Intelligent lamp control method and system based on brain wave control

Abstract

The invention provides an intelligent lamp control method and system based on brain wave control. The method comprises the steps of obtaining target data; the target data comprises brain wave signals of a user; performing feature extraction based on the brain wave signal to obtain a first feature parameter; obtaining a current thinking state of the user based on the first characteristic parameter, and generating a corresponding lamp control command according to the thinking state; the lamp control command comprises a correspondingly controlled lamp and lamp configuration information; and controlling a corresponding lamp based on the lamp control command. Based on the advanced brain wave detection technology and the machine learning algorithm, the user can control the light only through thinking activities, the user achieves unconscious control through the thinking activities, no physical operation or voice instruction is needed, the interaction process is more natural and convenient, wide application prospects are achieved, and the user experience is improved. The method can be applied to home furnishing, ward postoperative rehabilitation, old-age rehabilitation, space stations and the like.

Description

Technical Field

[0001] The present application belongs to the technical field of lamp control, and relates to a lamp intelligent control method based on brainwave control, and in particular to a lamp intelligent control method and system based on brainwave control. Background Art

[0002] With the development of smart homes, users have an increasing demand for convenient and natural ways of interaction. Lamps are an indispensable indoor decoration in people's daily lives. Traditional lighting control methods rely on manual operation or voice commands. Although these control methods simplify the interaction process, they still require active behavior from users, lack flexibility and intelligence, and bring great inconvenience to users. At the same time, lamps can only emit light at fixed brightness and color, and the lighting mode is relatively simple. Summary of the invention

[0003] The purpose of the present application is to provide a method and system for intelligent control of lamps based on brainwave control, so as to solve the problem that the control of lamps in the prior art relies on manual operation or voice commands of the user, resulting in a lack of flexibility and intelligence in the control of lamps, which brings great inconvenience to the user.

[0004] In a first aspect, the present application provides a method for intelligent control of lamps based on brainwave control, the method comprising: acquiring target data; the target data comprising a user's brainwave signal; performing feature extraction based on the brainwave signal to obtain a first feature parameter; acquiring the user's current thinking state based on the first feature parameter, and generating a corresponding lamp control command based on the thinking state; the lamp control command comprising a correspondingly controlled lamp and lamp configuration information; and controlling the corresponding lamp based on the lamp control command.

[0005] In an implementation of the first aspect, obtaining the user's current thinking state based on the first feature parameter includes: inputting the first feature parameter into a trained classifier to obtain a classification result; and predicting the user's current thinking state based on the classification result.

[0006] In an implementation of the first aspect, performing feature extraction based on the brain wave signal includes: performing wavelet transform denoising processing based on the brain wave signal to obtain a denoised brain wave signal; and extracting frequency band features related to the user's lighting control intention based on the denoised brain wave signal as the first feature parameter.

[0007] In an implementation of the first aspect, controlling the corresponding lamp based on the lamp control command includes: obtaining preset information of the lamp; the preset information includes a preset PWM frequency and a preset duty cycle range; obtaining the duty cycle to be adjusted of the lamp according to the lamp control command and the preset duty cycle range; adjusting the duty cycle of the lamp according to the preset PWM frequency and the duty cycle to be adjusted to control the lamp.

[0008] In an implementation method of the first aspect, it also includes: obtaining a user's brain wave signal after the lamp is adjusted; obtaining the user's current thinking state based on the user's brain wave signal; and regenerating a corresponding lamp control command based on the current thinking state to meet the user's personalized needs.

[0009] In a second aspect, the present application provides a method for intelligently controlling lamps based on brainwave control, characterized in that the method includes: obtaining a user's brainwave signal; performing a matching search based on the brainwave signal and preset user information to obtain a matching result; the preset user information includes the obtained user's brainwave signal; and controlling the corresponding lamp based on the matching result.

[0010] In an implementation of the second aspect, the method also includes: if the matching result is successful and the brain wave signal exists in the preset user information, then the corresponding lamp setting information is obtained according to the brain wave signal, so as to control the corresponding lamp through the lamp setting information; the lamp setting information includes the lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is obtained by the method described above; if the matching result is failed and the brain wave signal does not exist in the preset user information, then the corresponding lamp is controlled according to the brain wave signal by the method described above.

[0011] In the third aspect, the present application provides a method for intelligent control of lamps based on brainwave control, the method comprising: obtaining a user's brainwave signal; obtaining the user's current scene based on the brainwave signal; controlling the corresponding lamp based on the current scene and preset lamp setting information; the preset lamp setting information includes a lamp control command corresponding to the specific thinking state of the user to which the brainwave signal belongs; the lamp control command is obtained by the above-mentioned method.

[0012] In a fourth aspect, the present application provides a brainwave-controlled intelligent lighting control system, the system comprising: an acquisition module for acquiring target data; the target data comprises a user's brainwave signal; a feature extraction module for performing feature extraction based on the brainwave signal to obtain a first feature parameter; an instruction generation module for acquiring the user's current thinking state based on the first feature parameter, and generating a corresponding lighting control command based on the thinking state; the lighting control command comprises a correspondingly controlled lighting and lighting configuration information; a lighting control module for controlling the corresponding lighting based on the lighting control command.

[0013] In an implementation of the fourth aspect, the system further includes: an adaptive adjustment module, configured to obtain a user's brain wave signal after the lamp is adjusted; obtain the user's current thinking state according to the user's brain wave signal; and regenerate a corresponding lamp control command according to the current thinking state to meet the user's personalized needs; a multi-user control module, configured to perform a matching search based on the brain wave signal and preset user information to obtain a matching result; and control the corresponding lamp according to the matching result; if the matching result is successful and the brain wave signal exists in the preset user information, then the corresponding lamp setting information is obtained according to the brain wave signal so as to control the corresponding lamp through the lamp setting information; if the matching result is a failure, If the brain wave signal does not exist in the preset user information, the corresponding lamp is controlled according to the brain wave signal by the method described above; the preset user information includes the acquired user brain wave signal; the lamp setting information includes the lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is acquired by the method described above; a scene recognition module is used to acquire the current scene of the user according to the brain wave signal; control the corresponding lamp according to the current scene and the preset lamp setting information; the preset lamp setting information includes the lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is acquired by the method described above.

[0014] As described above, the brainwave-based intelligent control method and system for lighting described in this application have the following beneficial effects:

[0015] This application is based on advanced brain wave detection technology and machine learning algorithms. It detects the user's brain wave signals and extracts the frequency band features related to the user's lighting control intention from the detected brain wave signals. It identifies the user's current thinking state based on the extracted features, and further generates corresponding lighting control commands to control the corresponding lighting. This enables users to control the lights simply through thinking activities. Users achieve unconscious control through thinking activities without any physical operation or voice commands, making the interaction process more natural and convenient, and has broad application prospects, such as home, postoperative rehabilitation in wards, elderly care, space stations and other application scenarios. At the same time, this application can automatically adjust the brightness and color temperature of the light according to the user's real-time brain wave state, provide a lighting environment that better meets user needs, and provide users with an intelligent and natural lighting experience.

[0016] By monitoring the user's brain wave feedback, this application can adaptively adjust the control strategy to provide a personalized lighting experience. At the same time, by recording the user's brain wave data for a long time, analyzing each user's unique brain wave pattern, and adjusting the lighting setting parameters of the intention recognition model, it can learn and adapt to each user's unique brain wave pattern, achieve highly personalized lighting control, and enhance the user's comfort and experience.

