A lighting control method and system based on big data processing

Abstract

The present invention provides a lighting control method and system based on big data processing, which relates to the field of lighting control technology. The method includes acquiring a panoramic image of an office area; determining office area layout information and position coordinates of multiple lamps using a coordinate determination model based on the panoramic image of the office area; generating multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the office area layout information; acquiring a target simulated lighting image selected by a user from the multiple simulated lighting images of the office area; determining the power of each lamp based on the target simulated lighting image; and performing lighting control on each lamp based on the power of each lamp. The method can quickly and accurately determine a lighting control plan for an office environment.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting control, and in particular to a lighting control method and system based on big data processing. Background Art

[0002] As modern office environments continue to demand more comfort and energy efficiency, intelligent lighting systems have gradually become an important means of improving work efficiency and energy conservation. Office areas usually contain multiple functional areas, such as meeting rooms, open work areas, rest areas, etc., and each area has different lighting requirements. For example, a meeting room may require higher brightness to ensure visual clarity, while a rest area is more suitable for soft indirect light. Therefore, how to automatically adjust the lighting configuration according to the functional requirements of different areas is an urgent problem to be solved. Traditional lighting systems mostly rely on manual adjustment, which is not only time-consuming and labor-intensive, but also difficult to achieve precise control.

[0003] Therefore, how to quickly and accurately determine the lighting control plan for the office environment is a problem that needs to be solved urgently. Summary of the invention

[0004] The main technical problem solved by the present invention is how to quickly and accurately determine the lighting control scheme of an office environment.

[0005] According to a first aspect, the present invention provides a lighting control method based on big data processing, comprising: acquiring a panoramic image of an office area; determining office area layout information and position coordinates of multiple lamps using a coordinate determination model based on the panoramic image of the office area; generating multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the office area layout information; acquiring a target simulated lighting image selected by a user from the multiple simulated lighting images of the office area; determining the power of each lamp based on the target simulated lighting image; and performing lighting control on each lamp based on the power of each lamp.

[0006] In one possible implementation, determining the power of each lamp based on the target simulated lighting image includes: constructing a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, each node represents a lamp, the edge between two nodes represents the distance and direction between the two lamps, and the node feature of each node is the position coordinate of the lamp; processing the graph structure based on a graph convolutional network to determine multiple groups of lighting control schemes; determining a target lighting control scheme based on the office area layout information and the multiple groups of lighting control scheme usage information to determine a model; and determining the power of each lamp based on the target lighting control scheme.

[0007] In a possible implementation, the coordinate determination model is a convolutional neural network model, the input of the coordinate determination model is a panoramic image of the office area, and the output of the coordinate determination model is office area layout information and location coordinates of multiple lights.

[0008] In a possible implementation, the input of the graph convolutional network is the graph structure, and the output of the graph convolutional network is a target lighting control solution.

[0009] According to a second aspect, the present invention provides a lighting control system based on big data processing, comprising:

[0010] A first acquisition module is used to acquire a panoramic image of the office area;

[0011] A coordinate determination module, configured to determine office area layout information and position coordinates of a plurality of lamps using a coordinate determination model based on the panoramic image of the office area;

[0012] A generating module, configured to generate a plurality of simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the plurality of lamps and the layout information of the office area;

[0013] A second acquisition module is used to acquire a target simulated lighting image selected by a user from a plurality of simulated lighting images of an office area;

[0014] a power determination module, configured to determine the power of each lamp based on the target simulated lighting image;

[0015] The lighting control module is used to control each lamp based on the power of each lamp.

[0016] In a possible implementation, the power determination module is also used to: construct a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, each node represents a lamp, the edge between two nodes represents the distance and direction between the two lamps, and the node feature of each node is the position coordinate of the lamp; based on the graph convolutional network, the graph structure is processed to determine multiple groups of lighting control schemes; based on the office area layout information and the multiple groups of lighting control schemes, a model is used to determine the target lighting control scheme; based on the target lighting control scheme, the power of each lamp is determined.

