Dynamic atmosphere lamp control method and system based on music rhythm

Abstract

The invention relates to the technical field of atmosphere lamp control, in particular to a dynamic atmosphere lamp control method and system based on music rhythms. The method comprises the following steps: collecting a real-time audio signal stream, carrying out multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructing an audio rhythm feature perception map; performing spatial audio azimuth analysis based on the real-time audio signal stream, and performing adaptive dynamic atmosphere lamp parameter control based on the audio rhythm feature perception map to obtain an adaptive dynamic atmosphere lamp control strategy; according to the self-adaptive dynamic atmosphere lamp control strategy, initial atmosphere lamp control is carried out, a real-time image in the area is obtained, weak light intensity area coverage compensation optimization is carried out, and a dynamic atmosphere lamp space lighting effect optimization strategy is constructed; personalized natural physiological rhythm mining and physiological-music resonance frequency fine tuning are carried out, and user physiological-music resonance frequency fine tuning parameters are generated. According to the invention, high-response atmosphere lamp control which dynamically adapts to the light effect preference change of the user is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of atmosphere light control, and in particular to a method and system for controlling a dynamic atmosphere light based on music rhythm. Background Art

[0002] With the continuous development of smart homes, smart entertainment systems, and personalized spatial experience technologies, ambient lighting, a device that combines lighting with emotional expression, is increasingly being used in a variety of settings, including homes, entertainment venues, car interiors, and stage performances. Driven in particular by the demand for immersive entertainment and intelligent scene linkage, ambient lighting not only fulfills basic lighting functions but also becomes a crucial medium for creating atmosphere and enhancing emotional experiences. Compared to traditional, single, static lighting methods, dynamically controlled ambient lighting systems can significantly enhance the interactivity and immersion of a space through color changes, brightness adjustment, and rhythmic movements.

[0003] In practical applications, users are increasingly demanding the coordinated control of lighting with ambient sound or music. This is particularly true in settings such as home theaters, concerts, karaoke, and gyms, where the synergy between lighting and music effectively enhances the immersive audiovisual experience. However, most current ambient lighting control methods still rely on preset modes or simple audio trigger logic, making it difficult to accurately respond to and personalize the complex rhythmic characteristics of music. This control approach is slow to respond to changes in different music types and exhibits a monotonous performance, making it difficult to meet the diverse visual experience needs.

[0004] Furthermore, existing audio-lighting linkage technologies often rely on external audio sensors or simple frequency analysis modules, lacking a deep understanding of high-level features such as music structure, rhythmic intensity, and emotional dynamics. This results in insufficiently intelligent and dynamic lighting control. Furthermore, the requirements for lighting response vary across different scenarios, making it difficult for traditional methods to intelligently adjust lighting performance based on environmental context. Therefore, a dynamic ambient lighting control method that integrates music signal processing, rhythmic feature recognition, and intelligent control algorithms is urgently needed to achieve real-time perception and multi-dimensional response to musical rhythms. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a dynamic atmosphere light control method and system based on music rhythm to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a method for controlling a dynamic atmosphere light based on music rhythm, comprising the following steps: Step S1: collecting real-time audio signal streams, performing multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructing an audio rhythm feature perception map; Step S2: performing spatial audio orientation analysis based on the real-time audio signal stream, and performing adaptive dynamic ambient light parameter control based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy; Step S3: Perform preliminary ambient light control according to the adaptive dynamic ambient light control strategy, obtain real-time images in the area, perform compensation optimization for low-light intensity area coverage, and build a dynamic ambient light space lighting effect optimization strategy; Step S4: obtaining the user's real-time physiological state parameters, performing personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generating the user's physiological-music resonance frequency fine-tuning parameters; Step S5: Obtain the user's ambient light operation log, perform user-specified light effect adjustment analysis, and mine the user's light effect preference trajectory to construct a user light effect satisfaction prediction curve; Step S6: The dynamic atmosphere light space light effect optimization strategy is user preference-driven and regulated according to the user light effect satisfaction prediction curve and the user physiological-music resonance frequency fine-tuning parameters to perform the dynamic atmosphere light intelligent collaborative control operation.

[0007] In this specification, a dynamic atmosphere light control system based on music rhythm is provided, which is used to execute the dynamic atmosphere light control method based on music rhythm as described above, including: Audio rhythm perception: collects real-time audio signal streams, performs multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructs an audio rhythm feature perception map; The adaptive control module performs spatial audio orientation analysis based on the real-time audio signal stream and adaptively controls the dynamic ambient light parameters based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy. The light effect optimization module performs preliminary ambient light control based on the adaptive dynamic ambient light control strategy, obtains real-time images of the area, and performs compensation optimization for low-light intensity areas to build a dynamic ambient light space light effect optimization strategy; The resonance frequency fine-tuning module obtains the user's real-time physiological state parameters, performs personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generates the user's physiological-music resonance frequency fine-tuning parameters; The light effect preference mining module obtains user ambient light operation logs, analyzes user-specified light effect adjustments, and mines user light effect preference trajectories to construct a user light effect satisfaction prediction curve. The collaborative control module performs user preference-driven control of the dynamic atmosphere light space lighting optimization strategy based on the user lighting effect satisfaction prediction curve and the user's physiological-music resonance frequency fine-tuning parameters to perform dynamic atmosphere light intelligent control operations.

[0008] The beneficial effects of this invention include: multi-scale wavelet decomposition enables simultaneous perception of both high-frequency (rhythm, drum beats) and low-frequency (melody, harmony) components of audio, enhancing perception of musical rhythm and structure; constructing a rhythmic perception map facilitates structured representation of audio, providing rich time-frequency domain information for subsequent lighting control strategies; and enabling auditory-visual synchronization of ambient lighting control, achieving a truly dynamic lighting effect. By analyzing the spatial distribution of audio sources (e.g., left and right channels, and distance), the system dynamically adjusts the brightness and direction of lighting, creating a three-dimensional sense of space. Lighting aligns with the orientation of the audio source, enhancing the immersive audiovisual experience. Lighting parameters automatically adjust to the rhythm of the music and spatial location, preventing static lighting effects from disrupting the ambient experience. Image recognition is used to compensate for insufficient brightness in areas, preventing "blind spots" or "dead spots" in the space. Dynamic adjustments ensure uniform lighting throughout the room, improving the overall ambiance. A closed-loop perception-control-feedback mechanism is established, enhancing the system's intelligent adjustment capabilities. Leveraging the resonance between music and circadian rhythms (e.g., heart rate synchronization) enhances mood regulation. The system fine-tunes the lighting rhythm based on the user's current physiological state, creating an intelligent atmosphere of mind-body sync. Long-term use may help alleviate anxiety, stabilize mood, and improve sleep quality. User interaction logs reveal lighting preferences, such as color, brightness, and rhythm synchronization. This reduces the frequency of manual adjustments and enhances the intelligent matching experience. The system dynamically adapts to changes in user preferences, maintaining personalized adaptation over time. Combining the user's physiological state and lighting preferences, it enables comprehensive intelligent adjustment of lighting rhythm, color, and brightness. With continuous learning and adaptive capabilities, the system understands the user better with use, continuously optimizing matching results to create a dynamic, highly responsive and satisfying atmosphere lighting system. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a schematic flow chart of the steps of a method for controlling a dynamic atmosphere light based on music rhythm according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Schematic diagram of the detailed implementation steps of step S3. DETAILED DESCRIPTION

[0010] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0011] This application provides a method and system for controlling dynamic ambient lighting based on musical rhythms. The execution entities of the method and system include, but are not limited to, mechanical equipment, data processing platforms, cloud server nodes, and network upload devices that are equipped with the system, which can be considered general computing nodes of this application. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0012] See also Figures 1 to 4 The present invention provides a method for controlling a dynamic atmosphere light based on music rhythm, and the method comprises the following steps: Step S1: collecting real-time audio signal streams, performing multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructing an audio rhythm feature perception map; Step S2: performing spatial audio orientation analysis based on the real-time audio signal stream, and performing adaptive dynamic ambient light parameter control based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy; Step S3: Perform preliminary ambient light control according to the adaptive dynamic ambient light control strategy, obtain real-time images in the area, perform compensation optimization for low-light intensity area coverage, and build a dynamic ambient light space lighting effect optimization strategy; Step S4: obtaining the user's real-time physiological state parameters, performing personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generating the user's physiological-music resonance frequency fine-tuning parameters; Step S5: Obtain the user's ambient light operation log, perform user-specified light effect adjustment analysis, and mine the user's light effect preference trajectory to construct a user light effect satisfaction prediction curve; Step S6: The dynamic atmosphere light space light effect optimization strategy is user preference-driven and regulated according to the user light effect satisfaction prediction curve and the user physiological-music resonance frequency fine-tuning parameters to perform the dynamic atmosphere light intelligent collaborative control operation.

[0013] In the embodiment of the present invention, see Figure 1 , is a schematic flow chart of the steps of a method for controlling a dynamic atmosphere light based on music rhythm of the present invention. In this example, the steps of the method for controlling a dynamic atmosphere light based on music rhythm include: Step S1: collecting real-time audio signal streams, performing multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructing an audio rhythm feature perception map; In this embodiment, a real-time audio signal stream is captured. The goal of this step is to obtain clear audio data for subsequent analysis and processing. Experimental parameters are set, such as selecting an audio sampling rate of 44.1kHz to ensure high fidelity of the audio signal and setting the recording duration to 30 minutes to capture sufficient audio information. During the audio signal acquisition process, a high-sensitivity microphone or audio interface is used to record and store the audio signal in real time. The recording equipment is ensured to have good anti-interference capabilities and low noise characteristics to reduce the impact of ambient noise on the audio signal. Dynamic range compression technology can be used to automatically adjust the volume between strong and soft sounds to ensure signal integrity. After the audio signal is acquired, the data is stored on a computer or cloud server and marked with a timestamp and acquisition environment information for comparison and verification during subsequent analysis. During this process, signal quality is monitored in real time to ensure signal stability and clarity and to avoid data loss due to equipment failure or environmental changes. After the audio signal is acquired, multi-scale wavelet decomposition is performed. The goal of this step is to decompose the audio signal into multiple frequency subbands to extract its time-frequency characteristics. Set the experimental parameters, for example, choosing the Daubechies wavelet (db4) as the wavelet basis and setting the number of decomposition levels to 5 to capture more detailed frequency variations. The wavelet decomposition process decomposes the original audio signal into a series of sub-signals in different frequency bands by performing a continuous wavelet transform (CWT). This process first involves selecting an appropriate wavelet function. The Daubechies wavelet is highly effective in processing transient features in audio signals. Then, by calculating the wavelet coefficients, the energy characteristics and time domain information of each frequency band are extracted. During the decomposition process, it is important to select appropriate scaling factors and time windows to ensure the validity of the decomposition results. The coefficient graph obtained through the wavelet transform can intuitively display the variations of the audio signal across different frequencies and time. This process can reveal underlying patterns and regularities in the audio signal, laying the foundation for subsequent audio rhythm feature extraction. After completing the multi-scale wavelet decomposition, perform audio rhythm hierarchical structure perception. The goal of this step is to identify rhythmic features in the audio signal and construct a hierarchical structure map. Set the experimental parameters, for example, setting the analysis frequency band to 20 Hz to 20 kHz to cover the full frequency range audible to the human ear. The process of perceiving the hierarchical structure of audio rhythms first requires analyzing the individual frequency bands derived from wavelet decomposition to identify key features within the audio signal, such as rhythm, melody, and harmony. By calculating the energy distribution of each frequency band, the rhythmic characteristics of the audio signal can be extracted. The Hilbert transform is then used to calculate the instantaneous frequency and amplitude of the signal, identifying the main melodic and harmonic components within the audio. Cluster analysis methods (such as K-means or spectral clustering) can be used to classify the extracted rhythmic features, forming a hierarchical structure map. By visualizing different categories of rhythmic features, the temporal and frequency trends of the audio signal can be intuitively visualized.This process not only helps understand the components of the audio signal but also provides an important basis for subsequent audio processing and analysis. Based on the results of the audio rhythm hierarchical structure perception, an audio rhythm feature perception map is constructed. The goal of this step is to present the extracted audio features in a visual form to facilitate subsequent analysis and application. Experimental parameters are set, such as setting the map update frequency to once per minute to ensure that changes in the audio signal are reflected in real time. The process of constructing the audio rhythm feature perception map includes displaying the extracted rhythm feature data through visualization tools. Heat maps or time-frequency plots can be used to intuitively display the energy distribution and rhythm characteristics of different frequency bands. Use the Matplotlib or Seaborn libraries in Python to present the frequency and time information of the audio signal in a graphical form to help analysts identify important parts of the audio.

