Intelligent wearable device and voice-controlled lamp dimming method and system thereof

Abstract

The invention provides intelligent wearable equipment and a voice lamp control dimming method and system thereof, and belongs to the technical field of light control. Through networking configuration of the intelligent wearable device and the plurality of photoflood lamps, the photoflood lamps can accurately subscribe device message publishing, the stability and pertinence of lamp control instruction transmission are guaranteed, and the problem of signal interference or instruction mistransmission in a traditional lamp control mode is avoided. The target photography lamp to be dimmed can be accurately positioned by collecting the visual information of the lighting scene, generating the scene distribution information of the photography lamp and combining the recognition of the user voice signal and the semantic analysis extraction instruction, so that the problem of tedious screening of the target lamp in a multi-lamp scene is effectively solved, and the dimming accuracy is improved. The method is especially suitable for shooting scenes with complex lighting and a large number of lamps. Voice is used as a core control mode, visual positioning assistance is matched, operation does not need to be dependent on a traditional key console or a touch screen APP, and the lamp control process can be greatly simplified.

Description

Technical Field

[0001] This application relates to the field of lighting control technology, and in particular to a smart wearable device and its voice-controlled lighting dimming method and system. Background Technology

[0002] In the fields of photography and film production, lighting control is a core element in shaping the atmosphere of a scene, highlighting the subject, and enhancing visual expressiveness. Traditional lighting control methods mainly rely on physical button consoles or touchscreen apps, requiring photographers to manually adjust parameters such as brightness, color temperature, and lighting effects. While this approach is acceptable in static shooting scenarios, in dynamic shooting (such as tracking shots, multi-camera collaboration, or live broadcasts), photographers need to frequently switch between devices, leading to inefficiency, distraction, and disruption to the smoothness of the shoot. For example, in filmmaking, photographers must simultaneously adjust lighting and coordinate composition and actor movement; manual operation may delay crucial moments. Furthermore, in live broadcasts, quickly responding to audience interaction (such as real-time lighting adjustments) also presents a challenge.

[0003] In related technologies, voice control has been applied in the smart home field as an alternative, such as controlling light switches and basic dimming via voice assistants (like Alexa or Google Assistant). However, these solutions lack spatial awareness and cannot distinguish the specific light fixture the user intends to point to, leading to ambiguity in multi-light scenarios. Summary of the Invention

[0004] To address at least one of the aforementioned issues, this application provides a smart wearable device and its voice-controlled lighting dimming method and system. The aim is to collect visual information of the lighting scene and generate scene distribution information through the smart wearable device. Combined with voice recognition and semantic analysis, the target lighting fixture can be accurately located, enabling more convenient, accurate, and intelligent voice-controlled lighting control for photography, film and television shooting, and other scenarios.

[0005] According to one aspect of the embodiments of this application, a voice-controlled light dimming method is provided, applied to a smart wearable device, the method comprising:

[0006] The smart wearable device and multiple camera lights are networked together, enabling the multiple camera lights to subscribe to the message publication of the smart wearable device. The smart wearable device collects visual information of the lighting scene and generates scene distribution information of the multiple camera lights based on the visual information. The smart wearable device collects the user's voice signal and performs speech recognition and semantic parsing on the user's voice signal to extract user commands; The smart wearable device determines the target photography light to be dimmed based on the user's instructions and the scene distribution information of the multiple photography lights. The smart wearable device generates a corresponding dimming control command based on the user's instruction and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation.

[0007] In some embodiments, the scene distribution information includes a scene distribution map and / or a logical mapping relationship for characterizing the distribution information of the photography lights. Correspondingly, the smart wearable device collects visual information of the lighting scene and generates scene distribution information of the plurality of photography lights based on the visual information, including: The smart wearable device captures images of the current lighting scene to obtain scene images; The smart wearable device identifies the type of each camera light in the scene image and outputs a bounding box representing the position of the camera light; The smart wearable device generates a scene distribution map of each camera light and / or a logical mapping relationship to characterize the distribution information of the camera lights based on the depth information of the scene image and the bounding boxes corresponding to each camera light.

[0008] In some embodiments, the logical mapping relationship used to characterize the distribution information of the camera lights is a mapping relationship between each camera light and a set of position association parameters. The set of position association parameters includes the relative distance between the camera light and a scene reference point, the azimuth angle of the camera light relative to the scene reference point, the volume or shape estimation parameters of the camera light, the relative height of the camera light relative to the ground reference, or the angle of the optical axis of the camera light relative to the target being photographed.

[0009] In some embodiments, the smart wearable device identifies the types of various camera lights in the scene image, including: The smart wearable device determines the type of each photography light by recognizing the logos and / or QR code information on each photography light in the scene image; Alternatively, the smart wearable device can identify the type of each of the photography lights based on a pre-trained feature library that maps photography light types to shape and volume.

[0010] In some embodiments, after the smart wearable device generates a corresponding dimming control command based on the user instruction and sends the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation, the method further includes: The smart wearable device announces the result of the light adjustment operation through a voice broadcast module, and / or the smart wearable device displays the result of the light adjustment operation through a display module.

[0011] In some embodiments, the smart wearable device collects user voice signals and performs speech recognition and semantic parsing on the user voice signals to extract user commands, including: The smart wearable device collects the user's voice signal and converts the user's voice signal into text information through a local or cloud-based automatic speech recognition engine; The smart wearable device uses a natural language understanding module or a large model to perform semantic parsing on the text information in order to extract user instructions.

[0012] In some embodiments, the user instruction includes at least one user intent, which represents a light adjustment operation on one of the plurality of photographic lights.

[0013] In some embodiments, the lighting adjustment operation includes at least one of lighting brightness adjustment, lighting color temperature adjustment, lighting color adjustment, lighting focal length adjustment, lighting rotation, and lighting pitch angle adjustment.