[0017] This application realizes adaptive lighting adjustment for multiple users by identifying the brain wave signal of the current user in a multi-user environment and automatically switching the lighting setting information, ensuring that each user can obtain the lighting experience that best suits their needs.

[0018] This application can automatically identify the different scenarios of the user (such as office, rest, entertainment) based on the user's brain wave signals, and automatically adjust the lighting mode according to the user's current situation (such as work, rest, entertainment), to achieve seamless switching of lighting modes between these scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1A Shown is a schematic diagram of an application scenario based on brainwave control and intelligent lighting interaction as described in an embodiment of the present application.

[0020] Figure 1B Shown is a schematic diagram of the structure of the local control system described in an embodiment of the present application.

[0021] Figure 2 Shown is a flow chart of a method for intelligently controlling a lamp based on brainwave control in one embodiment of the present application.

[0022] Figure 3 Shown is a flow chart of another embodiment of the intelligent control method for lighting based on brainwave control described in the embodiment of the present application.

[0023] Figure 4Shown is a flow chart of another embodiment of the intelligent control method for lighting based on brainwave control described in the embodiment of the present application.

[0024] Figure 5 Shown is a schematic diagram of the structure of an intelligent control system for lighting based on brainwave control in one embodiment of the present application.

[0025] Figure 6 Shown is a structural schematic diagram of another embodiment of the intelligent control system for lighting based on brainwave control described in the embodiment of the present application.

[0026] Figure 7 Shown is a schematic diagram of the structure of an electronic device described in an embodiment of the present application.

[0027] Component number description

[0028] 11 Local Control System

[0029] 111 Brainwave Detection Module

[0030] 112 Signal Processing and Feature Extraction Module

[0031] 113 Intent Recognition and Command Generation Module

[0032] 114 Lighting control module

[0033] 115 Feedback and Adaptive Module

[0034] 12 Cloud Platform

[0035] 13 User terminal equipment

[0036] 14 Lamps

[0037] 2 Intelligent control system of lighting based on brainwave control

[0038] 21 Get Module

[0039] 22 Feature Extraction Module

[0040] 23 Instruction Generation Module

[0041] 24 Lighting control module

[0042] 25 Adaptive Adjustment Module

[0043] 26 Multi-user control module

[0044] 27 Scene Recognition Module

[0045] 3 Electronic devices

[0046] 31 Memory

[0047] 32 processors

[0048] Steps S1 to Sn DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0050] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0051] The following embodiments of the present application provide a method and system for intelligent control of lamps based on brainwave control, which solves the problem in the prior art that lamp control relies on manual operation or voice commands of the user, resulting in a lack of flexibility and intelligence in lamp control, causing great inconvenience to the user.

[0052] like Figure 1A-1B As shown, this embodiment provides an application scenario based on brainwave control and intelligent lighting interaction, specifically including: a local control system 11, a cloud platform 12, a user terminal device 13 and a lamp 14. The local control system 11, the cloud platform 12, the user terminal device 13 and the lamp 14 communicate through a standard interface, which is convenient for upgrading and expansion. The local control system 11 is used to process the core brainwave processing and lighting control logic. The cloud platform 12 is used to process complex model training and big data analysis to ensure a balance between real-time performance and computing efficiency. The user terminal device 13 collects the user's brainwave signal and transmits it to the local control system.

[0053] The local control system 11 includes core modules such as a brain wave detection module 111 , a signal processing and feature extraction module 112 , an intention recognition and command generation module 113 , a lighting control module 114 , and a feedback and adaptation module 115 .

[0054] In one embodiment, the brainwave detection module 111 uses a wearable brainwave detection device (such as a brainwave headband) to collect user brainwave signals in real time. The local control system 11 identifies the user's intention by analyzing specific brainwave features (such as attention, relaxation state, etc.).

[0055] In one embodiment, the signal processing and feature extraction module 112 pre-processes the brain wave signal, removes noise and extracts effective features (such as changes in the intensity of alpha waves and beta waves), and then analyzes these features through a machine learning algorithm to identify the user's thinking state.

[0056] In one embodiment, the intention recognition and command generation module 113 generates specific lighting control instructions based on the processed brain wave signals. For example, when the user is concentrating, the light brightness increases; when the user is relaxing, the light gradually dims; and the light color temperature is adjusted according to the user's mood.

[0057] In one embodiment, the lighting control module 114 automatically adjusts the brightness and color temperature of the lighting according to the recognized user intention to ensure that the lighting changes smoothly and naturally.

[0058] In one embodiment, the feedback and adaptation module 115 monitors the user's brain wave feedback, and the local control system can adaptively adjust the control strategy to provide a personalized lighting experience.

[0059] In one embodiment, an edge computing device is introduced on the user terminal device 13, and some complex calculations are delegated to the edge computing device, thereby reducing dependence on the cloud platform 12 and improving data processing speed.

[0060] It should be noted that the local control system in this application can automatically identify the different scenes in which the user is located (such as office, rest, and entertainment) and seamlessly switch the lighting mode between these scenes.

[0061] The intelligent control method and system of lamps based on brainwave control provided in the following embodiments of the present application, through advanced brainwave detection technology and machine learning algorithms, realize the ability of users to directly control lights through thinking activities. The intelligent control method and system of lamps based on brainwave control provided in the present application have broad application prospects in the field of smart homes, and are particularly suitable for user groups who pursue efficient and natural interaction methods. It not only improves the level of intelligence of lighting control, but also provides new possibilities for future human-computer interaction methods. The intelligent control method and system of lamps based on brainwave control described in the following embodiments of the present application can be applied to application scenarios such as smart homes, postoperative rehabilitation in wards, elderly care, space stations, etc., and the present application is not limited to this.

[0062] The technical solutions in the embodiments of the present application will be described in detail below in conjunction with the drawings in the embodiments of the present application.

[0063] like Figure 2 As shown, this embodiment provides a method for intelligently controlling a lamp based on brainwave control, and the method includes the following steps S11 to S14.

[0064] Step S11, obtaining target data; the target data includes the user's brain wave signal.

[0065] In one embodiment, the present application can accurately capture subtle changes in brain activity by using highly sensitive EEG sensors, such as dry electrode technology, to avoid the problem of traditional wet electrodes requiring conductive gel, thereby improving wearing comfort and convenience for long-term use. At the same time, through multi-channel EEG acquisition equipment, brain wave signals in the frontal lobe, parietal lobe, occipital lobe and other areas are captured through a multi-electrode array, which are highly related to functions such as attention, emotion, and visual perception. Brain wave data is transmitted in real time through wireless communication methods such as low-power Bluetooth (BLE) or Wi-Fi to ensure the stability and low latency of the transmission process.

[0066] In one embodiment, the present application collects the user's brain wave signals in real time through the user's wearable brain wave detection device (such as a brain wave headband). The wearable brain wave detection device can detect brain wave characteristics related to specific thinking states or intentions, such as concentration, relaxation, sleepiness, etc. Among them, the wearable brain wave detection device is a headband made of flexible material, which fits the head contour better, increases wearing comfort and signal acquisition accuracy.

[0067] It should be noted that brain waves are closely related to the state of thinking. Different brain wave bands correspond to different states of thinking and consciousness. Brain waves are bioelectric signals generated by the activities between neuron cells in the brain. Their frequency varies between 1 and 30 times per second and are mainly divided into four bands: delta waves, theta waves, alpha waves and beta waves.

