Method for automatically adjusting color temperature of LED light source in different scenes

Abstract

The invention relates to the technical field of LED light sources, in particular to an automatic color temperature adjusting method of an LED light source in different scenes, which comprises the following steps: S1, user situation detection: detecting user positions and behavior characteristics in a shared space in real time to form a situation data set; s2, multi-user situation identification: realizing regional identification of the multi-user situation; s3, environmental adaptability fine tuning: performing small-amplitude adjustment on the color temperature through an environmental adaptability fine tuning algorithm; s4, color temperature area distribution: dividing the shared space into a plurality of color temperature areas, and setting a corresponding color temperature value for each area; and S5, generating a color temperature regulation and control instruction: generating a regulation and control instruction for controlling each color temperature area. According to the invention, it is ensured that color temperature adjustment not only conforms to personal preference, but also can automatically adapt to environmental changes, so that visual comfort and space adaptability are effectively improved, and an intelligent lighting system is more intelligent and personalized.

Description

Technical Field

[0001] The invention relates to the technical field of LED light sources, and in particular to a method for automatically adjusting the color temperature of an LED light source in different scenes. Background Art

[0002] With the rapid development of intelligent lighting systems, personalized and dynamic lighting needs have gradually become prominent in multi-user shared spaces. The appropriate color temperature in different situations can directly affect the user's concentration, comfort and overall experience. For example, a higher color temperature in a work scene can improve concentration, while a lower color temperature in a rest scene can help relax. However, in a multi-user shared space, users' situational needs often differ. How to provide users in different areas with color temperature settings that meet their personalized needs and achieve dynamic adjustment of color temperature has become an urgent problem to be solved in the field of intelligent lighting.

[0003] Existing lighting systems mainly rely on static color temperature presets or simple manual adjustments, which makes it difficult to provide precise color temperature control based on the situational needs of different users and real-time environmental changes. Traditional color temperature adjustment methods mostly do not take into account personalized needs in multi-user environments, making it difficult to achieve color temperature differences and dynamic adaptation between regions. In addition, existing systems are often unable to effectively respond to changes in environmental parameters (such as light intensity and noise levels), resulting in the inability to guarantee user visual comfort when the environment fluctuates slightly. Overall, existing technologies have limited application value in multi-user shared spaces, and lack efficient and flexible intelligent adjustment solutions.

[0004] The present invention aims to provide a method for automatically adjusting the color temperature of an LED light source in different scenes, which can not only realize intelligent adjustment of color temperature and dynamically respond to user context and environmental changes, but also avoid the limitations of traditional static adjustment methods, provide users with a comfortable and optimized lighting experience, and enhance the application value of intelligent lighting systems. Summary of the invention

[0005] The invention provides a method for automatically adjusting the color temperature of an LED light source in different scenes.

[0006] The method for automatically adjusting the color temperature of an LED light source in different scenes comprises the following steps:

[0007] S1, user context detection: real-time detection of user locations and behavior characteristics in the shared space, acquisition of each user's activity area data, and formation of context data sets;

[0008] S2, multi-user situation identification: Analyze the situation data set, identify the personalized color temperature requirements of each user, automatically match the best color temperature configuration based on different situations, and realize regional identification of multi-user situations, including:

[0009] S21, data preprocessing: preprocessing the formed situation data set, including denoising, standardization and missing value filling;

[0010] S22, user context classification: Based on the preprocessed context data set, a fully connected neural network (FNN) model is used to classify each user's context and identify each user's context type (work, rest, meeting);

[0011] S23, optimal color temperature matching: automatically matches the color temperature value for each user based on the results of the scenario classification, and assigns the user to the corresponding color temperature area, realizing personalized color temperature control according to the color temperature requirements in different scenarios;

[0012] S3, environmental adaptability fine-tuning: Real-time detection of changes in environmental parameters (such as light intensity and noise level), and combined with the results of multi-user situation recognition, the environmental adaptability fine-tuning algorithm makes small adjustments to the color temperature to adapt to slight changes in the environment and optimize visual comfort;

[0013] S4, color temperature zone allocation: according to the results of multi-user situation recognition and environmental adaptability fine-tuning, the shared space is divided into multiple color temperature zones, and the corresponding color temperature value is set for each zone;

[0014] S5, color temperature control instruction generation: based on the result of color temperature area allocation, a control instruction for controlling each color temperature area is generated, and the color temperature output of the LED light source is automatically adjusted according to the control instruction.

