Lighting control method and system for different life stages, terminal and medium

Abstract

The application provides a life stage-oriented lighting control method and system, a terminal and a medium. The method comprises: acquiring life cycle data of a user, and constructing a life cycle feature vector; determining a life stage to which the user belongs according to the life cycle feature vector, and selecting an emotion weight model matched with the life stage; acquiring an emotion state parameter of the user, and constructing an emotion state vector; inputting the emotion state vector into the emotion weight model, and performing weighted mapping and constraint processing on the emotion state vector by the emotion weight model in combination with scene context information, to generate a target light parameter vector; and controlling a lighting device to output a light environment matched with the life stage and the emotion state of the user based on the target light parameter vector. The application solves the technical problem that the existing lighting technology is difficult to construct a stable, reliable and self-adaptive and optimized light environment in a normal life space due to low individualization degree and insufficient scene adaptability.

Description

Technical Field

[0001] This application belongs to the field of intelligent lighting technology, and relates to a lighting control method and system, terminal and medium for different life stages. Background Technology

[0002] With the continuous development of intelligent lighting technology, lighting systems have gradually evolved from traditional switch control, brightness adjustment, and color temperature adjustment to more refined and intelligent applications such as scene lighting, ambient lighting, health lighting, and mood lighting.

[0003] In existing technologies, some lighting control solutions can adjust the indoor lighting environment based on factors such as the user-selected scene theme, interior decoration style, changes in external ambient light, and user preferences, thereby improving spatial comfort, user experience, or environmental atmosphere. However, although the above solutions achieve personalized control to a certain extent, their core logic is still mainly limited to calling light templates based on static labels or preset rules.

[0004] Specifically, existing solutions typically use user age, interests, spatial function, or decoration style as fixed input conditions, and match them with pre-set standardized lighting themes or modes. This approach has significant technical limitations: on the one hand, it fails to fully consider key variables with long-term and dynamic evolution characteristics, resulting in lighting strategies that cannot adaptively adjust to changes in family members' physiological rhythms, visual needs, and psychological states; on the other hand, the static rule-based matching mechanism lacks the ability to continuously perceive and learn from the needs of the lighting environment, making it difficult to form a stable, reliable, and sustainably optimized closed-loop control effect. Summary of the Invention

[0005] This application provides a lighting control method, system, terminal, and medium for different life stages, addressing the technical problems of low personalization and insufficient scene adaptability that are common in existing lighting technologies.

[0006] Firstly, this application provides a lighting control method for different life stages, including:

[0007] Acquire user lifecycle data and construct lifecycle feature vectors based on the lifecycle data; the lifecycle data represents the steady-state characteristics of a user at a specific life stage, and the lifecycle feature vector is a structured representation formed by vectorizing the lifecycle data;

[0008] Based on the life cycle feature vector, the user's life stage is determined, and an emotion weight model matching the life stage is selected. The emotion weight model includes a basic mapping model and a personalized sub-model. The basic mapping model is used to describe the basic mapping relationship from the emotion state vector to the light parameter vector under the life stage. The personalized sub-model is used to make personalized corrections to the basic mapping relationship based on user feedback data.

[0009] The user's emotional state parameters are obtained, and the emotional state vector is constructed based on the emotional state parameters. The emotional state vector is input into the emotional weight model, and the emotional weight model combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector.

[0010] Based on the target light parameter vector, the lighting equipment is controlled to output a light environment that matches the user's life stage and emotional state.

[0011] In one implementation of the first aspect, controlling the output of a lighting device to match the user's life stage and emotional state based on the target light parameter vector includes:

[0012] The capability information of the lighting device is obtained, and a lighting device capability matrix is ​​constructed based on the capability information of the lighting device. The lighting device capability matrix is ​​a data structure that parametrically expresses the controllable output capability of the lighting device. The controllable output capability includes luminous flux range, color temperature range, color gamut range, channel structure, dimming depth, spatial coverage area, minimum response time, and maximum rate of change.

[0013] Based on the lighting equipment capability matrix, under the condition of satisfying the preset stage safety boundary and channel change rate constraints, the target light parameter vector is solved for channel constraints to obtain the channel control vector of the lighting equipment.

[0014] Based on the channel control vector, the corresponding lighting device is driven to output the light environment.

[0015] In one implementation of the first aspect, based on the lighting device capability matrix, and under the conditions of satisfying preset stage safety boundaries and channel change rate constraints, the target light parameter vector is solved for channel constraints to obtain the channel control vector of the lighting device, including:

[0016] The first optimization objective is to minimize the deviation between the actual output optical parameter vector and the target optical parameter vector, and the second optimization objective is to minimize the change between the current channel control vector and the previous channel control vector. A channel constraint optimization model is constructed as follows:

[0017] ;

[0018] And satisfy: 0≤d_i≤1, |d_i-d_i_prev|≤Δ_s, P∈R_s;

[0019] Where d is the channel control vector at the current moment, d=[d_1,d_2,...,d_i,...,d_n], n is the total number of channels of the lighting equipment, d_i represents the i-th channel control value in d; G_d represents the lighting equipment capability matrix; P represents the target light parameter vector; λ is the preset smoothing weight coefficient; d_prev represents the channel control vector at the previous moment; d_i_prev represents the i-th channel control value in d_prev; Δ_s is the maximum channel change rate corresponding to the life stage; R_s is the stage safety boundary corresponding to life stage s;

[0020] Based on the solution results of the channel constraint optimization model, the channel control vector of the lighting device is determined.

[0021] In one implementation of the first aspect, determining the user's life stage based on the life cycle feature vector and selecting an emotion weighting model that matches the life stage includes:

[0022] The life cycle feature vector is input into a preset life stage discriminator to obtain the stage probability of the user belonging to multiple preset life stages.

[0023] When the maximum probability in the stage probability is greater than or equal to a preset threshold, the life stage corresponding to the maximum probability is determined as the user's life stage, and an emotion weight model corresponding to the user's life stage is selected.

[0024] When the maximum probability among the stage probabilities is less than a preset threshold, two or more candidate life stages are determined from the multiple preset life stages, and the emotion weight models corresponding to the two or more candidate life stages are fused to generate an emotion weight model adapted to users in the transition stage.