[0068] Delta waves have a frequency of 0.5 to 3 Hz and usually occur during deep sleep or can be observed in adults when they are extremely tired or in a state of drowsiness. Related states: deep sleep, unconsciousness, infancy, intellectually immature adults, extreme fatigue and drowsiness or anesthesia.

[0069] The frequency of theta waves is 4-7 Hz, which is usually more significant in adults with frustrated will or depression, and in patients with mental illness. It is also the main component in the EEG of teenagers (10-17 years old). Related states: deep relaxation, meditation, enhanced creativity, hypnotic state, normal EEG components of teenagers (10-17 years old), frustrated will or depression of adults, and patients with mental illness.

[0070] The frequency of alpha waves is 8-13Hz, which is the basic rhythm of normal human brain waves. It is most obvious when awake, quiet and with eyes closed, and disappears when eyes are opened or receiving other stimuli. Related states: awake, quiet, relaxed state with eyes closed, meditation, calm and pleasant emotions, inspiration and creative thinking.

[0071] The frequency of β waves is 14-30 Hz, and they usually appear when people are nervous, agitated or excited. When people wake up from a nightmare, the original slow wave rhythm can be immediately replaced by this rhythm. Related states: nervous, agitated, excited.

[0072] In addition, there is a higher frequency gamma wave, which has a frequency of 30 to 80 Hz and usually appears when you are awake and focused on something.

[0073] The measurement of brain waves is usually done through electroencephalography (EEG), which is a process of observing brain wave activity by placing electrodes on the scalp. The EEG is a general reflection of the electrophysiological activity of brain nerve cell groups on the cerebral cortex or scalp surface. Clinical practice has shown that brain waves contain a lot of physiological and disease information. By processing brain waves, it can provide a basis for the identification of brain lesions.

[0074] The feature extraction of brain waves is crucial for the analysis of brain wave signals. Common features include time domain features (such as mean, standard deviation, energy, power, etc.), time-frequency domain features (such as power spectrum density, differential entropy, etc.) and spatial domain features (such as DASM, RASM, asymmetry coefficient, etc.). These features can be used for the classification and recognition of brain wave signals, such as in the fields of brain-computer interface, emotion monitoring, sleep analysis, etc. This application is not limited to these types of brain waves.

[0075] In one embodiment, the present application realizes adaptive electrode contact detection through a wearable brain wave detection device, and optimizes brain wave signal acquisition by adjusting electrode pressure and position. Specifically, electrode pressure refers to moderate pressure, and appropriate pressure can ensure that the electrode is in close contact with the scalp and reduce noise and artifacts. For example, a fixing belt is used to ensure that the electrode is in a fixed position and will not loosen due to head movement. Electrode position refers to precise positioning. According to the international 10-20 system, electrodes are placed in specific positions, and specific brain areas can be monitored. For example, if the state of concentration needs to be monitored, electrodes can be placed in the forehead area (Fz). Using a guide tool refers to using auxiliary tools, such as a guide template, to ensure the consistency and accuracy of the electrode position. Environmental interference reduction refers to adjusting the electrode position to avoid skin texture or hair affecting signal acquisition, and selecting a smoother area to avoid interference. Through these optimization measures, the present application can improve the signal-to-noise ratio of brain wave signals and obtain more accurate and stable data, thereby providing a more reliable basis for subsequent analysis and classification.

[0076] In this embodiment, the present application implements adaptive electrode contact detection through a wearable brain wave detection device, specifically including processes such as initialization, signal analysis, feedback adjustment and adaptive learning.

[0077] Furthermore, in this embodiment, in the initialization stage, when the user wears the device, the local control system detects the initial voltage value of each electrode and determines the contact state. In the signal analysis stage, frequency domain analysis, such as FFT, is used to process the signal collected by the electrode and evaluate the noise level. If the electrode is in poor contact with the skin, the noise will increase significantly. In the feedback adjustment stage, a sensor-based pressure detection module is used to automatically adjust the position of the electrode pressure according to the contact situation to ensure the optimal contact state between the electrode and the skin. In the adaptive learning stage, through the feedback of each collection, the local control system continuously learns and adjusts the contact conditions to optimize the quality of future signal acquisition.

[0078] In one embodiment, the local control system can learn and adjust the contact conditions through the large model to optimize the quality of future signal acquisition. The large model can be implemented using machine learning or deep learning technology. The input parameters and output parameters of the large model implementation process are specifically: the input parameters of the large model include signal characteristics, contact conditions, environmental factors, and user feedback information, etc. Signal characteristics include the power spectrum characteristics of the collected brain wave signals (such as α waves, β waves, etc.), and the time domain characteristics of the signal (mean, variance, etc.). Contact conditions include the pressure value of the electrode (such as the magnitude of the applied pressure), the specific position coordinates of the electrode (such as the electrode position of the 10-20 system), and the contact area between the electrode and the skin. Environmental factors include the ambient noise level during acquisition (such as electrical interference, external sounds, etc.), and the scalp state (such as hair density, scalp oil, etc.). User feedback includes the user's subjective evaluation of signal quality (such as clarity, interference level). The output parameters of the large model include optimization suggestions, signal quality prediction results, and adaptive adjustment strategies, etc. Optimization suggestions include the optimal pressure value applied to the electrode (such as increasing or decreasing pressure) and optimized electrode position recommendations (such as moving to specific coordinates). Signal quality prediction includes the expected signal quality score (e.g., good, medium, poor) and the predicted value of the signal-to-noise ratio (SNR). The adaptive adjustment strategy includes a specific adjustment strategy (e.g., adjusting the specific value of pressure or position at the next acquisition). Through continuous learning and optimization, the application enables the local control system to more effectively collect high-quality brain wave signals in subsequent signal acquisition. Large models can be implemented using a variety of techniques such as reinforcement learning and supervised learning.

[0079] In another embodiment, the present application uses a dual-mode detection method of brain wave and skin resistance to collect signals. In addition to EEG signals, the changes in the conductivity of the skin surface are monitored to indirectly reflect the activity of the individual's autonomic nervous system, especially in terms of emotions, cognitive load and stress response. The combination of EEG signals and skin resistance signals (EDA, Electrodermal Activity) further improves the judgment of emotions and attention.

[0080] Specifically, the present application improves the judgment of emotions and attention through brain wave signals and skin resistance signals, which can be achieved by using multimodal signal processing methods. The multimodal signal processing methods specifically include: data collection, feature extraction, multimodal fusion, classification and judgment, real-time feedback and adaptive adjustment, etc.

[0081] Data collection includes the collection of brain wave signals (EEG) and skin resistance signals (GSR). The brain wave signal (EEG) uses electroencephalogram equipment to collect brain wave signals, focusing on the changes in different frequency bands (such as alpha waves, beta waves, and theta waves) to determine the user's emotions and attention status. The skin resistance signal (GSR) monitors the changes in skin resistance through a conductivity instrument, reflecting the activity of the skin's sweat glands and is related to emotional fluctuations (such as tension and relaxation).

[0082] Feature extraction includes brain wave feature extraction and skin resistance feature extraction. Brain wave feature extraction uses spectrum analysis (such as Fourier transform) to extract power spectrum density in different frequency bands. Time domain features (mean, standard deviation, etc.) and nonlinear features (such as entropy) are calculated. Skin resistance feature extraction calculates the resistance change rate, fluctuation amplitude and corresponding instantaneous value to extract time series-based features such as moving average, peak detection, etc.