[0017] In a possible implementation, the coordinate determination model is a convolutional neural network model, the input of the coordinate determination model is a panoramic image of the office area, and the output of the coordinate determination model is office area layout information and location coordinates of multiple lights.

[0018] In a possible implementation, the input of the graph convolutional network is the graph structure, and the output of the graph convolutional network is a target lighting control solution.

[0019] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement a method as described above, the method comprising: obtaining a panoramic image of an office area; determining office area layout information and position coordinates of multiple lamps using a coordinate determination model based on the panoramic image of the office area; generating multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the office area layout information; obtaining a target simulated lighting image selected by a user from the multiple simulated lighting images of the office area; determining the power of each lamp based on the target simulated lighting image; and performing lighting control on each lamp based on the power of each lamp.

[0020] According to the fourth aspect, the present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned lighting control method based on big data processing, the method comprising: obtaining a panoramic image of an office area; determining office area layout information and position coordinates of multiple lamps using a coordinate determination model based on the panoramic image of the office area; generating multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the office area layout information; obtaining a target simulated lighting image selected by a user from the multiple simulated lighting images of the office area; determining the power of each lamp based on the target simulated lighting image; and performing lighting control on each lamp based on the power of each lamp.

[0021] The present invention provides a lighting control method and system based on big data processing, the method comprising acquiring a panoramic image of an office area; determining office area layout information and position coordinates of multiple lamps using a coordinate determination model based on the panoramic image of the office area; generating multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the office area layout information; acquiring a target simulated lighting image selected by a user from the multiple simulated lighting images of the office area; determining the power of each lamp based on the target simulated lighting image; and performing lighting control on each lamp based on the power of each lamp. The method can quickly and accurately determine a lighting control plan for an office environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an application scenario of a lighting control method based on big data processing provided by an embodiment of the present invention;

[0023] Figure 2A schematic diagram of a flow chart of a lighting control method based on big data processing provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of a process for determining the power of each lamp provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of a lighting control system based on big data processing provided by an embodiment of the present invention;

[0026] Figure 5 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0028] Figure 1 A schematic diagram of an application scenario of a lighting control method based on big data processing provided by an embodiment of the present invention. Figure 1 The application scenario of the lighting control method based on big data processing may include a server 11, a network 12, a terminal 13 and a storage device 14.

[0029] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 The lighting control method based on big data processing is shown in.

[0030] The network 12 may facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0031] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, and the like.

[0032] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of a lighting control method based on big data processing.

[0033] In an embodiment of the present invention, there is provided Figure 2 A lighting control method based on big data processing is shown, and the lighting control method based on big data processing includes steps S1 to S6:

[0034] Step S1, obtaining a panoramic image of an office area.

[0035] The panoramic image of the office area is obtained by photographing the office area with a panoramic camera.

[0036] Step S2: determining office area layout information and position coordinates of a plurality of lamps using a coordinate determination model based on the panoramic image of the office area.

[0037] The coordinate determination model is a convolutional neural network model, the input of the coordinate determination model is a panoramic image of the office area, and the output of the coordinate determination model is office area layout information and position coordinates of multiple lights.

[0038] The office area layout information is information describing the positional relationship of objects in the office area. The office area layout information includes, but is not limited to, the positions of furniture, partitions, doors, windows, etc. For example, the office area layout information includes the specific position coordinates of each table, chair, and window in the office.

[0039] The position coordinates of the multiple lamps are the specific positions of each lamp in the office area in space, and the position coordinates of the multiple lamps can be represented by two-dimensional or three-dimensional coordinates.

[0040] The convolutional neural network model can capture local features in the input image, such as edges and corners, by using a small-sized convolution kernel, thereby determining the layout information of the office area and the location coordinates of multiple lights.

[0041] Step S3: Generate multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the office area layout information.

[0042] The input of the generative adversarial network is the position coordinates of the multiple lights and the layout information of the office area, and the output of the generative adversarial network is multiple simulated lighting images of the office area.

[0043] Simulated lighting images are virtual lighting effect images generated by generative adversarial networks (GANs). Simulated lighting images show the visual effects under different lighting configurations.