[0014] Step S2: performing spatial audio orientation analysis based on the real-time audio signal stream, and performing adaptive dynamic ambient light parameter control based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy; In this example, experimental parameters were set, such as using a four-microphone array to collect audio signals to ensure accurate spatial positioning, and a sampling rate of 48kHz to capture high-quality audio. The spatial audio position resolution process first requires preprocessing the captured audio signals. This includes noise removal and gain adjustment to ensure audio clarity. During this process, digital signal processing techniques (such as the Fast Fourier Transform (FFT)) are used to convert the time-domain signal into the frequency domain for subsequent analysis. A sound source localization algorithm (such as the delay-sum method or direction-of-arrival (DOA)) is used to resolve the sound source position in the audio signal. The direction of the sound source is determined by calculating the delay between the signals received by different microphones. Parameters were set, such as a positioning accuracy of ±5 degrees, to ensure the reliability of the positioning results. During the positioning process, changes in the audio signal are monitored in real time to ensure the system can dynamically adapt to environmental changes. As the sound source moves in space, the system should be able to promptly update the source's position and transmit this information to the subsequent ambient lighting control system. After completing the spatial audio position resolution, further analysis is performed using the audio rhythm feature perception map. The goal of this step is to extract rhythmic features from the audio signal to provide a parameter basis for dynamic ambient lighting control. Experimental parameters are set, for example, the analysis frequency range is set to 20 Hz to 20 kHz to cover the entire audio range perceptible to the human ear. This process first requires performing a wavelet transform or FFT on the audio signal to extract the audio rhythmic features. By analyzing the energy distribution of the audio signal, rhythmic features such as rhythm, melody, and harmony are identified in different frequency bands. Clustering algorithms (such as K-means or spectral clustering) are then used to classify the extracted rhythmic features, forming an audio rhythmic feature perception map. This process helps identify key rhythmic elements in the audio signal, such as accents, bass, and treble. By combining audio rhythmic features with spatial audio orientation information, the rhythmic characteristics of different sound sources and their spatial distribution can be determined. This provides important data support for subsequent dynamic ambient lighting control strategies, ensuring that the lighting effects match the characteristics of the audio signal. After the audio rhythmic feature perception map is constructed, adaptive dynamic ambient lighting parameter control is performed. The goal of this step is to automatically adjust the parameters of the ambient lighting based on the characteristics of the real-time audio signal to create a lighting effect that coordinates with the audio content. Experimental parameters are set, such as setting the response time of the lighting change to 100 milliseconds, to ensure that the dynamic lighting effect is synchronized with the changes in the audio signal. The adaptive dynamic control process first requires determining the control parameters of the lighting, including brightness, color, flashing frequency, etc. By analyzing the rhythmic characteristics of the audio signal, the rules for lighting changes are set. When the low-frequency portion of the audio is enhanced, the lighting brightness should increase accordingly, while the high-frequency portion can adjust the changes in the lighting color.

[0015] When implementing dynamic control, a PID control algorithm can be used to adjust ambient lighting parameters in real time, enabling it to quickly respond to changes in the audio signal. Target parameters are set, such as a range of 0-1000 lumens for light brightness, and dynamically adjusted based on the real-time characteristics of the audio signal. The spatial layout of the lighting should also be considered to ensure that ambient lighting in different locations can adapt to the location of the sound source. For example, when the sound source is on the left, the left lighting should be brighter, while the right lighting can be relatively dim. Based on the real-time audio signal and the perceptual map of audio rhythmic characteristics, an adaptive dynamic ambient lighting control strategy is constructed. The goal of this step is to develop a complete control system that enables the ambient lighting to automatically adjust based on the audio content, enhancing the user experience. Experimental parameters are set, such as setting the control strategy update frequency to 5 times per second, to ensure real-time dynamic response. The control strategy development process involves integrating the real-time analysis results of the audio signal with the ambient lighting control system. A central controller is established to receive real-time audio signal analysis data and automatically adjust lighting parameters according to pre-set control rules. During implementation, a feedback mechanism is used to monitor the matching between the lighting effects and the audio signal. Leverage user feedback or sensor data to assess lighting effect satisfaction and further optimize control strategies. By continuously adjusting lighting parameters, ensure that lighting effects align with audio content, creating a more immersive atmosphere.

[0016] Step S3: Perform preliminary ambient light control according to the adaptive dynamic ambient light control strategy, obtain real-time images in the area, perform compensation optimization for low-light intensity area coverage, and build a dynamic ambient light space lighting effect optimization strategy; In this embodiment, the ambient lighting parameters are adjusted based on real-time audio signals and rhythmic characteristics to achieve synchronization with the audio content. Experimental parameters are set, such as the brightness range of the lights being set to 0 to 1000 lumens and the color range being set to RGB (0, 0, 0) to (255, 255, 255), to ensure that the lighting remains within the adjustable range. During the initial control process, the system receives real-time audio signal analysis results and dynamically adjusts the brightness and color of the ambient lighting based on the audio rhythmic characteristics. When the low-frequency components of the audio signal increase, the brightness of the ambient lighting is appropriately increased; otherwise, it is decreased. Simultaneously, the color of the lighting is adjusted based on the frequency spectrum characteristics of the audio to reflect the emotional changes in the audio. To achieve this control, PWM (pulse width modulation) technology is used to adjust the lighting. Specifically, the control period is set to 10 milliseconds, and the brightness of the lighting is adjusted by adjusting the duty cycle of the PWM signal. Furthermore, the distribution and layout of the ambient lighting are taken into consideration to ensure that the lighting in different locations changes in a coordinated manner to create an overall ambiance effect. During this process, the matching between the lighting effect and the audio signal is monitored in real time, and the lighting performance is evaluated through user feedback or sensor data. This process provides foundational data for subsequent lighting optimization, ensuring the system can dynamically adjust. After completing the initial ambient lighting control, real-time images of the area are acquired. The goal of this step is to monitor the lighting conditions within the area using real-time images to optimize coverage compensation for low-light areas. Experimental parameters are set, such as selecting an image acquisition resolution of 1920x1080 (1080p) and a frame rate of 30 fps to ensure clear and smooth images. During image acquisition, a high-resolution camera is used to capture the ambient lighting conditions within the area in real time. Image processing algorithms (such as adaptive histogram equalization) enhance image contrast and detail, making the lighting distribution more distinct. Light intensity within the area is monitored in real time, with particular attention paid to shadows and low-light areas for subsequent compensation optimization. To quantify light intensity, a light intensity calculation formula is used in image processing to extract the brightness value of each pixel and calculate the average light intensity within the area. A threshold is set to identify areas with brightness below a standard (e.g., 200 lumens), providing data support for subsequent low-light coverage compensation. After acquiring real-time images, coverage compensation optimization for low-light areas is performed. The goal of this step is to optimize the lighting effect of the entire area by adjusting the brightness and distribution of the ambient light to ensure uniform lighting. Experimental parameters are set, such as setting the compensation target brightness to 500 lumens to improve the lighting level in low-light areas. The compensation optimization process first requires identifying low-light areas and using previously extracted image data to calculate the specific location and light intensity of these areas. A region growing algorithm is used to mark and locate low-light areas for targeted compensation. Based on the location of the low-light areas, the brightness and distribution strategy of the ambient light are dynamically adjusted.For specific low-light areas, increase the brightness of ambient lighting near that area, using a linear interpolation algorithm for smooth transitions and ensuring a natural lighting effect. Additionally, consider adding additional ambient lighting to enhance lighting coverage. During compensation optimization, monitor the compensation effect in real time and recapture images of the area to assess lighting uniformity. Use image processing techniques (such as light intensity heat maps) to visually display the compensated lighting distribution and ensure the optimization achieves the desired results. Based on the results of preliminary control and compensation optimization, develop a dynamic ambient lighting spatial lighting optimization strategy. The goal of this step is to develop a complete lighting optimization solution to achieve dynamic and intelligent lighting adjustment. Experimental parameters are set, such as a system response time of 100 milliseconds, to ensure real-time adaptation to environmental changes. The optimization strategy development process involves integrating real-time monitoring data with the ambient lighting control system. A central control system receives real-time lighting data and ambient lighting control parameters within the area, creating a dynamic feedback mechanism. During implementation, adaptive control algorithms (such as fuzzy control or PID control) are used to adjust the brightness and distribution of the ambient lighting based on real-time lighting conditions. Set the objective function, such as maximizing the average light intensity in the area and minimizing the light unevenness, to ensure the optimization of the lighting effect.