[0015] Optionally, the user context detection in S1 includes:

[0016] S11, user location detection: using positioning sensors to collect the location information of each user in the shared space in real time;

[0017] S12, user behavior monitoring: using video surveillance equipment to monitor user behavior characteristics in real time, including movement, stay, and interaction;

[0018] S13, generating a context data set: integrating the location information and behavior characteristics of each user through a weighted algorithm to generate a context data set.

[0019] Optionally, the data preprocessing in S21 includes:

[0020] S211, denoising: removing noise data in the context data set, smoothing the context data set through a low-pass filter, and reducing high-frequency noise components in the data;

[0021] S212, standardization processing: standardizing the denoised context data set to scale data with different features to the same range;

[0022] S213, Missing value filling: For the situational data set with missing values ​​after standardization, the mean filling method is used to complete it.

[0023] Optionally, the fully connected neural network (FNN) model in S22 includes:

[0024] S221, the input layer is connected to the hidden layer: the preprocessed situation data set D i ′ is input to the first hidden layer of the fully connected neural network (FNN) model. Assume that the first hidden layer contains m neurons and the weight matrix is ​​W 1 ∈R m×n , the bias vector is b 1 ∈R m , the output vector of the first hidden layer is h 1 ;

[0025] S222, hidden layer to output layer connection: pass the output of the last hidden layer to the output layer. Assume that the output layer contains c neurons (i.e., the number of categories, work, rest, meeting), and the weight matrix of the output layer is W L ∈R c×m , the bias vector is b L ∈R c , the output layer is y;

[0026] S223, situation classification decision: Based on the probability distribution y of the output layer, the category with the maximum probability is selected as the classification result.

[0027] Optionally, the optimal color temperature matching in S23 includes:

[0028] S231, color temperature requirement determination: based on the situation classification result C i , define the target color temperature range for each scenario type (work, rest, meeting), each scenario type C i The corresponding target color temperature range is [T i,min ,T i,max ], where T i,min For user context type C i The minimum color temperature value, T i,max For user context type C i The highest color temperature value;

[0029] S232, color temperature matching calculation: For each user, according to his / her situation type C i Target color temperature range, calculate the matching personalized color temperature value T i ;

[0030] S233, color temperature area allocation: according to each user's personalized color temperature value T i , assign users to corresponding color temperature areas.

[0031] Optionally, the environmental adaptability fine-tuning in S3 includes:

[0032] S31, environmental parameter monitoring and change detection: real-time monitoring of environmental parameters in the shared space, including light intensity and noise level, recording the environmental parameter values ​​at each moment, calculating the change amplitude of the environmental parameters through the change detection algorithm, and determining whether it exceeds the preset fine-tuning threshold;

[0033] S32, color temperature fine-tuning calculation and adjustment: When it is detected that the change range of the environmental parameters exceeds the fine-tuning threshold, the current color temperature is slightly adjusted through the fine-tuning algorithm in combination with the result of multi-user scenario recognition.

[0034] Optionally, the environmental parameter monitoring and change detection in S31 includes:

[0035] S311, Real-time monitoring of environmental parameters: Use sensor devices to collect real-time environmental parameter values ​​in the shared space, including light intensity L t and noise level N t , and record the environmental parameter data at each moment t;

[0036] S312, calculation of change amplitude: using a change detection algorithm to calculate the light intensity change amplitude ΔL and the noise level change amplitude ΔN;

[0037] S313, fine-tuning threshold determination: Compare the calculated change amplitude with the preset fine-tuning threshold θ L and θ N For comparison, if ΔL>θ L Or ΔN>θ N , the color temperature fine-tuning operation is triggered.

[0038] Optionally, the color temperature fine-tuning calculation and adjustment in S32 includes:

[0039] S321, situation demand weight calculation: According to the results of multi-user situation recognition, the demand weight of each situation type is calculated, and the demand weight of each situation type is set to ω i ;

[0040] S322, color temperature fine-tuning amount calculation: based on the variation range of the environmental parameters and the weight of each scenario requirement, the color temperature fine-tuning amount is determined.