[0083] Multimodal fusion refers to the fusion of EEG and GSR features, which includes the following fusion methods: Feature-level fusion: combining the feature vectors of the two signals to form a new feature space. Decision-level fusion: classifying EEG and GSR signals separately, and then making a comprehensive judgment based on the output results of the two.

[0084] Classification and judgment include machine learning models and emotion and attention assessment. Machine learning models refer to the use of support vector machines (SVM), random forests or deep learning models (such as convolutional neural networks) to classify the fused features and identify emotions (such as happiness, anxiety) and attention states (such as high attention, low attention). Emotion and attention assessment refers to the output of emotion labels and attention states, providing real-time feedback and adaptive adjustments (such as lighting changes, sound effect adjustments).

[0085] Real-time feedback and adaptive adjustment means that based on the judgment results, the local control system can adjust environmental factors (such as light and volume) in real time to improve the user experience. For example, bright lights are provided when the user is concentrating, and soft light colors are used when the user is anxious.

[0086] This application combines brain waves and skin resistance signals to enable the local control system to more accurately judge the user's emotions and attention state, thereby achieving more intelligent interaction and optimized environment.

[0087] This application introduces optical fiber sensors combined with brain wave collection to reduce electromagnetic interference, enhance collection accuracy, and improve signal quality. Adaptive electrode contact detection technology is used to detect the contact between the electrode and the skin in real time, and the contact pressure is automatically adjusted to ensure signal stability.

[0088] Step S12: performing feature extraction based on the brain wave signal to obtain a first feature parameter.

[0089] In one embodiment of the present application, feature extraction based on the brain wave signal includes the following steps S121 to S122.

[0090] Step S121, performing wavelet transform denoising processing based on the brain wave signal to obtain a denoised brain wave signal;

[0091] Step S122: extracting frequency band features related to the user's lighting control intention based on the denoised brain wave signal as the first feature parameter.

[0092] Specifically, the user's brain wave signals are collected in real time through the head-mounted device. The collected brain wave signals usually contain interference such as noise. Therefore, they need to be preprocessed through methods such as bandpass filters and / or wavelet transforms to remove unnecessary noise and extract useful signal features (i.e., frequency band features related to the user's lighting control intentions, such as the amplitude and frequency changes of alpha waves (8-13Hz) and beta waves (13-30Hz)), i.e., the first characteristic parameters.

[0093] In one embodiment, the present application first preprocesses the acquired brain wave signal, including signal filtering, denoising and normalization processing, for example, removing environmental noise and artifacts through an adaptive noise elimination algorithm (such as an adaptive filter based on LMS). At the same time, ICA (Independent Component Analysis, ICA, independent component analysis) is used to separate interference signals related to blinking and muscle activity. Then, the brain wave features related to the user's specific intentions are extracted from the preprocessed brain wave signal. The feature extraction process includes frequency domain feature extraction and time domain feature extraction. The frequency domain feature extraction converts the brain wave signal into the frequency domain by applying the fast Fourier transform (FFT), and extracts the power spectral density (PSD) of α waves, β waves, θ waves and γ waves related to states such as attention, relaxation, and emotions. Time domain feature extraction obtains transient event features (for example, a sudden increase in α waves indicates an increase in attention) by analyzing the instantaneous changes of the signal using wavelet transform.

[0094] This application proposes a multimodal brainwave signal fusion method for the features extracted by frequency domain feature extraction and time domain feature extraction. It is not limited to a single frequency band. By fusing the change trends of signals in different frequency bands, a multidimensional feature vector is generated, thereby improving the recognition accuracy of complex thinking states. A recursive neural network (RNN) combined with a long short-term memory network (LSTM) is used to process time series data, predict future state changes of users, and adjust lighting settings in advance.

[0095] In one embodiment, the specific method of multimodal brain wave signal fusion mainly includes three key steps: feature extraction, feature fusion and classification. The following describes the technical implementation logic and features of each step with a detailed embodiment, specifically including data collection, feature extraction, feature fusion, classification and judgment, and real-time feedback and adjustment.

[0096] Specifically, in the data acquisition step, the signal source is acquired by simultaneously acquiring brain wave signals (EEG) and skin resistance signals (GSR), and the EEG device is used to record multi-channel EEG signals, and the GSR sensor monitors the change in skin resistance.

[0097] In the feature extraction step, brain wave signal features and skin resistance signal features are extracted. The brain wave signal feature extraction specifically includes: spectrum analysis is to perform fast Fourier transform (FFT) on the EEG signal to extract the power spectrum density of different frequency bands (such as α wave, β wave, θ wave, etc.). Time domain features are extracted by calculating the mean, standard deviation, maximum and minimum values ​​of the signal. Nonlinear features are extracted by calculating entropy, fractal dimension, etc. to capture the complexity of the signal. Skin resistance signal features are to extract the peak and trough information of the signal by calculating the fluctuation amplitude and change rate of skin resistance, and analyze the instantaneous response to emotional changes.

[0098] In the feature fusion step, a multidimensional feature vector is generated by combining the extracted EEG features (such as power spectrum, time domain and nonlinear features) and GSR features (such as rate of change, fluctuation amplitude) to form a multidimensional feature vector. For example: if 10 features are extracted from EEG and 5 features are extracted from GSR, then the final multidimensional feature vector will be 15 dimensions.

[0099] In the classification and judgment step, the fused feature vector is trained by using a machine learning model (such as random forest, support vector machine or deep learning model) to identify emotional states (such as anxiety, happiness) and attention levels (high, medium, low). For example, the model outputs emotional labels and attention states, which can be "anxious, high attention" or "relaxed, low attention".

[0100] In the real-time feedback and adjustment step, the feedback mechanism is used to automatically adjust the environment (such as lighting brightness and sound effects) based on the classification results. For example, the system can increase the brightness when the user is in a state of high attention, and lower the brightness and use soft tones when the user is in an anxious state.

[0101] This application combines EEG and GSR signals, and the local control system can generate a comprehensive multi-dimensional feature vector, and judge the user's emotions and attention state through a machine learning model, thereby realizing intelligent environmental adjustment and personalized experience.

[0102] In one embodiment, the present application performs signal denoising and feature extraction by using a wavelet transform denoising algorithm, and the specific implementation process includes signal input, multi-scale decomposition, denoising processing, signal reconstruction, and feature extraction.

[0103] Specifically, in this embodiment, in the signal input stage, the original brain wave signal is obtained from the brain wave detection module. In the multi-scale decomposition stage, discrete wavelet transform (DWT) is applied to decompose the original signal into sub-signals of different scales, such as Daubechies wavelet. In the denoising stage, the decomposed high-frequency signal is threshold processed to remove high-frequency noise and retain low-frequency signals. In the signal reconstruction stage, the processed signal is reconstructed by inverse wavelet transform to generate a denoised brain wave signal. In the feature extraction stage, the power characteristics of the relevant frequency bands are extracted from the reconstructed signal, such as the amplitude and frequency of α wave, β wave, and γ wave.

[0104] This application uses convolutional neural networks (CNN) to automatically learn deep features in brain wave signals, avoiding manual feature selection and improving the accuracy of intent recognition. This application uses cloud servers to perform complex brain wave signal processing and feature extraction, reducing the computational burden of the local control system and ensuring real-time performance.

