Lamp group control method and system and computer storage medium

Abstract

The invention provides a lamp set control method and system and a computer storage medium, a lamp set is provided with a center lamp and peripheral lamps, and the lamp set control method comprises the following steps: using a first model to respond to a user instruction, generating a scene image, performing color analysis on the image to generate a color pattern according to the scene image, color parameters of the scene image are extracted, and a first control instruction corresponding to the center lamp is generated according to a color pattern; acquiring lamp information of the lamp group, wherein the lamp information comprises a lamp type, a lamp layout and a lamp attribute; the color pattern, the color parameters and the lamp information are input into a second model, a second control instruction of the peripheral lamps is output from the second model, the second control instruction comprises a color control instruction matched with the local color of the peripheral lamps adjacent to the center lamp, and the lamp set is controlled through the first control instruction and the second control instruction.

Description

Technical Field

[0001] This application relates primarily to the field of lighting fixtures, and more particularly to a method, system, and computer storage medium for controlling lighting fixture groups. Background Technology

[0002] Lighting control systems are an essential component of smart homes. Compared to traditional lighting controls that only offer basic on / off control, dimming, and color adjustment, smart home lighting control systems offer greater interactivity and emphasize the creation of a unified scene by multiple light fixtures working together. With the evolution of large language models, this technology has also been applied to smart home lighting control systems.

[0003] While current smart home lighting control systems based on large language models can generate IoT (Internet of Things) commands for lighting fixtures end-to-end from natural language, several key limitations remain. First, directly mapping text to lighting parameters for multiple fixtures makes it difficult to guarantee color matching, visual rationality, and aesthetic consistency across the various fixtures, especially when dealing with themes featuring many colors, which can easily lead to color clashes or monotonous effects. Second, the generation of lighting parameters lacks spatial awareness; typically, different fixtures can only output uniform parameters, thus limiting the spatial accuracy and scene representation of lighting control. Summary of the Invention

[0004] Based on the above problems, this application proposes a lighting group control method, system, and computer storage medium to improve the visual rationality and aesthetic effect of the lighting group.

[0005] In a first aspect, this application proposes a method for controlling a lighting group, the lighting group having a central luminaire and peripheral luminaires. The method includes the following steps: using a first model to respond to a user command and generate a scene image; acquiring luminaire information of the lighting group, the luminaire information including luminaire type, luminaire layout, and luminaire attributes; performing color analysis on the image to generate a color pattern based on the scene image, and extracting color parameters from the scene image; generating a first control command corresponding to the central luminaire based on the color pattern; inputting the user command, scene image, color parameters, and luminaire information into a second model, and outputting a second control command for the peripheral luminaires from the second model, the second control command including a color control command that adapts to the local color of the peripheral luminaires adjacent to the central luminaire; and controlling the lighting group using the first control command and the second control command.

[0006] In some embodiments, the brightness and color temperature parameters of the scene image are extracted. These parameters are then input into the second model, causing the generated second control command to include both a brightness control command and a color temperature control command.

[0007] In some embodiments, the luminaire attributes include whether the color is adjustable, whether the brightness is adjustable, and whether the color temperature is adjustable.

[0008] In some embodiments, the luminaire type includes center luminaires, main lights, light strips, and spotlights.

[0009] In some embodiments, the step of obtaining the lighting layout includes: receiving the positions of the peripheral lighting fixtures relative to the central lighting fixture.

[0010] In some embodiments, the color parameters include a primary color, a secondary color, and an accent color. The primary color is the color with a coverage ratio in the scene image in a first interval, the secondary color is the color with a coverage ratio in the scene image in a second interval, and the accent color is the color with a coverage ratio in the scene image in a third interval. The coverage ratios of the first interval, the second interval, and the third interval decrease sequentially.

[0011] In some embodiments, the method further includes inputting the user instruction into the second model, and the second model also outputting a scene name and scene description.

[0012] In some embodiments, the scene image has a first resolution, and the color pattern has a second resolution, the second resolution being lower than the first resolution.