[0044] Generative adversarial networks consist of a generator and a discriminator. The generator is responsible for creating new data samples, while the discriminator evaluates the authenticity of these samples. The two compete with each other and make progress together.

[0045] The generator takes the coordinates of the lamp positions and the layout information of the office area as input and generates realistic lighting effect images. The discriminator is responsible for distinguishing between real images and fake images generated by the generator.

[0046] Step S4, obtaining a target simulated lighting image selected by a user from a plurality of simulated lighting images of an office area.

[0047] In some embodiments, multiple simulated lighting images of the office area may be displayed to the user, and a target simulated lighting image selected by the user may be acquired.

[0048] The target simulated lighting image is a final version selected by the user from multiple simulated lighting images and represents the lighting solution that the user is most satisfied with.

[0049] Step S5: determining the power of each lamp based on the target simulated lighting image.

[0050] In some embodiments, Figure 3 A schematic diagram of a process for determining the power of each lamp provided by an embodiment of the present invention, wherein the process for determining the power of each lamp comprises steps S21 to S24:

[0051] Step S21, constructing a graph structure, wherein the graph structure includes multiple nodes and multiple edges between the multiple nodes, each node represents a lamp, an edge between two nodes represents the distance and direction between the two lamps, and a node feature of each node is the position coordinate of the lamp.

[0052] A graph structure is a data structure that represents the relationship between objects. The graph structure consists of nodes (vertices) and edges (edges). In this context, each node represents a lamp, and the edge represents the distance and direction between lamps. For example, if there are three lamps A, B, and C in an office, the graph structure includes three nodes (A, B, C) and the edges between them (such as AB, BC, AC), and each edge comes with distance and direction information.

[0053] Step S22: Process the graph structure based on a graph convolutional network to determine multiple groups of lighting control solutions.

[0054] The input of the graph convolution network is the graph structure, and the output of the graph convolution network is the target light control solution. The graph convolution network is a neural network model specially designed for processing graph structure data.

[0055] Each lamp is a node, containing features such as location coordinates, while edges represent the distance and direction between lamps. Graph convolutional networks exploit the local connection characteristics in the graph structure, that is, the direct connection between adjacent nodes, which helps capture the spatial dependency and influence range between lamps.

[0056] By treating lamps as nodes and assigning their position coordinates as features, the actual physical layout can be directly mapped. The existence of edges and their attributes (such as distance and direction) clarify the relative position relationship between lamps, allowing graph convolutional networks to understand and use these relationships for effective prediction and decision-making.

[0057] There may be occlusion and reflection between lamps, which will affect the overall lighting effect. Through the graph structure, these local interaction effects can be easily modeled, and the graph convolutional network can be used to learn how to optimize these effects to achieve the best lighting effect.

[0058] The graph structure itself, as a powerful form of data representation, can accurately describe the layout of lamps in physical space and their mutual influence. The graph convolutional network can effectively utilize the spatial relationships and interactions between lamps to generate optimized control strategies.

[0059] Step S23: determining a target lighting control solution by using a model based on the office area layout information and the plurality of lighting control solution usage information.

[0060] The information determination model is a deep neural network model. The input of the information determination model is the office area layout information and the multiple groups of lighting control solutions, and the output of the information determination model is the target lighting control solution.

[0061] Through multiple layers of nonlinear transformation, deep neural networks can automatically extract high-level abstract features from input data. Deep neural networks can understand and utilize office area layout information (such as furniture location, partitions, etc.) and the complex relationship between different lighting control schemes. Deep neural networks can comprehensively consider multiple factors to make the best decision. When determining the target lighting control scheme, deep neural networks can consider the location and power settings of lamps, as well as how the specific layout of the office area affects light distribution, user comfort and other factors, and finally determine the target lighting control scheme.

