Light control method and device based on deep learning, equipment and storage medium

Abstract

The application relates to the field of artificial intelligence and discloses a light control method, device and equipment based on deep learning and a storage medium, which are used for realizing the intelligentization of light control. The method comprises the following steps: performing information segmentation processing on first light illumination information to obtain a plurality of second light illumination information; inputting the plurality of second light illumination information into a preset lamp configuration model for lamp configuration to obtain lamp configuration information corresponding to each second light illumination information; creating a light control strategy table according to the lamp configuration information corresponding to each second light illumination information; receiving a target illumination request sent by a second trigger instruction, responding to the target illumination request and generating a corresponding target control strategy according to the light control strategy table; performing light control on the target illumination request according to the target control strategy, collecting an illumination area image corresponding to the target illumination request, and transmitting the illumination area image to a preset light control platform.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and in particular to a lighting control method, apparatus, device, and storage medium based on deep learning. Background Technology

[0002] With the rapid development of IoT and AI technologies, lighting solutions are becoming more intelligent and efficient. Lighting control systems are controlled manually by sensors on the control panel to control and switch lighting.

[0003] However, the existing solutions only control the lights through sensors, which is not light control in the traditional sense of intelligence, meaning that the existing solutions have a low level of intelligence. Summary of the Invention

[0004] This invention provides a deep learning-based lighting control method, device, equipment, and storage medium for achieving intelligent lighting control.

[0005] The first aspect of this invention provides a deep learning-based lighting control method, the deep learning-based lighting control method comprising:

[0006] Obtain the lighting control task carried by the first trigger command, and extract the task information from the lighting control task to obtain the corresponding first lighting information;

[0007] The first lighting information is segmented to obtain multiple second lighting information;

[0008] The multiple second lighting information are input into a preset lighting configuration model to configure the lighting fixtures, thereby obtaining the lighting fixture configuration information corresponding to each second lighting information.

[0009] Create a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information;

[0010] Receive the target lighting request sent by the second trigger command, respond to the target lighting request and generate a corresponding target control strategy according to the lighting control strategy table;

[0011] The target lighting request is controlled according to the target control strategy, and the lighting area image corresponding to the target lighting request is acquired and transmitted to the preset lighting control platform.

[0012] In conjunction with the first aspect, in a first embodiment of the first aspect of the present invention, the step of obtaining the lighting control task carried by the first triggering command and extracting task information from the lighting control task to obtain the corresponding first lighting information includes:

[0013] Read the lighting control task sent by the first trigger command and determine the task association data corresponding to the lighting control task;

[0014] The task-related data is judged by its data volume. When the data volume of the task-related data is greater than a preset target value, the task-related data is prioritized and the first lighting information is generated.

[0015] When the amount of data associated with the task is less than or equal to the target value, the task-associated data is converted to generate the first lighting information.

[0016] In conjunction with the first aspect, in the second embodiment of the first aspect of the present invention, the step of performing information segmentation processing on the first lighting information to obtain multiple second lighting information includes:

[0017] Perform information identification analysis on the first lighting information to determine the target key identifier corresponding to the first lighting information;

[0018] The task type corresponding to the first lighting information is determined based on the target key identifier;

[0019] Obtain the information segmentation mode corresponding to the task type, and perform information segmentation processing on the first lighting information using the information segmentation mode to obtain multiple second lighting information.

[0020] In conjunction with the first aspect, in the third embodiment of the first aspect of the present invention, the step of inputting the plurality of second lighting information into a preset lighting configuration model for lighting configuration to obtain lighting configuration information corresponding to each second lighting information includes:

[0021] The multiple second lighting information is read and analyzed to determine the lighting fixture combination data corresponding to each second lighting information.

[0022] The luminaire combination data corresponding to each second lighting information is input into a preset luminaire configuration model, wherein the luminaire configuration model includes: an embedded layer, a multi-layer threshold cyclic network, and a fully connected layer;

[0023] The lighting configuration model is used to analyze the lighting combination data and output the lighting configuration information corresponding to each second lighting information.

[0024] In conjunction with the first aspect, in the fourth embodiment of the first aspect of the present invention, the step of creating a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information includes:

[0025] Encode the luminaire configuration information corresponding to each second lighting information to obtain the encoded data of each luminaire configuration information;

[0026] The encoded data of each lighting fixture configuration information is sorted to obtain an encoded sequence;

[0027] A lighting control strategy table corresponding to the lighting configuration information is created based on the encoded sequence.

