The intelligent sleep - assisting light therapy pillow adjusts its light therapy function in real - time according to the received control instructions.

[0144] In this embodiment, the biological rhythm data includes but is not limited to: the rate of change of body temperature, the rate of change of heart rate, the rate of change of respiratory frequency, and electroencephalogram characteristics.

[0145] In this embodiment, the multi - modal fusion model includes: an input branch, a feature extraction layer, a feature fusion layer, and a subsequent processing layer;

[0146] The input branch is used to design an independent input branch for each modality. Each branch is responsible for processing the data of one modality and extracting the features of that modality.

[0147] The feature extraction layer is used to extract features from the input data using neural network layers in each branch.

[0148] The feature fusion layer is used to fuse the features of different modalities at the intermediate layer after feature extraction.

[0149] The subsequent processing layer is used to generate the final prediction result based on the fused feature vector.

[0150] In this embodiment, the control instructions include an instruction for controlling the light intensity, an instruction for controlling the light color, an instruction for controlling the sound effect type, and an off instruction.

[0151] In summary, 1. The overall architecture of the sleep - assisting system combining light therapy and biological rhythm: A sleep - assisting system combining light therapy and biological rhythm includes a biological rhythm monitoring device, a computing terminal, a Bluetooth module, and an intelligent sleep - assisting light therapy pillow. The biological rhythm monitoring device is used to collect the user's biological rhythm data, such as body temperature, heart rate, respiratory frequency, etc., and transmit the data to the computing terminal through the Bluetooth module. After receiving the data, the computing terminal analyzes the data through a sleep staging algorithm, determines the user's current sleep stage, and generates corresponding control instructions. These control instructions are transmitted to the intelligent sleep - assisting light therapy pillow through the Bluetooth module, and the intelligent sleep - assisting light therapy pillow adjusts its light therapy function in real - time according to the received instructions, including light intensity, light color, and sound effect playback, etc., to adapt to the user's current sleep stage, thereby realizing the automatic control and real - time adjustment of the user's sleep process.

[0152] 2. Biological Rhythm Monitoring Device: The biological rhythm monitoring device is a wearable device, such as a smart bracelet, a smart watch or a dedicated biological rhythm monitor, which is built-in with multiple sensors, including a body temperature sensor, a heart rate sensor and a respiratory rate sensor, for real-time collection of the user's biological rhythm data. And the accuracy of the sensors needs to reach the medical grade standard. For example, the measurement accuracy of the body temperature sensor needs to reach ±0.1 °C, the measurement accuracy of the heart rate sensor needs to reach ±1 beat per minute, and the measurement accuracy of the respiratory rate sensor needs to reach ±1 breath per minute. The device establishes a connection with the computing terminal through the built-in Bluetooth module and transmits the collected data to the computing terminal in real time.

[0153] 3. Function Modules of the Intelligent Sleep Aid Light Therapy Pillow and Their Control: The intelligent sleep aid light therapy pillow is internally integrated with multiple function modules, including a light intensity adjustment module, a light color adjustment module and a sound effect playback module. The light intensity adjustment module uses a dimming circuit and can achieve light intensity adjustment from 0 to 1000 lux; the light color adjustment module uses RGB LED lights and can switch between warm yellow light and cold white light according to the control light color instruction; the sound effect playback module uses high-quality speakers and can play sleep aid music or natural sound effects according to the control sound effect type instruction. After receiving the control instructions transmitted by the computing terminal, the corresponding function modules of the intelligent sleep aid light therapy pillow will adjust their functions in real time to adapt to the user's current sleep stage.

[0154] 4. Redundancy Design of the System and Multimodal Data Fusion: The biological rhythm monitoring device and the intelligent sleep aid light therapy pillow are provided with multiple redundant sensors and function modules. The computing terminal adopts a sleep staging algorithm of a multimodal fusion model, including steps such as feature extraction, model structure design, feature fusion and model output, and can accurately determine the user's sleep stage.

[0155] 5. Personalized Sleep Aid Solution: The computing terminal sets a personalized sleep aid solution. The user can input personal sleep habits, preferences and needs through the user interface of the computing terminal. The computing terminal generates corresponding control instructions according to the user's personalized needs and sends them to the intelligent sleep aid light therapy pillow.