[0013] Secondly, this application also proposes a lighting group control system, the lighting group having a central lighting fixture and peripheral lighting fixtures, the system comprising: a memory for storing instructions executable by a processor; and a processor for executing the instructions to implement the method described in the first aspect.

[0014] Thirdly, this application also proposes a computer storage medium storing computer program code that, when executed by a processor, implements the method described in the first aspect.

[0015] Fourthly, this application also proposes a computer program product, including computer program code, which, when executed by one or more processors, implements the steps of the method described in the first aspect.

[0016] Compared with existing technologies, this application uses a scene image generated by a first model and its extracted color parameters. On the one hand, these parameters are mapped to the central luminaire to accurately reproduce the main color composition of the scene image. On the other hand, the scene image and color parameters are input into a second model, which generates control commands for the surrounding luminaires that are color-coordinated with the central luminaire. By using the scene image and its color features as a common intermediate representation, this ensures that the central luminaire and the surrounding luminaires not only conform to the laws of visual perception in color presentation, but also maintain the unity and coherence of the scene's semantics as a whole. Attached Figure Description

[0017] The accompanying drawings are included to provide a further understanding of this application; they are incorporated into and constitute a part of this application. The drawings illustrate embodiments of this application and, together with this specification, serve to explain the principles of this application. In the drawings: Figure 1 This is a scene diagram of a lighting assembly provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a lighting group control method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the visual saliency-weighted K-means++ clustering algorithm provided in an embodiment of this application; Figure 4 This is a device block diagram of a lamp group control method provided in an embodiment of this application; Figure 5 This is a rendering of a lighting group control method provided in an embodiment of this application; Figure 6 This is a rendering of a lighting group control method provided in another embodiment of this application.

[0018] Reference numerals: Center light fixture 110, Main light 120, Light strip 130, Spotlight 140, Intelligent lighting control panel 150, System 400, Client 410, Communication bus 411, Processor 412, Read-only memory 413, Random access memory 414, Communication port 415, Hard disk 416, First model 420, ASR module 430, Device-area mapping module 440, Image color analysis module 450, IoT instruction generation module 460, Second model 470, Network 480, Cloud server 490, Touch display component 491, Local processor 492, Communication component 493, Memory 494, Audio I / O 496, Power supply 495. Detailed Implementation

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this application. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0020] As indicated in this application, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0021] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0022] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is merely for the purpose of distinguishing the corresponding components. Unless otherwise stated, these terms have no special meaning and therefore should not be construed as limiting the scope of protection of this application. In addition, although the terminology used in this application is selected from commonly known and used terms, some terms mentioned in this application's specification may have been chosen by the applicant according to his or her judgment, and their detailed meanings are explained in the relevant sections of this description. Moreover, this application should be understood not only through the actual terms used, but also through the meaning implied by each term.

[0023] Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, various steps can be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more steps may be removed from these processes.

[0024] The lighting control method of this application will be described below through specific embodiments.

[0025] refer to Figure 1The lighting fixture group includes a central light fixture 110 and peripheral lights. In some embodiments, the peripheral lights further include a main light 120, a light strip 130, and spotlights 140. Therefore, the lighting fixture types include a central light fixture 110, a main light 120, a light strip 130, and spotlights 140. Peripheral lights are not limited to the types described above and may also include other types of lights, such as floor lamps. The central light fixture 110 occupies the center of the scene, with the main light 120, light strip 130, and spotlights 140 surrounding it. For example, the main light 120 is located on the ceiling, the spotlights 140 are located along the upper edge of the central light fixture 110, and the light strip 130 is located along the lower edge of the central light fixture. It is understood that the relative positions of the central light fixture 110, the main light 120, the light strip 130, and the spotlights 140 are not limited to the positions shown in the figure.