[0014] In some embodiments, the smart wearable device generates a corresponding dimming control command based on the user instruction and sends the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation, including: The smart wearable device obtains target parameter adjustment information corresponding to the target photography light to be dimmed according to the user's instructions; The smart wearable device acquires the current values ​​of the target parameters of the target photography light; The smart wearable device calculates the target value of the target parameter corresponding to the target photography light based on the current value of the target parameter of the target photography light and the target parameter adjustment information; The smart wearable device generates a corresponding dimming control command based on the target value of the target parameter corresponding to the target photography light, and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation.

[0015] In some embodiments, the smart wearable device generates a corresponding dimming control command based on the user instruction and sends the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation, including: The smart wearable device obtains target parameter adjustment information corresponding to the target photography light to be dimmed according to the user's instructions; The smart wearable device generates a corresponding dimming control command based on the target parameter adjustment information corresponding to the target photography light, and sends the dimming control command to the target photography light, so that the target photography light calculates the target value of the target parameter corresponding to the target photography light based on the current value of the target parameter of the target photography light and the target parameter adjustment information, and performs corresponding light adjustment operation based on the target value of the target parameter.

[0016] In some embodiments, the smart wearable device pre-configures the light adjustment operation type, adjustment step size, and maximum adjustable value for each type of photographic light.

[0017] According to one aspect of the embodiments of this application, a smart wearable device is provided, comprising: A wireless communication module is provided, through which the smart wearable device communicates with each photographic light; An image acquisition module, used to acquire visual information about the lighting scene; A voice acquisition module, which is used to acquire user voice signals; The main control module is connected to the wireless communication module, the voice acquisition module, and the image acquisition module, respectively. The main control module is used to execute the method described in any embodiment of this application.

[0018] In some embodiments, the smart wearable device further includes: A voice broadcast module is connected to the main control module and is used to broadcast the results of the lighting adjustment operation. and / or a display module, the display module being connected to the main control module, the display module being used to display the result of the light adjustment operation.

[0019] In some embodiments, the smart wearable device further includes: An NFC module is connected to the main control module. When the smart wearable device approaches the photography light, the NFC module performs NFC communication and triggers the smart wearable device to establish a communication connection with the photography light.

[0020] According to one aspect of the embodiments of this application, a voice-controlled lighting dimming system is provided, comprising: The smart wearable device described in any embodiment of this application; Multiple photographic lights are connected in communication with the smart wearable device, wherein the smart wearable device is configured to send messages to the multiple photographic lights.

[0021] The technical solutions provided by the embodiments of this application have at least the following beneficial effects: The solution disclosed in this application, through the network configuration of smart wearable devices and multiple photography lights, enables the photography lights to accurately subscribe to device message releases, ensuring the stability and specificity of light control command transmission and avoiding the problems of signal interference or command mistransmission in traditional light control methods. By collecting visual information of the lighting scene and generating photography light scene distribution information, combined with the recognition of user voice signals and semantic parsing to extract commands, the target photography light to be dimmed can be accurately located, effectively solving the pain point of cumbersome target light selection in multi-light scenes, especially suitable for shooting and other scenes with complex lighting and a large number of lights. Using voice as the core control method, coupled with visual positioning assistance, there is no need to rely on traditional button consoles or touch screen APP operations, which can greatly simplify the light control process. Users can issue dimming commands in real time and conveniently during shooting. At the same time, based on the accurate matching of scene distribution information and semantic parsing, it ensures that the dimming control commands are highly consistent with the target lights and adjustment needs, improving the accuracy and efficiency of light adjustment, providing users with a more intelligent and flexible light control experience, and further optimizing the operation process and effect of shooting lighting.

[0022] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the principles of this application.

[0024] Figure 1 This is a schematic diagram of the architecture of a voice-controlled lighting dimming system provided in one embodiment of this application.

[0025] Figure 2 This is a first structural schematic block diagram of a smart wearable device provided in an embodiment of this application.

[0026] Figure 3 This is a schematic block diagram of the second structure of a smart wearable device provided in an embodiment of this application.

[0027] Figure 4 This is a structural diagram of a smart glasses provided in an embodiment of this application.

[0028] Figure 5 This is a structural diagram of another type of smart glasses provided in an embodiment of this application.

[0029] Figure 6 This is a flowchart of a voice-controlled light dimming method performed by a smart wearable device according to an embodiment of this application.

[0030] Figure 7This is a flowchart illustrating the steps of a smart wearable device, according to an embodiment of this application, to collect visual information of a lighting scene and generate scene distribution information of multiple camera lights based on the visual information.

[0031] Figure 8 This is a flowchart illustrating the steps of a smart wearable device according to an embodiment of the present application to collect user voice signals and perform speech recognition and semantic parsing on the user voice signals to extract user commands.

[0032] Figure 9 This is a flowchart illustrating the steps of a smart wearable device according to an embodiment of the present application to generate a corresponding dimming control command based on a user instruction and send the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation.

[0033] Figure 10 This is another step in the flowchart of an embodiment of the present application of a smart wearable device that generates a corresponding dimming control command according to a user instruction and sends the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation. Detailed Implementation

[0034] To make the objectives, implementation methods, and advantages of this application clearer, exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided to make the description of this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. It should be noted that the brief descriptions of terminology in this application are merely for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0035] In the description of this application, it should be understood that the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include one or more features.

[0036] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] In photography and film shooting, the dimming control of photography lights is a crucial aspect of ensuring shooting results. Traditional methods of dimming photography lights mainly rely on wired button control consoles or mobile device touch screen apps. Wired control consoles suffer from complex wiring and limited control range, making them unsuitable for scenarios with multiple lights distributed across the scene. Furthermore, operation requires the user to be close to the control console, interrupting the shooting process and impacting efficiency. Mobile apps, on the other hand, require the user to hold the device and operate it by touch, which can easily distract the user during shooting. It is also difficult to quickly and accurately locate the target light, especially in scenarios where multiple lights work together, requiring manual selection of light numbers or positions, which is cumbersome and prone to selection errors.