[0105] It should be noted that alpha waves, beta waves, theta waves and gamma waves are four different brain waves, which correspond to different brain activity states and frequency ranges. The frequency range of alpha waves (alpha waves) is 8 to 13Hz. Alpha waves usually appear when you are relaxed but awake, such as when you close your eyes and sit quietly. It helps reduce stress and anxiety and promotes physical and mental relaxation. The frequency range of beta waves (beta waves) is 13 to 30Hz. Beta waves are closely related to daily thinking, problem solving, and logical reasoning, and often appear when people are awake and focused on their tasks. High levels of beta wave activity may be associated with anxiety and stress. Theta waves (theta waves) have a frequency range of 4 to 8Hz. Theta waves often appear when people feel sleepy or in light sleep, and are also related to creativity and intuitive thinking. This brain wave is closely associated with relaxation, meditation, and light sleep stages. The frequency range of gamma waves (gamma waves) is above 30Hz. Gamma waves are associated with high cognitive functions, such as complex information processing and decision-making processes. It is active when the brain performs advanced cognitive processing. Increased gamma waves are associated with improved learning, memory, and perceptual integration. Alpha, beta, theta, and gamma waves each represent a different state of brain activity, ranging from relaxation to high alertness. Understanding the characteristics of these brain waves can not only help people better understand how the brain works in different situations, but also guide people on how to optimize cognitive and emotional health by adjusting their own mental state.

[0106] Step S13: acquiring the user's current mental state based on the first characteristic parameter, and generating a corresponding lamp control command according to the mental state; the lamp control command includes a corresponding controlled lamp and lamp configuration information.

[0107] In one embodiment of the present application, obtaining the user's current thinking state based on the first characteristic parameter includes the following steps S131 to S132.

[0108] Step S131: input the first feature parameter into the trained classifier to obtain a classification result.

[0109] Step S132: predict the user's current thinking state based on the classification result.

[0110] Specifically, the application generates corresponding lighting control commands based on the classification results. For example, when the model recognizes that the user is in a state of high attention and has strong alpha wave activity, the local control system believes that the user wants the lights to be brighter and generates a corresponding brightness increase command. For the adjustment of color temperature, the local control system will determine whether to adjust the color to warm or cool based on the user's emotion-related brain wave characteristics (such as gamma wave activity).

[0111] In one embodiment, the present application classifies and analyzes the first feature parameters using a machine learning model (such as a support vector machine (SVM) or a random forest) to identify the user's current state of mind and intention. By using a support vector machine (SVM) or a random forest (Random Forest) for classification, for the training set of the training support vector machine (SVM) and the random forest (Random Forest), the user's brain wave data in different situations can be used to identify the user's attention, relaxation, excitement and other states through the obtained classification results. Based on the extracted brain wave features, the present application predicts the user's state changes in the next few seconds, generates control commands in advance, and improves the response speed of the local control system.

[0112] In one embodiment, the present application classifies brain wave signals (the first characteristic parameter) using a support vector machine (SVM) classifier to identify the user's mental state and generate a light control command. The specific implementation process includes data preparation, feature annotation, model training, model verification, and real-time prediction.

[0113] Specifically, in this embodiment, in the data preparation stage, brain wave features, such as the frequency and amplitude of α waves and β waves, are obtained from the signal processing module as input data. In the feature annotation stage, these features are annotated with the corresponding thinking states (such as concentration, relaxation, and sleepiness) to form a training set. In the model training stage, the training data set is used to train the SVM classifier, and the kernel function (usually using the RBF kernel function, Radial Basis Function kernel, radial basis function kernel, referred to as RBF kernel) is defined to map the nonlinear problem to a high-dimensional space. In the model verification stage, the accuracy of the model is verified by the cross-validation method, and the hyperparameters are adjusted to improve performance. In the real-time prediction stage, the user's real-time brain wave features are input into the SVM classifier, the current thinking state is predicted in real time, and the corresponding lighting control instructions are generated.

[0114] More specifically, in this embodiment, the user's lighting control intention is identified based on the user's real-time brainwave characteristics. Different thinking states and brainwave characteristics correspond to different lighting control commands. For example, brightening the lights: When the local control system detects that the user is concentrating or thinking "brightening the lights", it issues a command to increase the brightness of the lights. Dimming the lights: When the user is in a relaxed or sleepy state, the local control system recognizes the user's intention to dim the lights and automatically lowers the brightness. Color temperature adjustment: The local control system can also detect changes in the user's emotions, identify the user's color temperature preference (such as cool or warm tones) through brainwave characteristics, and adjust the color temperature of the lights.

[0115] This application inputs the extracted brain wave signal features into the trained classifier for classification, and predicts the user's current state of mind based on the classification results. Input of the classifier: The input feature vector can be a combination of the above-extracted features, forming input data in a high-dimensional space, which may include the energy value and statistical characteristics of each waveform. Output of the classifier: The output can be a discrete state label, such as: "relaxed", "focused", "fatigued", "stressed", etc.

[0116] In one embodiment, the classification output corresponds to the user's mental state: "Relaxation" state: suitable for warm and soft lights. "Focus" state: suitable for cool and bright lights. "Tiredness" state: dim the lights and use a gentle color temperature. "Pressure" state: soft colored light to help relieve stress.

[0117] In one embodiment, the present application uses a Bayesian network model to perform multivariate analysis and adjusts the lighting control strategy in combination with environmental factors (such as indoor temperature and sound) to form an intelligent multi-dimensional interactive experience. The present application allows for flexible judgments to be made in uncertain situations, such as when the user's mental state is between concentration and relaxation, gradual lighting adjustments can be made.

[0118] While adjusting the lighting control strategy, this application also optimizes the lighting control strategy by using the deep reinforcement learning (DRL) algorithm, continuously adjusts the model parameters through real-time user feedback, and finally forms an adaptive lighting control solution. This application combines brain wave characteristics and emotion calculation models to identify the user's emotional state and adjust the lighting according to the user's emotions, such as providing warmer light to alleviate negative emotions.

[0119] Step S14: controlling the corresponding lamp based on the lamp control command.

[0120] In an embodiment of the present application, controlling the corresponding lamp based on the lamp control command includes the following steps S141 to S143.

[0121] Step S141, obtaining preset information of the lamp; the preset information includes a preset PWM frequency and a preset duty cycle range;

[0122] Step S142: acquiring the duty cycle to be adjusted of the lamp according to the lamp control command and the preset duty cycle range;

[0123] Step S143: adjusting the duty cycle of the lamp according to the preset PWM frequency and the duty cycle to be adjusted, so as to control the lamp.

[0124] In one embodiment, the present application automatically adjusts the brightness and color temperature of the light according to the lamp control command. The present application controls the corresponding lamp through PWM dimming control and RGBW LED color temperature control. PWM dimming control is based on PWM modulated LED driver, which accurately controls the brightness change of the light, and ensures the smoothness and naturalness of the brightness change by adjusting the PWM frequency and duty cycle. RGBW LED color temperature control is to achieve seamless color temperature adjustment from warm white light to cold white light by controlling the ratio of RGB and white light LEDs, and can automatically select the appropriate color temperature according to the emotional state detected by the user's brain wave.