[0026] In some embodiments, the central luminaire 110 is a flexible film light box. The flexible film light box contains multiple light strips, each with multiple independently controllable bulbs arranged on it. A generated low-resolution color pattern can be mapped onto the light strips of the flexible film light box via a first control command. For example, the color pattern has a resolution of 15×15 pixels, and the physical layout of the light strips and bulbs in the flexible film light box is configured as a 15x15 matrix structure. When an IoT control command is received, the flexible film light box maps the color information of each pixel in the color pattern to the corresponding bulb at the row and column position, causing it to display the corresponding color. This allows the visual effect of the low-resolution color pattern to be fully reproduced on the flexible film light box.

[0027] In one embodiment, an intelligent lighting control panel 150 is configured to receive various commands input by the user. In another embodiment, a control system is configured to control the operation of the lighting group.

[0028] refer to Figure 2 and Figure 4 The lighting group control method proposed in this application includes the following steps: Step S210: Use the first model 420 to respond to user commands and generate scene images.

[0029] In this step, the user command can be a voice signal, and the first model 420 can be a large-scale artificial intelligence (AI) model. This AI model has the function of generating scene images based on the standardized text converted from the voice signal. The generated scene images are high-fidelity images with fewer colors and simpler patterns. For example, when the user gives the voice command "generate an aurora scene," an aurora scene image is generated in this step. Other examples of high-fidelity scene images include sunset scene images and star scene images.

[0030] In some embodiments, the Automatic Speech Recognition (ASR) module 430 can convert the speech signal received from the user into corresponding standardized text. Specifically, the ASR module 430 first preprocesses the speech signal, including noise reduction and frame segmentation, then extracts acoustic feature parameters, and subsequently decodes it using a pre-trained acoustic model and language model to convert the speech sequence into a text sequence. Through context correction and normalization, it finally outputs standardized text with a unified format and conforming to grammatical rules. This standardized text can be directly input into a large AI model to generate corresponding scene images. The efficient and accurate speech-to-text conversion achieved by the ASR module 430, and the generated standardized text, eliminates ambiguity and redundancy in spoken expression, providing clear and standardized input for subsequent image generation by the large AI model, thus improving the accuracy and consistency of image generation.

[0031] In some embodiments, the AI ​​that receives the standardized text generated through transformation to generate scene images can be advanced models such as DALL.E3, Stable Diffusion, or Midjourney, which possess text-to-image generation capabilities. Through the multimodal generalization capabilities of large AI models, no preset scene is required, and any natural language input is supported.

[0032] In some embodiments, to ensure that the generated scene images possess high-fidelity visual features with fewer color variations and simpler patterns, the selected large AI model needs to be fine-tuned based on a preset stylized dataset. This allows the model to retain its general generation capabilities while enhancing its understanding and execution of abstract constraints such as color simplification and pattern simplification, thereby enabling it to stably output scene images with a consistent style and meeting requirements based on the input standardized text.

[0033] Step S220: Obtain the lighting information of the lighting group, including lighting type, lighting layout and lighting attributes.

[0034] In some embodiments, reference Figure 1 The steps for obtaining the lighting layout include receiving the positions of the surrounding lights relative to the central light fixture 110. The lighting layout refers to the specific orientation of the central light fixture 110 and the surrounding lights within the user's space, as well as the positional relationship of the surrounding lights relative to the central light fixture 110. For example, the surrounding lights can be arranged around the central light fixture 110. The lighting layout is input by the user on the intelligent lighting control panel 150 based on the actual conditions within the space.

[0035] In some embodiments, reference Figure 1 , Figure 2 and Figure 4A device-area mapping module 440 is established to process the layout information of the lighting fixtures input by the user. Specifically, this module maps the top, bottom, left, and right orientations of the scene image generated in step S210 on a two-dimensional plane to the actual installation orientations of the surrounding lighting fixtures. Low-resolution color patterns are mapped to the central lighting fixture 110. If the main light 120 is located above the central lighting fixture 110, the device-area mapping module 440 allocates the color information of the upper area of ​​the scene image to the main light 120, making it represent the main hue of the upper half of the image. Similarly, if the light strip 130 is located below the central lighting fixture 110, the color information of the lower area of ​​the scene image will be mapped to the light strip 130, thereby forming a corresponding color light effect below. Through this orientation matching, spatial perception synchronization from image space to lighting fixture layout is achieved. By establishing a precise mapping between image orientation and lighting fixture orientation, the final light effect is consistent with the original image content in terms of spatial distribution, forming a layered and structured lighting scene, enhancing the realism and immersion of the visual experience. This modular mapping mechanism supports the layout of lighting fixtures of different sizes and shapes, and can automatically complete the area allocation by having the user input the positional relationship of the lighting fixtures.