[0039] In related technologies, voice control has been applied in the smart home field as an alternative, such as controlling light switches and basic dimming via voice assistants (like Alexa or Google Assistant). However, these solutions lack spatial awareness and cannot distinguish the specific light fixture the user intends to point to, leading to ambiguity in multi-light scenarios.

[0040] Based on this, embodiments of this application provide a smart wearable device and its voice-controlled lighting dimming method and system. The smart wearable device collects visual information of the lighting scene and generates scene distribution information. Combined with voice recognition and semantic analysis, it can accurately locate target lighting fixtures, realizing more convenient, accurate and intelligent voice dimming control of photography lights in scenarios such as photography and film shooting.

[0041] Reference Figure 1 , Figure 1 This is a schematic diagram of the architecture of a voice-controlled lighting dimming system provided in one embodiment of this application. Figure 1 As shown, the voice-controlled lighting dimming system includes a smart wearable device 100 and multiple photographic lights 200. The multiple photographic lights 200 are wirelessly connected to the smart wearable device 100, which is configured to send messages to each of the photographic lights 200. Each photographic light 200 has a unique device identifier and is configured with a unicast address and / or a multicast address.

[0042] The smart wearable device 100 can wirelessly connect with each of the on-site photography lights 200. Specifically, the smart wearable device 100 can network with multiple on-site photography lights 200 through its built-in wireless communication module. This networking can be achieved through various standard communication protocols, such as Wi-Fi, Bluetooth, BLE, and other industry-known communication standard protocols. Alternatively, the smart wearable device 100 can network with each photography light 200 through the wireless communication module 110 using various proprietary / private communication protocols, such as wireless communication modules using frequency bands like 5.8GHz, 2.4GHz, 1.9GHz, and 1.4GHz, and implementing networking through custom protocols. In some embodiments, an intermediate device (such as a mobile phone) is used as a communication bridge to establish a communication connection between the smart wearable device 100 and the multiple photography lights 200. In some embodiments, the wireless communication module 110 can also employ various generations of mobile communication standard protocols such as 3G / 4G / 5G.

[0043] Specifically, in this embodiment, a smart wearable device 100 can be used as the master node of a Bluetooth Mesh network. A unicast address and / or multicast address can be configured for each photography light 200 with a unique device identifier to achieve multi-light networking. This supports both precise control of a single light and the need for coordinated control of multiple lights, adapting to the lighting requirements of complex shooting scenarios. Simultaneously, the smart wearable device 100 can collect visual information of the lighting scene and generate scene distribution information for multiple photography lights 200. Based on the scene distribution information and user voice commands, it can accurately locate target lights and generate corresponding dimming commands based on user voice commands, sending them to the corresponding target lights to drive them to perform corresponding light adjustment operations, achieving precise light adjustment.

[0044] It should be noted that in this embodiment, the network configurator can be the smart wearable device 100 (i.e., "the publisher also acts as the network configurator"), or it can be a device terminal (such as a mobile phone, tablet, computer, or other devices) with a corresponding application (APP) installed. In this case, the device terminal is only responsible for completing the network configuration of the photography light. After the configuration is completed, the core control authority of the network can be transferred to the smart wearable device 100, and it will no longer participate in subsequent light control command interactions. The core responsibility of the smart wearable device 100 as the "master node" is not limited to network configuration, but after the network is established, as the core message publisher in the network, it initiates and issues key commands: on the one hand, it obtains the status data of the photography light by scanning the Bluetooth signal strength (RSSI) to complete the target device location; on the other hand, it generates dimming control commands based on user voice commands and sends them to the target photography light through the BLE Mesh protocol stack (unicast address corresponds to a single light, multicast address corresponds to a group of lights) to drive the light adjustment operation. In other words, the "network configuration and access" and "control command issuance" of Bluetooth Mesh networking can be completed by different devices. The network configuration device is only responsible for the device to enter the network, while the smart wearable device 100, as the "master node", plays the role of "message publisher" and takes the lead in generating and issuing light control commands.

[0045] In some embodiments, the smart wearable device 100 can also establish a communication connection with the cloud, thereby uploading the collected user voice signals to the cloud, whereby the cloud performs voice recognition and semantic parsing to extract user intent or user instructions, and then sends the extracted user instructions to the smart wearable device 100.

[0046] Among them, the smart wearable device 100 includes headsets (or earphones, headphones), smart glasses, bracelets, watches, rings, helmets and other wearable or wearable devices. The specific form of the smart wearable device 100 is not specifically limited in the embodiments of this application.

[0047] As a controlled terminal, the Photography Light 200 possesses a unique device identifier (such as a MAC address or UUID) and can be equipped with a built-in communication module compatible with the wireless communication module of smart wearable devices to support wireless communication connections. During the network configuration phase, the Photography Light 200 is assigned a unicast address (for precise control of a single light) and / or a multicast address (for collaborative control of multiple lights in groups). Some models support NFC functionality for convenient "NFC-enabled light addition." The light source types for the Photography Light 200 can cover dual-color temperature LEDs, RGB LEDs, RGBW, RGBWW, etc., and product forms can include stick lights, board lights, COB lights, inflatable lights, cushion lights, flashes, etc., adapting to the lighting needs of different shooting scenarios. The photography light 200 can respond to commands issued by the smart wearable device, and realize multi-dimensional adjustment of brightness, color temperature, color, light focus, rotation / tilt angle, etc. It supports fixed value adjustment and step adjustment of default step size (such as 10%). Some can also realize special light effects such as dynamic light horse. It also has status feedback capability, which can synchronize the dimming result (success / failure) and current parameters to the smart wearable device 100.

[0048] Reference Figure 2 , Figure 2 This is a first structural schematic block diagram of a smart wearable device according to an embodiment of this application. The smart wearable device 100 includes a wireless communication module 110. The smart wearable device 100 can wirelessly connect with each of the on-site photography lights 200 through the wireless communication module 110.