[0028] In conjunction with the first aspect, in a fifth embodiment of the first aspect of the present invention, the step of controlling the target lighting request according to the target control strategy, acquiring an image of the lighting area corresponding to the target lighting request, and transmitting the lighting area image to a preset lighting control platform includes:

[0029] The target control strategy is analyzed to determine the corresponding lighting control steps;

[0030] The lighting control steps described above are used to control the lighting of the target lighting request.

[0031] The image of the lighting area corresponding to the target lighting request is acquired and transmitted to the preset lighting control platform.

[0032] In conjunction with the first aspect, in a sixth embodiment of the first aspect of the present invention, the deep learning-based lighting control method further includes:

[0033] The lighting control platform performs lighting analysis on the image of the lighting area to obtain the lighting analysis results;

[0034] The target control strategy is optimized based on the lighting analysis results to generate an optimized lighting control scheme.

[0035] A second aspect of the present invention provides a deep learning-based lighting control device, the deep learning-based lighting control device comprising:

[0036] The acquisition module is used to acquire the lighting control task carried by the first trigger command, and extract the task information of the lighting control task to obtain the corresponding first lighting information.

[0037] The processing module is used to perform information segmentation processing on the first lighting information to obtain multiple second lighting information;

[0038] The configuration module is used to input the multiple second lighting information into a preset lighting configuration model to configure the lighting fixtures, thereby obtaining the lighting fixture configuration information corresponding to each second lighting information.

[0039] A module is created to generate a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information.

[0040] The generation module is used to receive the target lighting request sent by the second triggering command, respond to the target lighting request, and generate a corresponding target control strategy according to the lighting control strategy table.

[0041] The control module is used to control the lighting of the target lighting request according to the target control strategy, acquire the lighting area image corresponding to the target lighting request, and transmit the lighting area image to the preset lighting control platform.

[0042] In conjunction with the second aspect, in the first embodiment of the second aspect of the present invention, the acquisition module is specifically used for:

[0043] Read the lighting control task sent by the first trigger command and determine the task association data corresponding to the lighting control task;

[0044] The task-related data is judged by its data volume. When the data volume of the task-related data is greater than a preset target value, the task-related data is prioritized and the first lighting information is generated.

[0045] When the amount of data associated with the task is less than or equal to the target value, the task-associated data is converted to generate the first lighting information.

[0046] In conjunction with the second aspect, in a second embodiment of the second aspect of the present invention, the processing module is specifically used for:

[0047] Perform information identification analysis on the first lighting information to determine the target key identifier corresponding to the first lighting information;

[0048] The task type corresponding to the first lighting information is determined based on the target key identifier;

[0049] Obtain the information segmentation mode corresponding to the task type, and perform information segmentation processing on the first lighting information using the information segmentation mode to obtain multiple second lighting information.

[0050] In conjunction with the second aspect, in the third embodiment of the second aspect of the present invention, the configuration module is specifically used for:

[0051] The multiple second lighting information is read and analyzed to determine the lighting fixture combination data corresponding to each second lighting information.

[0052] The luminaire combination data corresponding to each second lighting information is input into a preset luminaire configuration model, wherein the luminaire configuration model includes: an embedded layer, a multi-layer threshold cyclic network, and a fully connected layer;

[0053] The lighting configuration model is used to analyze the lighting combination data and output the lighting configuration information corresponding to each second lighting information.

[0054] In conjunction with the second aspect, in the fourth embodiment of the second aspect of the present invention, the creation module is specifically used for:

[0055] Encode the luminaire configuration information corresponding to each second lighting information to obtain the encoded data of each luminaire configuration information;

[0056] The encoded data of each lighting fixture configuration information is sorted to obtain an encoded sequence;

[0057] A lighting control strategy table corresponding to the lighting configuration information is created based on the encoded sequence.

[0058] In conjunction with the second aspect, in the fifth embodiment of the second aspect of the present invention, the control module is specifically used for:

[0059] The target control strategy is analyzed to determine the corresponding lighting control steps;

[0060] The lighting control steps described above are used to control the lighting of the target lighting request.