[0156] The specific process of the computing terminal according to the user's personalized needs includes:

[0157] 1. Input and Modeling of Personalized Needs

[0158] User Data Collection: Through the user interface of the computing terminal, the user inputs the following personalized parameters:

[0159] Sleep Preferences: Bedtime preference (such as "early sleeper" or "night owl"), light color preference (warm yellow light / cold white light), sound effect type selection (natural sound effects / white noise / light music);

[0160] Health Goals: Target sleep onset duration (e.g., within 30 minutes), proportion of deep sleep duration (e.g., ≥25%), light therapy sensitivity (high / medium / low);

[0161] Historical Data Synchronization: Automatically import the sleep stage distribution, light therapy parameter adjustment records, and physiological indicators (such as average heart rate, body temperature baseline) of the user in the past 7 days.

[0162] Personalized Model Construction: Using a hybrid clustering and regression algorithm, the users are classified into the following categories:

[0163] Category A (Highly Sensitive to Light Therapy): The adjustment rate of light intensity ≤ 3 lux / second, and the cold white light switching threshold is advanced by 20 minutes;

[0164] Category B (Sound Effect Dependent): The sound effect volume is increased by 20% during the sleep onset stage, and the sound effect is automatically turned off during the deep sleep stage;

[0165] Category C (Body Temperature Driven): Using the body temperature change rate ΔT(t) as the core indicator, dynamically adjust the timing of light color switching.

[0166] 2. Control Instruction Generation Logic

[0167] Generation of Sleep Stage - Light Therapy Parameter Mapping Table: Based on the user category and health goals, generate personalized mapping rules, as shown in Table 1:

[0168] Table 1

[0169]

[0170] Dynamic Instruction Correction Mechanism:

[0171] Real - time Feedback Correction: If the deviation between the current sleep stage and the prediction exceeds the threshold (e.g., the actual duration of the light sleep period far exceeds the target value), trigger a correction based on the PID controller to dynamically adjust the light intensity change rate:

[0172]

[0173] Among them, e(t) is the difference between the actual and target sleep stages, K p = 0.8, K i = 0.2, K d = 0.1 (optimized for Category A);

[0174] Long - term Adaptive Optimization: Update the user category label every 7 days, and optimize the mapping table parameters through reinforcement learning (Q - Learning). The reward function is:

[0175] R = ω 1 · Shrinkage of sleep onset duration + ω 2 · Increase rate of deep sleep proportion - ω 3· Light therapy interference times (ω 1 = 0.6, ω 2 = 0.3, ω 3 = 0.1, with adjustable weights).

[0176] Embodiment 3

[0177] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements an intelligent sleep aid control system integrating light therapy and biological rhythm described in any one of the above embodiments.

[0178] Figure 3 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 achieve communication connection with each other inside the device through the bus 1050.

[0179] The processor 1010 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0180] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0181] The input / output interface 1030 is used to connect to an input / output module to achieve information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0182] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to enable communication and interaction between this device and other devices. The communication module can achieve communication through wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0183] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0184] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0185] The system of the above embodiment is used to implement the corresponding sleep aid system control method combining electroencephalogram regulation in any of the previous embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0186] Embodiment Four

[0187] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute an intelligent sleep aid control system integrating light therapy and biological rhythm as described in any of the above embodiments.

[0188] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0189] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the sleep aid system control method combined with brain wave regulation as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0190] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples; under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of brevity.

[0191] In addition, for the sake of simplicity of description and discussion, and in order not to make the embodiments of the present invention difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the device may be shown in block diagram form in order to avoid making the embodiments of the present invention difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present invention are to be implemented (i.e., these details should be completely within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present invention, it will be apparent to those skilled in the art that the embodiments of the present invention can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0192] Although the present invention has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0193] Thus, the units of the examples described in the embodiments of this application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0194] The embodiments described above are only descriptions of the preferred modes of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solution of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. An intelligent sleep-aiding control system integrating light therapy and biological rhythm, characterized in that: include: Biorhythm monitoring equipment, computing terminals, Bluetooth modules, and smart sleep-aiding light therapy pillows; The biorhythm monitoring device is used to collect the biorhythm data of the user and transmit the data to the computing terminal through the Bluetooth module; The computing terminal is used to analyze the biorhythm data through a sleep staging algorithm, determine the current sleep stage of the user, and generate corresponding control instructions, and transmit the control instructions to the smart sleep-aiding light therapy pillow through the Bluetooth module; The intelligent sleep-aiding light therapy pillow is used to adjust the light therapy function in real time according to the received control instructions to adapt to the user's current sleep stage, thereby realizing automatic control and real-time adjustment of the user's sleep process.