[0125] In some embodiments, the present application controls lamps by combining a gradual adjustment mode with an immediate response mode to ensure that the user's visual experience is smooth, natural, and non-obtrusive, avoiding discomfort to the user. Specifically, when the user switches between a focused or relaxed state, the lamp light can gradually adjust the brightness and color temperature to provide a more comfortable transition experience. At the same time, when the user shows a strong intention, the lamp adjustment can respond immediately. At the same time, the present application supports personalized configuration of lights. By learning the user's long-term preferences (such as liking brighter light during a certain period of time), a personalized profile is generated so that the lamp adjustment can automatically adapt to the user's habits.

[0126] In one embodiment, the present application achieves a smooth dimming effect by using PWM to control the change of light brightness. The specific implementation process includes initialization parameters, input signal processing, PWM signal generation, smooth adjustment, feedback adjustment and other processes.

[0127] Furthermore, in this embodiment, in the initialization parameter stage, the PWM frequency (e.g., 1kHz) and duty cycle range (0%-100%) are set to represent the minimum brightness and maximum brightness. In the input signal processing stage, the light adjustment instruction (such as brightness increase or decrease) received from the intention recognition module is converted into the duty cycle adjustment amount. In the PWM signal generation stage, a PWM signal is generated through a timer interrupt to adjust the voltage duty cycle of the LED lamp, thereby changing the brightness. In the smooth adjustment stage, when changing the brightness, linear interpolation is used to gradually change the duty cycle to ensure smooth brightness changes and avoid flickering. Feedback adjustment: Continuously monitor the user's brain wave signals and adjust the PWM duty cycle in real time to ensure that the light brightness meets user needs.

[0128] In some embodiments, the lamp in the present application includes several lamps. The present application uses mesh network technologies such as Bluetooth, Zigbee, WiFi, and Thread to enable multiple lamps to work together to create a more unified lighting effect, which is suitable for large space applications. At the same time, optical communication (Li-Fi) is used to transmit data while adjusting indoor lighting, thereby improving the versatility of the local control system.

[0129] In one embodiment of the present application, the brainwave-based intelligent lighting control method further includes the following steps S15 to S17.

[0130] Step S15, obtaining the user's brain wave signal after the lamp is adjusted;

[0131] Step S16, obtaining the current thinking state of the user according to the brain wave signal of the user;

[0132] Step S17: regenerate corresponding lighting control commands according to the current thinking state to meet the personalized needs of the user.

[0133] Specifically, the local control system continuously monitors the user's brain wave changes, especially the reaction after the lighting is adjusted. If it detects that the user's brain waves show dissatisfaction or the intention to adjust again, the local control system will respond in time and re-optimize the lighting settings. By collecting and analyzing the user's long-term brain wave data, the intention recognition process is continuously adjusted and optimized to better match the user's personalized needs.

[0134] In one embodiment, the present application supports real-time feedback collection and personalized lighting control. Real-time feedback collection continuously collects user brain wave feedback and compares it with the brain wave state before and after the lighting adjustment. If it is found that the user's brain wave is in an unsatisfactory state, the local control system will make fine adjustments. Personalized lighting control records the user's brain wave data for a long time, analyzes each user's unique brain wave pattern, and adjusts the parameters of the intent recognition model to provide more personalized lighting control.

[0135] In one embodiment, the present application supports multi-user adaptive lighting adjustment. In a multi-user environment, the lighting control configuration is automatically switched by identifying the brainwave patterns of different users, ensuring that each user can get the lighting experience that best suits their needs. At the same time, combined with deep learning technology, the local control system can identify the potential patterns of users in the long-term use process, predict user behavior and make lighting adjustments in advance.

[0136] In one embodiment, the present application optimizes the lighting control strategy through deep reinforcement learning (DRL), so that the local control system can adaptively adjust the lighting settings according to user feedback. The specific implementation process includes environment and state definition, reward function design, exploration and utilization, and model optimization.

[0137] Further, in this embodiment, in the environment and state definition stage, the environment includes the user's brain wave state, current light brightness and color temperature. The state includes the brain wave characteristics collected each time (such as alpha wave and beta wave intensity). The action is the light brightness and color temperature that the local control system can adjust. In the reward function design stage, a reward function based on user satisfaction is defined. For example, if the user's brain wave characteristics show a relaxed or focused state, the local control system will give a positive reward; if dissatisfaction is detected (such as the intention to adjust again), a negative reward is given. For example, the deep neural network (DNN) in the deep Q network (DQN) is used to approximate the Q value function and predict the expected rewards for taking different actions in each state. After each operation, the network weights are updated according to the actual rewards obtained. In the exploration and utilization stage, in the early stage of the operation of the local control system, the local control system tries different lighting adjustment strategies through "exploration"; in the long-term use process, the best strategy learned is gradually "utilized" to optimize the user experience. In the model optimization stage, through experience replay and target network mechanism, the model is prevented from falling into the local optimum and the lighting control strategy is continuously improved.

[0138] In one embodiment, the present application collects user activity and environmental information (such as location, movement) through sensors, and combines it with brain wave data, so that the local control system can adaptively adjust the lighting settings to make the ambient light more compatible with the user's situation. At the same time, blockchain technology is used to protect the privacy of the user's brain wave data, ensure data security, and allow users to authorize different devices to share control data.

[0139] This application can monitor the effect of light adjustment in real time and provide feedback based on the user's brain wave changes. If the user's brain wave signal shows dissatisfaction (such as the intention to adjust again), the local control system will immediately adjust the strategy to meet the user's needs. At the same time, through the long-term accumulation of brain wave data and user behavior data, the local control system can adaptively adjust the algorithm to provide more accurate and personalized lighting control.

[0140] The present application uses an embodiment to specifically illustrate the overall implementation process of the intelligent control method for lamps based on brainwave control described in the present application, which specifically includes the steps of brainwave signal acquisition, brainwave signal feature extraction, classification and recognition, and lighting control command generation.

[0141] In the step of collecting brain wave signals, an EEG (electroencephalogram) device is used to collect brain wave signals. The device can be worn on the head and record the potential changes of multiple channels. The frequency of the collected signal is usually 256Hz or higher, and the duration can be set to several minutes to obtain enough data.

[0142] In the step of extracting brain wave signal features, the spectrum of brain wave signals is analyzed by Fourier transform (FFT) to decompose the signals into components of different frequencies. The extracted features include: power spectrum density of alpha wave (8-12Hz), beta wave (12-30Hz), theta wave (4-8Hz), delta wave (0.5-4Hz), etc. It may also include the time domain features of the signal (such as mean, variance) and nonlinear features (such as entropy).

[0143] In the classification and recognition step, the extracted brain wave signal features are input into the trained classifier for classification, and the user's current mental state is predicted based on the classification results. Input of the classifier: The input feature vector can be a combination of the above-extracted features, forming input data in a high-dimensional space, which may include the energy value and statistical characteristics of each waveform. Output of the classifier: The output can be a discrete state label, such as: "relaxed", "focused", "fatigued", "stressed", etc.

[0144] In one embodiment, the classification output corresponds to the user's mental state: "Relaxation" state: suitable for warm and soft lights. "Focus" state: suitable for cool and bright lights. "Tiredness" state: dim the lights and use a gentle color temperature. "Pressure" state: soft colored light to help relieve stress.

[0145] In the step of generating the lighting control command, the lighting control command corresponding to each state is as follows, for example: "Relax" → Command: Adjust the light to 2700K, 50% brightness. "Focus" → Command: Adjust the light to 5000K, 100% brightness. "Fatigue" → Command: Adjust the light to 3000K, 30% brightness. "Pressure" → Command: Start the RGB color light, and the color changes softly.