[0061] The image of the lighting area corresponding to the target lighting request is acquired and transmitted to the preset lighting control platform.

[0062] In conjunction with the second aspect, in a sixth embodiment of the second aspect of the present invention, the deep learning-based lighting control device further includes:

[0063] The optimization module is used to perform lighting analysis on the image of the lighting area through the lighting control platform to obtain lighting analysis results; and to optimize the target control strategy based on the lighting analysis results to generate an optimized lighting control scheme.

[0064] A third aspect of the present invention provides a deep learning-based lighting control device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the deep learning-based lighting control device to execute the aforementioned deep learning-based lighting control method.

[0065] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the aforementioned deep learning-based lighting control method.

[0066] In the technical solution provided by this invention, information segmentation processing is performed on the first lighting information to obtain multiple second lighting information; the multiple second lighting information are respectively input into a preset lighting configuration model for lighting configuration to obtain lighting configuration information corresponding to each second lighting information; a lighting control strategy table is created based on the lighting configuration information corresponding to each second lighting information; a target lighting request sent by a second trigger command is received, the target lighting request is responded to, and a corresponding target control strategy is generated according to the lighting control strategy table; lighting control is performed on the target lighting request according to the target control strategy, and the lighting area image corresponding to the target lighting request is collected, and the lighting area image is transmitted to a preset lighting control platform. This invention improves the accuracy of lighting configuration by performing lighting configuration analysis through a deep learning lighting configuration model, and then performs lighting control on the target lighting request according to the target control strategy and collects the lighting area image corresponding to the target lighting request, thereby optimizing the lighting control strategy, realizing intelligent lighting control, and improving the accuracy of lighting control. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of an embodiment of the deep learning-based lighting control method of the present invention;

[0068] Figure 2 This is a flowchart of the information segmentation process in an embodiment of the present invention;

[0069] Figure 3 This is a flowchart illustrating the lamp configuration in an embodiment of the present invention;

[0070] Figure 4 This is a flowchart illustrating the creation of a lighting control strategy table in an embodiment of the present invention;

[0071] Figure 5 This is a schematic diagram of one embodiment of a deep learning-based lighting control device according to the present invention;

[0072] Figure 6 This is a schematic diagram of another embodiment of the deep learning-based lighting control device of the present invention;

[0073] Figure 7 This is a schematic diagram of one embodiment of a deep learning-based lighting control device according to the present invention. Implementation

[0074] This invention provides a deep learning-based lighting control method, apparatus, device, and storage medium for achieving intelligent lighting control. The terms "first," "second," "third," "fourth," etc. (if applicable) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0075] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the deep learning-based lighting control method in this invention includes:

[0076] S101. Obtain the lighting control task carried by the first trigger command, and extract the task information of the lighting control task to obtain the corresponding first lighting information.

[0077] It is understood that the executing entity of this invention can be a deep learning-based lighting control device, a terminal, or a server; no specific limitation is made here. This embodiment of the invention will be described using a server as an example.

[0078] Specifically, the server obtains the lighting control task carried by the first trigger command. The lighting control task is pre-set and includes corresponding lighting information. Further, the server extracts task information from the lighting control task. Specifically, the server identifies the command for the lighting control task, determines multiple corresponding lighting control commands, and extracts information based on these multiple lighting control commands to obtain the corresponding first lighting information.

[0079] S102. Perform information segmentation processing on the first lighting information to obtain multiple second lighting information;

[0080] Specifically, the server performs information segmentation processing on the first lighting information. During information segmentation, the server analyzes the information identifier of the first lighting information to determine the corresponding target key identifier. Then, the server determines the corresponding information database through the target key information identifier, and determines the task type corresponding to the target key identifier through the information database. The server then performs information segmentation pattern matching through the task type to determine the corresponding information segmentation pattern. Finally, the server performs information segmentation processing on the first lighting information through the information segmentation pattern to obtain multiple second lighting information.

[0081] S103. Input multiple second lighting information into a preset lighting configuration model to configure the lighting fixtures, and obtain the lighting fixture configuration information corresponding to each second lighting information.

[0082] It should be noted that the server inputs multiple second lighting information into a preset lighting configuration model to perform lighting combination analysis, determines the corresponding lighting combination data, and then the server confirms the configuration information of the lighting combination to obtain the lighting configuration information corresponding to each second lighting information.