[0025] In one implementation of the first aspect, the basic mapping model includes a stage initial light parameter vector, an emotion weight matrix, a light parameter response matrix, a stage basic bias, and a stage safety boundary; the emotion state vector is input to the emotion weight model, and the emotion weight model, in conjunction with scene context information, performs weighted mapping and constraint processing on the emotion state vector to generate a target light parameter vector, including:

[0026] Obtain the scene context information; the scene context information includes spatial semantic information, lighting temporal rhythm information, user activity information, and lighting device capability information;

[0027] The emotional state vector is weighted based on the emotional weight matrix to obtain weighted emotional features.

[0028] The weighted emotion features and the scene context information are input into a preset mapping function for context fusion mapping to obtain the emotion lighting adjustment amount;

[0029] Based on the light parameter response matrix, and combined with the initial light parameter vector of the stage and the basic bias of the stage, the emotion lighting modulation amount is responded to and mapped to obtain the candidate light parameter vector.

[0030] The candidate optical parameter vector is constrained and pruned based on the stage safety boundary to generate the target optical parameter vector.

[0031] In one implementation of the first aspect, when multiple users exist within the same shared space, the method further includes performing partitioned collaborative optimization on the target light parameter vectors corresponding to each of the multiple users; the partitioned collaborative optimization step includes:

[0032] Obtain the target light parameter vector for each user, as well as the spatial position of each user in the shared space;

[0033] Based on the spatial location of each user and the spatial coverage of the lighting equipment, the lighting control area in the shared space is divided into a local control area and a shared control area;

[0034] For the local control area, the spatial correlation degree between each user and the local control area is calculated, and the dominant user is determined based on the spatial correlation degree; the target light parameter vector corresponding to the dominant user is used as the target light parameter vector of the local control area.

[0035] For the shared control area, the collaborative weight of each user in the shared control area is calculated based on the user's corresponding spatial location, emotional confidence, life stage, activity priority, and security priority.

[0036] Based on the target light parameter vectors corresponding to each user and the collaborative weights, an optimization model for the target light parameters of the shared control region is established; the optimization model for the target light parameters of the shared control region is expressed as follows:

[0037] ;

[0038] Where P represents the target light parameter vector, satisfying P∈∩R_i, R_i is the stage safety boundary corresponding to user i, and ∩R_i represents the intersection of stage safety boundaries corresponding to multiple users; w_i represents the collaborative weight of user i in the shared control area; P_i is the target light parameter vector corresponding to user i; λ represents the preset smoothing weight coefficient; Ω(P) represents the regularization constraint term composed of spatial continuity, energy consumption, comfort and smooth transition constraints;

[0039] Based on the solution results of the target light parameter optimization model of the shared control region, the target light parameter vector of the shared control region is determined.

[0040] One implementation of the first aspect also includes:

[0041] Acquire user feedback data; the user feedback data includes explicit user feedback data, secondary lighting adjustment behavior data, scene dwell time data, dynamic effect active turn-off command data, voice feedback data, or preset non-privacy standard sensor features;

[0042] Based on the user feedback data, the user's feedback characteristics to the current output light environment are obtained, and the user's feedback error to the current output light environment is calculated based on the feedback characteristics.

[0043] Based on the feedback error, the parameters of the personalized sub-model are updated, while keeping the basic mapping model unchanged during the update process.

[0044] Secondly, this application provides a lighting control system for different life stages, including:

[0045] The stage feature construction module is used to acquire user lifecycle data and construct lifecycle feature vectors based on the lifecycle data; the lifecycle data represents the steady-state characteristics of a user at a specific life stage, and the lifecycle feature vector is a structured representation formed after vectorizing the lifecycle data.

[0046] The model determination module is used to determine the user's life stage based on the life cycle feature vector and select an emotion weight model that matches the life stage. The emotion weight model includes a basic mapping model and a personalized sub-model. The basic mapping model is used to describe the basic mapping relationship from the emotion state vector to the light parameter vector under the life stage. The personalized sub-model is used to make personalized corrections to the basic mapping relationship based on user feedback data.

[0047] The parameter generation module is used to obtain the user's emotional state parameters and construct the emotional state vector based on the emotional state parameters; the emotional state vector is input into the emotional weight model, and the emotional weight model combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector;

[0048] The output control module is used to control the lighting equipment to output a light environment that matches the user's life stage and emotional state based on the target light parameter vector.

[0049] Thirdly, this application provides a terminal, including:

[0050] The memory is used to store computer programs;

[0051] A processor, the processor being configured to execute a computer program stored in the memory, so as to cause the terminal to perform any of the methods described above.

[0052] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the preceding claims.

[0053] As described above, the lighting control method, system, terminal, and medium for different life stages described in this application have the following beneficial effects:

[0054] (1) Using the emotion weight model, multi-dimensional features such as emotion state, life cycle data, scene context information and stage safety boundary are vectorized and fused, so that the generated target light parameter vector is no longer a fixed template output, but a parameterized result with stage adaptability, emotion adaptability, scene adaptability and safety interpretability.

[0055] (2) The feedback learning mechanism is used to implement constrained updates to the personalized sub-model, ensuring that the lighting strategy continues to iterate with the user's life cycle state, effectively solving the problem of control strategy lag and rigidity caused by traditional fixed stage labels. Attached Figure Description

[0056] Figure 1 The flowchart shown is a lighting control method for different life stages according to an embodiment of this application.

[0057] Figure 2 The flowchart shown is a process for determining an emotion weight model based on a life cycle feature vector in one embodiment of this application.

[0058] Figure 3 The flowchart shown is a process for generating the target light parameter vector in one embodiment of this application.

[0059] Figure 4 The flowchart shown is a flowchart of the generation of the target light parameter vector in another embodiment of this application.

[0060] Figure 5 The flowchart shown is a process for controlling the output light environment of a lighting device based on a target light parameter vector according to an embodiment of this application.

[0061] Figure 6 The flowchart shown is a multi-user partition collaborative optimization process in one embodiment of this application.

[0062] Figure 7 The flowchart shown is a process for updating a personalized sub-model in one embodiment of this application.

[0063] Figure 8 The diagram shown is a structural schematic of a lighting control system for different life stages according to an embodiment of this application.

[0064] Figure 9 The diagram shown is a structural schematic of a lighting system according to an embodiment of this application.