[0036] In some embodiments, luminaire attributes include whether the color is adjustable, whether the brightness is adjustable, and whether the color temperature is adjustable. Adjustable color refers to whether the luminaire supports adjustment of hue and saturation, such as supporting full-color RGB, dual-color-temperature white light, or fixed monochromatic light; adjustable brightness refers to whether the luminaire supports continuous or stepped adjustment of brightness levels, such as through PWM dimming or intelligent dimming interfaces; adjustable color temperature refers to whether, for white light luminaires, it supports continuous or segmented adjustment of color temperature within a range. These attributes can be configured through a user interface or obtained from luminaire identification information, thereby enabling control of various types of luminaires.

[0037] Step S230: Perform color analysis on the image to generate a color pattern based on the scene image and extract the color parameters of the scene image.

[0038] In this step, the generated high-fidelity scene image can be color analyzed by the image color analysis module 450. The result of the color analysis includes the color parameters of the scene image. The image color analysis module 450 will also reduce the generated high-fidelity scene image to a low-resolution color pattern.

[0039] In some embodiments, the scene image has a first resolution, and the color pattern has a second resolution, which is lower than the first resolution. The upper limit of the second resolution is 30×30 pixels. By controlling the resolution of the color pattern at this lower level, the color pattern forms large color blocks when displayed, thus presenting a simple and high-contrast visual style. The low-resolution, large-color-block image characteristics and the physical structure of the central light fixture 110, such as a flexible film light box, such as a matrix-arranged LED light strip, can be better coordinated. It should be noted that in the embodiments of this application, the upper limit of the second resolution is set to 30×30 pixels, mainly based on the physical environment constraints in actual application scenarios and the physical structure limitations of the flexible film light box, such as the size of the light box unit and the density of LED beads, which is a preferred range. However, theoretically, in the absence of the above physical limitations, the upper limit of the second resolution can be extended to a higher value, such as 2000×2000 pixels. Therefore, all embodiments with a second resolution less than or equal to 2000×2000 pixels should fall within the protection scope of the claims of this application.

[0040] In some embodiments, color parameters include a primary color, a secondary color, and an accent color. The primary color is the color with a coverage ratio in the first interval of the scene image, and it typically constitutes the overall tone and background of the image. The secondary color is the color with a coverage ratio in the second interval of the scene image. The secondary color can harmonize or contrast with the primary color, shaping the basic structure and hierarchy of the image. The accent color is the color with a coverage ratio in the third interval of the scene image. Accent colors are typically distributed in small areas as dots or lines, serving to highlight the visual focus and enrich details. The first, second, and third intervals decrease in size sequentially. By extracting the primary, secondary, and accent colors, the color design of the color pattern can be accurately presented when mapping the color pattern onto the flexible film lightbox.

[0041] In some embodiments, the image color analysis module 450 includes a built-in color analysis algorithm for extracting primary, secondary, and accent colors, and analyzing the brightness and color temperature of each region. The image color analysis module 450 algorithm includes a visually saliency-weighted K-means++ clustering algorithm. (Reference) Figure 3 The K-means++ clustering algorithm includes the following steps: Step S310: Preprocess the generated scene image.