[0083] S104. Create a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information;

[0084] Specifically, the server confirms each second lighting information, determines the corresponding lighting fixture configuration information, further encodes the lighting fixture configuration information corresponding to each second lighting information, determines the encoded data corresponding to each lighting fixture configuration information, sorts the encoded data corresponding to each lighting fixture configuration information, determines the encoding sequence, and finally, the server creates a lighting control strategy table based on the encoding sequence.

[0085] S105. Receive the target lighting request sent by the second trigger command, respond to the target lighting request and generate the corresponding target control strategy according to the lighting control strategy table;

[0086] Specifically, the server receives the target lighting request sent by the second triggering instruction, parses the target lighting request, determines the corresponding parsing information, and further responds to the target lighting request based on the parsing information and generates the corresponding target control policy based on the lighting control policy table.

[0087] S106. Perform lighting control on the target lighting request according to the target control strategy, collect the lighting area image corresponding to the target lighting request, and transmit the lighting area image to the preset lighting control platform.

[0088] Specifically, the server controls the lighting of the target lighting request according to the target control strategy, and then uses a preset image acquisition device to acquire the lighting area image corresponding to the target lighting request, and then transmits the lighting area image to the preset lighting control platform.

[0089] In this embodiment of the invention, the first lighting information is segmented to obtain multiple second lighting information; the multiple second lighting information are input into a preset lighting configuration model for lighting configuration to obtain lighting configuration information corresponding to each second lighting information; a lighting control strategy table is created based on the lighting configuration information corresponding to each second lighting information; a target lighting request sent by a second trigger command is received, the target lighting request is responded to, and a corresponding target control strategy is generated according to the lighting control strategy table; lighting control is performed on the target lighting request according to the target control strategy, and an image of the lighting area corresponding to the target lighting request is collected, and the image of the lighting area is transmitted to a preset lighting control platform. This invention improves the accuracy of lighting configuration by performing lighting configuration analysis through a deep learning lighting configuration model, and then performs lighting control on the target lighting request according to the target control strategy and collects an image of the lighting area corresponding to the target lighting request, thereby optimizing the lighting control strategy, realizing intelligent lighting control, and improving the accuracy of lighting control.

[0090] In one specific embodiment, the process of performing step S101 may specifically include the following steps:

[0091] (1) Read the lighting control task sent by the first trigger command and determine the task association data corresponding to the lighting control task;

[0092] (2) The data volume of the task-related data is judged. When the data volume of the task-related data is greater than the preset target value, the task-related data is prioritized and the first lighting information is generated.

[0093] (3) When the amount of data associated with the task is less than or equal to the target value, the task associated data is converted to generate the first lighting information.

[0094] Specifically, the server reads the lighting control task sent by the first trigger command, determines the task-related data corresponding to the lighting control task, and assigns the lighting control task to a service node in the task storage cluster. The lighting control task includes the task type of the task to be read. It should be noted that the service node stores the task in the corresponding information parsing database according to the task type of the task to be read. Then, the server determines the task-related data corresponding to the lighting control task based on the information parsing database. Further, the server judges the data volume of the task-related data. When the data volume of the task-related data is greater than a preset target value, the task-related data is prioritized and first lighting information is generated. When judging the data volume, the server traverses the task-related data to determine the data volume of the task-related data. Then, the server judges the data volume of the task-related data. When the data volume of the task-related data is greater than a preset target value, the task-related data is prioritized and first lighting information is generated. When the data volume of the task-related data is less than or equal to the target value, the task-related data is converted into information to generate the first lighting information.

[0095] In one specific embodiment, such as Figure 2 As shown, the process of executing step S102 can specifically include the following steps:

[0096] S201. Perform information identification analysis on the first lighting information to determine the target key identifiers corresponding to the first lighting information;

[0097] S202. Determine the task type corresponding to the first lighting information based on the target key identifier;

[0098] S203. Obtain the information segmentation mode corresponding to the task type, and perform information segmentation processing on the first lighting information through the information segmentation mode to obtain multiple second lighting information.