[0041] Optionally, the color temperature area allocation in S4 includes:

[0042] S41, user context clustering: based on the results of multi-user context recognition, users with similar context requirements are clustered in the same area through the K-means clustering algorithm to form several user context groups;

[0043] S42, color temperature area division: after the user scenario clustering is completed, the shared space is divided into multiple color temperature areas through Voronoi diagram division based on the location and number of scenario groups;

[0044] S43, regional color temperature value setting: Based on the result of environmental adaptability fine-tuning, set the corresponding color temperature value T for each color temperature area. k .

[0045] Optionally, the generation of the color temperature control instruction in S5 includes:

[0046] S51, control instruction generation: set the target color temperature value T of each color temperature area k Convert into LED light source control instructions and generate corresponding color temperature control instructions, including color temperature value and adjustment rate parameters;

[0047] S52, automatic color temperature adjustment: According to the generated control instructions, the LED light source output of each color temperature area is automatically adjusted to gradually reach the target color temperature T k .

[0048] Beneficial effects of the present invention:

[0049] The present invention enables the system to respond to the personalized needs of each user in a shared space in real time through multi-user context recognition, optimal color temperature matching and environmental adaptability fine-tuning. Through accurate user context detection and context classification based on the FNN model, it can quickly identify the user's activity status and match the optimal color temperature configuration for each context type. Combining multi-user context requirements and real-time environmental data, it ensures that color temperature adjustment not only meets personal preferences, but also automatically adapts to environmental changes, effectively improving visual comfort and spatial adaptability, making the intelligent lighting system more intelligent and personalized.

[0050] The present invention divides a shared space into a plurality of color temperature zones that meet the needs of different situations through color temperature zone allocation and color temperature control instruction generation, and automatically generates control instructions for LED light sources. The color temperature zone division is based on user situation clustering and Voronoi diagram division method, ensuring that the color temperature setting of each zone meets the personalized needs of users in the zone and reduces color temperature interference between different situations. Through the environmental adaptability fine-tuning mechanism, color temperature control can dynamically respond to environmental changes and provide flexible lighting adjustment, thereby improving the user's lighting experience and the practicality of intelligent lighting.

[0051] The present invention, by combining user context, real-time environment and personalized needs, enables the system to work efficiently in a complex, dynamic multi-user environment. Through intelligent color temperature control and fine area division, it effectively improves the response speed, adaptability and user satisfaction of the intelligent lighting system, provides users with a more comfortable and efficient lighting solution, and expands the application value of intelligent lighting in a changing environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a flow chart of an adjustment method according to an embodiment of the present invention;

[0054] Figure 2 Schematic diagram of multi-user context recognition according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0056] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0057] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0058] like Figure 1-Figure 2 As shown, the method for automatically adjusting the color temperature of an LED light source in different scenes includes the following steps:

[0059] S1, user context detection: real-time detection of user locations and behavior characteristics in the shared space, acquisition of each user's activity area data, and formation of context data sets;

[0060] S2, multi-user situation identification: Analyze the situation data set, identify the personalized color temperature requirements of each user, automatically match the best color temperature configuration based on different situations, and realize regional identification of multi-user situations, including:

[0061] S21, data preprocessing: preprocessing the formed situation data set, including denoising, standardization and missing value filling;

[0062] S22, user context classification: Based on the preprocessed context data set, a fully connected neural network (FNN) model is used to classify each user's context and identify each user's context type (work, rest, meeting);

[0063] S23, optimal color temperature matching: automatically matches the color temperature value for each user based on the results of the scenario classification, and assigns the user to the corresponding color temperature area. According to the color temperature requirements in different scenarios, personalized color temperature control is achieved to ensure that each area in the space meets the personalized needs of the user;

[0064] S3, environmental adaptability fine-tuning: Real-time detection of changes in environmental parameters (such as light intensity and noise level), and combined with the results of multi-user situation recognition, the environmental adaptability fine-tuning algorithm makes small adjustments to the color temperature to adapt to slight changes in the environment and optimize visual comfort;

[0065] S4, color temperature zone allocation: according to the results of multi-user situation recognition and environmental adaptability fine-tuning, the shared space is divided into multiple color temperature zones, and the corresponding color temperature value is set for each zone;

[0066] S5, color temperature control instruction generation: based on the result of color temperature area allocation, a control instruction for controlling each color temperature area is generated, and the color temperature output of the LED light source is automatically adjusted according to the control instruction to achieve a dynamic and personalized lighting effect;

[0067] Through the above content, the personalized color temperature requirements of each user in the shared space can be realized, ensuring that the color temperature control of different areas not only meets personal preferences, but also can adapt to environmental changes in real time. It not only improves visual comfort, but also optimizes the lighting effect through intelligent adjustment, avoids the limitations of traditional static color temperature adjustment methods, and realizes dynamic and personalized lighting control. It can provide more accurate and efficient lighting management in complex scenes with multiple users and changing environments, thereby enhancing the application value of the intelligent lighting system.