[0017] Step S4: obtaining the user's real-time physiological state parameters, performing personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generating the user's physiological-music resonance frequency fine-tuning parameters; In this embodiment, after obtaining user authorization, wearable devices (such as smartwatches or physiological sensors) are used to collect the user's physiological data during the physiological state parameter acquisition process. These devices can monitor key physiological indicators such as heart rate, skin temperature, and respiratory rate in real time. Device accuracy and reliability are ensured, and sensors are regularly calibrated to improve data quality. The acquired physiological state data is transmitted in real time to a central processing system for data storage and management. Each data point should be timestamped to ensure traceability for subsequent analysis. During this process, signal stability is monitored in real time to ensure data is free of interference, and missing or outliers are promptly addressed to maintain data integrity. After acquiring the user's physiological state parameters, personalized natural circadian rhythm mining is performed. The goal of this step is to analyze the user's physiological data and identify individual circadian rhythm characteristics. Experimental parameters are set, such as selecting a 5-minute analysis window, to capture changing trends in the physiological data. The personalized rhythm mining process first requires preprocessing of the physiological data, including denoising and normalization. A filter (such as a low-pass filter) is used to remove high-frequency noise, and the data is then normalized for subsequent analysis. Data is modeled using time series analysis methods (such as the autoregressive moving average (ARIMA) model) to identify cyclical variations in physiological indicators. By calculating the mean and standard deviation of indicators such as the user's heart rate and respiratory rate, individual circadian rhythm characteristics are extracted. Heart rate variability can be analyzed to identify the frequency and amplitude of the user's natural rhythm. Furthermore, a Fourier transform can be used to convert physiological signals into the frequency domain, identify the primary frequency components, and extract the user's physiological resonance frequency. This process lays the foundation for subsequent fine-tuning of the physiological-music resonance frequency. After completing personalized natural circadian rhythm mining, fine-tuning of the physiological-music resonance frequency is performed. This step aims to adjust the frequency parameters of the music based on the user's circadian rhythm characteristics to achieve optimal resonance. Experimental parameters are set, for example, to adjust the frequency range of the music from 20Hz to 200Hz to cover most musical frequency bands. Fine-tuning the physiological-music resonance frequency first requires selecting suitable music material. Music samples of varying frequencies can be used to ensure coverage of a variety of styles and tempos. Spectral analysis of the music samples is performed to identify the primary audio frequency components. Then, using a fine-tuning algorithm, the music frequency is adjusted based on the user's physiological resonant frequency. If the user's physiological resonant frequency is 60Hz, the fundamental frequency of the music is adjusted to match this frequency. Using audio processing software (such as Ableton Live or Audacity), the pitch and speed of the audio are adjusted to ensure that the music matches the user's physiological rhythm. During the fine-tuning process, the user's feedback is monitored in real time to assess the impact of the music on their physiological state. Physiological monitoring equipment is used to record changes in the user's heart rate while listening to the fine-tuned music to ensure that the adjustment produces a positive physiological response. This generates the user's physiological-music resonant frequency fine-tuning parameters.The goal of this step is to convert the fine-tuning results into actionable parameters to facilitate subsequent dynamic music playback and atmosphere control. Experimental parameters are set, such as setting the update frequency of fine-tuning parameters to once every 5 minutes to ensure real-time adjustment based on the user's physiological state. The process of generating fine-tuning parameters involves integrating the identified physiological resonance frequency with the music frequency adjustment value to create a personalized parameter file. This file should include the user's physiological state, the current music frequency, and the recommended adjustment range for subsequent use in the music playback system. During the implementation process, a user-friendly interface is established to allow users to view and adjust these parameters. Users can monitor their physiological state in real time through the application and manually adjust the music frequency as needed.

[0018] Step S5: Obtain the user's ambient light operation log, perform user-specified light effect adjustment analysis, and mine the user's light effect preference trajectory to construct a user light effect satisfaction prediction curve; In this embodiment, during the acquisition of operation logs, a smart home control system monitors user operations on ambient lighting in real time. Whenever a user adjusts the brightness, color, or mode of the lighting, the system automatically records relevant information, including the timestamp, operation type (e.g., adjusting brightness or changing color), target brightness, and color value. This data is stored in a central database for subsequent analysis. To ensure data quality, system stability is regularly checked to ensure that the operation log accurately captures every user interaction. Furthermore, the database structure is designed so that each record clearly identifies the user identity, device information, and operation details, facilitating grouping and statistical analysis during subsequent analysis. After acquiring user operation logs, user-specified lighting effect adjustment analysis is performed. This step aims to analyze users' lighting effect adjustment behaviors in different environments and situations to identify their lighting effect preferences. Experimental parameters are set, such as selecting a one-week analysis window, to capture user lighting effect adjustment trends. During the lighting effect adjustment analysis, the acquired operation logs are first organized and cleaned. Duplicate and invalid operation records are removed to ensure data accuracy. Statistical analysis of users' lighting effect adjustment behaviors is performed using data analysis tools (e.g., the Pandas library in Python). The frequency of use of each lighting effect mode (such as warm light, cool light, and dimming) can be calculated to identify user preferences. Using visualization tools (such as Matplotlib or Seaborn), charts can be generated to illustrate user lighting effect adjustment behavior, showing changes in lighting effect preferences over time. Analyze user lighting effect preferences in different scenarios, such as work, relaxation, and socializing, to identify lighting effect needs in specific situations. After completing the lighting effect adjustment analysis, conduct user lighting effect preference trajectory mining. This step aims to analyze user operation history to extract the user's lighting effect preference trajectory for personalized recommendations. Experimental parameters can be set, such as setting the trajectory mining time range to three months to fully reflect users' long-term preferences. The process of user lighting effect preference trajectory mining involves time series analysis of operation logs. By chronologically arranging users' lighting effect adjustment records, trends in their lighting effect preferences can be identified. A sliding window technique can be used to segment user operation records into multiple time periods and analyze lighting effect choices within each time period. Clustering algorithms (such as K-means or DBSCAN) can be used to categorize users' lighting effect preferences and identify different user groups. Users can be categorized into "high brightness preferencers," "low brightness preferencers," and "color preferencers," creating user profiles. This process provides a basis for subsequent personalized recommendations. Furthermore, sequential pattern mining algorithms (such as GSP or PrefixSpan) can be used to extract common sequences of user lighting effect preferences and identify the trajectory of user lighting effect choices in specific situations. This helps understand user lighting effect usage habits and changes in preferences over a specific time period.Based on the user's lighting preference trajectory, a user lighting satisfaction prediction curve is constructed. The goal of this step is to predict the user's future satisfaction with lighting effects based on their operational history and preference characteristics. Experimental parameters are set, such as setting a satisfaction score range of 1 to 10, to quantify the user's lighting satisfaction. The process of constructing the satisfaction prediction curve involves selecting an appropriate machine learning model (such as linear regression or random forest) and training it using the user's lighting preference data. The user's lighting effect selection, contextual information, and corresponding satisfaction score are used as training data to build a model to predict user satisfaction under different lighting effect settings. After model training is completed, cross-validation is used to evaluate the model's accuracy to ensure the reliability of the prediction results. By comparing actual user feedback with the model's prediction results, the model parameters are adjusted to improve prediction accuracy.

[0019] Step S6: The dynamic atmosphere light space light effect optimization strategy is user preference-driven and regulated according to the user light effect satisfaction prediction curve and the user physiological-music resonance frequency fine-tuning parameters to perform the dynamic atmosphere light intelligent collaborative control operation.

[0020] In this embodiment, experimental parameters are set, such as a satisfaction rating scale of 1 to 10, to quantify user satisfaction. While collecting satisfaction prediction curves, a machine learning model (such as random forest or linear regression) is trained on user lighting effect preference data. The lighting effect settings, contextual information, and corresponding satisfaction ratings from the user's operation log are used as training data to build a model that predicts user satisfaction with different lighting effect combinations. After model training is complete, cross-validation is used to evaluate the model's accuracy to ensure the reliability of the prediction results. By comparing actual user feedback with the model's predictions, model parameters are gradually optimized to improve the accuracy of satisfaction predictions. The resulting prediction curve will demonstrate the changing trends in user satisfaction under different lighting conditions, forming a visual chart to facilitate subsequent analysis. After collecting the user's lighting effect satisfaction prediction curves, the user's physiological-music resonance frequency fine-tuning parameters are integrated. This step aims to combine the user's physiological response with the lighting effect settings to achieve more precise ambient lighting control. Experimental parameters are set, such as setting the resonance frequency range to 20Hz to 200Hz to cover most music frequency bands. The process of integrating physiological-music resonance frequency parameters involves acquiring real-time physiological data (such as heart rate and respiratory rate) from the user's physiological monitoring device, as well as the user's music resonance frequency. By analyzing this data, the user's resonance frequency in specific physiological states is identified and matched with the user's lighting preference. Using data fusion technology, the physiological data is combined with the lighting satisfaction prediction curve to form a comprehensive user preference model. If the user prefers warm light and low-frequency music in a specific physiological state (such as relaxation), this information can be incorporated into the dynamic ambient lighting control strategy. After integrating the user's satisfaction prediction curve and physiological-music resonance frequency parameters, a user preference-driven control strategy is generated. The goal of this step is to dynamically adjust the ambient lighting parameters based on the user's lighting preference and physiological response to achieve the best user experience. Experimental parameters are set, such as a 100 millisecond control response time, to ensure real-time adjustments. The process of generating the control strategy involves establishing a central control system that receives real-time user physiological data and satisfaction prediction information. Based on the user's current physiological state and predicted satisfaction, the system automatically adjusts the ambient lighting's brightness, color, and pattern. If the user's heart rate decreases and their satisfaction is predicted to be high, the system can choose to increase the brightness of the warm light to enhance the user's sense of relaxation. At the same time, a feedback mechanism is used to monitor the effectiveness of lighting control. By collecting real-time user feedback data, the system evaluates the impact of lighting adjustments on the user's physiological state and satisfaction. If user feedback is poor, the system automatically adjusts its strategy to ensure continuous optimization of the user experience. Based on the control strategy driven by user preferences, intelligent collaborative control of dynamic ambient lighting is performed. The goal of this step is to achieve automated control of ambient lighting, enabling the lighting to dynamically change based on the user's real-time physiological state and satisfaction prediction.Experimental parameters are set, such as setting the lighting control update frequency to 5 times per second to ensure timely response to user needs. The control process involves applying the generated control strategy to the ambient lighting through the smart home system. The system monitors the user's physiological state and satisfaction in real time, analyzing this data to dynamically adjust the various ambient lighting parameters. If the user exhibits a high level of relaxation under a specific physiological state, the system automatically selects appropriate lighting settings, such as low-brightness warm light, and combines them with corresponding music frequencies to enhance the overall experience.

[0021] In this embodiment, refer to Figure 2 , is a flowchart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Collect real-time audio signal streams; perform multi-scale wavelet decomposition on the real-time audio signal streams to obtain time-frequency spectra of different scales; Calculating the frequency fluctuation of the time-frequency spectrum and performing frequency fluctuation distribution analysis to generate frequency fluctuation distribution features of different scales; Tracking the frequency time series distribution of the frequency fluctuation distribution characteristics to construct an audio frequency time series fluctuation curve; Perform audio rhythm mapping based on time-frequency spectra of different scales and construct audio third-order spatial rhythm feature maps; Based on the audio third-order spatial rhythm feature map and frequency-time fluctuation curve, multi-scale rhythm hierarchical structure perception is performed to construct an audio rhythm feature perception map.