[0049] The wireless communication module 110 is primarily responsible for establishing and maintaining stable wireless links with multiple photography lights 200. This module supports various network protocols and frequency bands to adapt to different connection requirements, power consumption, and bandwidth requirements in various scenarios. The smart wearable device 100 networks with the photography lights 200 through the wireless communication module 110, specifically through various standard communication protocols, such as Wi-Fi, Bluetooth, BLE, and other industry-known communication standard protocols.

[0050] The wireless communication module 110 can also be configured to support a specific single network protocol and frequency band, or it can be a wireless communication module including two or more protocols or frequency bands. For example, the wireless communication module 110 can simultaneously include a Bluetooth module and a 2.4GHz module working together. The Bluetooth module uses the standard Bluetooth protocol for communication, while the 2.4GHz module uses a custom protocol (non-standard) for communication. Through collaborative management and frequency hopping algorithms, it can automatically switch between the two communication modules to achieve optimal communication. As another example, the wireless communication module 110 can be a dual-band module, including communication modules for both 2.4GHz and 1.9GHz frequency bands. Communication between the two frequency bands can be switched through the frequency band management module of the protocol stack or a dynamic frequency selection algorithm to avoid current interference bands and improve call signal quality. The two frequency bands can also work together simultaneously, forming two parallel communication links, one link responsible for uplink data transmission and the other for downlink data transmission, or the transmission of a portion of the data required by the system can be pre-defined by one of the wireless modules.

[0051] The wireless communication module 110 can be fixed inside the circuit board of the smart wearable device 100, i.e., as standard built-in hardware at the factory, or the wireless communication module 110 can be installed in a pluggable / detachable manner on the dedicated wireless module interface of the smart wearable device 100. This design allows users to replace or upgrade the communication module according to the actual network environment, thus enhancing the adaptability and future compatibility of the device.

[0052] Specifically, the wireless communication module 110 can be a Bluetooth module, which supports wireless communication connection protocols. The smart wearable device can act as the master node of the Mesh network, initiating the networking process and establishing a stable wireless communication connection with each of the photographic lights 200 that has a unique device identifier (such as a MAC address or UUID) and is equipped with a Bluetooth module. During the network configuration phase, the wireless communication module 110 assigns a dedicated unicast address to each connected photographic light 200 (for precise single-light control), and also supports assigning multicast addresses to some photographic lights according to actual control needs (for multi-light group collaborative control). It also assists the smart wearable device 100 in maintaining a complete address mapping table, clearly associating the light ID of each photographic light 200 with its corresponding unicast / multicast address, ensuring orderly device management after networking. Furthermore, during subsequent light control, the wireless communication module 110 is also responsible for accurately sending the parsed BLE Mesh dimming control commands to the corresponding address of the target photographic light 200, ensuring the stability and timeliness of command transmission and laying the communication foundation for the smooth execution of the entire voice-controlled dimming process.

[0053] Reference Figure 2The smart wearable device 100 also includes a voice acquisition module 120, which is used to acquire user voice signals. The voice acquisition module 120 is the core input module for realizing voice-controlled lighting dimming functions. Its core component is a microphone array, which can accurately capture various voice commands issued by the user in scenarios such as photography and film shooting. Simultaneously, the voice acquisition module 120 also possesses powerful audio preprocessing capabilities. Through noise reduction, echo cancellation, and other technologies, it can effectively filter out interference factors such as ambient noise and equipment operating sounds at the shooting location, ensuring the purity and clarity of the acquired voice signals and laying a high-quality foundation for subsequent voice processing. The voice signals acquired by the voice acquisition module 120 can cover various types, including single-parameter commands (such as "adjust headlight brightness to 88%)" and multi-parameter composite commands (such as "increase headlight color temperature, decrease auxiliary light brightness, decrease background brightness"). The voice acquisition module 120 can also completely retain the speech features such as pauses in the user's speech, which is convenient for the subsequent ASR engine to recognize and convert into text signals with punctuation marks or segmentation marks. This helps the natural language understanding (NLU) module to accurately segment intent and parse key information (such as target device, control action, adjustment parameters and parameter values). It is a key bridge connecting user commands and device lighting operation, and provides core support for the smooth start of the entire voice lighting control process.

[0054] Reference Figure 2 The smart wearable device 100 also includes an image acquisition module 130, which is used to acquire visual information of the lighting scene. The image acquisition module 130 can integrate a high-definition camera (some devices can be equipped with a TOF module or binocular vision components). The camera has the ability to clearly capture various photographic lights in the lighting environment, and can capture visual features such as the appearance, model logo, and installation position of the lights. The TOF module or binocular vision components can be used to assist in acquiring depth information, improve the accuracy of the three-dimensional position recognition of the lights, and adapt to the lighting layout in different shooting scenarios (such as multiple lights scattered, close-range dense arrangement, etc.).

[0055] After the user wears the smart wearable device 100, the image acquisition module 130 can be activated to capture the current lighting scene by active triggering (such as the voice command "capture the lighting scene") or automatic triggering (default acquisition after network setup is completed). This captures RGB images containing all the photography lights, ensuring that the outlines of the lights in the images are clear and their features are identifiable, thus providing high-quality raw data for subsequent recognition.

[0056] The captured scene images are transmitted to the main control module of the smart wearable device (which can integrate an image processing unit). Using a preset recognition algorithm (such as a matching library based on the lamp's shape, 3D dimensions, and manufacturer model, or feature comparison using the model logo on the lamp), the key visual features of each lamp are extracted, enabling accurate identification of the lamp model and quantity. For example, it can distinguish between different models of photography lights such as the Godox MG4KR and P1200R, while simultaneously outputting the bounding boxes of all lamps to clearly define the position and range of each lamp in the image.