[0099] Specifically, the server performs information identification analysis on the first lighting information to determine the target key identifier corresponding to the first lighting information. Based on the received target key identifier, the server performs target recognition analysis and task type analysis to determine the task type corresponding to the first lighting information. Further, the server obtains the information segmentation pattern corresponding to the task type and performs information segmentation processing on the first lighting information through the information segmentation pattern. During the information segmentation processing, the server preprocesses the first lighting information and performs initial segmentation, dividing the lighting brightness in the first lighting information into three types: foreground brightness, background brightness, and uncertain brightness. Using different lighting information, the foreground brightness, background brightness, and uncertain brightness are reclassified to obtain multiple second lighting information.

[0100] In one specific embodiment, such as Figure 3 As shown, the process of executing step S103 can specifically include the following steps:

[0101] S301. Read and analyze multiple second lighting information to determine the lamp combination data corresponding to each second lighting information;

[0102] S302. Input the luminaire combination data corresponding to each second lighting information into the preset luminaire configuration model, wherein the luminaire configuration model includes: an embedded layer, a multi-layer threshold cyclic network and a fully connected layer.

[0103] S303. Perform lamp configuration analysis on the lamp combination data through the lamp configuration model, and output the lamp configuration information corresponding to each second lighting information.

[0104] Specifically, the server reads and analyzes multiple secondary lighting information entries to determine the corresponding lighting fixture combination data for each secondary lighting information entry. Specifically, the server imports a lighting fixture combination entity table from a pre-set template data source. This entity table corresponds to a tag model. Tag entity attributes are extracted, and multiple fields are selected from the tag model to extract its entity attributes. Data tags are created, tag layering rules are set for the tag model, and tag lighting fixture combinations are calculated. Based on the set tag layering rules, the corresponding tag lighting fixture combination layered data is filtered and generated. Then, the server performs lighting fixture configuration analysis based on the tag lighting fixture combination layered data and outputs the lighting fixture configuration information corresponding to each secondary lighting information entry.

[0105] In one specific embodiment, such as Figure 4 As shown, the process of executing step S104 can specifically include the following steps:

[0106] S401. Encode the luminaire configuration information corresponding to each second lighting information to obtain the encoded data of each luminaire configuration information;

[0107] S402. Sort the encoded data of each lighting fixture configuration information to obtain the encoded sequence;

[0108] S403. Create a lighting control strategy table corresponding to the lighting configuration information based on the encoding sequence.

[0109] Specifically, the server encodes the lighting configuration information corresponding to each second lighting information to obtain the encoded data of each lighting configuration information. The server obtains the symbol information corresponding to the lighting configuration information to be encoded. The symbol information includes at least two strings and at least one separator. The separator is used to separate the two strings. The symbol information is encoded in a preset order to obtain the encoded data of each lighting configuration information. The encoded data of each lighting configuration information is sorted to obtain the encoding sequence. The lighting control strategy table corresponding to the lighting configuration information is created based on the encoding sequence.

[0110] In one specific embodiment, the process of executing step S106 may specifically include the following steps:

[0111] (1) Analyze the target control strategy and determine the corresponding lighting control steps;

[0112] (2) Perform lighting control on the target lighting request through the lighting control steps;

[0113] (3) Collect the image of the lighting area corresponding to the target lighting request and transmit the image of the lighting area to the preset lighting control platform.

[0114] Specifically, the target control strategy is analyzed to determine the corresponding lighting control steps. Specifically, the server identifies the target control strategy and performs strategy analysis to determine the corresponding lighting control steps. Each lighting control step contains corresponding control logic for each lamp. Furthermore, the server performs lighting control on the target lighting request based on the lighting control steps and the lighting control logic within them, acquires the lighting area image corresponding to the target lighting request, and transmits the lighting area image to the preset lighting control platform.

[0115] In one specific embodiment, the above-described deep learning-based lighting control method further includes the following steps:

[0116] (1) Perform lighting analysis on the image of the lighting area through the lighting control platform to obtain the lighting analysis results;

[0117] (2) Optimize the target control strategy based on the lighting analysis results and generate an optimized lighting control scheme.

[0118] Specifically, the server performs lighting analysis on the image of the lighting area through the lighting control platform to obtain lighting analysis results. The server analyzes the image of the lighting area through environmental parameters. During the analysis, the server analyzes the lighting brightness from multiple perspectives, including the brightness deviation, the overall brightness uniformity, and the longitudinal brightness uniformity, to obtain lighting analysis results. Based on the lighting analysis results, the target control strategy is optimized to generate an optimized lighting control scheme.