[0042] In this step, the scene image is decomposed into a multi-scale Gaussian pyramid to simulate visual perception at different viewing distances. Then, color, brightness, and orientation—three features closely related to human vision—are calculated. The visual salience of each location is quantified through center-periphery contrast calculation. Finally, multi-scale, multi-feature information is integrated to generate a normalized attention weight distribution map, i.e., a saliency probability map S, where pixels... The weight is , This represents the weight of the p-th pixel after the pixel has been flattened.

[0043] Step S320: Perform color space conversion on the scene image.

[0044] In this step, the original RGB color is decomposed and converted to the Oklab color space.

[0045] Step S330: Perform weighted clustering algorithm calculation.

[0046] In this step, the weighted K-means++ algorithm is used to extract the primary color, secondary color, and accent color, where the objective function is: (1) In formula (1), Let be the saliency weight of the p-th pixel. For the first The center of a color cluster. It is the first The set of all pixels in a color cluster. The number of color clusters, The value is 3, which represents the primary color, secondary color, and accent color.

[0047] Step S340: Define the primary color, secondary color, and accent color.

[0048] In this step, the area weights of the clustering results are used. With color saturation When sorting, area weight is considered first. The main color is The largest color cluster with the smallest color difference distance. Secondary colors. Secondly, there are color clusters that typically form an analogy or contrast with the main color, and accent colors. Although small, it is visually significant. Extremely high, and the color block with the greatest European distance from the primary or secondary color in the Oklab space, and Relatively high. Then, based on area weighting... Calculate the area proportions of the primary color, secondary color, and accent color in the scene image. The number of primary, secondary, and accent colors is 1 each.

[0049] By using the visual saliency-weighted K-means++ clustering algorithm, the generated weight map accurately quantifies the visual importance of different regions, ensuring that subsequent color clustering results are more in line with human observation habits. Furthermore, based on multi-dimensional sorting and definition rules such as area weight and saturation, the system can automatically, efficiently, and stably separate color sets from scene images—namely, primary colors, secondary colors, accent colors, and the area proportion of each color—providing more accurate color information for the subsequent color rendering of lighting fixtures.

[0050] In some embodiments, the image color analysis module 450 is also used to extract the brightness parameters and color temperature parameters of the scene image. Specifically, the brightness parameters can be obtained by converting the original RGB color to the Oklab color space, and the color temperature parameters can be obtained using a color temperature extraction algorithm, such as a white balance algorithm.

[0051] Continue to refer to Figure 1 , Figure 2 and Figure 4 Step S240: Generate a first control command corresponding to the central luminaire based on the color pattern.

[0052] In this step, the color pattern extracted from the scene image is used to generate the first control command for the central luminaire 110, and the generated color pattern is mapped onto the central luminaire 110.

[0053] In some embodiments, the IoT instruction generation module 460 generates a first control instruction for the control center lighting fixture 110. The IoT instruction generation module 460 maps color parameters, brightness parameters, and color temperature parameters obtained through scene image analysis to adjustable parameter values ​​for specific lighting fixtures. Based on the physical layout of the flexible light box, such as the number of light strips, bulb arrangement, and addressing, a first control instruction adapted to the flexible light box is generated. Specifically, this module assigns each pixel of the low-resolution color pattern to the bulb addressing on a specific light strip according to a preset mapping rule. Then, referring to the area ratio of the primary color, secondary color, and accent color in the scene image, the distribution ratio and arrangement order of different colored bulbs in each light strip are set respectively, thereby achieving a clear color hierarchy. Further, the module uses the extracted brightness and color temperature parameters to adjust the overall or zoned brightness and white light color temperature of each bulb, ultimately generating a set of control instructions containing color, brightness, and color temperature control information, conforming to the light box communication protocol, to drive the flexible light box to reproduce a lighting effect matching the colors of the scene image.

[0054] Step S250: Input user instructions, scene images, color parameters and lighting information into the second model 470, and output the second control instructions for the peripheral lighting from the second model 470. The second control instructions include color control instructions that adapt the local color of the peripheral lighting adjacent to the central lighting.