[0022] In this embodiment, a suitable audio acquisition device is selected, such as a highly sensitive microphone or audio interface. Assume that a digital audio interface with a sampling rate of 44.1kHz is used to ensure that sufficient audio details are captured. After connecting the microphone, use audio processing software (such as Audacity or MATLAB) to perform real-time acquisition of audio signals. During the acquisition process, set the recording time of the audio signal stream. Set it to continuously record 10 minutes of audio signals. Monitor the signal strength of the audio input to ensure that it is not distorted due to overload. Ensure the quality and stability of the signal by displaying the audio waveform in real time. Obtain a signal stream containing 10 minutes of audio to provide raw data for subsequent multi-scale wavelet decomposition and analysis. After completing the acquisition of the real-time audio signal stream, perform multi-scale wavelet decomposition. This step aims to decompose the audio signal into different frequency components to facilitate time-frequency analysis. Select a suitable mother wavelet function, such as Morlet wavelet or Daubechies wavelet, to facilitate the decomposition of the audio signal. Use a wavelet transform toolkit (such as PyWavelets or MATLAB's Wavelet Toolbox) to perform wavelet transform on the collected audio signal. Set multiple scales for decomposition, for example, select scales from 1 to 8 for analysis. Through wavelet transform, the original signal is decomposed into multiple approximate and detail coefficients to generate corresponding time-frequency spectra. Each scale corresponds to a different frequency range, which can reveal the characteristics of the audio signal at different frequencies. After wavelet decomposition, time-frequency spectra of different scales are obtained, and the frequency distribution and energy distribution of each scale are recorded. These time-frequency spectra will provide basic data for subsequent frequency fluctuation analysis. After obtaining time-frequency spectra of different scales, the frequency fluctuations of the time-frequency spectra are calculated, and frequency fluctuation distribution analysis is performed. This step aims to reveal the changing characteristics of frequency components over time.

[0023] Frequency information is extracted from the time-frequency spectrum of each scale, and the mean and standard deviation of the frequency are calculated. The time-frequency spectrum of scale 2 can be analyzed to obtain the statistical data of its frequency fluctuations. Assume that at this scale, the mean value of the frequency fluctuation is 440Hz and the standard deviation is 50Hz. Perform frequency fluctuation distribution analysis and draw a distribution histogram of frequency fluctuations to show the frequency of occurrence of different frequency components. This can be achieved through Python's Matplotlib library or the drawing function in MATLAB. Record the distribution characteristics of frequencies at different scales, such as the prominent performance of high-frequency components in certain time periods. Generate frequency fluctuation distribution characteristics at different scales to provide data support for subsequent time series tracking and rhythm mapping. After obtaining the frequency fluctuation distribution characteristics, perform frequency time series distribution tracking and construct an audio frequency time series fluctuation curve. This step aims to visualize the frequency fluctuation information in order to analyze the dynamic changes of the audio signal. Arrange the frequency fluctuation data in time series to generate frequency time series data. Assume that the frequency value at each time point is: Time point 1: 440Hz Time point 2: 450Hz Time point 3: 430Hz Use a time series chart to display the frequency fluctuation curve. Use Matplotlib or other visualization tools to plot the frequency values ​​as a curve that changes over time. The fluctuations of the curve reflect the rhythm and changes of the audio signal and can intuitively show the dynamic characteristics of the frequency. In this way, an audio frequency time series fluctuation curve is constructed, providing a basis for subsequent rhythm mapping and rhythmic feature analysis. After completing the construction of the frequency time series fluctuation curve, perform audio rhythm mapping. This step aims to visualize the rhythmic characteristics of the audio signal for easy identification and analysis. Analyze the rhythmic patterns in the frequency time series fluctuation curve. The main rhythmic components can be identified by calculating the autocorrelation function of the periodic pattern. Suppose that a main rhythm period of 2 seconds is found in the frequency time series curve.

[0024] Based on the identified rhythmic cycles, they are mapped into a third-order space. A three-dimensional visualization tool (such as Matplotlib's 3D plotting function) is used to construct a third-order audio spatial rhythmic feature map. Each point represents a specific frequency and time combination, reflecting the rhythmic characteristics of the audio signal. The generated third-order audio spatial rhythmic feature map clearly demonstrates the rhythmic variations in the audio signal, providing a foundation for subsequent rhythmic feature perception. Based on the third-order audio spatial rhythmic feature map and the frequency-time fluctuation curve, a multi-scale rhythmic hierarchy is perceived to construct an audio rhythmic feature perception map. This step aims to comprehensively analyze the rhythmic characteristics of the audio signal for a deeper understanding of the audio content. The third-order audio spatial rhythmic feature map and the frequency-time fluctuation curve are combined to identify rhythmic features of different frequency and rhythmic combinations. Hierarchical clustering analysis is used to cluster similar rhythmic patterns to form a rhythmic hierarchy. An audio rhythmic feature perception map is generated to display the characteristics of each rhythmic hierarchy. Assume that, within a certain hierarchy, rhythms in the frequency range of 400-500Hz have a distinct rhythmic feel. Through such comprehensive analysis, we can achieve multi-scale rhythmic hierarchical perception of audio signals, and ultimately construct a rich audio rhythmic feature perception map, providing a basis for subsequent audio signal processing and applications.

[0025] In this embodiment, the specific steps of performing audio rhythm mapping based on time-frequency spectra of different scales and constructing an audio third-order spatial rhythm feature map are as follows: Perform deep audio feature analysis on time-frequency spectra of audio at different scales to extract the rhythm structure tensor, pitch variation tensor, and rhythm density tensor of the audio signal; Based on the rhythm structure tensor, the global rhythm prosody analysis is carried out to obtain the characteristics of the temporal resonance structure change; Fit the time variation of low-frequency components according to the pitch variation tensor and extract the low-frequency component variation sequence; Perform transient frequency mutation detection on the low-frequency component change sequence and identify transient beat transition points; Mining audio emotion tensor fluctuations based on the rhythm density tensor to obtain real-time audio emotion tensor fluctuation features; The third-order spatial audio rhythm mapping is performed on the changing characteristics of the temporal resonance structure, the transient beat transition points and the real-time audio emotion tensor fluctuation characteristics to construct the audio third-order spatial rhythm feature map.

[0026] In this embodiment, a wavelet transform or short-time Fourier transform (STFT) method is used to generate a time-frequency spectrum of audio. Assuming Morlet wavelet analysis is used, the scale parameter is set between 1 and 8 to ensure coverage of different frequency ranges. These methods can be used to obtain the distribution of the audio signal in time and frequency. A rhythmic structure tensor is extracted from the generated time-frequency spectrum. This can be achieved by calculating the energy distribution of the audio signal, recording the energy value of the frequency component at each moment to form a three-dimensional tensor (time, frequency, and energy dimensions). Similarly, a pitch variation tensor is extracted. By analyzing the frequency center of the audio signal and its variations, the temporal variation of the pitch can be determined. The rhythmic density tensor is constructed by calculating the energy density and its rate of change within a specific frequency band. The rhythmic structure tensor, pitch variation tensor, and rhythmic density tensor provide basic data for subsequent analysis. After obtaining the rhythmic structure tensor of the audio signal, global rhythmic prosody analysis is performed. This step aims to extract the temporal resonance structure variation characteristics of the audio signal, helping to understand the overall rhythmic sense of the audio. Analyze the energy distribution within the rhythmic structure tensor and identify the main rhythmic components by calculating statistical features of the entire tensor (such as mean, standard deviation, and peak). Signal processing tools (such as the SciPy library) can be used to perform a Fourier transform on the tensor to extract its frequency components. Dynamic time warping (DTW) or similarity analysis methods can be used to compare rhythmic structures across different time periods to identify global rhythmic variations. For example, suppose the average period of a rhythmic cadence changes from 1.5 seconds to 1.2 seconds over a certain period, indicating an acceleration of the tempo. These analyses reveal the characteristics of temporal resonance structure variations, clarifying the rhythmic characteristics of the audio signal across different time periods and providing data support for subsequent audio feature mapping. Following global rhythmic prosody analysis, the temporal variation of the low-frequency component is fitted based on the pitch variation tensor. This step aims to extract the sequence of low-frequency component variations in the audio signal, facilitating subsequent detection of transient frequency mutations.

[0027] Extract the low-frequency component from the pitch variation tensor. Assuming the low-frequency range is set to 20Hz to 200Hz, use a bandpass filter to process the audio signal and extract the low-frequency components. Through time-domain signal analysis, record the amplitude and phase changes of the low-frequency components. Use curve fitting methods (such as polynomial fitting or spline interpolation) to model the temporal variation of the low-frequency components. Assume that a low-frequency variation function is obtained through fitting, which can well describe the variation trend of the low-frequency components. Obtain a low-frequency component variation sequence to provide basic data for transient frequency mutation detection. After obtaining the low-frequency component variation sequence, perform transient frequency mutation detection to identify transient beat transition points. This step aims to capture mutation phenomena in the audio signal and help understand its dynamic characteristics.

[0028] Use a transient detection algorithm (such as the short-time energy method or the zero-crossing rate method) to analyze the low-frequency component change sequence. Set an appropriate threshold to identify transient points where the frequency changes suddenly. For example, set the threshold to 0.3. Any time the low-frequency component changes above the threshold, it is marked as a transient transition. Record all identified transient transitions and analyze their distribution within the audio signal. Suppose five transient transitions are detected throughout the entire signal, located at 0.5 seconds, 1.2 seconds, 2.0 seconds, 3.1 seconds, and 4.5 seconds. Identifying transient beat transitions provides important data for subsequent emotion analysis and rhythm mapping. Mining the audio emotion tensor fluctuations based on the rhythm density tensor yields real-time emotion tensor fluctuation features. This step aims to analyze the emotional variation characteristics within the audio signal. Emotional features are extracted from the rhythm density tensor. By analyzing the rhythm intensity and frequency of the audio signal, emotion categories (such as happiness, sadness, anger, etc.) are assigned and classified using emotion recognition algorithms (such as support vector machines or deep learning models). Record the emotional fluctuation characteristics at different time points. Suppose that in some time periods, the emotional characteristics of the audio signal are identified as "excited" and in other time periods as "dull." Through these analyses, we can obtain the real-time audio emotion tensor fluctuation characteristics, reflecting the emotional changes of the audio signal.