[0068] User context detection in S1 includes:

[0069] S11, user position detection: using positioning sensors to collect the position information of each user in the shared space in real time and determine the user's position in the space;

[0070] S12, user behavior monitoring: using video surveillance equipment to monitor user behavior characteristics in real time, including movement, stay, and interaction;

[0071] S13, generating a context data set: integrating the location information and behavior characteristics of each user through a weighted algorithm to generate a context data set, which is expressed as:

[0072] D i =w p ·p i +w b b i ;

[0073] Among them, w p and w b are the weights of location information and behavior features, respectively, and w p +w b =1, p i and b i are the location information and behavior characteristics of user i, D i is the context data set of user i;

[0074] Through the above content, the user's activity status in the shared space can be captured comprehensively and accurately, taking into account not only the user's spatial position, but also the user's behavior pattern, thereby generating a comprehensive set of situational data that can cope with complex and changeable user needs and environmental changes, and improving the responsiveness of the intelligent lighting system in a dynamic environment and the user experience.

[0075] The data preprocessing in S21 includes:

[0076] S211, denoising: removing the noise data in the context data set, smoothing the context data set through a low-pass filter, and reducing the high-frequency noise components in the data, which is expressed as:

[0077] d ij ′=α·d ij +(1-α)·d i(j-1) ′;

[0078] Among them, α is the smoothing coefficient, the value range is [0,1], which is used to adjust the denoising effect, d ij ′ is the jth eigenvalue of the i-th sample after denoising, d ij is the jth eigenvalue of the i-th sample in the original context data, d i(j-1) ′ is the eigenvalue of the i-th sample at time j-1 after denoising;

[0079] S212, standardization processing: standardize the denoised context data set, and scale the data with different features to the same range, expressed as:

[0080]

[0081] Among them, μ j and σ j are the mean and standard deviation of feature j, d ij ″ is the jth eigenvalue of the i-th sample after standardization;

[0082] S213, missing value filling: For the context data set with missing values ​​after standardization, the mean filling method is used to fill it, which is expressed as:

[0083]

[0084] Where N is the number of samples with complete data, d ij ″′ is the jth eigenvalue of the ith sample after missing values ​​are filled, d kj ″ is the j-th eigenvalue of the k-th sample;

[0085] Through the above content, the quality and consistency of situational data are improved. De-noising eliminates high-frequency noise in data collection, making the data smoother and more stable. Standardization scales the values ​​of different features to the same range, eliminating differences in feature scales and ensuring the equivalent impact of different features in the analysis. Missing value filling ensures the integrity of the data and avoids model errors caused by missing data.

[0086] The fully connected neural network (FNN) model in S22 includes:

[0087] S221, the input layer is connected to the hidden layer: the preprocessed situation data set D i ′ is input to the first hidden layer of the fully connected neural network (FNN) model. Assume that the first hidden layer contains m neurons and the weight matrix is ​​W 1∈R m×n , the bias vector is b 1 ∈R m , the output vector of the first hidden layer is h 1 , expressed as:

[0088] h 1 =σ(W 1 ·D i ′+b 1 );

[0089] Where σ is the Leaky ReLU activation function;

[0090]

[0091] Among them, z is the linear combination input value of the hidden layer;

[0092] S222, hidden layer to output layer connection: pass the output of the last hidden layer to the output layer. Assume that the output layer contains c neurons (i.e., the number of categories, work, rest, meeting), and the weight matrix of the output layer is W L ∈R c×m , the bias vector is b L ∈R c , the output layer is y, expressed as:

[0093] y=Softmax(W L ·h L +b L );

[0094] Among them, Softmax is the activation function of the output layer;

[0095] S223, situation classification decision: Based on the probability distribution y of the output layer, the category with the maximum probability is selected as the classification result, which is expressed as:

[0096]

[0097] Among them, C i is the situation classification result, Indicates selection y j The category j corresponding to the maximum value is taken as the user's context classification result;

[0098] Through the above content, different situation types in multi-user shared spaces can be identified quickly and accurately, which not only improves the classification accuracy in multi-user environments, but also ensures that the system can dynamically respond to the situational needs of different users, providing a reliable data basis for personalized color temperature control, and enhancing the applicability and user experience in complex scenarios.