[0055] In this step, the second model 470 can be a large AI model, which is a multimodal model capable of receiving and outputting multimodal information, such as receiving image information and natural language information and outputting natural language. For example, the large AI model is a commercially available large model such as the Qwen3 model. The output of the second model 470 includes color control instructions for the surrounding lights, so that the colors presented by the surrounding lights match the low-pixel color pattern presented by the central light 110, forming a harmonious lighting atmosphere.

[0056] In some embodiments, the instruction information input to the second model 470 includes user instructions input by the user into the first model 420 and processed into standard text by the ASR module 430, a scene image generated by the first model 420, color parameters extracted from the scene image, and information about surrounding lighting fixtures. Specifically, the color parameters extracted from the scene image, including primary color, secondary color, accent color, brightness, and color temperature, are input to the second model 470 to provide accurate color and optical constraints, thereby effectively mitigating potential generation illusions. Specifically, the color presented by the central lighting fixture 110 is directly derived from the color parameters extracted from the scene image, while the color control instructions for the surrounding lighting fixtures are generated by the second model 470. By inputting the aforementioned obtained color parameters into the second model 470, it can output color control instructions for the surrounding lighting fixtures that coordinate with the color of the central lighting fixture 110, ensuring color consistency between the two sets of lighting fixtures in the final presentation and avoiding color deviations or visual conflicts caused by free generation by the model. Furthermore, this ensures that the second model 470, while focusing on the details of the scene image, does not neglect the color scheme of the scene image.

[0057] In some embodiments, the instruction information input to the second model 470 further includes user-specified spatial area information for generating lights, spatial position mapping information of surrounding lights and scene images, and built-in lighting designer dimming preferences. Wherein, reference Figure 1 Users can select different target spatial areas, such as the living room, bedroom, or specific functional zones, through the intelligent lighting control panel 150, and input the information of all surrounding lighting fixtures in that area into the second model 470. In this way, users can independently generate and present adapted lighting effects for different spatial areas, thereby realizing the applicability and personalized control capability of the lighting control method in the actual spatial environment.

[0058] In some embodiments, the output information of the second model 470 further includes a scene name and scene description. Specifically, the scene name and scene description describing the scene image are generated based on the user instructions input to the second model and the scene image. The scene description and the color control instructions for the surrounding lighting are output simultaneously by the second model, so the description and the lighting effects of the surrounding lighting are simultaneous and their coordination is more accurate and harmonious, resulting in a high degree of alignment between the description, scene name, and actual lighting effect.

[0059] In some embodiments, to further optimize the color control effect of surrounding lights, the second model 470 needs to be fine-tuned according to the lighting designer's dimming preferences. Specifically, a model can be established based on specific lighting aesthetic evaluation criteria, and a reinforcement learning framework can be used to iteratively optimize the second model 470. This ensures that its output color commands not only coordinate with the central light fixture 110 but also actively conform to specific aesthetic styles, such as warm, calm, dynamic, or minimalist. This training process can be completed offline, ensuring that the fine-tuned model maintains high real-time performance and stability while improving aesthetic expressiveness.

[0060] Step S260: Control the lighting group using the first control command and the second control command.

[0061] In this step, the first control command output by the first model 420 and the second control command generated by the second model 470 control the central luminaire 110 and the peripheral luminaires, respectively. Specifically, the scene image generated by the first model 420 and the color parameters extracted from the scene image are mapped to the central luminaire 110 to accurately reproduce the main color composition in the scene image. Simultaneously, the scene image and color parameters are input to the second model 470, which generates control commands for the peripheral luminaires that are color-coordinated with the central luminaire 110. By using the scene image and its color features as a common intermediate representation, it is ensured that the central luminaire 110 and the peripheral luminaires not only conform to the laws of visual perception in color presentation but also maintain the unity and coherence of the scene's semantics as a whole.

[0062] In some embodiments, the color control command output by the second model 470 is input into the IoT command generation module 460 to generate IoT control commands for the surrounding lights. The IoT commands control the color parameters of the surrounding lights to present harmonious lighting colors that complement the central light fixture 110.