[0029] A third-order spatial audio rhythm mapping is performed on the temporal resonance structure variation features, transient beat transition points, and real-time audio emotion tensor fluctuation features to construct an audio third-order spatial rhythm feature map. The temporal resonance structure variation features and transient transition points are combined to form a set of data points in three-dimensional space. These data points can be displayed using three-dimensional visualization tools (such as Matplotlib's 3D plotting function). Using the real-time audio emotion tensor fluctuation features, the data points in three-dimensional space are labeled and colored to reflect the changes in audio rhythm under different emotional states. Points in an "excited" state might appear red, while points in a "depressed" state might appear blue. This constructed audio third-order spatial rhythm feature map clearly demonstrates the comprehensive characteristics of the audio signal in the time, frequency, and emotional dimensions, providing important visual support for subsequent audio signal processing and analysis.

[0030] In this embodiment, refer to Figure 3 , is a flowchart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Perform spatial audio orientation analysis based on real-time audio signal stream to obtain the spatial orientation of different audio signals; Perform three-dimensional audio propagation positioning simulation on the spatial orientation of different audio signals and extract the spatial propagation position information of each audio signal; Fit the audio position distribution to the spatial propagation position information and build a real-time audio spatial distribution model; Identify the adjustable ambient light strips in the area and calculate the position coordinates of each adjustable ambient light strip; Based on the position coordinates of each adjustable ambient light strip, the real-time audio spatial distribution model is accurately matched to build an ambient light distribution matching network; Based on the audio rhythm feature perception map, the distributed matching network of the atmosphere light is used to adaptively control the dynamic atmosphere light parameters, and an adaptive dynamic atmosphere light control strategy is obtained.

[0031] In this embodiment, one or more microphone arrays are used to collect audio signals. Assume that a four-microphone array is configured to ensure that audio signals from different directions can be captured. The microphones can be arranged in a square or circular pattern to improve spatial resolution. Beamforming technology is used to perform spatial audio orientation analysis. The beamforming algorithm weights and phase-adjusts the signals from different microphones to enhance signals from specific directions and suppress noise from other directions. By calculating the delay of the audio signals received by different microphones, the direction of the audio source can be estimated. Assume that the algorithm processes the spatial orientations of the two audio signals to be 30° and 150°, respectively. This orientation information provides basic data for subsequent three-dimensional positioning simulation. After completing the spatial audio orientation analysis, a three-dimensional audio propagation positioning simulation is performed. This step aims to extract the spatial propagation position information of each audio signal and construct a propagation model of the audio signal.

[0032] Based on the known audio direction and microphone array position, a sound wave propagation model (such as the spherical wave propagation model) is used to perform a 3D positioning simulation. Assuming the center of the microphone array is (0, 0, 0), the spatial coordinates of the audio source are calculated based on different azimuths and distances. For an audio signal with an azimuth angle of 30° and a distance of 5 meters, its 3D coordinates can be calculated as: x=5 * cos(30°) ≈ 4.33 y=5 * sin(30°) ≈ 2.5 z=0 (assuming it is on the same plane) This method generates spatial propagation position information for each audio signal and records this information for subsequent analysis. After obtaining the spatial propagation position information for the audio signal, audio position distribution fitting is performed. This step aims to construct a real-time audio spatial distribution model to better understand the spatial distribution characteristics of the audio signal. The spatial position data for all audio signals is organized into a single dataset. This position data is then modeled using data fitting methods (such as Gaussian process regression or kriging interpolation) to generate a spatial distribution model for the audio signal. For multiple audio sources, their position coordinates are assumed to include multiple points, such as (4.33, 2.5, 0), (1.0, 3.0, 0), (2.5, 1.0, 0), and so on. Using interpolation methods, a continuous audio distribution model is constructed that reflects the intensity and distribution characteristics of audio signals in different areas. This generated real-time audio spatial distribution model provides the basis for subsequent ambient lighting matching and dynamic control.

[0033] Identify the adjustable ambient light strips in the area and calculate the position coordinates of each adjustable ambient light strip. The purpose of this step is to ensure that the ambient light can effectively match the audio signal. Use a laser rangefinder or ultrasonic sensor to measure the position of the ambient light strips. Assume that there are multiple adjustable ambient light strips in the area, installed in different locations. By measuring the coordinates of each ambient light strip, record its position. Assume that the coordinates of the three ambient light strips are: Light strip 1: (3.0, 4.0, 0) Light strip 2: (5.0, 1.0, 0) Light strip 3: (1.0, 2.5, 0) These position coordinates will be used for subsequent audio matching and dynamic control to ensure that the light strip can respond to changes in the audio signal.

[0034] After obtaining the position coordinates of the adjustable ambient light strips, accurate audio matching is performed against the real-time audio spatial distribution model based on these coordinates. This step aims to construct an ambient light distribution matching network, enabling the light strips to dynamically interact with audio signals. The distance between each ambient light strip and the audio source in the audio spatial distribution model is calculated. By comparing the spatial positions of the light strips and the audio sources, the audio signal that best responds to each light strip is determined. A nearest neighbor algorithm is used to find the audio signal source closest to each ambient light strip. An ambient light distribution matching network is constructed. Each light strip is assigned one or more audio signal sources, ensuring that the light strips can adjust to the intensity and characteristics of different audio signals. This creates a dynamic ambient light distribution matching network, achieving coordination between the audio signal and the light strips. Based on the audio rhythm feature perception map, the ambient light distribution matching network is used to adaptively control dynamic ambient light parameters. This step aims to automatically adjust the brightness and color of the ambient light based on changes in the audio signal to create a suitable ambient atmosphere. The audio rhythm feature perception map is analyzed to extract characteristics such as rhythm, frequency, and emotion of the audio signal. Assume that the audio signal has a rhythm frequency of 120 BPM and an emotional characteristic of "excitement." Set the control strategy for the ambient lighting. If the audio signal is "exciting," set the light strip's brightness to a higher value (e.g., 80%) and a warmer color. If the audio signal is "dull," reduce the brightness (e.g., 30%) and use a cooler color. Adjust the light's brightness based on the music's amplitude; the greater the amplitude, the brighter the light. Adjust the light's color based on the music's frequency distribution, with low frequencies corresponding to warm tones and high frequencies to cool tones. Adjust the light's flashing frequency based on the music's rhythm, with fast-paced music corresponding to rapid flashes and slow-paced music corresponding to slow changes. By dynamically adjusting the light strip's parameters, an adaptive control strategy is implemented to enhance the audio experience. This creates an ambient lighting control system that responds to changes in the audio signal in real time.

[0035] In this embodiment, refer to Figure 4 , is a flowchart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Perform preliminary ambient light control based on the adaptive dynamic ambient light control strategy and obtain real-time images of the area based on smart home devices; Performing ambient light spatial layout analysis on real-time images within the area to obtain ambient light spatial layout characteristics; Perform geometric structure distribution recognition on real-time images within the area to generate indoor geometric structure distribution features; Build a 3D indoor area model by performing 3D point cloud modeling based on the spatial layout characteristics of ambient light and the distribution characteristics of indoor geometric structures; The three-dimensional indoor area model is used to compensate and optimize the coverage of weak light intensity areas, and a dynamic atmosphere lighting space lighting effect optimization strategy is constructed.

[0036] In this embodiment, real-time audio signal information is acquired. Assuming the user wishes to relax in a quiet environment, the system analyzes the audio signal as low-frequency and soft. Based on these characteristics, the system automatically adjusts the brightness and color temperature of the ambient light. The brightness of the ambient light is set to 50% and the color temperature to 3000K (warm white light) to create a warm and comfortable environment. Control commands are sent using a smart home control system (such as Home Assistant or SmartThings) to ensure that the ambient light responds to changes in the audio signal in real time. After implementing initial ambient light control, the system uses smart home devices to acquire real-time images of the area. This step aims to capture the current state of the indoor environment for subsequent environmental analysis. Real-time image acquisition is performed using a smart camera (such as a webcam or home security camera). Assume the camera has a resolution of 1920x1080 and a frame rate of 30 frames per second to ensure sufficiently clear images. When acquiring images, a timed acquisition schedule is set, for example, capturing an image every 5 seconds. Images are transmitted to the main control system using image processing software (such as OpenCV) for subsequent analysis. Ensure image acquisition stability and regularly check the camera's operating status to ensure image quality. The system captures a series of real-time images within an area, providing raw data for subsequent ambient light and geometry analysis. After acquiring the real-time images within the area, the system conducts an ambient light spatial layout analysis. This step aims to extract the distribution characteristics of indoor light and understand its spatial distribution. Image processing techniques are used to analyze the light distribution within the real-time images. By calculating the brightness value of each pixel, grayscale processing is used to convert the RGB image into a grayscale image. For example, if the average brightness of a region in the image is 75 (out of a maximum of 255), this indicates that the area is brightly lit.

[0037] Threshold segmentation techniques are used to identify areas of light intensity. A threshold (e.g., 60) is set to distinguish between bright and dim areas. The spatial distribution characteristics of the light are calculated by calculating the proportion of each area. Bright areas account for 40% of the total image, while dim areas account for 60%. An ambient light spatial distribution map is generated, clearly showing the light distribution characteristics of different indoor areas and providing a foundation for subsequent geometric structure analysis. After completing the ambient light spatial distribution analysis, geometric structure distribution recognition is performed on the real-time image within the area. This step aims to extract indoor geometric features for subsequent 3D modeling. Edge detection algorithms (such as Canny edge detection) are used to process the image to identify the outlines of indoor objects. By extracting the edge features of objects in the image, the geometric structure of the objects is constructed. Morphological operations (such as dilation and erosion) are used to further optimize the edge detection results and remove noise and small interference. Based on the identified outlines, the geometric structure characteristics of indoor objects, such as walls, furniture, and windows, are extracted. Assume that three walls and one window are identified in the image. The coordinates and dimensions of these structures are recorded. A geometric structure distribution map is generated, laying the foundation for subsequent 3D modeling. After obtaining the indoor geometric structure distribution characteristics, 3D point cloud modeling is performed based on the spatial layout characteristics of the ambient light and the indoor geometric structure distribution characteristics. The purpose of this step is to construct a complete 3D model of the indoor area. Combining the lighting layout and geometric structure characteristics, modeling is performed using 3D modeling software (such as Blender or SketchUp). Based on the identified geometric features, a 3D object model is constructed and the light distribution information is mapped onto the model. 3D point cloud data of the indoor area is generated using point cloud technology. Point cloud data is acquired through laser scanning or structured light scanning, and the position and color information of each point is recorded and integrated into the 3D model. Assuming that the generated 3D point cloud model contains 100,000 points, it can accurately reflect the indoor environment's geometric structure and light distribution characteristics. This complete 3D indoor area model is constructed, providing a foundation for subsequent lighting optimization.