[0062] In some embodiments, the information determination model includes a solution information determination layer, a personnel perceived comfort determination layer, and a solution determination layer. The input of the solution information determination layer is the office area layout information and the multiple groups of lighting control solutions. The output of the solution information determination layer is the lighting distribution map of the office area for each lighting control solution and the energy consumption of each lighting control solution. The input of the personnel perceived comfort determination layer is the office area layout information, the multiple groups of lighting control solutions, and the lighting distribution map of the office area for each lighting control solution. The output of the personnel perceived comfort determination layer is the personnel perceived comfort of each lighting control solution. The input of the solution determination layer is the personnel perceived comfort of each lighting control solution, the lighting distribution map of the office area for each lighting control solution, and the energy consumption of each lighting control solution. The output of the solution determination layer is the target lighting control solution.

[0063] Step S24: determining the power of each lamp based on the target lighting control solution.

[0064] After the target light control scheme is determined, the power of each lamp is determined based on the target light control scheme.

[0065] Step S6: performing lighting control on each lamp based on the power of each lamp.

[0066] After the power of each lamp is determined, the lighting of each lamp is controlled based on the power of each lamp.

[0067] Based on the same inventive concept, Figure 4 A schematic diagram of a lighting control system based on big data processing provided by an embodiment of the present invention, the lighting control system based on big data processing includes:

[0068] A first acquisition module 41 is used to acquire a panoramic image of the office area;

[0069] A coordinate determination module 42, configured to determine office area layout information and position coordinates of a plurality of lamps using a coordinate determination model based on the panoramic image of the office area;

[0070] A generating module 43, configured to generate a plurality of simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the plurality of lamps and the layout information of the office area;

[0071] A second acquisition module 44 is used to acquire a target simulated lighting image selected by a user from a plurality of simulated lighting images of an office area;

[0072] A power determination module 45, configured to determine the power of each lamp based on the target simulated illumination image;

[0073] The light control module 46 is used to control each light based on the power of each light.

[0074] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, such as Figure 5 As shown, including:

[0075] The invention comprises: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and is configured to be executed by the processor 51 to implement the lighting control method based on big data processing as provided above, the method comprising: obtaining a screen recording operation video of a user's favorite software and a lighting control description text; determining an interactive interface and user interface preference information of the user's favorite software based on an analysis model of the screen recording operation video of the user's favorite software; determining a minimum number of modules required by the user and a maximum number of modules required by the user based on the lighting control description text; generating multiple simulated software interactive interfaces using a generative adversarial network based on the minimum number of modules required by the user, the maximum number of modules required by the user, the interactive interface of the user's favorite software, and the user interface preference information; and determining a target software interactive interface based on the multiple simulated software interactive interfaces.

[0076] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by the processor 51, implements the aforementioned lighting control method based on big data processing, the method comprising: obtaining a panoramic image of an office area; determining the layout information of the office area and the position coordinates of multiple lamps using a coordinate determination model based on the panoramic image of the office area; generating multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lamps and the layout information of the office area; obtaining a target simulated lighting image selected by a user from the multiple simulated lighting images of the office area; determining the power of each lamp based on the target simulated lighting image; and performing lighting control on each lamp based on the power of each lamp.

[0077] The lighting control method based on big data processing provided in the embodiment of the present application can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (ultra-mobile personal computers, UMPCs), handheld computers, netbooks, personal digital assistants (personal digital assistants, PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (augmented reality, AR) \ virtual reality (virtual reality, VR) devices, smart home devices, car computers and other electronic devices, and the embodiment of the present application does not impose any restrictions on this.