[0099] The best color temperature matching in S23 includes:

[0100] S231, color temperature requirement determination: based on the situation classification result C i , define the target color temperature range for each scenario type (work, rest, meeting), each scenario type C i The corresponding target color temperature range is [T i,min ,T i,max ], where T i,min For user context type C i The minimum color temperature value, T i,max For user context type C i The highest color temperature value;

[0101] T i,min 、T i,max It is set according to the situational needs and user comfort, including:

[0102] The setting methods include:

[0103] Working situation: Working situations usually require high color temperature (cool tones) to improve concentration, so a higher color temperature range is set;

[0104] Resting scene: The resting scene tends to have low color temperature (warm tones) to create a relaxing atmosphere;

[0105] Meeting situation: Meeting situations require a moderate color temperature, which can maintain a certain level of concentration without being too glaring;

[0106] Color temperature range setting: According to different scene types, set the target color temperature range for each scene [T i,min ,T i,max ], expressed as:

[0107] T 工作,min =T base +ΔT 工作 ;

[0108] T 工作,max =T base +2×ΔT 工作 ;

[0109] T 休息,min =T base -2×ΔT 休息 ;

[0110] T 休息,max =T base -ΔT 休息 ;

[0111] T 会议,min =T base -ΔT 会议 ;

[0112] T会议,max =T base +ΔT 会议 ;

[0113] Where, ΔT 工作 , ΔT 休息 and ΔT 会议 The color temperature adjustment ranges for work, rest and meeting situations depend on the needs of different situations. base is the basic color temperature value;

[0114] The following are some examples:

[0115] Assume T base =4000K, ΔT 工作 =500K, ΔT 休息 =300K, ΔT 会议 =200K, then:

[0116] Working situation: [4500K, 5000K];

[0117] Resting situation: [3400K, 3700K];

[0118] Meeting scenario: [3800K, 4200K];

[0119] S232, color temperature matching calculation: For each user, according to his / her situation type C i Target color temperature range, calculate the matching personalized color temperature value T i , expressed as:

[0120] T i =T i,min +β(T i,max -T i,min );

[0121] Among them, β is the smoothing coefficient, and its value range is [0,1];

[0122] S233, color temperature area allocation: according to each user's personalized color temperature value T i , assign users to corresponding color temperature areas;

[0123] Through the above content, the appropriate color temperature range is automatically set according to the situation type (work, rest, meeting) to provide optimized lighting conditions for each situation. By allocating color temperature to the required range of different situation types, the work situation obtains cool colors to improve concentration, the rest situation obtains warm colors to create a comfortable atmosphere, and the meeting situation maintains a moderate color temperature to balance the concentration and comfort of the participants, ensuring that the color temperature adjustment is more in line with the actual needs of users, making the lighting experience of shared spaces more personalized and humane, and greatly improving the user's visual comfort and environmental adaptability.

[0124] Environmental adaptation fine-tuning in S3 includes:

[0125] S31, environmental parameter monitoring and change detection: real-time monitoring of environmental parameters in the shared space, including light intensity and noise level, recording the environmental parameter values ​​at each moment, calculating the change amplitude of the environmental parameters through the change detection algorithm, and determining whether it exceeds the preset fine-tuning threshold;

[0126] S32, color temperature fine-tuning calculation and adjustment: when it is detected that the change range of the environmental parameters exceeds the fine-tuning threshold, the current color temperature is slightly adjusted by a fine-tuning algorithm in combination with the result of multi-user context recognition;

[0127] Through the above content, the color temperature can be automatically fine-tuned when there are slight changes in light or noise, avoiding user discomfort due to environmental instability, thereby providing a more comfortable visual experience. Compared with static color temperature adjustment, environmental adaptability fine-tuning enhances the flexibility and responsiveness of the system, making the lighting system more in line with actual usage scenarios, and improving user satisfaction and environmental adaptability of smart lighting.