[0038] Optimize the coverage compensation of low-light-intensity areas in the three-dimensional indoor area model. The purpose of this step is to ensure that low-light areas are effectively compensated for lighting to improve the overall ambient brightness. Analyze the light intensity distribution in the three-dimensional model and identify low-light-intensity areas. Assume that the average light intensity of an area is identified to be lower than 40 (out of 255), and compensation is required. Use dynamic lighting simulation technology to compensate for low-light areas. You can use virtual light sources for simulation and adjust the position, brightness, and color of the light source to increase the light intensity in the area. Set the compensating light source close to the low-light area and set the brightness to 80%. Generate a dynamic ambient light space lighting optimization strategy to ensure that low-light areas can be effectively compensated under different times and environmental conditions. In this way, the overall comfort and visual effects of the indoor environment are improved.

[0039] In this embodiment, the specific steps of performing compensation optimization on the weak light intensity area coverage of the three-dimensional indoor area model and constructing a dynamic atmosphere light space lighting effect optimization strategy are as follows: Track the distribution of ambient light rays in the 3D indoor area model and construct a heat map of the ambient light ray distribution; Detect weak interaction areas of ambient light rays on the ambient light distribution heat map and mark the weak interaction areas of ambient light rays; Identify adjacent ambient light strips based on the weak interaction area of ​​the ambient light; Evaluate the spatial lighting balance of areas with weak interaction of ambient lighting to determine the required intensity of lighting compensation in these areas; Performing an atmosphere light coverage compensation calculation on the illumination compensation requirement intensity based on the adjacent atmosphere light strips to generate an atmosphere light coverage compensation parameter; The adaptive dynamic atmosphere light control strategy is used to optimize the spatial lighting effect according to the atmosphere light coverage compensation parameters, and a dynamic atmosphere light spatial lighting effect optimization strategy is constructed.

[0040] In this embodiment, a ray tracing algorithm (such as path tracing or ray casting) is used to simulate the lighting of the indoor model. Assume that multiple ambient lights are configured in the model, and the light source characteristics of each light (such as light intensity, beam angle, and light temperature) are recorded. The light intensity of each ambient light is set to 800 lumens and the beam angle is set to 60 degrees. During the simulation process, light is emitted from each ambient light, reflected and refracted by objects in the space, and finally reaches each spatial point. By calculating the light intensity reaching each point, a heat map is generated. Using a heat map visualization tool (such as Matplotlib or the Heatmap library), the light intensity is mapped to color, with red indicating high light intensity (>300 lumens) and blue indicating low light intensity (<100 lumens). The resulting ambient light light distribution heat map can clearly display the lighting distribution characteristics of various areas in the room. After generating the ambient light light distribution heat map, weak interaction areas of ambient light lights are detected. The purpose of this step is to mark areas with insufficient light intensity for subsequent compensation processing. A threshold for light intensity is set to identify weak interaction areas. Assume a threshold of 100 lumens. Any area with light intensity below this threshold is considered a weak interaction area. By traversing each pixel in the heat map, areas with light intensity below the threshold are recorded. Image processing techniques, such as the connected component labeling algorithm, are used to mark these weak interaction areas. By identifying their outlines, they can be distinguished from other areas. The detected weak interaction areas are 2 square meters in size. These areas are marked and their spatial coordinates are recorded for subsequent analysis. Successfully marking the areas with weak interaction in ambient light provides basic data for evaluating lighting compensation needs. After marking the weak interaction areas, adjacent ambient light strips are identified. This step aims to determine which ambient light strips can be used for lighting compensation to improve indoor lighting uniformity. Using a spatial coordinate system, the coordinates of the weak interaction areas are compared with the positions of all ambient light strips. Assume the coordinates of the ambient light strips are (3.0, 4.0, 0), (5.0, 1.0, 0), and (1.0, 2.5, 0). The distances between the weak interaction areas and each ambient light strip are calculated. Use the Euclidean distance formula to determine which light strips are closest to the weak interaction area. If the coordinates of a weak interaction area are (4.0, 3.0, 0), the distance to light strip 1 is calculated as: Distance = √((4.0-3.0)² + (3.0-4.0)²) = √(1 + 1) = √2 ≈ 1.41 meters.

[0041] In this way, the ambient light strips within a certain distance from the weak interaction area are identified for subsequent lighting compensation calculations. After identifying the adjacent ambient light strips, the spatial lighting balance of the weak interaction area is evaluated. The purpose of this step is to evaluate the intensity of the lighting compensation requirements in these areas in order to reasonably allocate light sources. Calculate the average lighting intensity of the weak interaction area. By extracting the lighting data in the area, calculate the average lighting intensity. Assuming that the lighting intensity data in the weak interaction area is [80, 70, 60] lumens, the average lighting intensity is calculated as: Average = (80 + 70 + 60) / 3 = 70 lumens; Calculate the required intensity of light compensation. Set the ideal light intensity (such as 300 lumens) and calculate the required intensity: Required intensity = ideal intensity - average light intensity = 300-70 = 230 lumens; This required intensity will be used in subsequent lighting compensation calculations to ensure that the lighting in weak interaction areas is effectively improved. After obtaining the required intensity for lighting compensation, the intensity is calculated for ambient light coverage compensation based on the adjacent ambient light strips. The purpose of this step is to adjust the output of the ambient light according to the required intensity to meet the lighting requirements of the weak interaction area. Determine the light output characteristics of the adjacent ambient light strips. Assume that the maximum light output of the adjacent light strips 1 and 2 is 800 lumens and 600 lumens, respectively. Calculate the compensation output value of each light strip based on the required intensity. Set the compensation strategy to determine how to distribute the lighting requirements. The required intensity can be evenly distributed to the adjacent light strips, or weightedly distributed according to the maximum light output of each light strip. If even distribution is chosen, the compensation output of each light strip is: Light strip 1 compensation = 230 lumens / 2 = 115 lumens Light strip 2 compensation = 230 lumens / 2 = 115 lumens Generate ambient light coverage compensation parameters to provide a basis for subsequent dynamic control. Based on the ambient light coverage compensation parameters, optimize the spatial lighting effect of the adaptive dynamic ambient light control strategy. This step aims to ensure ideal indoor lighting and enhance the user experience. Combining the compensation parameters with real-time environmental data, adjust the ambient light output. Use the control module in the smart home system to send corresponding control commands to each ambient light. Set the output of light strip 1 to 115 lumens and the output of light strip 2 to 115 lumens. Monitor lighting changes and make real-time adjustments to ensure that the lighting intensity in low-interaction areas remains within the ideal range. Use feedback mechanisms (such as light sensors) to monitor light intensity in real time and immediately adjust the light strip output if insufficient light is detected. This dynamic ambient light spatial lighting optimization strategy enables intelligent adjustment of indoor lighting, ensuring the best visual experience for users under varying environmental conditions.

[0042] In this embodiment, step S4 includes the following steps: The user's heart rate and respiratory rate are collected by the user's smart wearable device to obtain the user's real-time physiological status parameters; Conduct personalized natural physiological rhythm mining based on the user's real-time physiological state parameters to generate personalized natural physiological rhythm cycles; Based on the audio rhythm feature perception map, the personalized natural physiological rhythm cycle is analyzed for phase synchronization to obtain the user-audio rhythm matching degree; Based on the user-audio rhythm matching degree, the physiological-music resonance frequency is fine-tuned to generate the user physiological-music resonance frequency fine-tuning parameters.

[0043] In this embodiment, a suitable smart wearable device, such as a smartwatch or heart rate monitor, is selected. These devices typically have heart rate and respiratory rate monitoring functions. Assume that the selected device has a high-precision sensor that can update data once per second. After the user wears the device, the system collects data in real time, recording heart rate (e.g., beats per minute) and respiratory rate (e.g., breaths per minute). Assume that during one monitoring session, the user's heart rate is 75 bpm and respiratory rate is 16 bpm. This data is transmitted to the main control system via Bluetooth or Wi-Fi for storage and analysis. These real-time physiological state parameters will lay the foundation for subsequent rhythm mining and music resonance analysis. After obtaining the user's real-time physiological state parameters, personalized natural physiological rhythm mining is performed. The purpose of this step is to analyze the user's physiological data and generate personalized rhythmic cycles that suit their physiological characteristics. The heart rate and respiratory rate data are processed using time series analysis methods. A sliding window technique can be used to calculate the average heart rate and respiratory rate for each time period. Set the window size to 5 minutes, gradually slide the window, and record the average value within each window. Use Fourier transform to analyze the data spectrum and identify the main periodic components. Suppose the Fourier transform results show that the main frequency component of the heart rate data is 0.5Hz (corresponding to one cycle every 120 seconds), while the respiratory rate is 0.2Hz (corresponding to one cycle every 300 seconds).

[0044] Through these analyses, a personalized natural circadian rhythm cycle is generated for the user, recording the periodic variations in heart rate and respiratory rate to reflect the user's circadian rhythm. After the personalized natural circadian rhythm cycle is mined, phase synchronization analysis is performed based on the audio rhythmic feature perceptual map to determine the degree of match between the user and the audio rhythm. This step aims to assess the compatibility between the user's circadian rhythm and the audio rhythm. The audio rhythmic feature map is obtained and its frequency, rhythm, and timing information are analyzed. Assuming the primary rhythmic frequency of the audio is 120 beats per minute (BPM), which converts to 2 Hz, the user's natural circadian rhythm cycle is compared with the audio rhythm, and phase synchronization analysis is used to assess the degree of match. This can be achieved by calculating the phase difference. If the user's heart rate cycle is close to the audio rhythm cycle, the match is high. Assuming the user's heart rate cycle is 120 seconds (0.5 Hz), the phase difference is calculated compared to the audio rhythm cycle (30 seconds). This method determines the degree of match between the user and the audio rhythm, for example, a 75% match. After determining the user-audio rhythm match, fine-tuning of the physiological-music resonance frequency is performed.

[0045] A fine-tuning strategy is set to determine the frequency adjustment based on the degree of match. If the match is less than 50%, the music's rhythmic frequency needs to be increased; if the match is between 50% and 75%, a slight adjustment is made; if the match is above 75%, the current frequency is maintained. For example, if the current music frequency is 2Hz, based on a 75% match, the frequency is fine-tuned to 2.1Hz to promote better physiological resonance. The fine-tuning process can be achieved using digital signal processing techniques, by changing the audio signal's sampling rate or using audio effects. Fine-tuning parameters for the user's physiological-music resonance frequency are generated to support subsequent music playback and adjustments.

[0046] In this embodiment, the specific steps of step S5 are: Obtain user atmosphere light operation logs; extract user lighting effect adjustment instructions based on user atmosphere light operation logs; Perform specified light effect adjustment analysis on the user's light effect adjustment instructions and extract the user's subjective light effect preference vector; Calculate the color, brightness, and change rate of the user's subjective light effect preference vector, perform multi-dimensional feature encoding, and construct a multimodal representation space for light effects; Extracting the ambient light parameters before the user's operation based on the user's ambient light operation log; Calculating the user-adjusted parameter deviation in the light effect multimodal representation space according to the ambient light parameters before the user operation, thereby obtaining the user-adjusted light effect parameter deviation value; The user's lighting effect preference trajectory is mined based on the deviation value of the lighting effect parameters adjusted by the user, and a user lighting effect satisfaction prediction curve is constructed.