[0119] The above describes the deep learning-based lighting control method in the embodiments of the present invention. The following describes the deep learning-based lighting control device in the embodiments of the present invention. Please refer to [link / reference]. Figure 5 One embodiment of the deep learning-based lighting control device of the present invention includes:

[0120] The acquisition module 501 is used to acquire the lighting control task carried by the first trigger command, and extract the task information of the lighting control task to obtain the corresponding first lighting information.

[0121] Processing module 502 is used to perform information segmentation processing on the first lighting information to obtain multiple second lighting information;

[0122] The configuration module 503 is used to input the plurality of second lighting information into a preset lighting configuration model for lighting configuration, and obtain lighting configuration information corresponding to each second lighting information.

[0123] Create module 504 to create a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information;

[0124] The generation module 505 is used to receive a target lighting request sent by the second triggering instruction, respond to the target lighting request, and generate a corresponding target control strategy according to the lighting control strategy table.

[0125] The control module 506 is used to control the lighting of the target lighting request according to the target control strategy, acquire the lighting area image corresponding to the target lighting request, and transmit the lighting area image to the preset lighting control platform.

[0126] Through the collaborative efforts of the aforementioned components, the first lighting information is segmented to obtain multiple second lighting information items. These multiple second lighting information items are then input into a pre-set lighting configuration model for lighting configuration, resulting in lighting configuration information corresponding to each second lighting information item. A lighting control strategy table is created based on the lighting configuration information corresponding to each second lighting information item. A target lighting request sent by a second trigger command is received, the target lighting request is responded to, and a corresponding target control strategy is generated according to the lighting control strategy table. Lighting control is applied to the target lighting request according to the target control strategy, and an image of the lighting area corresponding to the target lighting request is acquired and transmitted to a pre-set lighting control platform. This invention improves the accuracy of lighting configuration by using a deep learning-based lighting configuration model for lighting configuration analysis. Then, lighting control is applied to the target lighting request according to the target control strategy, and an image of the lighting area corresponding to the target lighting request is acquired, thereby optimizing the lighting control strategy and achieving intelligent lighting control while improving its accuracy.

[0127] Please see Figure 6 Another embodiment of the deep learning-based lighting control device in this invention includes:

[0128] The acquisition module 501 is used to acquire the lighting control task carried by the first trigger command, and extract the task information of the lighting control task to obtain the corresponding first lighting information.

[0129] Processing module 502 is used to perform information segmentation processing on the first lighting information to obtain multiple second lighting information;

[0130] The configuration module 503 is used to input the plurality of second lighting information into a preset lighting configuration model for lighting configuration, and obtain lighting configuration information corresponding to each second lighting information.

[0131] Create module 504 to create a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information;

[0132] The generation module 505 is used to receive a target lighting request sent by the second triggering instruction, respond to the target lighting request, and generate a corresponding target control strategy according to the lighting control strategy table.

[0133] The control module 506 is used to control the lighting of the target lighting request according to the target control strategy, acquire the lighting area image corresponding to the target lighting request, and transmit the lighting area image to the preset lighting control platform.

[0134] Optionally, the acquisition module 501 is specifically used for:

[0135] Read the lighting control task sent by the first trigger command and determine the task association data corresponding to the lighting control task;

[0136] The task-related data is judged by its data volume. When the data volume of the task-related data is greater than a preset target value, the task-related data is prioritized and the first lighting information is generated.

[0137] When the amount of data associated with the task is less than or equal to the target value, the task-associated data is converted to generate the first lighting information.

[0138] Optionally, the processing module 502 is specifically used for:

[0139] Perform information identification analysis on the first lighting information to determine the target key identifier corresponding to the first lighting information;

[0140] The task type corresponding to the first lighting information is determined based on the target key identifier;

[0141] Obtain the information segmentation mode corresponding to the task type, and perform information segmentation processing on the first lighting information using the information segmentation mode to obtain multiple second lighting information.

[0142] Optionally, the configuration module 503 is specifically used for:

[0143] The multiple second lighting information is read and analyzed to determine the lighting fixture combination data corresponding to each second lighting information.