[0128] Environmental parameter monitoring and change detection in S31 include:

[0129] S311, Real-time monitoring of environmental parameters: Use sensor devices to collect real-time environmental parameter values ​​in the shared space, including light intensity L t and noise level N t , and record the environmental parameter data at each moment t;

[0130] S312, change amplitude calculation: Use the change detection algorithm to calculate the light intensity change amplitude ΔL and the noise level change amplitude ΔN, expressed as:

[0131] ΔL=|L t -L t-1 |;

[0132] ΔN=|N t -N t-1 |;

[0133] Among them, L t-1 and N t-1 Respectively represent the light intensity and noise level at the previous time point;

[0134] S313, fine-tuning threshold determination: Compare the calculated change amplitude with the preset fine-tuning threshold θ L and θ N For comparison, if ΔL>θ L Or ΔN>θ N , then the color temperature fine-tuning operation is triggered;

[0135] Fine-tune the threshold θL and θ N Based on historical data settings, including:

[0136] Calculation of average change amplitude: Assume that in the past time period T, the change data of light intensity and noise level are and The average variation of light intensity and noise level is and Respectively expressed as:

[0137]

[0138]

[0139] Threshold setting: Add a tolerance coefficient α to set the fine-tuning threshold, expressed as:

[0140]

[0141]

[0142] Among them, α is the tolerance coefficient, which is used to adjust the sensitivity of the fine-tuning threshold and its value range is [1.2, 1.5];

[0143] Through the above content, it is possible to effectively distinguish between slight fluctuations and significant changes, ensuring that color temperature fine-tuning is triggered only when needed, thereby avoiding interference caused by frequent adjustments. At the same time, it can respond quickly when the environment changes significantly, improving the stability and adaptability of the system, allowing the intelligent lighting system to continue to provide a comfortable lighting experience in a changing environment, optimizing the overall user experience.

[0144] Color temperature fine-tuning calculation and adjustment in S32 include:

[0145] S321, situation demand weight calculation: According to the results of multi-user situation recognition, the demand weight of each situation type is calculated, and the demand weight of each situation type is set to ω i , expressed as:

[0146]

[0147] Among them, N i is the number of users currently in situation type i, reflecting the number of users in this situation type, α i is the priority coefficient of situation type i, n is the total number of situation types, N j is the number of users of situation type j, α j is the priority coefficient of situation type j;

[0148] S322, color temperature fine-tuning amount calculation: based on the change range of environmental parameters and the weight of each scenario requirement, determine the color temperature fine-tuning amount, expressed as:

[0149]

[0150] Among them, T current is the current color temperature value, γ is the fine-tuning coefficient used to control the amplitude of color temperature adjustment, and ΔP is the amplitude of environmental parameter change (such as the larger of the light intensity change ΔL or the noise level change ΔN);

[0151] Through the above content, combined with the situational demand weights of multiple users, dynamic response to changes in environmental parameters can be achieved to achieve accurate and flexible color temperature control. When the environment changes, not only the number of users of each situation type is considered, but also important situations are given a higher influence according to the priority coefficient, thereby balancing the needs of multiple users and ensuring that the color temperature adjustment is more in line with the actual application scenarios. The adaptability and personalization of color temperature control are improved, so that the intelligent lighting system can provide a more comfortable and optimized lighting environment in a multi-user shared space, enhancing the overall user experience and satisfaction.

[0152] Color temperature zone assignments in S4 include:

[0153] S41, user context clustering: Based on the results of multi-user context recognition, users with similar context requirements are clustered in the same area through the K-means clustering algorithm to form several user context groups, which are expressed as:

[0154]

[0155] Among them, C k represents the set of the kth situation group, μ k is the centroid (center point) of the kth situation group, K is the total number of situation groups, x i The user's situational feature vector (including location information and color temperature requirements);

[0156] S42, color temperature area division: After the user scenario clustering is completed, the shared space is divided into multiple color temperature areas through Voronoi diagram division based on the location and number of scenario groups, ensuring that the user scenario requirements of each area are as balanced as possible, expressed as:

[0157]