[0047] In this embodiment, a smart home system (such as Home Assistant or SmartThings) is used to record the user's operation behavior on the ambient light in real time. Each time the user adjusts the lighting settings, the system will record the operation time, operation type (such as on, off, brightness adjustment, color change, etc.), and the newly set parameters. Suppose that in a certain operation, the user adjusts the light brightness to 70% and the color temperature to 3000K, and records the operation time as 11:00 on May 13, 2023. All operation logs will be stored in the database as structured data for subsequent analysis. Successfully obtaining the user's ambient light operation log provides basic data for subsequent light effect adjustment analysis. After obtaining the user operation log, the user's light effect adjustment instructions are extracted. The purpose of this step is to analyze the user's adjustment behavior and identify their light effect preferences. The user operation log is parsed to extract instructions related to light effect adjustment. Data parsing tools (such as Python's pandas library) can be used to process the operation log and filter out records containing brightness and color parameters. The following instructions are extracted from the operation log: Time: May 13, 2023, 11:00 AM, Brightness: 70%, Color Temperature: 3000K Time: 13:00, May 13, 2023, Brightness: 100%, Color Temperature: 5000K The extracted instructions are organized into a light effect adjustment instruction vector, recording each light effect adjustment made by the user. These instructions will provide the basis for the subsequent generation of the user's subjective light effect preference vector. After extracting the user's light effect adjustment instructions, a specific light effect adjustment analysis is performed to extract the user's subjective light effect preference vector. The purpose of this step is to analyze the user's light effect adjustment behavior and form a personalized light effect preference feature. The dimensions of the light effect preference vector are defined, including features such as brightness, color, and rate of change. Assume that the following dimensions are selected: Luminance Color Temperature Change Rate Based on the user's lighting effect adjustment instructions, the average value and rate of change of each parameter are calculated. Assuming that the user recorded brightness of 70%, 100%, and 80% in multiple operations, their brightness preference is: Average Brightness = (70 + 100 + 80) / 3 = 83.33%.

[0048] The rate of change can be calculated by calculating the brightness difference and time difference between adjacent operations. If it takes 1 hour to adjust from 70% to 100%, the rate of change is: Rate of change = (100-70) / 1 = 30% / hour Construct the user's subjective light effect preference vector, for example: Preference vector = [83.33, 4000K, 30% / hour]. This will provide the basis for subsequent feature encoding. After extracting the user's subjective lighting preference vector, multi-dimensional feature encoding is performed to construct a multimodal representation space for lighting effects. This step aims to transform the user's lighting preferences into a spatial model that can be used for analysis and prediction. The dimensions of the multimodal representation space are defined based on the user's preference vector. The spatial dimensions are set to three, corresponding to brightness, color temperature, and rate of change. Feature encoding methods (such as normalization or standardization) are used to process the preference vector. Assume that after normalization, the new vector obtained is: Normalized preference vector = [0.67, 0.5, 0.75]. This method maps the user's lighting preferences into the multimodal representation space, facilitating subsequent parameter adjustment and satisfaction analysis. After constructing the multimodal representation space for lighting effects, the ambient lighting parameters before the user's operation are extracted. This step aims to understand the environmental conditions before the user makes lighting effect adjustments, which will facilitate subsequent deviation calculations.

[0049] Extract the lighting parameters before the user makes any adjustments from the user's operation log. Assume that the lighting parameters before the user makes the last brightness adjustment are: Brightness: 50% Color temperature: 3500K Record these parameters to form a pre-operation light effect parameter vector. These parameters will provide a reference for subsequent deviation calculations. After extracting the lighting parameters before the user's operation, the user adjustment parameter deviation of the light effect multimodal representation space is calculated based on these parameters. The purpose of this step is to evaluate the difference between the user's light effect adjustment and their preferences. Calculate the deviation between the user's pre-operation ambient light parameters and the user's subjective light effect preference vector. Assuming that the user's preference vector is [83.33, 4000K, 30% / hour], and the pre-operation parameters are [50%, 3500K], the deviation is calculated as follows: Brightness deviation = 83.33-50 = 33.33; Color temperature deviation = 4000-3500 = 500; The deviation values ​​are recorded to form a deviation vector, for example: deviation vector = [33.33, 500]. This deviation vector will provide data support for the subsequent construction of a satisfaction prediction curve. The user's lighting preference trajectory is mined based on the deviation values ​​of the lighting parameter adjustments to construct a user lighting satisfaction prediction curve. The purpose of this step is to predict user lighting satisfaction by analyzing the deviation values. Deviation data from multiple users is collected as a sample dataset. A machine learning model (such as linear regression or support vector machine) is trained on the deviation data to build a satisfaction prediction model. Assume the collected deviation data is: deviation data = [[30, 400], [20, 300], [15, 200], ...]; use the trained model to predict the user's lighting deviation and obtain a satisfaction prediction value. Assume the model outputs a satisfaction score of 0.85, indicating high user satisfaction. Generate a user lighting satisfaction prediction curve, graphically displaying the corresponding satisfaction levels for different deviation values. This will provide an important reference for subsequent lighting adjustment and optimization.

[0050] In this embodiment, the specific steps of step S6 are: Based on the user light effect satisfaction prediction curve and the user physiological-music resonance frequency fine-tuning parameters, the dynamic atmosphere light space light effect optimization strategy is controlled by user preferences, and a user preference light effect parameter control strategy is constructed; Performing deep semantic structure analysis on the audio rhythm feature perception map to identify different audio semantic structures, including climax segments, transition segments, and quiet segments; Predicting audio structure changes for different audio semantic structures to obtain audio structure change prediction data; Optimize the smooth transition of light effects based on the audio structure change prediction data to obtain the optimization parameters for the smooth transition of light effects; Perform lighting rendering preheating calculations for ambient lights based on the lighting effect smooth transition optimization parameters, and build an adaptive lighting effect rendering smoothness engine. Based on the adaptive lighting rendering smoothness engine and user-preferred lighting parameter control strategy, it performs intelligent collaborative control of dynamic atmosphere lights.

[0051] In this embodiment, the user's lighting efficiency satisfaction prediction data is first collected. For example, it is assumed that the user's satisfaction ratings for different lighting parameters are as follows: Brightness: 80% (satisfaction = 0.85) Color temperature: 3500K (satisfaction = 0.90) Rate of change: 15% / hour (satisfaction = 0.80) Lighting settings are further adjusted by fine-tuning the user's physiological-music resonance frequency. If the user's resonance frequency is 2.1Hz, the lighting frequency can be synchronized to enhance the physiological resonance effect. Using intelligent control algorithms (such as fuzzy logic control or PID control), user satisfaction is mapped to lighting parameters to generate a user-preferred lighting parameter control strategy. This strategy dynamically adjusts to user needs in real time, ensuring that the lighting effect remains within a satisfactory range. Constructing a user-preferred lighting parameter control strategy provides a foundation for subsequent audio structure change prediction and lighting effect optimization. After establishing the user preference-driven control strategy, deep semantic structure analysis is performed on the audio rhythm feature perception map. The goal of this step is to identify different audio semantic structures to achieve precise lighting effect matching during dynamic control. Audio signal processing techniques (such as short-time Fourier transform and wavelet transform) are used to analyze the audio signal and extract its frequency and time domain features. Assume that the audio signal obtained from the analysis has the following structure: Climax: The intensity and frequency of the audio reach their highest point and lasts for 30 seconds.

[0052] Transition section: The transition from the climax section to the quiet section, lasting 20 seconds.

[0053] Silence: The audio intensity is significantly reduced and lasts for 40 seconds.

[0054] Use machine learning algorithms (such as cluster analysis) to classify the extracted features to identify different semantic structures of the audio. By comparing the features of different paragraphs, a structured audio analysis result is formed. Successfully identify the climax, transition, and quiet segments of the audio, laying the foundation for subsequent audio structure change prediction and lighting effect optimization. After identifying different audio semantic structures, predict audio structure changes for these structures. The purpose of this step is to predict subsequent changes in the audio in order to achieve a smooth transition of lighting effects. Use time series prediction models (such as ARIMA models or LSTM networks) to model changes in audio structure. By analyzing past audio data, predict future changes in audio segments. Assume that the predicted audio structure change data is: After the climax section ends, the estimated time to enter the transition section is 5 seconds.

[0055] After the transition phase, the estimated time to enter the quiet phase is 10 seconds.

[0056] The predicted data is recorded to form audio structure change prediction data. This data will provide a reference for subsequent lighting effect transition optimization. Obtaining audio structure change prediction data lays the foundation for optimizing smooth lighting effect transitions. After obtaining the audio structure change prediction data, the lighting effect smooth transition is optimized based on this data to obtain the optimized parameters for smooth lighting effect transitions. This step aims to ensure that the lighting effect transitions naturally and smoothly with the audio changes. Key lighting effect transition parameters are set, such as brightness transition time and color change rate. The time required for the brightness to gradually decrease from 100% to 30% is set to 5 seconds, and the color change rate from warm white to cool white is set to 20K / second. Linear interpolation is used to calculate the lighting effect parameters at each time point. If the brightness needs to decrease from 100% to 30% within 5 seconds, the brightness change per second is: Change per second = (100% - 30%) / 5 seconds = 14% / second. The optimized parameters for smooth lighting effect transitions are generated to ensure that the lighting changes are synchronized with the audio structure changes. After generating optimized parameters for smooth lighting transitions, the ambient lighting is pre-rendered. This step aims to prepare the lighting effects in advance to ensure a quick response to audio changes. A lighting rendering engine (such as OpenGL or Unity) is used for pre-rendering. Based on the previously generated lighting parameters, the lighting effects for each stage are set. Assume that the required pre-rendered brightness during the transition is 60% and the color temperature is 4000K. The rendering engine calculates the lighting state at each time point to ensure a smooth and seamless transition. If pre-rendering is performed within 3 seconds, the lighting parameters are calculated for each time point. An adaptive lighting rendering smoothness engine is constructed to enable real-time management and adjustment of dynamic lighting effects. Based on this adaptive lighting rendering smoothness engine and user-preferred lighting parameter control strategies, intelligent collaborative control of dynamic ambient lighting is implemented. This step ensures that the lighting synchronizes with audio changes, enhancing the user's sensory experience. The user-preferred lighting parameter control strategies and the lighting rendering smoothness engine are integrated to form an intelligent control system. This system receives real-time data on audio signal changes and automatically adjusts the lighting effects based on the changes in the audio segments. Control algorithms (such as PID controllers) finely adjust lighting to ensure that the lighting output matches the changes in the audio structure. During audio climaxes, the lighting brightness is increased to 100%, and the color temperature is adjusted based on user preferences. Dynamic ambient lighting intelligently coordinates control, achieving efficient synergy between audio and lighting, enhancing the overall user experience.