[0144] The luminaire combination data corresponding to each second lighting information is input into a preset luminaire configuration model, wherein the luminaire configuration model includes: an embedded layer, a multi-layer threshold cyclic network, and a fully connected layer;

[0145] The lighting configuration model is used to analyze the lighting combination data and output the lighting configuration information corresponding to each second lighting information.

[0146] Optionally, the creation module 504 is specifically used for:

[0147] Encode the luminaire configuration information corresponding to each second lighting information to obtain the encoded data of each luminaire configuration information;

[0148] The encoded data of each lighting fixture configuration information is sorted to obtain an encoded sequence;

[0149] A lighting control strategy table corresponding to the lighting configuration information is created based on the encoded sequence.

[0150] Optionally, the control module 506 is specifically used for:

[0151] The target control strategy is analyzed to determine the corresponding lighting control steps;

[0152] The lighting control steps described above are used to control the lighting of the target lighting request.

[0153] The image of the lighting area corresponding to the target lighting request is acquired and transmitted to the preset lighting control platform.

[0154] Optionally, the deep learning-based lighting control device further includes:

[0155] The optimization module 507 is used to perform lighting analysis on the image of the lighting area through the lighting control platform to obtain lighting analysis results; and to optimize the target control strategy based on the lighting analysis results to generate an optimized lighting control scheme.

[0156] In this embodiment of the invention, the first lighting information is segmented to obtain multiple second lighting information; the multiple second lighting information are input into a preset lighting configuration model for lighting configuration to obtain lighting configuration information corresponding to each second lighting information; a lighting control strategy table is created based on the lighting configuration information corresponding to each second lighting information; a target lighting request sent by a second trigger command is received, the target lighting request is responded to, and a corresponding target control strategy is generated according to the lighting control strategy table; lighting control is performed on the target lighting request according to the target control strategy, and an image of the lighting area corresponding to the target lighting request is collected, and the image of the lighting area is transmitted to a preset lighting control platform. This invention improves the accuracy of lighting configuration by performing lighting configuration analysis through a deep learning lighting configuration model, and then performs lighting control on the target lighting request according to the target control strategy and collects an image of the lighting area corresponding to the target lighting request, thereby optimizing the lighting control strategy, realizing intelligent lighting control, and improving the accuracy of lighting control.

[0157] above Figure 5 and Figure 6 The deep learning-based lighting control device in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The deep learning-based lighting control device in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0158] Figure 7This is a schematic diagram of a deep learning-based lighting control device 600 provided in an embodiment of the present invention. The deep learning-based lighting control device 600 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) for storing application programs 633 or data 632. The memory 620 and storage media 630 can be temporary or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the deep learning-based lighting control device 600. Furthermore, the processor 610 may be configured to communicate with the storage media 630 and execute the series of instruction operations in the storage media 630 on the deep learning-based lighting control device 600.

[0159] The deep learning-based lighting control device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input / output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 7 The illustrated deep learning-based lighting control device structure does not constitute a limitation on deep learning-based lighting control devices, which may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0160] The present invention also provides a deep learning-based lighting control device, which includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor performs the steps of the deep learning-based lighting control method in the above embodiments.

[0161] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the deep learning-based lighting control method.

[0162] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0163] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0164] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A deep learning-based lighting control method, characterized in that, The deep learning-based lighting control method includes: Obtain the lighting control task carried by the first trigger command, and extract the task information from the lighting control task to obtain the corresponding first lighting information; The first lighting information is segmented to obtain multiple second lighting information; specifically, this includes: performing information identification analysis on the first lighting information to determine the target key identifier corresponding to the first lighting information; determining the task type corresponding to the first lighting information based on the target key identifier; obtaining the information segmentation pattern corresponding to the task type, and performing information segmentation on the first lighting information through the information segmentation pattern to obtain multiple second lighting information. The process involves inputting the multiple second lighting information entries into a preset lighting fixture configuration model for lighting fixture configuration, thereby obtaining lighting fixture configuration information corresponding to each second lighting information entry. Specifically, this includes: reading and analyzing the multiple second lighting information entries to determine the lighting fixture combination data corresponding to each second lighting information entry; inputting the lighting fixture combination data corresponding to each second lighting information entry into a preset lighting fixture configuration model, wherein the lighting fixture configuration model includes an embedded layer, a multi-layer threshold recurrent network, and a fully connected layer; and performing lighting fixture configuration analysis on the lighting fixture combination data through the lighting fixture configuration model to output the lighting fixture configuration information corresponding to each second lighting information entry. Create a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information; Receive the target lighting request sent by the second trigger command, respond to the target lighting request and generate a corresponding target control strategy according to the lighting control strategy table; The target lighting request is controlled according to the target control strategy, and the lighting area image corresponding to the target lighting request is acquired and transmitted to the preset lighting control platform.