[0063] refer to Figure 2 and Figure 4 The above-described lighting control method will now be described using a specific embodiment.

[0064] The user inputs the command: "Give me an aurora feel." The first model 420 generates a high-fidelity scene image with an aurora style, including a night sky and flowing light streaks, based on the user's command. The image color analysis module 450 analyzes the color parameters of the generated scene image, including the primary color, secondary color, accent color, and their area proportions, as well as color temperature and brightness. Specifically, the primary color is ice blue (RGB 0,180,255), occupying 50% of the area; the secondary color is emerald green (RGB 0,200,150), occupying 20% ​​of the area; and the accent color is violet (RGB 180,30,255), occupying 10% of the area. The overall color temperature is cool (5000–6500K), and the brightness is low to medium. Furthermore, the image color analysis module 450 reduces the resolution of the scene image, generating a color pattern with a resolution of 15×15 pixels.

[0065] The color pattern, extracted color parameters, and lighting information are used by the IoT command generation module 460 to generate IoT lighting control commands to control the central lighting fixture 110, i.e., the flexible film lightbox, to display a resolution of 15. 15 colors and patterns.

[0066] The user-inputted commands, aurora-style scene images, color parameters, and surrounding lighting information are input into the second model 470. The second model 470 outputs color control commands for the surrounding lighting, which are then used by the IoT command generation module 460 to generate IoT commands. This causes the surrounding lighting to present a lighting atmosphere that complements the aurora-style scene image, while simultaneously generating the narration "Cool emerald green, ice blue, and violet intertwine, simulating the mysterious light and shadow of the aurora flowing in the night sky..." and the scene name "Aurora Fantasy".

[0067] Figure 4 This is a block diagram of a lighting control method, system, and computer storage medium according to an embodiment of this application. (Reference) Figure 1 and Figure 4 The system 400 consists of a client 490 and a cloud server 410, which communicate via a network 480. The lighting control method proposed in this application can be deployed on the cloud server 410. The client 490 includes an intelligent lighting control panel 150, which receives user operations and uploads them to the cloud server 410. The cloud server 410 generates control commands according to the lighting control method and sends them to the client 490. Through centralized cloud processing, system function upgrades and updates can be achieved without modifying the local execution unit, greatly improving maintenance convenience.

[0068] refer to Figure 4 Cloud server 410 is used to implement Figure 2The method shown may include an internal communication bus 411, a processor 412, a read-only memory (ROM) 413, a random access memory (RAM) 414, a communication port 415, and a hard disk 416. The internal communication bus 411 enables data communication between the components of the cloud server 410. The processor 412 can make judgments and issue prompts. In some embodiments, the processor 412 may consist of one or more processors. The communication port 415 enables data communication between the cloud server 410 and external systems. In some embodiments, the cloud server 410 can send and receive information and data from a network through the communication port 415. The cloud server 410 may also include different forms of program storage units and data storage units, such as the hard disk 416, read-only memory (ROM) 413, and random access memory (RAM) 414, capable of storing various data files used for computer processing and / or communication, as well as possible program instructions executed by the processor 412. The processor executes these instructions to implement the main part of the method. The first model 420, ASR module 430, device-area mapping module 440, image color analysis module 450, IoT instruction generation module 460 and second model 470 in the above-mentioned lighting group control method can be implemented as computer programs, stored in hard disk 416, and loaded into processor 412 for execution.

[0069] refer to Figure 1 and Figure 4 The client 490 may include a touch display unit 491, a local processor 492, a communication unit 493, memory 494, audio I / O 496, and a power supply 495. The touch display unit 491 receives user touch operations and displays light status, spatial location information, and an interactive interface; the memory 494 stores data used for processing and / or communication, as well as interactive interface configuration information; the audio I / O 496 includes a microphone and a speaker for acquiring user commands and playing voice. The local processor 492 processes touch signals, audio signals, and control commands from the cloud server and controls the content displayed by the touch display unit 491; the communication unit 493 enables the client 490 to communicate with external systems; and the power supply 495 supplies power to the internal modules.