[0146] like Figure 3 As shown, an embodiment of the present application provides a method for intelligently controlling lamps based on brainwave control, and the method includes the following steps S21 to S23.

[0147] Step S21, obtaining the user's brain wave signal;

[0148] Step S22, performing a match search based on the brain wave signal and preset user information to obtain a matching result; the preset user information includes the obtained user brain wave signal;

[0149] Step S23: Control the corresponding lamp according to the matching result.

[0150] In an embodiment of the present application, controlling the corresponding lamp according to the matching result includes the following steps S231 to S232.

[0151] Step S231: if the matching result is successful and the brain wave signal exists in the preset user information, then the corresponding lamp setting information is obtained according to the brain wave signal, so as to control the corresponding lamp through the lamp setting information; the lamp setting information includes a lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is obtained by the above-mentioned lamp intelligent control method based on brain wave control;

[0152] Step S232: If the matching result is a failure, the brain wave signal does not exist in the preset user information, then the corresponding lamp is controlled according to the brain wave signal through the above-mentioned brain wave-based intelligent lamp control method.

[0153] In one embodiment, the present application supports multi-user adaptive lighting adjustment. Each user has his or her own unique brainwave pattern and lighting preference. In a multi-user environment, the corresponding lighting control scheme is applied by automatically switching or automatically identifying the brainwave patterns of different users, ensuring that each user can obtain the lighting experience that best meets their needs. At the same time, combined with deep learning technology, the local control system can identify the potential patterns of users in the long-term use process, predict user behavior and make lighting adjustments in advance.

[0154] In one embodiment, the present application proposes a method for intelligent control of lamps based on brainwave control that supports multi-user brainwave pattern recognition, by automatically identifying the current user in a multi-user environment and applying the corresponding lighting control scheme. The specific implementation process includes brainwave data collection, user identification model classification and recognition, personalized configuration loading, feedback learning, and user switching mechanism.

[0155] Furthermore, in this embodiment, in the brain wave data collection stage, the brain wave signal data collected from different users are stored locally or in the cloud. In the user identification model stage, the K nearest neighbor (KNN) algorithm is used to classify and identify different users according to their brain wave characteristics (such as a unique combination of alpha wave and beta wave intensities). At each startup, the local control system identifies the current user by comparing the similarity between the current brain wave data and the existing user data. In the personalized configuration loading stage, after identifying the user, the user's lighting control preference profile (for example, the brightness and color temperature preference settings of the lamps under the current user's specific state) is loaded. In the feedback learning stage, through feedback after multiple uses, the local control system continuously updates the preference model of each user to ensure that the lighting settings are more personalized. In the user switching mechanism stage, when the local control system detects a user switch (the brain wave pattern does not match the current profile), the local control system automatically switches to the new user settings.

[0156] like Figure 4As shown, an embodiment of the present application provides a method for intelligently controlling lamps based on brainwave control, and the method includes the following steps S31 to S33.

[0157] Step S31, obtaining the user's brain wave signal;

[0158] Step S32, obtaining the current scene of the user according to the brain wave signal;

[0159] Step S33, controlling corresponding lamps according to the current scene and preset lamp setting information; the preset lamp setting information includes lamp control commands corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control commands are obtained by the above-mentioned intelligent lamp control method based on brain wave control.

[0160] In one embodiment, the lighting mode is automatically adjusted according to the user's current situation (such as work, rest, entertainment), and the specific implementation process includes sensor data fusion, scene classification, scene switching rules, adaptive adjustment, and real-time adjustment.

[0161] Furthermore, in this embodiment, in the sensor data fusion stage, the current scene information is analyzed by combining environmental sensors (such as light, temperature, motion sensors) and brain wave signals. In the scene classification stage, a decision tree model is applied to classify scenes according to the input sensor data, such as work scenes, rest scenes, etc., and judged using features such as brain wave state (focus / relaxation), ambient brightness, temperature, etc. In the scene switching rule stage, once the scene classification model detects that the scene has changed (such as switching from work to rest), the local control system automatically adjusts the light brightness and color temperature according to the preset rules. In the adaptive adjustment stage, through long-term usage records, the local control system learns the user's lighting preferences in different scenes (such as brighter when working and warmer light when resting), and automatically optimizes the adjustment strategy. In the real-time adjustment stage, when the user's brain wave state shows a relaxed or sleepy state, the local control system will judge in advance that the user may enter a rest scene, and gradually reduce the brightness and adjust the color temperature.

[0162] The protection scope of the intelligent control method for lamps based on brainwave control described in the embodiment of the present application is not limited to the execution order of the steps listed in the present embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0163] The embodiment of the present application also provides a brainwave-controlled intelligent control system for lamps, which can implement the brainwave-controlled intelligent control method for lamps described in the present application. However, the implementation device of the brainwave-controlled intelligent control method for lamps described in the present application includes but is not limited to the structure of the brainwave-controlled intelligent control system for lamps listed in the present embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0164] like Figure 5 As shown, this embodiment provides a lamp intelligent control system based on brainwave control, and the system 2 includes: an acquisition module 21, a feature extraction module 22, an instruction generation module 23 and a lamp control module 24.

[0165] The acquisition module 21 is used to acquire target data; the target data includes the user's brain wave signal;

[0166] The feature extraction module 22 is used to perform feature extraction based on the brain wave signal to obtain a first feature parameter;

[0167] The instruction generation module 23 is used to obtain the user's current thinking state based on the first characteristic parameter, and generate a corresponding lamp control command according to the thinking state; the lamp control command includes the corresponding controlled lamp and lamp configuration information;

[0168] The lamp control module 24 is used to control the corresponding lamp based on the lamp control command.

[0169] like Figure 6 As shown, the system 2 further includes: an adaptive adjustment module 25 , a multi-user control module 26 and a scene recognition module 27 .

[0170] The adaptive adjustment module 25 is used to obtain the user's brain wave signal after the lamp is adjusted; obtain the user's current thinking state according to the user's brain wave signal; and regenerate the corresponding lamp control command according to the current thinking state to meet the user's personalized needs;

[0171] The multi-user control module 26 is used to perform a match search based on the brain wave signal and the preset user information to obtain a matching result; and control the corresponding lamp according to the matching result; the preset user information includes the acquired user brain wave signal;

[0172] If the matching result is successful, the brain wave signal exists in the preset user information, then the corresponding lamp setting information is obtained according to the brain wave signal, so as to control the corresponding lamp through the lamp setting information; the lamp setting information includes the lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is obtained by the above-mentioned lamp intelligent control method based on brain wave control;

[0173] If the matching result is a failure, the brain wave signal does not exist in the preset user information, then the corresponding lamp is controlled according to the brain wave signal by the above-mentioned intelligent control method for lamps based on brain wave control;

[0174] The scene recognition module 27 is used to obtain the current scene of the user based on the brain wave signal; control the corresponding lamps according to the current scene and preset lamp setting information; the preset lamp setting information includes the lamp control commands corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control commands are obtained by the above-mentioned brainwave-based lamp intelligent control method.

[0175] It should be noted that the functions or operations of the acquisition module 21, feature extraction module 22, instruction generation module 23, lighting control module 24, adaptive adjustment module 25, multi-user control module 26 and scene recognition module 27 described in the embodiment of the present disclosure correspond one by one to the steps in the above-mentioned brainwave-based lighting intelligent control method, so they will not be repeated here.