[0065] Figure 10 The diagram shown is a structural schematic of a terminal according to an embodiment of this application. Detailed Implementation

[0066] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0067] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0068] The following embodiments of this application provide lighting control methods, systems, terminals, and media for different life stages. This solution uses an emotion weighting model to vectorize and fuse multi-dimensional features such as emotional state, lifecycle data, scene context information, and stage safety boundaries. This enables the dynamic generation of a lighting environment that precisely matches the user's life stage and real-time emotional state. It effectively solves the technical problem that existing lighting technologies, due to their low personalization and insufficient scene adaptability, struggle to construct stable, reliable, and adaptively optimized lighting environments in normal living spaces.

[0069] This application can be widely applied to various residential lighting environments, including family mood lighting, all-age functional lighting (including dedicated scenes for children, teenagers, young adults, and the elderly), parent-child sharing, and multi-member zone collaborative control. The lighting control methods tailored to different life stages can be executed by at least one of terminal devices, edge computing nodes, cloud servers, or cloud-edge collaborative platforms. Specific implementation carriers include home gateways, local edge computing devices, dedicated lighting controllers, mobile terminals, and cloud servers.

[0070] The following will describe in detail the principles and implementation methods of a lighting control method and system, terminal and medium for different life stages according to this embodiment, so that those skilled in the art can understand the lighting control method and system, terminal and medium for different life stages according to this embodiment without creative labor.

[0071] Please see Figure 1 The above is a flowchart of a lighting control method for different life stages in one embodiment of this application.

[0072] like Figure 1 As shown, this embodiment provides a lighting control method for different life stages, including the following steps S100 to S400.

[0073] In step S100, user lifecycle data is obtained, and a lifecycle feature vector is constructed based on the lifecycle data.

[0074] The lifecycle data represents the steady-state characteristics of a user at a specific life stage, and the lifecycle feature vector is a structured representation formed by vectorizing the lifecycle data.

[0075] In this embodiment, the lifecycle data includes basic user data, circadian rhythm data, visual sensitivity data, activity scenario data, family role data, and historical feedback data.

[0076] Specifically, the user's basic data includes at least one of the following: age, age group, year of birth, height stage, learning stage, working stage, and retirement status. The circadian rhythm data includes at least one of the following: wake-up time, sleep time, nap time, frequency of nighttime awakenings, weekday / weekend sleep-wake cycles, seasonal sleep-wake cycles, and historical lighting usage time distribution. The visual sensitivity data includes at least one of the following: glare sensitivity level, short-wavelength light sensitivity level, nighttime low-brightness adaptation ability, color stimulation acceptance, dynamic lighting effect acceptance, and user-initiated preferences for eye protection, low stimulation, or age-appropriate lighting. The activity scenario data includes scenario tags such as learning, reading, working, audio-visual entertainment, gaming, sports, and rest. The family role data includes at least one role attribute among child, teenager, adult, parent, person being cared for, caregiver, elderly, visitor, controlling user, or temporary user. The historical feedback data includes records of user adjustments to the historical lighting environment, scene dwell time, records of dynamic effects being turned off, records of brightness or color temperature regression, user explicit evaluation records, and long-term preference records formed in different spaces and time periods.

[0077] In one embodiment of this application, obtaining user lifecycle data includes: obtaining basic profile information actively filled in or authorized for import by the user; reading non-sensitive interaction logs generated by the lighting system within a historical time window; obtaining user preference configurations in mobile applications, smart panels, voice entry points, or lighting scene panels; and obtaining usage records of lighting devices in different spaces.

[0078] It should be noted that this application may not collect original facial images, original voice content, heart rate, blood pressure, body temperature, electroencephalogram (EEG), electrodermatology (ED), or other biometric or highly sensitive physiological data, thereby reducing system implementation costs and privacy risks.

[0079] In one embodiment of this application, before constructing the lifecycle feature vector, the lifecycle data is further preprocessed. The preprocessing includes at least one of outlier removal, missing value imputation, time granularity unification, discrete label encoding, continuous variable normalization, privacy anonymization, and data validity verification.

[0080] In this implementation, by introducing lifecycle data, the system can unify users' visual safety needs, mood lighting needs, activity needs, and long-term preferences at different life stages into a computable parameter expression, enabling multidimensional heterogeneous needs to be parameterized in a unified vector space.

[0081] In step S200, the user's life stage is determined based on the life cycle feature vector, and an emotion weight model that matches the life stage is selected.

[0082] In this embodiment, the life stages include childhood, adolescence, youth, middle age, and old age. In some embodiments, the life stages can be further subdivided into preschool, school-age, adolescence, early career, parenting, stress recovery, retirement adaptation, and age-appropriate care.

[0083] The emotion weighting model describes the mapping logic from a user's emotional state to lighting parameters at a corresponding life stage. Specifically, the emotion weighting model includes a basic mapping model and a personalized sub-model. The basic mapping model describes the basic mapping relationship from the emotional state vector to the light parameter vector at the corresponding life stage. The personalized sub-model is used to personalize the basic mapping relationship based on user feedback data.

[0084] In one embodiment of this application, the basic mapping model includes a stage initial light parameter vector, an emotion weight matrix, a light parameter response matrix, a stage basic bias, and a stage safety boundary. The basic mapping model is expressed as:

[0085] M_s={P0_s,W_s,H_s,B_s,R_s};

[0086] Where P0_s represents the initial light parameter vector of the stage; M_s is the basic mapping model; W_s is the emotion weight matrix; H_s is the light parameter response matrix; B_s is the stage basic bias; and R_s is the stage safety boundary corresponding to life stage s.

[0087] Specifically, the initial light parameter vector for a given stage represents the baseline light environment state at the current life stage, serving as the starting anchor for light parameter generation. It includes steady-state values ​​such as the recommended default brightness, color temperature, and spectral distribution for that stage. The emotion weight matrix characterizes the influence weights of different emotional state parameters on various dimensions of the output light environment, reflecting the differences in sensitivity to light requirements under specific life stages. The light parameter response matrix establishes a structured mapping relationship from the emotion vector to the specific light output. The stage-based bias represents the inherent light preference compensation term for the current life stage, used to correct perceptual biases caused by age-related changes in visual characteristics (such as lens aging and pupil constriction), ensuring that the output light parameters match the user's actual physiological experience. The stage safety boundary limits at least one of the target light parameter vectors, including maximum brightness, minimum brightness, illuminance range, correlated color temperature range, short-wavelength energy ratio, color saturation range, dynamic change rate, dynamic change amplitude, transition time, glare threshold, flicker risk threshold, and the spatial coverage of the luminaire group.