[0078] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0079] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0080] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0081] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0082] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A lighting control method based on big data processing, characterized in that: include: Obtain panoramic images of the office area; Determine office area layout information and position coordinates of a plurality of lamps using a coordinate determination model based on the panoramic image of the office area; Generate multiple simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the multiple lights and the office area layout information; Acquire a target simulated lighting image selected by a user from a plurality of simulated lighting images of an office area; Determining the power of each lamp based on the target simulated lighting image, wherein determining the power of each lamp based on the target simulated lighting image comprises: Constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, each node representing a lamp, an edge between two nodes representing a distance and a direction between the two lamps, and a node feature of each node being a position coordinate of the lamp; Processing the graph structure based on a graph convolutional network to determine multiple groups of lighting control solutions; Based on the office area layout information and the multiple groups of lighting control schemes, a target lighting control scheme is determined using an information determination model, the information determination model includes a scheme information determination layer, a personnel perceived comfort determination layer, and a scheme determination layer, the input of the scheme information determination layer is the office area layout information and the multiple groups of lighting control schemes, the output of the scheme information determination layer is the illumination distribution map of the office area of ​​each lighting control scheme, and the energy consumption of each lighting control scheme, the input of the personnel perceived comfort determination layer is the office area layout information, the multiple groups of lighting control schemes, and the illumination distribution map of the office area of ​​each lighting control scheme, and the output of the personnel perceived comfort determination layer is the personnel perceived comfort of each lighting control scheme; the input of the scheme determination layer is the personnel perceived comfort of each lighting control scheme, the illumination distribution map of the office area of ​​each lighting control scheme, and the energy consumption of each lighting control scheme, and the output of the scheme determination layer is the target lighting control scheme; determining the power of each lamp based on the target lighting control scheme; Lighting control is performed on each lamp based on the power of each lamp.

2. The lighting control method based on big data processing according to claim 1, characterized in that: The coordinate determination model is a convolutional neural network model, the input of the coordinate determination model is a panoramic image of the office area, and the output of the coordinate determination model is office area layout information and position coordinates of multiple lights.

3. The lighting control method based on big data processing according to claim 1, characterized in that: The input of the graph convolutional network is the graph structure, and the output of the graph convolutional network is the target lighting control solution.

4. A lighting control system based on big data processing, characterized in that: include: A first acquisition module is used to acquire a panoramic image of the office area; A coordinate determination module, configured to determine office area layout information and position coordinates of a plurality of lamps using a coordinate determination model based on the panoramic image of the office area; A generating module, configured to generate a plurality of simulated lighting images of the office area using a generative adversarial network based on the position coordinates of the plurality of lamps and the layout information of the office area; A second acquisition module is used to acquire a target simulated lighting image selected by a user from a plurality of simulated lighting images of an office area; A power determination module is used to determine the power of each lamp based on the target simulated lighting image, and the power determination module is also used to: Constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, each node representing a lamp, an edge between two nodes representing a distance and a direction between the two lamps, and a node feature of each node being a position coordinate of the lamp; Processing the graph structure based on a graph convolutional network to determine multiple groups of lighting control solutions; Based on the office area layout information and the multiple groups of lighting control schemes, a target lighting control scheme is determined using an information determination model, the information determination model includes a scheme information determination layer, a personnel perceived comfort determination layer, and a scheme determination layer, the input of the scheme information determination layer is the office area layout information and the multiple groups of lighting control schemes, the output of the scheme information determination layer is the illumination distribution map of the office area of ​​each lighting control scheme, and the energy consumption of each lighting control scheme, the input of the personnel perceived comfort determination layer is the office area layout information, the multiple groups of lighting control schemes, and the illumination distribution map of the office area of ​​each lighting control scheme, and the output of the personnel perceived comfort determination layer is the personnel perceived comfort of each lighting control scheme; the input of the scheme determination layer is the personnel perceived comfort of each lighting control scheme, the illumination distribution map of the office area of ​​each lighting control scheme, and the energy consumption of each lighting control scheme, and the output of the scheme determination layer is the target lighting control scheme; determining the power of each lamp based on the target lighting control scheme; The lighting control module is used to control each lamp based on the power of each lamp.

5. The lighting control system based on big data processing as claimed in claim 4, characterized in that: The coordinate determination model is a convolutional neural network model, the input of the coordinate determination model is a panoramic image of the office area, and the output of the coordinate determination model is office area layout information and position coordinates of multiple lights.

6. The lighting control system based on big data processing as claimed in claim 4, characterized in that: The input of the graph convolutional network is the graph structure, and the output of the graph convolutional network is the target lighting control solution.

7. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the lighting control method based on big data processing as described in any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the lighting control method based on big data processing as described in any one of claims 1 to 3 is implemented.

Images