[0176] In the several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules or units, which can be electrical, mechanical or other forms.

[0177] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0178] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0179] like Figure 7 As shown, this embodiment provides an electronic device, and the electronic device 3 includes: a memory 31 and a processor 32.

[0180] The memory 31 is used to store executable programs; and

[0181] The processor 32 is used to execute the program so that the electronic device 3 executes the above-mentioned intelligent control method for lamps based on brainwave control.

[0182] The present application embodiment also provides a computer-readable storage medium. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be completed by a program to instruct the processor, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state hard disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state hard disk (SSD)), etc.

[0183] The present application embodiment may also provide a computer program product, the computer program product including one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer or data center.

[0184] When the computer program product is executed by a computer, the computer executes the method described in the above method embodiment. The computer program product may be a software installation package, and when the above method is required, the computer program product may be downloaded and executed on a computer.

[0185] In summary, the brainwave-based intelligent control method and system for lamps described in this application have the following beneficial effects:

[0186] This application is based on advanced brain wave detection technology and machine learning algorithms. It detects the user's brain wave signals and extracts the frequency band features related to the user's lighting control intention from the detected brain wave signals. It identifies the user's current thinking state based on the extracted features, and further generates corresponding lighting control commands to control the corresponding lighting. This enables users to control the lights simply through thinking activities. Users achieve unconscious control through thinking activities without any physical operation or voice commands, making the interaction process more natural and convenient, and has broad application prospects, such as home, postoperative rehabilitation in wards, elderly care, space stations and other application scenarios. At the same time, this application can automatically adjust the brightness and color temperature of the light according to the user's real-time brain wave state, provide a lighting environment that better meets user needs, and provide users with an intelligent and natural lighting experience.

[0187] By monitoring the user's brain wave feedback, this application can adaptively adjust the control strategy to provide a personalized lighting experience. At the same time, by recording the user's brain wave data for a long time, analyzing each user's unique brain wave pattern, and adjusting the lighting setting parameters of the intention recognition model, it can learn and adapt to each user's unique brain wave pattern, achieve highly personalized lighting control, and enhance the user's comfort and experience.

[0188] This application realizes adaptive lighting adjustment for multiple users by identifying the brain wave signal of the current user in a multi-user environment and automatically switching the lighting setting information, ensuring that each user can obtain the lighting experience that best suits their needs.

[0189] This application can automatically identify the different scenarios of the user (such as office, rest, entertainment) based on the user's brain wave signals, and automatically adjust the lighting mode according to the user's current situation (such as work, rest, entertainment), to achieve seamless switching of lighting modes between these scenes.

[0190] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0191] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for intelligently controlling lamps based on brainwave control, characterized in that: The method comprises: Acquiring target data; the target data includes a user's brain wave signal; Performing feature extraction based on the brain wave signal to obtain a first feature parameter; Acquire the user's current state of mind based on the first characteristic parameter, and generate a corresponding lamp control command according to the state of mind; the lamp control command includes a corresponding controlled lamp and lamp configuration information; The corresponding lamp is controlled based on the lamp control command.

2. The method for intelligently controlling lamps based on brainwave control according to claim 1, characterized in that: Acquiring the user's current thinking state based on the first characteristic parameter includes: Inputting the first feature parameter into the trained classifier to obtain a classification result; The user's current state of mind is predicted based on the classification result.

3. The method for intelligently controlling lamps based on brainwave control according to claim 1, characterized in that: Feature extraction based on the brain wave signal includes: Performing wavelet transform denoising processing on the brain wave signal to obtain a denoised brain wave signal; Based on the denoised brain wave signal, frequency band features related to the user's lighting control intention are extracted as the first feature parameters.

4. The method for intelligently controlling lamps based on brainwave control according to claim 1, characterized in that: Controlling the corresponding lamp based on the lamp control command includes: Acquire preset information of the lamp; the preset information includes a preset PWM frequency and a preset duty cycle range; According to the lamp control command and the preset duty cycle range, obtaining the duty cycle to be adjusted of the lamp; The duty cycle of the lamp is adjusted according to the preset PWM frequency and the duty cycle to be adjusted to control the lamp.

5. The method for intelligently controlling lamps based on brainwave control according to claim 1, characterized in that: Also includes: Acquiring a user's brain wave signal after the lamp is adjusted; Acquiring the current thinking state of the user according to the user's brain wave signal; The corresponding lighting control commands are regenerated according to the current state of mind to meet the personalized needs of the user.

6. A method for intelligently controlling lamps based on brainwave control, characterized in that: The method comprises: Obtain the user's brain wave signal; Perform a match search based on the brain wave signal and preset user information to obtain a matching result; the preset user information includes the acquired user brain wave signal; Control the corresponding lamps according to the matching results.

7. The method for intelligently controlling lamps based on brainwave control according to claim 6, characterized in that: According to the matching results, the corresponding lamps are controlled: If the matching result is successful, and the brain wave signal exists in the preset user information, then the corresponding lamp setting information is obtained according to the brain wave signal, so as to control the corresponding lamp through the lamp setting information; the lamp setting information includes a lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is obtained by the method according to any one of claims 1 to 5; If the matching result is a failure, the brain wave signal does not exist in the preset user information, and the corresponding lamp is controlled according to the brain wave signal by the method described in any one of claims 1 to 5.

8. A method for intelligent control of lamps based on brainwave control, characterized in that: include: Obtain the user's brain wave signal; Acquire the current scene of the user according to the brain wave signal; The corresponding lamps are controlled according to the current scene and preset lamp setting information; the preset lamp setting information includes lamp control commands corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control commands are obtained by the method described in any one of claims 1 to 5.

9. A brainwave-based intelligent lighting control system, characterized in that: include: An acquisition module, used to acquire target data; the target data includes a user's brain wave signal; A feature extraction module, used for performing feature extraction based on the brain wave signal to obtain a first feature parameter; An instruction generation module, used for acquiring the current state of mind of the user based on the first characteristic parameter, and generating a corresponding lamp control command according to the state of mind; the lamp control command includes a corresponding controlled lamp and lamp configuration information; The lamp control module is used to control the corresponding lamp based on the lamp control command.

10. The brainwave-controlled intelligent lighting control system according to claim 9, characterized in that: Also includes: An adaptive adjustment module, used to obtain the user's brain wave signal after the lamp is adjusted; and obtain the user's current thinking state according to the user's brain wave signal; Regenerate corresponding lighting control commands according to the current state of mind, so as to meet the personalized needs of the user; A multi-user control module, used to perform a match search based on the brain wave signal and preset user information to obtain a matching result; and control corresponding lamps based on the matching result; If the matching result is successful and the brain wave signal exists in the preset user information, the corresponding lamp setting information is obtained according to the brain wave signal, so as to control the corresponding lamp through the lamp setting information; If the matching result is a failure, and the brain wave signal does not exist in the preset user information, the corresponding lamp is controlled according to the brain wave signal by the method described in any one of claims 1 to 5; the preset user information includes the acquired user brain wave signal; the lamp setting information includes the lamp control command corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control command is obtained by the method described in any one of claims 1 to 5; A scene recognition module, used to obtain the current scene of the user according to the brain wave signal; The corresponding lamps are controlled according to the current scene and preset lamp setting information; the preset lamp setting information includes lamp control commands corresponding to the specific thinking state of the user to which the brain wave signal belongs; the lamp control commands are obtained by the method described in any one of claims 1 to 5.

Images