[0088] Please see Figure 2The above is a flowchart of a model for determining emotion weights based on life cycle feature vectors in one embodiment of this application.

[0089] like Figure 2 As shown, determining the user's life stage based on the life cycle feature vector and selecting an emotion weight model that matches the life stage includes the following steps S201 to S203.

[0090] In step S201, the life cycle feature vector is input to the preset life stage discriminator to obtain the stage probability of the user belonging to multiple preset life stages.

[0091] The preset life stage discriminator can be implemented using a rule discriminator, a statistical classifier, a machine learning classification model, or a combination thereof.

[0092] In one embodiment of this application, the probability of a user belonging to a preset life stage can be determined by the following formula:

[0093] P(s|L_u)=softmax(A_s·L_u+B_s);

[0094] Where P(s|L_u) represents the probability that a user belongs to life stage s given the life cycle feature vector L_u; A_s represents the stage discrimination parameter matrix corresponding to life stage s; B_s represents the stage basis bias; and softmax represents the normalized exponential function.

[0095] In step S202, when the maximum probability in the stage probability is greater than or equal to a preset threshold, the life stage corresponding to the maximum probability is determined as the user's life stage, and an emotion weight model corresponding to the user's life stage is selected.

[0096] For example, when a user's probability of being in the childhood stage is 0.83 and the preset stage threshold is 0.70, the system determines that the user belongs to the childhood stage and selects the emotion weight model corresponding to the childhood stage.

[0097] In step S203, when the maximum probability in the stage probability is less than a preset threshold, two or more candidate life stages are determined from the multiple preset life stages, and the emotion weight models corresponding to the two or more candidate life stages are fused to generate an emotion weight model adapted to users in the transition stage.

[0098] For example, when the probability of a user being in the youth stage is 0.52 and the probability of being in the middle-aged stage is 0.41, and neither of them reaches the preset stage threshold, the system does not forcibly divide the user into a single stage. Instead, it generates a stage mixed weight based on the probability of the two candidate stages, and integrates the emotional weight models of the youth and middle-aged stages accordingly, so that the output light environment takes into account the lighting needs of both the youth and middle-aged stages.

[0099] In one embodiment of this application, the fusion process can be expressed as:

[0100] M_u= ,and =1, β_s≥0;

[0101] Where M_u represents the fusion emotion weight model corresponding to user u; β_s represents the stage mixed weight corresponding to life stage s; and M_s represents the emotion weight model corresponding to life stage s.

[0102] In this implementation, through the stage probability discrimination and stage model fusion mechanism, the system can adapt to user growth, changes in life status, changes in caregiver roles, or changes in critical stages, avoiding rigid lighting output caused by fixed life stage labels.

[0103] It should be noted that the life stages described in this application are not equivalent to a single age group. For users of the same age group, if there are significant differences in their circadian rhythms, visual sensitivity, activity scenarios, and family roles, then their corresponding life cycle feature vectors and the subsequently selected life stage emotional weighting models can be different. This avoids the insufficient adaptation accuracy caused by using only age for coarse-grained lighting grading.

[0104] In step S300, the user's emotional state parameters are obtained, and the emotional state vector is constructed based on the emotional state parameters. The emotional state vector is then input into the emotional weight model, which combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector.

[0105] Please see Figure 3 The above is a flowchart illustrating the generation of the target light parameter vector in one embodiment of this application.

[0106] The emotional state parameters include at least the emotion type, emotion intensity, emotion duration, emotion change rate, and emotion recognition confidence level.

[0107] Specifically, the emotion type may include calmness, relaxation, focus, pleasure, excitement, tension, anxiety, fatigue, depression, irritability, confusion, or a tendency to sleep. The emotion intensity is used to characterize the strength of the corresponding emotion type; the emotion duration is used to characterize the duration of the current emotional state within a preset time window; the emotion change rate is used to characterize the direction and rate of change of emotion intensity or emotion type over time; and the emotion recognition confidence level is used to characterize the reliability of the current emotional state parameters.

[0108] The emotional state parameters can be obtained from user input, speech semantic parsing, speech prosody features, mobile terminal interaction, lighting interaction events, wearable devices, millimeter-wave radar, environmental sensors, behavioral events, or a combination thereof.

[0109] To reduce privacy risks, in some implementations, the system only receives structured emotion state parameters output by the upstream emotion recognition module, and does not store the original images, original voice or sensitive physiological data in the lighting control system.

[0110] In one embodiment of this application, obtaining the user's emotional state parameters and constructing the emotional state vector based on the emotional state parameters includes: receiving emotional intent information input by the user through a mobile application, smart panel, or voice input; performing natural language parsing on the emotional intent information to determine the emotion type; determining the emotion intensity based on emotion intensity words, speech prosody features, interaction frequency, scene dwell time, or the intensity level selected by the user; determining the emotion duration based on continuous input time, scene dwell time, duration of historical events, or user confirmation information; determining the emotion change rate based on changes in emotion type or interaction behavior within a preset time window; and determining the emotion recognition confidence level based on the output probability of the emotion recognition model.

[0111] For example, the emotional state vector of user u at time t can be represented as:

[0112] E_u(t)=[m_u(t), I_u(t), D_u(t), R_u(t), C_u(t)];

[0113] Where m_u(t) represents the emotion type; I_u(t) represents the emotion intensity; D_u(t) represents the emotion duration; R_u(t) represents the emotion change rate; and C_u(t) represents the emotion recognition confidence level.

[0114] Please see Figure 4 The above is a flowchart illustrating the generation of the target light parameter vector in another embodiment of this application.

[0115] like Figure 4As shown, the emotional state vector is input into the emotional weight model, and the emotional weight model combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector, including the following steps S301 to S305.

[0116] In step S301, the scene context information is obtained.

[0117] The scene context information includes spatial semantic information, lighting temporal rhythm information, user activity information, and lighting device capability information. The spatial semantic information may include space labels such as bedroom, children's room, elderly person's room, living room, dining room, study, corridor, or bathroom; the lighting temporal rhythm information may include the current time, sunrise and sunset times, bedtime period, study period, or low-stimulation period at night; the user activity information may include activity types such as reading and writing, electronic screen use, leisure watching movies, dining and socializing, sleeping and resting, getting up at night to move around, and meditation and relaxation; the lighting device capability information may include luminous flux range, color temperature range, color gamut range, channel structure, dimming depth, spatial coverage area, minimum response time, and maximum rate of change.