[0057] For scenarios requiring selection of target lights based on spatial relationships (such as "closest to me" or "far right"), the image acquisition module 130 can acquire depth information in two ways. First, it uses AI depth estimation models trained with MiDaS or DepthAnything to process the RGB image and output a depth map (pixel brightness represents distance; brighter pixels indicate closer proximity, darker pixels indicate farther distance). Second, if the smart wearable device supports dual cameras or multi-angle shooting, it can calculate more accurate relative distances through stereo matching and triangulation. Combining the depth information with the light fixture positions in the image, a distribution map of the lights in the scene is generated, clearly defining the spatial relationships such as relative distances and azimuth angles (e.g., light 1 azimuth angle 0°, light 3 azimuth angle 45°). Absolutely precise depth or angle data is not required; only the need to distinguish the relative positions of the lights is needed.

[0058] It should be noted that the visual information (lamp model, quantity, relative position, azimuth angle, etc.) acquired and processed by the image acquisition module 130 is associated with the device address mapping table (lamp ID-unicast address / multicast address) of the network (such as Bluetooth mesh networking) and the user commands parsed by voice recognition. When the user issues commands such as "turn up the brightness of the nearest lamp" or "turn down the color temperature of the rightmost lamp", the system can accurately match the corresponding target lamp ID and control address based on the visual information provided by the image acquisition module 130, providing a key basis for the generation and transmission of dimming control commands and ensuring the accuracy of voice control.

[0059] Reference Figure 2The smart wearable device 100 also includes a main control module 140. The wireless communication module 110, voice acquisition module 120, and image acquisition module 130 are connected to the main control module 140. The main control module 140 may be a main processor with integrated Bluetooth functionality. The main control module 140 is used to perform voice recognition and semantic analysis on the user's voice signal acquired by the voice acquisition module 120 to extract user commands. Simultaneously, the main control module 140 is also used to process the visual information of the lighting scene acquired by the image acquisition module 130, review the scene distribution information of multiple camera lights, and, based on the user commands and the scene distribution information of multiple camera lights, determine the target camera light to be dimmed. Then, it generates a corresponding dimming control command based on the user commands and sends the dimming control command to the target camera light through the wireless communication module 110 to drive the target camera light to perform the corresponding lighting adjustment operation. This completes the voice dimming control of the camera lights within the shooting scene.

[0060] Reference Figure 3 , Figure 3 This is a schematic block diagram of the second structure of a smart wearable device provided in an embodiment of this application. Figure 3 As shown, the smart wearable device 100 may also include an NFC module 150. The NFC module 150 is connected to the main control module 140. When the smart wearable device 100 is close to the photography light 200, the NFC module 150 performs NFC communication and triggers the smart wearable device 100 to establish a communication connection with the photography light 200.

[0061] The NFC module 150 serves as a convenient auxiliary module for wireless communication connections. It establishes a connection with and is managed by the main control module 140, its core function being to simplify the network access process for the photography light 200. When a user brings the smart wearable device 100 close to the NFC-enabled photography light 200, the NFC module 150 quickly establishes near-field communication with the corresponding NFC component of the photography light 200, automatically completing device authentication (based on the photography light's unique device identifier, such as MAC address or UUID), and triggering the main control module 140 to initiate the wireless communication connection process, eliminating the need for complex manual pairing operations by the user. During communication, the NFC module 150 assists in transmitting basic device information of the photography light (such as model and supported control parameters) to the main control module 140, providing data support for the main control module 140 to quickly allocate unicast and / or multicast addresses for the photography light and update the address mapping table. This significantly shortens network setup time, improves device access efficiency in multi-light lighting scenarios, allows users to more easily build a lighting control system, and further enhances the ease of use of voice-controlled lighting via smart wearable devices.

[0062] Reference Figure 3The smart wearable device may also include a voice broadcast module 160. The voice broadcast module 160 is connected to the main control module 140 and is used to announce the results of the lighting adjustment operation. After the main control module 140 completes the dimming command and receives feedback from the target camera light, it synchronizes the dimming result (success or failure) and key information to the voice broadcast module 160. This module uses text-to-speech (TTS) technology to convert text information into natural speech for broadcast. Specifically, if the dimming is successful, the voice broadcast module 160 will accurately announce the operation details. For example, if the user command is "Adjust the brightness of the nearest light to me to 80%", the voice broadcast module 160 can announce "The brightness of the nearest light to me has been adjusted to 80%". If it is a step adjustment (such as "Increase brightness"), the voice broadcast module 160 can announce the corresponding state after the step adjustment. If dimming fails (e.g., signal timeout, lamp offline, lamp does not support this parameter adjustment), the voice broadcast module 160 can promptly broadcast fault prompts, such as "Adjustment failed, please check if the lamp is online" or "This lamp does not support color temperature adjustment," helping users quickly locate the problem. The voice broadcast module 160's voice is clear, concise, and highly recognizable, adaptable to complex shooting environments, ensuring users can know the lighting control results in real time without viewing the display interface, further enhancing the convenience and interactive experience of voice-controlled lighting, making the entire lighting control process more intuitive and efficient.

[0063] Reference Figure 3 The smart wearable device may also include a display module 170. The display module 170 is connected to the main control module 140 and is used to display the results of the lighting adjustment operation. The display module 170 can be used to intuitively present the relevant results of the lighting adjustment operation, providing visual feedback to the user and forming a dual feedback mechanism with the voice broadcast module 160.