[0158] Among them, R k is the color temperature area k, that is, the area in the shared space belonging to the situation group k, p is an arbitrary point in the space, representing a position in the shared space, used to determine the color temperature area to which it belongs, and space represents the overall range of the shared space, indicating the spatial area containing all users, μ kis the center point of situation group k, μ j is the center point of situation group j, j represents other situation groups, and j≠k, ∥p-μ k ∥ is the center point μ from point p to situation group k k Euclidean distance, ∥p-μ j ∥ is the point p to the center point μ of situation group j j The Euclidean distance of

[0159] S43, regional color temperature value setting: Based on the result of environmental adaptability fine-tuning, set the corresponding color temperature value T for each color temperature area. k , expressed as:

[0160] T k =T target,k +γ·ΔP;

[0161] Among them, T target,k is the target color temperature value of situation group k, which is usually determined by the situation type (work, rest, meeting), γ is the environmental adaptability fine-tuning coefficient, which is used to adjust the color temperature fine-tuning amplitude, and ΔP is the environmental parameter change amplitude, such as the larger of the light intensity change ΔL or the noise level change ΔN, which is used to adjust the color temperature to adapt to environmental changes;

[0162] Through the above content, color temperature interference between users in different situations is effectively avoided, thereby providing personalized lighting for each area. Combined with the fine-tuning mechanism of environmental parameters, the color temperature area can dynamically respond to external changes, making the lighting experience more flexible and comfortable, significantly improving the system's adaptability and user satisfaction, and enabling smart lighting to have efficient and accurate personalized service capabilities in a multi-user environment.

[0163] The color temperature control command generation in S5 includes:

[0164] S51, control instruction generation: set the target color temperature value T of each color temperature area k Convert into LED light source control instructions, generate corresponding color temperature control instructions, including color temperature value and adjustment rate parameters, to ensure that the LED light source gradually reaches the target color temperature and maintains a smooth transition of light;

[0165] S52, automatic color temperature adjustment: According to the generated control instructions, the LED light source output of each color temperature area is automatically adjusted to gradually reach the target color temperature T k , to achieve personalized color temperature control in multiple areas;

[0166] Through the above content, accurate and automatic color temperature adjustment is achieved, ensuring that the LED light source in each area can be dynamically adjusted according to user scenarios and environmental changes, gradually reaching the ideal target color temperature, providing smooth lighting transitions, and automatic command generation improves the response efficiency of the lighting system, making smart lighting more personalized and adaptable in multi-user environments, providing users with a more comfortable and demand-oriented lighting experience.

[0167] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0168] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for automatically adjusting the color temperature of an LED light source in different scenes, characterized in that: The following steps are involved: S1, user context detection: real-time detection of user locations and behavior characteristics in the shared space, acquisition of each user's activity area data, and formation of context data sets; S2, multi-user situation identification: Analyze the situation data set, identify the personalized color temperature requirements of each user, automatically match the best color temperature configuration based on different situations, and realize regional identification of multi-user situations, including: S21, data preprocessing: preprocessing the formed situation data set, including denoising, standardization and missing value filling; S22, user context classification: based on the preprocessed context data set, use a fully connected neural network model to classify each user's context and identify each user's context type; S23, optimal color temperature matching: automatically matches the color temperature value for each user based on the results of the scenario classification, and assigns the user to the corresponding color temperature area, realizing personalized color temperature control according to the color temperature requirements in different scenarios; S3, environmental adaptability fine-tuning: Real-time detection of changes in environmental parameters, and combined with the results of multi-user situation recognition, the environmental adaptability fine-tuning algorithm makes small adjustments to the color temperature to adapt to slight changes in the environment and optimize visual comfort; S4, color temperature zone allocation: according to the results of multi-user situation recognition and environmental adaptability fine-tuning, the shared space is divided into multiple color temperature zones, and the corresponding color temperature value is set for each zone; S5, color temperature control instruction generation: based on the result of color temperature area allocation, a control instruction for controlling each color temperature area is generated, and the color temperature output of the LED light source is automatically adjusted according to the control instruction.

2. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 1, characterized in that: The user context detection in S1 includes: S11, user location detection: using positioning sensors to collect the location information of each user in the shared space in real time; S12, user behavior monitoring: using video surveillance equipment to monitor user behavior characteristics in real time, including movement, stay, and interaction; S13, generating a context data set: integrating the location information and behavior characteristics of each user through a weighted algorithm to generate a context data set.

3. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 1, characterized in that: The data preprocessing in S21 includes: S211, denoising: removing noise data in the context data set, smoothing the context data set through a low-pass filter, and reducing high-frequency noise components in the data; S212, standardization processing: standardizing the denoised context data set to scale data with different features to the same range; S213, Missing value filling: For the situational data set with missing values ​​after standardization, the mean filling method is used to complete it.

4. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 3, characterized in that: The fully connected neural network model in S22 includes: S221, the input layer is connected to the hidden layer: the preprocessed situation data set D i ′ Input to the first hidden layer of the fully connected neural network model. Assume that the first hidden layer contains m neurons and the weight matrix is ​​W1∈R m×n , the bias vector is b1∈R m , the output vector of the first hidden layer is h1; S222, hidden layer to output layer connection: pass the output of the last hidden layer to the output layer. Assume that the output layer contains c neurons and the weight matrix of the output layer is W L ∈R c×m , the bias vector is b L ∈R c , the output layer is y; S223, situation classification decision: Based on the probability distribution y of the output layer, the category with the maximum probability is selected as the classification result.

5. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 4, characterized in that: The best color temperature matching in the S23 includes: S231, color temperature requirement determination: based on the situation classification result C i , define the target color temperature range for each scenario type, each scenario type C i The corresponding target color temperature range is [T i,min ,T i,max ], where T i,min For user context type C i The minimum color temperature value, T i,max For user context type C i The highest color temperature value; S232, color temperature matching calculation: For each user, according to his / her situation type C i Target color temperature range, calculate the matching personalized color temperature value T i ; S233, color temperature area allocation: according to each user's personalized color temperature value T i , assign users to corresponding color temperature areas.

6. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 1, characterized in that: The environmental adaptability fine-tuning in S3 includes: S31, environmental parameter monitoring and change detection: real-time monitoring of environmental parameters in the shared space, including light intensity and noise level, recording the environmental parameter values ​​at each moment, calculating the change amplitude of the environmental parameters through the change detection algorithm, and determining whether it exceeds the preset fine-tuning threshold; S32, color temperature fine-tuning calculation and adjustment: When it is detected that the change range of the environmental parameters exceeds the fine-tuning threshold, the current color temperature is slightly adjusted through the fine-tuning algorithm in combination with the results of multi-user scenario recognition.

7. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 6, characterized in that: The environmental parameter monitoring and change detection in S31 includes: S311, Real-time monitoring of environmental parameters: Use sensor devices to collect real-time environmental parameter values ​​in the shared space, including light intensity L t and noise level N t , and record the environmental parameter data at each moment t; S312, calculation of change amplitude: using a change detection algorithm to calculate the light intensity change amplitude ΔL and the noise level change amplitude ΔN; S313, fine-tuning threshold determination: Compare the calculated change amplitude with the preset fine-tuning threshold θ L and θ N For comparison, if ΔL>θ L Or ΔN>θ N , the color temperature fine-tuning operation is triggered.

8. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 7, characterized in that: The color temperature fine-tuning calculation and adjustment in S32 include: S321, situation demand weight calculation: According to the results of multi-user situation recognition, the demand weight of each situation type is calculated, and the demand weight of each situation type is set to ω i ; S322, color temperature fine-tuning amount calculation: based on the variation range of the environmental parameters and the weight of each scenario requirement, the color temperature fine-tuning amount is determined.

9. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 8, characterized in that: The color temperature area allocation in S4 includes: S41, user context clustering: based on the results of multi-user context recognition, users with similar context requirements are clustered in the same area through the K-means clustering algorithm to form several user context groups; S42, color temperature area division: after the user scenario clustering is completed, the shared space is divided into multiple color temperature areas through Voronoi diagram division based on the location and number of scenario groups; S43, regional color temperature value setting: Based on the result of environmental adaptability fine-tuning, set the corresponding color temperature value T for each color temperature area. k .

10. The method for automatically adjusting the color temperature of an LED light source in different scenes according to claim 9, characterized in that: The color temperature control instruction generation in S5 includes: S51, control instruction generation: set the target color temperature value T of each color temperature area k Convert into LED light source control instructions and generate corresponding color temperature control instructions, including color temperature value and adjustment rate parameters; S52, automatic color temperature adjustment: According to the generated control instructions, the LED light source output of each color temperature area is automatically adjusted to gradually reach the target color temperature T k .

Images