[0118] In step S302, the emotion state vector is weighted based on the emotion weight matrix to obtain weighted emotion features.

[0119] Different life stages correspond to different emotion weight matrices, therefore the same emotional intensity and duration will produce different light environment adjustment amplitudes at different life stages. For example, in childhood, emotional fluctuations have a higher inhibitory weight on dynamic speed and saturation; in old age, visual sensitivity characteristics and safety constraints such as illuminance, glare, and dynamic speed have a higher weight.

[0120] In step S303, the weighted emotion features and the scene context information are input into a preset mapping function for context fusion mapping to obtain the emotion lighting adjustment amount.

[0121] Specifically, the preset mapping function can be implemented using a rule function, a lookup table function, a neural network model, a regression model, or a combination thereof.

[0122] This embodiment avoids mapping based solely on emotional states by introducing scene context information.

[0123] In step S304, based on the light parameter response matrix and in combination with the initial light parameter vector of the stage and the basic bias of the stage, the emotion lighting adjustment amount is responded to and mapped to obtain a candidate light parameter vector.

[0124] In step S305, the candidate optical parameter vector is constrained and pruned based on the stage safety boundary to generate the target optical parameter vector.

[0125] In one embodiment of this application, the target light parameter vector can be represented as:

[0126] P_u(t)=Clip_Rs(P0_s+H_s·f(W_s·E_u(t),Ctx_u(t))+B_s);

[0127] Where P_u(t) represents the target light parameter vector corresponding to user u; Clip_Rs is used to restrict the generated light parameter vector within the stage safety boundary R_s; P0_s represents the initial light parameter vector of the stage; H_s represents the light parameter response matrix; f represents the mapping function; W_s represents the emotion weight matrix; E_u(t) represents the emotion state vector corresponding to user u; Ctx_u(t) represents the scene context information corresponding to user u; and B_s represents the stage basic bias.

[0128] The target light parameter vector includes brightness or illuminance, correlated color temperature, color coordinates, saturation, shortwave energy ratio, dynamic change rate, dynamic change amplitude, transition time, and spatial distribution weight.

[0129] In this implementation, an emotion weight model is used to vectorize and fuse the emotion state vector with the life cycle feature vector, scene context information and stage safety boundary, so that the generated target light parameter vector is no longer a fixed template output, but a parameterized result with stage adaptability, emotion adaptability, scene adaptability and safety interpretability.

[0130] In step S400, based on the target light parameter vector, the lighting device is controlled to output a light environment that matches the user's life stage and emotional state.

[0131] Please see Figure 5 The above is a flowchart illustrating the control of the output light environment of a lighting device based on a target light parameter vector in one embodiment of this application.

[0132] like Figure 5 As shown, controlling the output of the lighting equipment to match the user's life stage and emotional state based on the target light parameter vector includes the following steps S401 to S404.

[0133] In step S401, the capability information of the lighting device is obtained, and a lighting device capability matrix is ​​constructed based on the capability information of the lighting device.

[0134] The lighting equipment may include at least one of the following: RGB+CCT multi-channel lamps, RGBW lamps, full-color pixel lamps, spotlights, light strips, ceiling lights, panel lights, table lamps, bedside lamps, path lights, or pixelated lighting curtains.

[0135] The lighting equipment capability matrix is ​​a data structure that parametrically expresses the controllable output capabilities of lighting equipment. The controllable output capabilities include luminous flux range, color temperature range, color gamut range, channel structure, dimming depth, spatial coverage area, minimum response time, and maximum rate of change.

[0136] In step S402, based on the lighting equipment capability matrix, and under the condition of satisfying the preset stage safety boundary and channel change rate constraints, the target light parameter vector is solved for channel constraints to obtain the channel control vector of the lighting equipment.

[0137] In one embodiment of this application, based on the lighting device capability matrix, and under the conditions of satisfying the preset stage safety boundary and channel change rate constraints, the target light parameter vector is solved for channel constraints to obtain the channel control vector of the lighting device, including:

[0138] The first optimization objective is to minimize the deviation between the actual output optical parameter vector and the target optical parameter vector, and the second optimization objective is to minimize the change between the current channel control vector and the previous channel control vector. A channel constraint optimization model is constructed as follows:

[0139] ;

[0140] And satisfy: 0≤d_i≤1, |d_i-d_i_prev|≤Δ_s, P∈R_s;

[0141] Where d is the channel control vector at the current moment, d=[d_1,d_2,...,d_i,...,d_n], n is the total number of channels of the lighting device, d_i represents the i-th channel control value in d; G_d represents the capability matrix of the lighting device; P represents the target light parameter vector; λ is the preset smoothing weight coefficient; d_prev represents the channel control vector at the previous moment; d_i_prev represents the i-th channel control value in d_prev; Δ_s is the maximum channel change rate corresponding to the life stage; R_s is the stage safety boundary corresponding to life stage s.

[0142] Based on the solution results of the channel constraint optimization model, the channel control vector of the lighting device is determined.

[0143] In step S403, based on the channel control vector, the corresponding lighting device is driven to output the light environment.

[0144] In this implementation, the target emotional light parameters are converted into lamp channel-level control values ​​by solving the device capability matrix and channel constraints. The risks of glare, flicker, sudden changes, excessive short-wave stimulation or excessive dynamic stimulation are reduced by staged safety boundaries, thereby improving the comfort and safety of long-term home use.

[0145] In one embodiment of this application, when the lighting device does not support a full color space, the system can downgrade the target light parameter vector to the closest achievable light environment according to the device's capabilities, and record the mapping error for subsequent feedback learning.

[0146] In another embodiment of this application, when the lighting device is a pixel light strip or a pixelated lighting curtain, a pixel-level target light parameter vector or a segmented target light parameter vector can be generated according to the spatial distribution weight in the target light parameter vector; when solving the pixel-level channel control value or the segmented channel control value, a spatial smoothing constraint is applied to adjacent pixels or adjacent light fixture groups so that at least one of the differences in brightness, color coordinates, color temperature, saturation, dynamic change rate or dynamic change amplitude between adjacent pixels or adjacent light fixture groups is less than the corresponding preset threshold, thereby avoiding obvious color block abrupt changes.

[0147] In one embodiment of this application, when there are multiple users in the same shared space, the method further includes performing partitioned collaborative optimization on the target light parameter vectors corresponding to the multiple users respectively.