[0064] After the main control module 140 completes the issuance of the dimming command and the reception of the result, it will synchronize information such as the dimming status and key parameters to the display module 170. Specifically, if dimming is successful, the display module 170 can clearly display a dimming success prompt message, and can also sequentially or cyclically display the specific parameters of the target lamp (or lamp group) after dimming, such as "the rightmost lamp currently has a color temperature of 4100K", allowing users to accurately grasp the current working status of the lamp. If dimming fails (such as signal timeout, lamp offline, lamp not supporting the corresponding parameter adjustment), the display module 170 will display a fault prompt message, such as "adjustment failed, please check if the lamp is online" or "this lamp does not support color temperature adjustment", to help users quickly troubleshoot the problem. The display module 170 features a simple, clear, and highly recognizable interface that is compatible with wearable devices such as smart glasses. Users can obtain information directly through their eyes without any additional operation. Especially in noisy shooting environments where it is inconvenient to rely on voice broadcasts, it can effectively ensure that users know the lighting control results in a timely manner, further improving the convenience, intuitiveness, and reliability of voice-controlled lighting.

[0065] Reference Figure 4 and Figure 5 , Figure 4 This is a structural diagram of a smart glasses embodiment provided in this application. Figure 5 This is a structural diagram of another type of smart glasses provided in one embodiment of this application. This application uses smart glasses as an example of a smart wearable device 100 for detailed description. The smart glasses include a display lens 1 (used to present dimming results, lighting parameters, and fault prompts), an integrated microphone 2 (or microphone array, used to collect voice signals and perform noise reduction and echo cancellation preprocessing), a speaker 3 (used to broadcast dimming results and fault prompts), and a charging port 4 (to ensure device battery life). The smart glasses also include a main processor 5 with integrated Bluetooth (i.e., the aforementioned main control module 140) and a camera 6 (used for taking pictures). All hardware components are compactly arranged within the smart glasses body, satisfying both wearability convenience and supporting the entire process of operation from networking, command acquisition and parsing to lighting control feedback through collaborative work.

[0066] Reference Figure 6 , Figure 6 This is a flowchart of a voice-controlled light dimming method performed by a smart wearable device according to an embodiment of this application. The smart wearable device can be any of the smart wearable devices provided in any embodiment of this application. The method includes, but is not limited to, steps S610 to S650.

[0067] Step S610: Configure the smart wearable device and multiple camera lights to form a network, so that the multiple camera lights can subscribe to the message publication of the smart wearable device.

[0068] In this step, the smart wearable device 100 and multiple photography lights 200 are first configured to form a network, enabling the multiple photography lights 200 to subscribe to the message broadcasts from the smart wearable device 100. Specifically, the smart wearable device 100 can first establish a wireless communication connection with the multiple photography lights 200 through its built-in wireless communication module. For example, the smart wearable device 100 (such as smart glasses, smart helmets, smart vests, etc.) can act as the master node of the Bluetooth Mesh network to initiate the networking process and establish a stable wireless connection with multiple photography lights 200 on site that have unique device identifiers (such as MAC addresses or UUIDs). During the networking process, "NFC adding lights" can be achieved through the NFC module, which simplifies the connection operation of the photography lights 200. During the network configuration phase, the smart wearable device 100 assigns a dedicated unicast address to each connected camera light 200 (for precise control of a single light). It also supports assigning multicast addresses to some camera lights 200 based on the needs of multi-light group collaborative control (such as grouping multiple background lights into one group and assigning a unified multicast address). Simultaneously, it maintains a complete address mapping table, clearly associating the light ID of each camera light 200 with the corresponding unicast / multicast address. At the same time, it can build and store the device capability model of each camera light during this phase (recording supported control parameters such as brightness, color temperature, color, etc.), laying the foundation for subsequent precise light control, command parsing, and device matching, ensuring that each camera light can be managed and controlled in an orderly manner after network configuration.

[0069] In step S620, the smart wearable device collects visual information of the lighting scene and generates scene distribution information of multiple camera lights based on the visual information.

[0070] In this step, the smart wearable device can first trigger visual information acquisition through its integrated camera (which can be paired with a TOF module or binocular vision components). This acquisition supports automatic acquisition after network setup is complete, and can also be actively triggered by the user via voice commands or physical buttons. First, high-definition RGB images of the lighting scene are acquired (clearly capturing the appearance, model, logo, and other features of all the photography lights) along with raw depth data. Then, the acquired RGB images can undergo preprocessing such as noise reduction and contrast enhancement, and the raw depth data can be calibrated and filtered to remove outliers. Next, using a pre-set light fixture recognition library (containing the manufacturer, model, corresponding shape, size, and logo features), image recognition algorithms can identify the number and specific models of the photography lights in the scene. Simultaneously, image segmentation algorithms can extract the outline and bounding box coordinates of each light fixture, clarifying its position within the image. Then, depth maps (where pixel brightness represents relative distance) can be generated by processing RGB images using AI depth estimation models (such as MiDaS and Depth Anything). Alternatively, more precise relative distances can be calculated using stereo matching and triangulation methods based on multi-angle images from dual cameras. Combining this with the position coordinates of the lights in the image, the relative distance order and azimuth angle of each light (based on the user's field of vision center) are determined, quantifying the spatial relationships between the lights. Finally, information such as the number of lights, model, relative distance, azimuth angle, and bounding box coordinates are integrated and linked to the address mapping table (light ID - unicast address / multicast address) maintained during the Bluetooth mesh networking phase to generate a structured scene distribution information table and store it in a local cache. This scene distribution information can be synchronized to semantic parsing and target matching, and supports real-time updates when adding lights or adjusting light positions, providing accurate data support for subsequent target light positioning.

[0071] Specifically, refer to Figure 7 , Figure 7 This is a flowchart of the steps of a smart wearable device according to an embodiment of the present application to collect visual information of a lighting scene and generate scene distribution information of multiple camera lights based on the visual information, including but not limited to steps S710 to S730.

[0072] Step S710: The smart wearable device takes a picture of the current lighting scene to obtain a scene image; Step S720: The smart wearable device identifies the type of each camera light in the scene image and outputs a bounding box representing the position of the camera light. In step S730, the smart wearable device generates a scene distribution map of each camera light and / or a logical mapping relationship to characterize the distribution information of the camera lights, based on the depth information of the scene image and the bounding boxes corresponding to each camera light.