2. The deep learning-based lighting control method according to claim 1, characterized in that, The step of obtaining the lighting control task carried by the first trigger command and extracting task information from the lighting control task to obtain the corresponding first lighting information includes: Read the lighting control task sent by the first trigger command and determine the task association data corresponding to the lighting control task; The task-related data is judged by its data volume. When the data volume of the task-related data is greater than a preset target value, the task-related data is prioritized and the first lighting information is generated. When the amount of data associated with the task is less than or equal to the target value, the task-associated data is converted to generate the first lighting information.

3. The deep learning-based lighting control method according to claim 1, characterized in that, The step of creating a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information includes: Encode the luminaire configuration information corresponding to each second lighting information to obtain the encoded data of each luminaire configuration information; The encoded data of each lighting fixture configuration information is sorted to obtain an encoded sequence; A lighting control strategy table corresponding to the lighting configuration information is created based on the encoded sequence.

4. The deep learning-based lighting control method according to claim 1, characterized in that, The step of controlling the lighting according to the target lighting request based on the target control strategy, acquiring an image of the lighting area corresponding to the target lighting request, and transmitting the lighting area image to a preset lighting control platform includes: The target control strategy is analyzed to determine the corresponding lighting control steps; The lighting control steps described above are used to control the lighting of the target lighting request. The image of the lighting area corresponding to the target lighting request is acquired and transmitted to the preset lighting control platform.

5. The deep learning-based lighting control method according to claim 1, characterized in that, The deep learning-based lighting control method also includes: The lighting control platform performs lighting analysis on the image of the lighting area to obtain the lighting analysis results; The target control strategy is optimized based on the lighting analysis results to generate an optimized lighting control scheme.

6. A lighting control device based on deep learning, characterized in that, The deep learning-based lighting control device includes: The acquisition module is used to acquire the lighting control task carried by the first trigger command, and extract the task information of the lighting control task to obtain the corresponding first lighting information. The processing module is used to perform information segmentation processing on the first lighting information to obtain multiple second lighting information; specifically, it includes: performing information identification analysis on the first lighting information to determine the target key identifier corresponding to the first lighting information; determining the task type corresponding to the first lighting information based on the target key identifier; obtaining the information segmentation mode corresponding to the task type, and performing information segmentation processing on the first lighting information through the information segmentation mode to obtain multiple second lighting information. The configuration module is used to input the plurality of second lighting information into a preset lighting configuration model for lighting configuration, thereby obtaining lighting configuration information corresponding to each second lighting information. Specifically, this includes: reading and analyzing the plurality of second lighting information to determine the lighting combination data corresponding to each second lighting information; inputting the lighting combination data corresponding to each second lighting information into the preset lighting configuration model, wherein the lighting configuration model includes: an embedded layer, a multi-layer threshold recurrent network, and a fully connected layer; and performing lighting configuration analysis on the lighting combination data through the lighting configuration model to output the lighting configuration information corresponding to each second lighting information. A module is created to generate a lighting control strategy table based on the luminaire configuration information corresponding to each second lighting information. The generation module is used to receive the target lighting request sent by the second triggering command, respond to the target lighting request, and generate a corresponding target control strategy according to the lighting control strategy table. The control module is used to control the lighting of the target lighting request according to the target control strategy, acquire the lighting area image corresponding to the target lighting request, and transmit the lighting area image to the preset lighting control platform.

7. A lighting control device based on deep learning, characterized in that, The deep learning-based lighting control device includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the deep learning-based lighting control device to execute the deep learning-based lighting control method as described in any one of claims 1-5.

8. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the deep learning-based lighting control method as described in any one of claims 1-5.

Images