[0148] Please see Figure 6 The diagram shown is a flowchart of multi-user partition collaborative optimization in one embodiment of this application.

[0149] like Figure 6 As shown, the partition collaborative optimization step includes the following steps S500 to S505.

[0150] In step S500, the target light parameter vector corresponding to each user and the spatial position of each user in the shared space are obtained.

[0151] This application can determine the spatial location in the shared space through one or more of the following methods: mobile terminal account, wearable device, BLE beacon, UWB positioning, smart panel operation position, voice source direction, millimeter-wave radar, camera, or user-selected method.

[0152] It should be noted that the specific process for obtaining the target light parameter vector for each user has been fully described in steps S100 to S400 above. Since this part is consistent with the technical solution of the aforementioned embodiments, it will not be repeated here.

[0153] In step S501, based on the spatial location of each user and the spatial coverage of the lighting equipment, the lighting control area in the shared space is divided into a local control area and a shared control area.

[0154] For example, the local control area may correspond to a reading corner, a children's activity area, a seating area for the elderly, or a part of the dining table; the shared control area may correspond to the main lighting area of ​​the living room, the basic lighting area of ​​the dining room, or a public passageway.

[0155] In step S502, for the local control area, the spatial correlation degree between each user and the local control area is calculated, and the dominant user is determined based on the spatial correlation degree; the target light parameter vector corresponding to the dominant user is used as the target light parameter vector of the local control area.

[0156] In step S503, for the shared control area, the collaborative weight of each user in the shared control area is calculated based on the user's corresponding spatial location, emotional confidence level, life stage, activity priority, and security priority.

[0157] In one embodiment, the safety priority of children, elderly users, or those being cared for may be higher than that of ordinary adults; users engaged in high-safety-related activities such as reading, caregiving, or nighttime travel may have a higher coordination weight than users engaged in ordinary recreational activities.

[0158] In step S504, based on the target light parameter vector corresponding to each user and the collaborative weight, an optimization model for the target light parameters of the shared control area is established.

[0159] Specifically, the target light parameter optimization model of the shared control region is expressed as follows:

[0160] ;

[0161] Where P represents the target light parameter vector, satisfying P∈∩R_i, R_i is the stage safety boundary corresponding to user i, and ∩R_i represents the intersection of the stage safety boundaries corresponding to multiple users; w_i represents the collaborative weight of user i in the shared control area; P_i is the target light parameter vector corresponding to user i; λ represents the preset smoothing weight coefficient; Ω(P) represents the regularization constraint term composed of spatial continuity, energy consumption, comfort and smooth transition constraints.

[0162] When there is a conflict between the stage security boundaries corresponding to multiple users, priority is given to satisfying at least one of the following: security boundary, explicit user instructions, protective constraints for children or elderly users, and constraints of areas strongly related to the current activity. Shared light fields and local light fields are formed through partitioned output, weighted fusion, or independent control of local lighting groups.

[0163] In step S505, the target light parameter vector of the shared control region is determined based on the solution results of the target light parameter optimization model of the shared control region.

[0164] In this implementation, when there are conflicts in the target emotion lighting parameter vectors of multiple users, the system does not simply average the needs of each user, but combines the safety boundaries of life stages, spatial location, activity priority and lighting equipment coverage to perform partitioned collaborative optimization, thereby achieving the coexistence of shared light field and local light field.

[0165] In one embodiment of this application, when multiple spatial or multiple light field nodes are running simultaneously, a spatial continuity constraint is applied to the target light parameter vector and / or illumination device channel control value between adjacent light field nodes, so that at least one of the differences in brightness, color temperature, color coordinates, saturation, dynamic change rate, dynamic change amplitude, or transition time between adjacent light field nodes is less than the corresponding preset threshold.

[0166] In one embodiment of this application, the lighting control method for different life stages described in this application further includes constrained updates of personalized sub-models based on user feedback data.

[0167] Please see Figure 7 The above is a flowchart of the personalized sub-model update in one embodiment of this application.

[0168] like Figure 7 As shown, the process of constraining the update of the personalized sub-model based on user feedback data includes the following steps S600 to S602.

[0169] In step S600, user feedback data is obtained.

[0170] The user feedback data includes explicit user feedback data, secondary lighting adjustment behavior data, scene dwell time data, dynamic effect active shutdown command data, voice feedback data, or preset non-privacy standard sensor features.

[0171] In step S601, based on the user feedback data, the user's feedback characteristics to the current output light environment are obtained, and the user's feedback error to the current output light environment is calculated according to the feedback characteristics.

[0172] The feedback error may include at least one of the following: target brightness error, target color temperature error, saturation preference error, dynamic speed error, transition time preference error, and spatial distribution error.

[0173] In step S602, based on the feedback error, the parameters of the personalized sub-model are updated, while keeping the basic mapping model unchanged during the update process.

[0174] In one embodiment of this application, the update of the user personalization sub-model can be represented as:

[0175] θ_u(t+1)=Proj_Rs(θ_u(t)+α·e_u(t)·Φ(E_u(t),Ctx_u(t)));

[0176] Where θ_u represents the personalized parameters corresponding to user u; α represents the learning rate; e_u(t) represents the feedback error corresponding to user u; Φ represents the feature function; E_u(t) represents the emotional state vector corresponding to user u; Ctx_u(t) represents the scene context information corresponding to user u; Proj_Rs represents the projection operator constructed based on the stage safety boundary R_s corresponding to life stage s, which is used to restrict the updated user personalized parameters within a feasible range without exceeding the stage safety boundary R_s.

[0177] In this implementation, a feedback learning mechanism is used to implement constrained updates to the personalized sub-model, ensuring that the lighting strategy continuously iterates with the user's lifecycle state, effectively solving the problem of control strategy lag and rigidity caused by traditional fixed stage labels.

[0178] It should be noted that the scope of protection of the lighting control method for different life stages described in the embodiments of this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, replacing, splitting, or combining steps based on the principles of this application should be included within the scope of protection of this application.

[0179] The present application will be further described below with reference to specific application embodiments. It should be understood that the following embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the scope of protection of the present application.