[0073] In this embodiment, the scene distribution information includes a scene distribution map and / or a logical mapping relationship used to characterize the distribution information of the lighting lights. The scene distribution map is a visual / structured image-like data representation of the lighting scene, which intuitively presents the spatial arrangement of all lighting lights without requiring absolute coordinates, only specifying their relative positions. Its generation logic is as follows: combining the bounding boxes (two-dimensional positions) of each lighting light with depth information (three-dimensional distance) to construct a three-dimensional scene model, marking the outline, type, relative distance, and approximate location of each light fixture (e.g., "the panel light is on the left, closest, and the COB light is on the right, farther away"). This scene distribution map provides an intuitive basis for interpreting spatial commands such as "closest to me" and "farthest right," helping the system quickly locate the range of candidate lighting fixtures.

[0074] The logical mapping relationship used to characterize the distribution information of photographic lights is the mapping relationship between each photographic light and a set of position-related parameters. This logical mapping relationship is a digital key-value pair data system. The core is to assign a unique identifier (such as a light ID) to each photographic light and establish a mapping between this identifier and "a set of position-related parameters" to realize the calculability of distribution information, which can be quickly accessed and analyzed by smart wearable devices. The set of position-related parameters may include the relative distance between the photographic light and a scene reference point, the azimuth angle of the photographic light relative to the scene reference point, the volume or shape estimation parameters of the photographic light, the relative height of the photographic light relative to the ground reference, or the angle of the optical axis of the photographic light relative to the target being photographed. The scene reference point can be centered on the user's smart wearable device by default (i.e., the user's position), or it can be customized as the target being photographed, a fixed point on the ground, etc. The relative distance between the photographic light and the scene reference point can be obtained through depth information calculation, without requiring absolute physical distance, only needing to meet the requirement of "distinguishing the relative distance of each light" (e.g., "light 1 relative distance 1.8m, light 2 relative distance 2.5m"), supporting filtering commands such as "closest to me" and "farthest light". The azimuth angle of the camera light relative to the scene reference point is calculated clockwise / counterclockwise from the center of the reference point's field of view (e.g., directly in front of the user) at 0° (e.g., "Light 1 azimuth 0° (directly in front), Light 2 azimuth 320° (left rear), Light 3 azimuth 45° (right front)"). This is the core basis for interpreting azimuth commands such as "the rightmost light" and "the left rear light". The volume or shape estimation parameters of the camera light can be extracted through image recognition to determine its outline and size features, estimating its volume (e.g., "length 60cm, width 15cm") or shape type (e.g., "long strip, round, flat"), which can help distinguish between similar-looking lights (e.g., "the largest stick light"). The relative height of the camera light relative to the ground reference is based on the scene ground, obtaining the light height value through visual detection or preset configuration (e.g., "Light 1 height 2.2m, Light 4 height 1.3m"), adapting to dimming commands such as "high-altitude light" and "ground light". In the angle between the optical axis of a photographic light and the target being photographed, the optical axis is the center line of the light emission of the light fixture. The angle between the optical axis and the target can be obtained through image analysis or sensor detection (such as "the optical axis of light 2 is 30° with the target (oblique beam), the optical axis of light 5 is 0° with the target (direct beam)"). This can support precise dimming commands such as "warming the color temperature of the light directly shining on the target".

[0075] In this embodiment, the smart wearable device can first initiate lighting scene shooting through the integrated image acquisition module (high-definition camera, which can be paired with a TOF module or binocular vision components) to obtain a complete and clear RGB image covering all the photography lights. Two shooting triggering methods are supported: one is automatic triggering after network setup is complete, ensuring the integrity of the initial lighting scene information; the other is active triggering by the user through voice commands (such as "shoot lighting scene") or physical buttons, adapting to the information update needs after the light fixture positions are adjusted.

[0076] Next, the smart wearable device can perform targeted processing on the collected scene images to complete the "type recognition" and "position calibration" processing. Specifically, the smart wearable device can perform feature matching through image recognition algorithms based on a preset lamp recognition library (containing data such as the shape, three-dimensional size, logo features, and type attributes of different manufacturers and models of photographic lamps). There are two recognition methods: (1) Direct recognition: By recognizing the logo and / or QR code information on each photographic lamp in the scene image, the type of each photographic lamp can be determined. For example, the type of the lamp can be matched by the model logo on the surface of the lamp (such as Godox MG4KR, P1200R) (such as stick lamp, board lamp, COB lamp, flash lamp, etc.); (2) Indirect recognition: Based on the feature library of photographic lamp type and shape-volume mapping pre-trained, the type of each photographic lamp can be identified. For example, for lamps without obvious logos, their type can be determined by comparing the shape outline, three-dimensional size and recognition library data (such as long strip corresponding to stick lamp, flat shape corresponding to board lamp). Meanwhile, smart wearable devices can use image segmentation algorithms to extract the outline of each identified camera light, generate corresponding bounding boxes (represented by image pixel coordinates), and clarify the two-dimensional position range of each light in the scene image.

[0077] Finally, the smart wearable device can combine the depth information of the scene image with the bounding boxes of each camera light, and through data integration and calculation, generate a scene distribution map and / or logical mapping relationship, completing the transformation from the original image to structured distribution information. Among them, the depth information can be calculated in two ways: (1) AI model estimation: input the RGB image into the trained depth estimation model (such as MiDaS, Depth Anything), and output a depth map (pixel brightness represents relative distance, the brighter the image, the closer it is to the user, and the darker the image, the farther away it is); (2) stereo matching calculation: if the smart wearable device supports dual cameras or multi-angle shooting, the image can be stereo matched by triangulation to obtain more accurate relative depth data. The embodiments of this application are based on the bounding box of each camera light, extract the depth information of the area where it is located, and combine the type of light fixture and the position coordinates to generate an intuitive scene distribution map (visually presenting the relative position and distance relationship of each light fixture) or construct a structured logical mapping relationship (establishing a one-to-one correspondence between the light fixture and the position associated parameters). Specifically, the two types of information can be output separately or in combination according to the actual lighting control needs.