2. The intelligent sleep-aiding control system integrating light therapy and biological rhythm according to claim 1 is characterized in that: The biorhythm monitoring device has multiple built-in sensors, including a body temperature sensor, a heart rate sensor, and a respiratory rate sensor; The biorhythm data include but are not limited to: body temperature change rate, heart rate change rate, respiratory rate change rate, and brain wave characteristics.

3. The intelligent sleep-aiding control system integrating light therapy and biological rhythm according to claim 1, characterized in that: The computing terminal comprises: a preprocessing unit and an analyzing unit; The preprocessing unit is used to preprocess the biorhythm data, including filtering and smoothing to remove noise; The analysis unit is used to integrate a variety of pre-processed biorhythm data by introducing a multimodal fusion model to achieve comprehensive monitoring and analysis of the user's sleep state and determine the user's current sleep stage; Among them, the multimodal fusion model includes: input branch, feature extraction layer, feature fusion layer, and subsequent processing layer; The input branch is used to design an independent input branch for each modality, and each branch is responsible for processing data of one modality and extracting features of the modality; The feature extraction layer is used to extract features from input data using a neural network layer in each branch; The feature fusion layer is used to fuse features of different modalities in the middle layer after feature extraction; The subsequent processing layer is used to generate a final prediction result based on the fused feature vector.

4. The intelligent sleep-aiding control system integrating light therapy and biological rhythm according to claim 1, characterized in that: The intelligent sleep-aiding light therapy pillow comprises: a light intensity adjustment module, a light color adjustment module and a sound effect playing module; The light intensity adjustment module uses a dimming circuit to adjust the light intensity from 0 to 1000 lux; The light color adjustment module uses RGB LED lights to switch between warm yellow light and cool white light according to the light color control instruction; The sound effect playing module uses a high-quality speaker to play sleep-aiding music or natural sound effects according to the control sound effect type instruction.

5. An intelligent sleep-aiding control method integrating light therapy and biological rhythm, characterized in that: The intelligent sleep-aid control system integrating light therapy and biological rhythm as described in any one of claims 1 to 4 is used to implement the sleep-aid control method, which comprises the following steps: Collect the user's biorhythm data through biorhythm monitoring equipment; The collected biorhythm data is transmitted to the computing terminal via the Bluetooth module; The computing terminal pre-processes the received biorhythm data to remove noise; The pre-processed data is analyzed through a multimodal fusion model to determine the user's current sleep stage; According to the determined sleep stage, corresponding control instructions are generated through the computing terminal; Send control instructions to the smart sleep-aiding light therapy pillow via the Bluetooth module; The intelligent sleep-aiding light therapy pillow adjusts the light therapy function in real time according to the received control instructions.

6. The intelligent sleep-aiding control method integrating light therapy and biological rhythm according to claim 5, characterized in that: The biorhythm data include but are not limited to: body temperature change rate, heart rate change rate, respiratory rate change rate, and brain wave characteristics.

7. The intelligent sleep-aiding control method integrating light therapy and biological rhythm according to claim 5, characterized in that: The multimodal fusion model includes: input branch, feature extraction layer, feature fusion layer, and subsequent processing layer; The input branch is used to design an independent input branch for each modality, and each branch is responsible for processing data of one modality and extracting features of the modality; The feature extraction layer is used to extract features from input data using a neural network layer in each branch; The feature fusion layer is used to fuse features of different modalities in the middle layer after feature extraction; The subsequent processing layer is used to generate a final prediction result based on the fused feature vector.

8. The intelligent sleep-aiding control method integrating light therapy and biological rhythm according to claim 5, characterized in that: The control instructions include a light intensity control instruction, a light color control instruction, a sound effect type control instruction, and a close instruction.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the intelligent sleep-aid control system integrating light therapy and biological rhythm as described in any one of claims 1 to 4 is executed.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the intelligent sleep-aiding control system integrating light therapy and biological rhythm as described in any one of claims 1 to 4.

Images