[0180] In a child's bedtime lighting scenario, the system identifies the user as a child, their circadian rhythm indicates they are within 30 minutes of bedtime, and historical feedback shows the user has repeatedly turned off high-saturation dynamic lighting effects before sleep. Current emotional state parameters indicate the user is excited, with high emotional intensity, but the emotion recognition confidence level meets the preset threshold. The system selects the emotion weighting model corresponding to the child's stage and, based on the safety boundaries of the child's stage, reduces the proportion of short-wavelength energy, color saturation, and dynamic change amplitude. The target color temperature is gradually adjusted to the 2700K to 3000K warm white light range, and the target illuminance is controlled within a soft lighting range for a relatively long duration.

[0181] In a family shared living room scenario, children need to relax before bed, middle-aged users need to read, and young adults need to enjoy audio-visual entertainment. The system generates target light parameter vectors for each user and divides the space into local control areas and shared control areas based on user location, life stage safety priority, activity priority, and lighting equipment coverage. For the sofa area where children are located, the system uses a low-stimulation, warm-colored, and low-dynamic local lighting environment; for the reading area of ​​middle-aged users, the system provides stable, moderate illuminance, and low-glare local lighting; for the shared main lighting area, the system solves for a neutral and comfortable target light parameter vector within the intersection of the safety boundaries of multiple user stages. This creates a lighting effect where shared and local light fields coexist within the same shared space.

[0182] Please see Figure 8 The diagram shows a schematic representation of a lighting control system for different life stages according to an embodiment of this application.

[0183] like Figure 8 As shown, this application provides a lighting control system for different life stages, including:

[0184] The stage feature construction module is used to acquire user lifecycle data and construct lifecycle feature vectors based on the lifecycle data; the lifecycle feature vectors include age features, circadian rhythm features, visual sensitivity features, activity scene features, family role features, and historical feedback features.

[0185] The model determination module is used to determine the user's life stage based on the life cycle feature vector and select an emotion weight model that matches the life stage. The emotion weight model includes a basic mapping model and a personalized sub-model. The basic mapping model is used to describe the basic mapping relationship from the emotion state vector to the light parameter vector under the life stage. The personalized sub-model is used to make personalized corrections to the basic mapping relationship based on user feedback data.

[0186] The parameter generation module is used to obtain the user's emotional state parameters and construct the emotional state vector based on the emotional state parameters; the emotional state vector is input into the emotional weight model, and the emotional weight model combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector.

[0187] The output control module is used to control the lighting equipment to output a light environment that matches the user's life stage and emotional state based on the target light parameter vector.

[0188] It should be noted that the structure and principle of each module of the lighting control system described in this embodiment correspond one-to-one with the steps in the lighting control methods for different life stages described above, and therefore will not be repeated here. Each module can be implemented in software, hardware, firmware, or a combination thereof, or it can be integrated into a home gateway, smart lighting controller, server, mobile terminal, or the lighting equipment itself.

[0189] Please see Figure 9 The image shown is a schematic diagram of the structure of a lighting system according to an embodiment of this application.

[0190] like Figure 9 As shown, the lighting system includes one or more lighting devices and a lighting control system for different life stages; wherein the lighting control system for different life stages is connected to the lighting devices and is used to execute the lighting control method for different life stages described in this application.

[0191] Please see Figure 10 The image shown is a schematic diagram of the structure of a terminal according to an embodiment of this application.

[0192] like Figure 10 As shown, this application provides a terminal, including:

[0193] A memory for storing computer programs.

[0194] A processor, the processor being configured to execute a computer program stored in the memory, so as to cause the terminal to perform any of the methods described above.

[0195] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0196] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0197] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this 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.

[0198] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0199] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the methods described in any of the above embodiments. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0200] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0201] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A lighting control method for different life stages, characterized in that, include: Acquire user lifecycle data and construct lifecycle feature vectors based on the lifecycle data; the lifecycle data represents the steady-state characteristics of a user at a specific life stage, and the lifecycle feature vector is a structured representation formed by vectorizing the lifecycle data; Based on the life cycle feature vector, the user's life stage is determined, and an emotion weight model matching the life stage is selected. The emotion weight model includes a basic mapping model and a personalized sub-model, wherein the basic mapping model is used to describe the basic mapping relationship from the emotion state vector to the light parameter vector under the life stage. The personalized sub-model is used to make personalized corrections to the basic mapping relationship based on user feedback data. The user's emotional state parameters are obtained, and the emotional state vector is constructed based on the emotional state parameters. The emotional state vector is input into the emotional weight model, and the emotional weight model combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector. Based on the target light parameter vector, control the lighting equipment to output a light environment that matches the user's life stage and emotional state; When there are multiple users in the same shared space, the method also includes partitioned collaborative optimization of the target light parameter vectors corresponding to each user. The partition collaborative optimization steps include: Obtain the target light parameter vector for each user, as well as the spatial position of each user in the shared space; Based on the spatial location of each user and the spatial coverage of the lighting equipment, the lighting control area in the shared space is divided into a local control area and a shared control area; For the local control area, the spatial correlation degree between each user and the local control area is calculated, and the dominant user is determined based on the spatial correlation degree; the target light parameter vector corresponding to the dominant user is used as the target light parameter vector of the local control area. For the shared control area, the collaborative weight of each user in the shared control area is calculated based on the user's corresponding spatial location, emotional confidence, life stage, activity priority, and security priority. Based on the target light parameter vectors corresponding to each user and the collaborative weights, an optimization model for the target light parameters of the shared control region is established; the optimization model for the target light parameters of the shared control region is expressed as follows: ； Where P represents the target light parameter vector, satisfying P∈∩R_i, R_i is the stage safety boundary corresponding to user i, and ∩R_i represents the intersection of the stage safety boundaries corresponding to multiple users; w_i represents the collaborative weight of user i in the shared control area; P_i is the target light parameter vector corresponding to user i; λ represents the preset smoothing weight coefficient; Ω(P) represents the regularization constraint term composed of spatial continuity, energy consumption, comfort and smooth transition constraints; Based on the solution results of the target light parameter optimization model of the shared control region, the target light parameter vector of the shared control region is determined.

2. The method according to claim 1, characterized in that, Based on the target light parameter vector, controlling the lighting equipment to output a light environment that matches the user's life stage and emotional state includes: The capability information of the lighting device is obtained, and a lighting device capability matrix is ​​constructed based on the capability information of the lighting device. The lighting device capability matrix is ​​a data structure that parametrically expresses the controllable output capability of the lighting device. The controllable output capability includes luminous flux range, color temperature range, color gamut range, channel structure, dimming depth, spatial coverage area, minimum response time, and maximum rate of change. Based on the lighting equipment capability matrix, under the condition of satisfying the preset stage safety boundary and channel change rate constraints, the target light parameter vector is solved for channel constraints to obtain the channel control vector of the lighting equipment. Based on the channel control vector, the corresponding lighting device is driven to output the light environment.