[0070] This application also includes a computer-readable medium storing computer program code that, when executed by a processor, implements the aforementioned lamp group control method.

[0071] refer to Figure 5 and Figure 6The figure shows the actual effect of the lighting group control method according to an embodiment of this application. The figure illustrates the overall lighting effect of the lighting group after applying this method. The lighting group includes a central light fixture and peripheral light fixtures. This method has wide applicability and can be flexibly adapted to various practical environments, such as... Figure 5 The office scene shown, or Figure 6 The home life scenes shown demonstrate good scene adaptability and visual expressiveness.

[0072] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0073] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0074] Some aspects of this application can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The aforementioned hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." The processor may be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. Furthermore, aspects of this application may manifest as computer products residing in one or more computer-readable media, including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), optical discs (e.g., compressed CDs, digital multifunction DVDs, etc.), smart cards, and flash memory devices (e.g., cards, sticks, key drives, etc.).

[0075] A computer-readable medium may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. A computer-readable medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or similar media, or any combination of the above media.

[0076] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0077] Although this application has been described with reference to specific embodiments, those skilled in the art should recognize that the above embodiments are only used to illustrate this application, and various equivalent changes or substitutions can be made without departing from the spirit of this application. Therefore, any changes or modifications to the above embodiments within the essential spirit of this application will fall within the scope of the claims of this application.

Claims

1. A method for controlling a lighting group, the lighting group having a central luminaire and peripheral luminaires, the method comprising the following steps: The first model is used to respond to user commands and generate scene images; Obtain the lighting information of the lighting group, the lighting information including lighting type, lighting layout and lighting attributes; The image is subjected to color analysis to generate a color pattern based on the scene image, and the color parameters of the scene image are extracted. A first control command corresponding to the central luminaire is generated based on the color pattern; The user instructions, scene image, color parameters, and lighting information are input into the second model. The second model outputs a second control instruction for the surrounding lighting fixtures. This second control instruction includes a color control instruction that adapts the local color of the surrounding lighting fixtures adjacent to the central lighting fixture. The first control command and the second control command are used to control the lighting group.

2. The method as described in claim 1, characterized in that, Also includes: Extract the brightness and color temperature parameters of the scene image; The brightness and color temperature parameters are input into the second model, so that the generated second control command includes a brightness control command and a color temperature control command.

3. The method as described in claim 2, characterized in that, The lighting fixture attributes include whether the color is adjustable, whether the brightness is adjustable, and whether the color temperature is adjustable.

4. The method as described in claim 1, characterized in that, The types of lighting fixtures include center lights, main lights, light strips, and spotlights.

5. The method as described in claim 1, characterized in that, The step of obtaining the lighting layout includes: receiving the position of the peripheral lighting fixtures relative to the central lighting fixture.

6. The method as described in claim 1, characterized in that, The color parameters include a primary color, a secondary color, and an accent color. The primary color is the color with a coverage ratio in the scene image in the first interval, the secondary color is the color with a coverage ratio in the scene image in the second interval, and the accent color is the color with a coverage ratio in the scene image in the third interval. The coverage ratios of the first interval, the second interval, and the third interval decrease sequentially.

7. The method as described in claim 1, characterized in that, It also includes inputting the user command into the second model, and the second model also outputting a scene name and scene description.

8. The method as described in claim 1, characterized in that, The scene image has a first resolution, and the color pattern has a second resolution, which is lower than the first resolution.

9. A lighting group control system, the lighting group having a central luminaire and peripheral luminaires, the system comprising: Memory is used to store instructions that can be executed by the processor; as well as A processor for executing the instructions to implement the method as described in any one of claims 1-8.

10. A computer storage medium storing computer program code, which, when executed by a processor, implements the method as claimed in any one of claims 1-8.

11. A computer program product comprising computer program code, wherein when the computer program code is executed by one or more processors, the one or more processors implement the steps of the method as described in any one of claims 1-8.

Images