[0057] In this embodiment, a dynamic atmosphere light control system based on music rhythm is provided, which is used to execute the dynamic atmosphere light control method based on music rhythm as described above, including: Audio rhythm perception: collects real-time audio signal streams, performs multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructs an audio rhythm feature perception map; The adaptive control module performs spatial audio orientation analysis based on the real-time audio signal stream and adaptively controls the dynamic ambient light parameters based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy. The light effect optimization module performs preliminary ambient light control based on the adaptive dynamic ambient light control strategy, obtains real-time images of the area, and performs compensation optimization for low-light intensity areas to build a dynamic ambient light space light effect optimization strategy; The resonance frequency fine-tuning module obtains the user's real-time physiological state parameters, performs personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generates the user's physiological-music resonance frequency fine-tuning parameters; The light effect preference mining module obtains user ambient light operation logs, analyzes user-specified light effect adjustments, and mines user light effect preference trajectories to construct a user light effect satisfaction prediction curve. The collaborative control module performs user preference-driven control of the dynamic atmosphere light space lighting optimization strategy based on the user lighting effect satisfaction prediction curve and the user's physiological-music resonance frequency fine-tuning parameters to perform dynamic atmosphere light intelligent control operations.

[0058] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0059] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily 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 is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling dynamic atmosphere lights based on music rhythm, characterized in that: The following steps are involved: Step S1: collecting real-time audio signal streams, performing multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructing an audio rhythm feature perception map; Step S2: performing spatial audio orientation analysis based on the real-time audio signal stream, and performing adaptive dynamic ambient light parameter control based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy; Step S3: Perform preliminary ambient light control according to the adaptive dynamic ambient light control strategy, obtain real-time images in the area, perform compensation optimization for low-light intensity area coverage, and build a dynamic ambient light space lighting effect optimization strategy; Step S4: obtaining the user's real-time physiological state parameters, performing personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generating the user's physiological-music resonance frequency fine-tuning parameters; Step S5: Obtain the user's ambient light operation log, perform user-specified light effect adjustment analysis, and mine the user's light effect preference trajectory to construct a user light effect satisfaction prediction curve; Step S6: The dynamic atmosphere light space light effect optimization strategy is user preference-driven and regulated according to the user light effect satisfaction prediction curve and the user physiological-music resonance frequency fine-tuning parameters to perform the dynamic atmosphere light intelligent collaborative control operation.

2. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 1, characterized in that: The specific steps of step S1 are: Collect real-time audio signal streams; perform multi-scale wavelet decomposition on the real-time audio signal streams to obtain time-frequency spectra of different scales; Calculating the frequency fluctuation of the time-frequency spectrum and performing frequency fluctuation distribution analysis to generate frequency fluctuation distribution features of different scales; Tracking the frequency time series distribution of the frequency fluctuation distribution characteristics to construct an audio frequency time series fluctuation curve; Perform audio rhythm mapping based on time-frequency spectra of different scales and construct audio third-order spatial rhythm feature maps; Based on the audio third-order spatial rhythm feature map and frequency-time fluctuation curve, multi-scale rhythm hierarchical structure perception is performed to construct an audio rhythm feature perception map.

3. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 2, characterized in that: The specific steps of performing audio rhythm mapping based on time-frequency spectra of different scales and constructing an audio third-order spatial rhythm feature map are as follows: Perform deep audio feature analysis on time-frequency spectra of audio at different scales to extract the rhythm structure tensor, pitch variation tensor, and rhythm density tensor of the audio signal; Based on the rhythm structure tensor, the global rhythm prosody analysis is carried out to obtain the characteristics of the temporal resonance structure change; Fit the time variation of low-frequency components according to the pitch variation tensor and extract the low-frequency component variation sequence; Perform transient frequency mutation detection on the low-frequency component change sequence and identify transient beat transition points; Mining audio emotion tensor fluctuations based on the rhythm density tensor to obtain real-time audio emotion tensor fluctuation features; The third-order spatial audio rhythm mapping is performed on the changing characteristics of the temporal resonance structure, the transient beat transition points and the real-time audio emotion tensor fluctuation characteristics to construct the audio third-order spatial rhythm feature map.

4. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 1, characterized in that: The specific steps of step S2 are: Perform spatial audio orientation analysis based on real-time audio signal stream to obtain the spatial orientation of different audio signals; Perform three-dimensional audio propagation positioning simulation on the spatial orientation of different audio signals and extract the spatial propagation position information of each audio signal; Fit the audio position distribution to the spatial propagation position information and build a real-time audio spatial distribution model; Identify the adjustable ambient light strips in the area and calculate the position coordinates of each adjustable ambient light strip; Based on the position coordinates of each adjustable ambient light strip, the real-time audio spatial distribution model is accurately matched to build an ambient light distribution matching network; Based on the audio rhythm feature perception map, the distributed matching network of the atmosphere light is used to adaptively control the dynamic atmosphere light parameters, and an adaptive dynamic atmosphere light control strategy is obtained.

5. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 1, characterized in that: The specific steps of step S3 are: Perform preliminary ambient light control based on the adaptive dynamic ambient light control strategy and obtain real-time images of the area based on smart home devices; Performing ambient light spatial layout analysis on real-time images within the area to obtain ambient light spatial layout characteristics; Perform geometric structure distribution recognition on real-time images within the area to generate indoor geometric structure distribution features; Build a 3D indoor area model by performing 3D point cloud modeling based on the spatial layout characteristics of ambient light and the distribution characteristics of indoor geometric structures; The three-dimensional indoor area model is used to compensate and optimize the coverage of weak light intensity areas, and a dynamic atmosphere lighting space lighting effect optimization strategy is constructed.

6. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 5, characterized in that: The specific steps of performing compensation optimization on the weak light intensity area coverage of the three-dimensional indoor area model and constructing a dynamic atmosphere light space lighting effect optimization strategy are as follows: Track the distribution of ambient light rays in the 3D indoor area model and construct a heat map of the ambient light ray distribution; Detect weak interaction areas of ambient light rays on the ambient light distribution heat map and mark the weak interaction areas of ambient light rays; Identify adjacent ambient light strips based on the weak interaction area of ​​the ambient light; Evaluate the spatial lighting balance of areas with weak interaction of ambient lighting to determine the required intensity of lighting compensation in these areas; Performing an atmosphere light coverage compensation calculation on the illumination compensation requirement intensity based on the adjacent atmosphere light strips to generate an atmosphere light coverage compensation parameter; The adaptive dynamic atmosphere light control strategy is used to optimize the spatial lighting effect according to the atmosphere light coverage compensation parameters, and a dynamic atmosphere light spatial lighting effect optimization strategy is constructed.

7. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 1, characterized in that: The specific steps of step S4 are: The user's heart rate and respiratory rate are collected by the user's smart wearable device to obtain the user's real-time physiological status parameters; Conduct personalized natural physiological rhythm mining based on the user's real-time physiological state parameters to generate personalized natural physiological rhythm cycles; Based on the audio rhythm feature perception map, the personalized natural physiological rhythm cycle is analyzed for phase synchronization to obtain the user-audio rhythm matching degree; Based on the user-audio rhythm matching degree, the physiological-music resonance frequency is fine-tuned to generate the user physiological-music resonance frequency fine-tuning parameters.

8. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 1, characterized in that: The specific steps of step S5 are: Obtain user atmosphere light operation logs; extract user lighting effect adjustment instructions based on user atmosphere light operation logs; Perform specified light effect adjustment analysis on the user's light effect adjustment instructions and extract the user's subjective light effect preference vector; Calculate the color, brightness, and change rate of the user's subjective light effect preference vector, perform multi-dimensional feature encoding, and construct a multimodal representation space for light effects; Extracting the ambient light parameters before the user's operation based on the user's ambient light operation log; Calculating the user-adjusted parameter deviation in the light effect multimodal representation space according to the ambient light parameters before the user operation, thereby obtaining the user-adjusted light effect parameter deviation value; The user's lighting effect preference trajectory is mined based on the deviation value of the lighting effect parameters adjusted by the user, and a user lighting effect satisfaction prediction curve is constructed.

9. The method for controlling dynamic atmosphere lights based on music rhythm according to claim 1, characterized in that: The specific steps of step S6 are: Based on the user light effect satisfaction prediction curve and the user physiological-music resonance frequency fine-tuning parameters, the dynamic atmosphere light space light effect optimization strategy is controlled by user preferences, and a user preference light effect parameter control strategy is constructed; Performing deep semantic structure analysis on the audio rhythm feature perception map to identify different audio semantic structures, including climax segments, transition segments, and quiet segments; Predicting audio structure changes for different audio semantic structures to obtain audio structure change prediction data; Optimize the smooth transition of light effects based on the audio structure change prediction data to obtain the optimization parameters for the smooth transition of light effects; Perform lighting rendering preheating calculations for ambient lights based on the lighting effect smooth transition optimization parameters, and build an adaptive lighting effect rendering smoothness engine. Based on the adaptive lighting rendering smoothness engine and user-preferred lighting parameter control strategy, it performs intelligent collaborative control of dynamic atmosphere lights.

10. A dynamic atmosphere light control system based on music rhythm, characterized in that: The method for controlling a dynamic ambient light based on music rhythm as claimed in claim 1 comprises: Audio rhythm perception: collects real-time audio signal streams, performs multi-scale wavelet decomposition and audio rhythm hierarchical structure perception, and constructs an audio rhythm feature perception map; The adaptive control module performs spatial audio orientation analysis based on the real-time audio signal stream and adaptively controls the dynamic ambient light parameters based on the audio rhythm feature perception map to obtain an adaptive dynamic ambient light control strategy. The light effect optimization module performs preliminary ambient light control based on the adaptive dynamic ambient light control strategy, obtains real-time images of the area, and performs compensation optimization for low-light intensity areas to build a dynamic ambient light space light effect optimization strategy; The resonance frequency fine-tuning module obtains the user's real-time physiological state parameters, performs personalized natural physiological rhythm mining and physiological-music resonance frequency fine-tuning, and generates the user's physiological-music resonance frequency fine-tuning parameters; The light effect preference mining module obtains user ambient light operation logs, analyzes user-specified light effect adjustments, and mines user light effect preference trajectories to construct a user light effect satisfaction prediction curve. The collaborative control module performs user preference-driven control of the dynamic atmosphere light space lighting optimization strategy based on the user lighting effect satisfaction prediction curve and the user's physiological-music resonance frequency fine-tuning parameters to perform dynamic atmosphere light intelligent control operations.

Images