3. The method according to claim 2, characterized in that, Based on the lighting equipment capability matrix, and under the conditions of satisfying the preset stage safety boundary and channel change rate constraints, the target light parameter vector is solved for channel constraints to obtain the channel control vector of the lighting equipment, including: The first optimization objective is to minimize the deviation between the actual output optical parameter vector and the target optical parameter vector, and the second optimization objective is to minimize the change between the current channel control vector and the previous channel control vector. A channel constraint optimization model is constructed as follows: ； And satisfy: 0≤d_i≤1, |d_i-d_i_prev|≤Δ_s, P∈R_s; Where d is the channel control vector at the current moment, d=[d_1,d_2,...,d_i,...,d_n], n is the total number of channels of the lighting equipment, d_i represents the i-th channel control value in d; G_d represents the lighting equipment capability matrix; P represents the target light parameter vector; λ is the preset smoothing weight coefficient; d_prev represents the channel control vector at the previous moment; d_i_prev represents the i-th channel control value in d_prev; Δ_s is the maximum channel change rate corresponding to the life stage; R_s is the stage safety boundary corresponding to life stage s; Based on the solution results of the channel constraint optimization model, the channel control vector of the lighting device is determined.

4. The method according to claim 1, characterized in that, Based on the lifecycle feature vector, the user's life stage is determined, and an emotion weighting model matching the life stage is selected, including: The life cycle feature vector is input into a preset life stage discriminator to obtain the stage probability of the user belonging to multiple preset life stages. When the maximum probability in the stage probability is greater than or equal to a preset threshold, the life stage corresponding to the maximum probability is determined as the user's life stage, and an emotion weight model corresponding to the user's life stage is selected. When the maximum probability among the stage probabilities is less than a preset threshold, two or more candidate life stages are determined from the multiple preset life stages, and the emotion weight models corresponding to the two or more candidate life stages are fused to generate an emotion weight model adapted to users in the transition stage.

5. The method according to claim 1, characterized in that, The basic mapping model includes a stage initial light parameter vector, an emotion weight matrix, a light parameter response matrix, a stage basic bias, and a stage safety boundary. The emotion state vector is input into the emotion weight model, which, combined with scene context information, performs weighted mapping and constraint processing on the emotion state vector to generate the target light parameter vector, including: Obtain the scene context information; the scene context information includes spatial semantic information, lighting temporal rhythm information, user activity information, and lighting device capability information; The emotional state vector is weighted based on the emotional weight matrix to obtain weighted emotional features. The weighted emotion features and the scene context information are input into a preset mapping function for context fusion mapping to obtain the emotion lighting adjustment amount; Based on the light parameter response matrix, and combined with the initial light parameter vector of the stage and the basic bias of the stage, the emotion lighting modulation amount is responded to and mapped to obtain the candidate light parameter vector. The candidate optical parameter vector is constrained and pruned based on the stage safety boundary to generate the target optical parameter vector.

6. The method according to claim 1, characterized in that, Also includes: Acquire user feedback data; the user feedback data includes explicit user feedback data, secondary lighting adjustment behavior data, scene dwell time data, dynamic effect active turn-off command data, voice feedback data, or preset non-privacy standard sensor features; Based on the user feedback data, the user's feedback characteristics to the current output light environment are obtained, and the user's feedback error to the current output light environment is calculated based on the feedback characteristics. Based on the feedback error, the parameters of the personalized sub-model are updated, while keeping the basic mapping model unchanged during the update process.

7. A lighting control system for different life stages, characterized in that, include: The stage feature construction module is used to acquire user lifecycle data and construct lifecycle feature vectors based on the lifecycle data; the lifecycle data represents the steady-state characteristics of a user at a specific life stage, and the lifecycle feature vector is a structured representation formed after vectorizing the lifecycle data. The model determination module is used to determine the user's life stage based on the life cycle feature vector and select an emotion weight model that matches the life stage; the emotion weight model includes a basic mapping model and a personalized sub-model, wherein the basic mapping model is used to describe the basic mapping relationship from the emotion state vector to the light parameter vector under the life stage; The personalized sub-model is used to make personalized corrections to the basic mapping relationship based on user feedback data. The parameter generation module is used to obtain the user's emotional state parameters and construct the emotional state vector based on the emotional state parameters; the emotional state vector is input into the emotional weight model, and the emotional weight model combines the scene context information to perform weighted mapping and constraint processing on the emotional state vector to generate the target light parameter vector; The output control module is used to control the lighting equipment to output a light environment that matches the user's life stage and emotional state based on the target light parameter vector. When there are multiple users in the same shared space, the method also includes partitioned collaborative optimization of the target light parameter vectors corresponding to each user. The partition collaborative optimization steps include: Obtain the target light parameter vector for each user, as well as the spatial position of each user in the shared space; Based on the spatial location of each user and the spatial coverage of the lighting equipment, the lighting control area in the shared space is divided into a local control area and a shared control area; For the local control area, the spatial correlation degree between each user and the local control area is calculated, and the dominant user is determined based on the spatial correlation degree; the target light parameter vector corresponding to the dominant user is used as the target light parameter vector of the local control area. For the shared control area, the collaborative weight of each user in the shared control area is calculated based on the user's corresponding spatial location, emotional confidence, life stage, activity priority, and security priority. Based on the target light parameter vectors corresponding to each user and the collaborative weights, an optimization model for the target light parameters of the shared control region is established; the optimization model for the target light parameters of the shared control region is expressed as follows: ； Where P represents the target light parameter vector, satisfying P∈∩R_i, R_i is the stage safety boundary corresponding to user i, and ∩R_i represents the intersection of stage safety boundaries corresponding to multiple users; w_i represents the collaborative weight of user i in the shared control area; P_i is the target light parameter vector corresponding to user i; λ represents the preset smoothing weight coefficient; Ω(P) represents the regularization constraint term composed of spatial continuity, energy consumption, comfort and smooth transition constraints; Based on the solution results of the target light parameter optimization model of the shared control region, the target light parameter vector of the shared control region is determined.

8. A terminal, characterized in that, include: The memory is used to store computer programs; A processor for executing a computer program stored in the memory to cause the terminal to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images