[0078] In step S630, the smart wearable device collects the user's voice signal and performs speech recognition and semantic parsing on the user's voice signal to extract user commands.

[0079] In this step, the smart wearable device 100 can collect the user's voice signal for controlling the lights in the shooting scene through its built-in microphone array. After collection, it first performs preprocessing such as noise reduction and echo cancellation to filter environmental interference and improve signal purity. Then, it calls the local or cloud-based ASR (speech recognition) engine, combines acoustic and language models for decoding, and converts the voice signal into a text signal. It can also recognize pauses in the user's speech and automatically insert punctuation marks or segmentation marks (e.g., converting "increase the color temperature of the leftmost light and decrease the brightness of the rightmost light" into "increase the color temperature of the leftmost light and decrease the brightness of the rightmost light"). Finally, it uses natural language processing to... The Natural Language Understanding (NLU) module or large model performs semantic parsing on text signals. On the one hand, it segments the complex text to extract multiple independent instruction intents. On the other hand, it extracts key information for each intent, including target device selection conditions (such as "leftmost", "rightmost", etc.), control actions (adjust up, adjust down, adjust to), adjustment parameters (brightness, color temperature, color, focus, etc.) and parameter values ​​(such as 88%, default step size 10%). It also supports the parsing of synonyms such as "warming up" and "cooling down" and the decomposition of complex multi-parameter instructions. Finally, it forms clear and executable user instructions, providing a basis for subsequent target lamp determination and dimming control instruction generation.

[0080] The user instructions include at least one user intent, which represents a lighting adjustment operation for one of a plurality of photography lights. Each user intent explicitly targets a specific lighting adjustment operation for one (or a group of) photography lights in a Bluetooth Mesh network. Specifically, the smart wearable device first collects the user's spoken language for controlling the lights through a microphone array (i.e., the voice acquisition module). After noise reduction and echo cancellation preprocessing, the language is converted into text signals by a local or cloud-based ASR engine. During this process, pauses in the user's spoken language are identified and punctuation marks (such as commas and periods) are inserted to provide a basis for intent segmentation. Subsequently, the Natural Language Understanding (NLU) module parses the text, first segmenting the complex text containing multiple lighting control requests into independent user intents (e.g., the user's voice "increase the color temperature of the leftmost light, decrease the brightness of the leftmost light" can be segmented into two intents: "increase the color temperature of the leftmost light" and "decrease the brightness of the leftmost light"). Each intent revolves around a single adjustment target. The target device selection for these intents relies on the generated scene distribution map of each camera light or the logical mapping relationship representing the distribution information of camera lights, accurately locking onto the corresponding single or group of camera lights. Each intent also fully includes control actions (adjust up, adjust down, adjust to, etc.), adjustment parameters (brightness, color temperature, color, light focus, etc.) and parameter values ​​(such as specific percentages, default 10% steps). It supports the parsing of synonyms such as "warming up" and "cooling down" and verifies whether the target light supports the corresponding adjustment parameters through the device capability model, ensuring that each intent can drive the target camera light to perform effective light adjustment operations, adapting to the diverse single or group light control needs in the shooting scene, and achieving precise binding of semantic tags and light control intents.

[0081] Lighting adjustment operations include at least one of the following: brightness adjustment, color temperature adjustment, color adjustment, focus adjustment, rotation adjustment, and tilt angle adjustment. Brightness adjustment supports both fixed numerical adjustments (e.g., to 80%) and preset step adjustments (e.g., 10%). Mesh models commonly use a range of 0-255 or 0-100% to quantize brightness values. Color temperature adjustment supports precise adjustments based on synonyms such as "warmer," "warmer" (corresponding to a decrease in color temperature), "cooler," and "cooler" (corresponding to an increase in color temperature). Color adjustment is compatible with various light sources such as dual-color temperature LEDs, RGB LEDs, RGBW, and RGBWW, and some also support special lighting effects modes such as dynamic color light effects. Focus, rotation, and tilt angle adjustments can be implemented mechanically or electronically based on user voice commands to meet the lighting angle and focus requirements of different shooting scenarios. These adjustments can be triggered by single-parameter or multi-parameter composite voice commands, which are then analyzed by smart wearable devices to generate corresponding control signals that drive the target lighting precisely.

[0082] Specifically, refer to Figure 8 , Figure 8 This application provides a flowchart of the steps for a smart wearable device to collect user voice signals and perform speech recognition and semantic parsing on the user voice signals to extract user instructions, including but not limited to steps S810 to S820.

[0083] Step S810: The smart wearable device collects the user's voice signal and converts the user's voice signal into text information through a local or cloud-based automatic speech recognition engine. In step S820, the smart wearable device performs semantic parsing of the text information through a natural language understanding module or a large model to extract user instructions.

[0084] In this embodiment, the smart wearable device 100 can accurately collect the user's voice signals for controlling lights in scenarios such as photography and film shooting through its built-in microphone array. These signals can cover various types, including single-parameter commands (such as "adjust the brightness of the leftmost light to 88%)" and multi-parameter composite commands (such as "increase the color temperature of the leftmost light and decrease the brightness of the rightmost light"). After collection, the device first performs preprocessing on the voice signal, such as noise reduction and echo cancellation, to effectively filter out interference factors such as ambient noise and equipment operating sounds at the shooting location, ensuring signal purity. Subsequently, the smart wearable device 100 can call upon a local or cloud-based Automatic Speech Recognition (ASR) engine, combining an acoustic model and a language model for decoding. The acoustic model is responsible for determining the optimal phoneme sequence that generates the acoustic features of the speech, while the language model, based on massive amounts of text training results, selects the most grammatically and semantically reasonable word sequence, ultimately converting the speech signal into text information. During this process, the engine can recognize pauses in the user's spoken language and automatically insert punctuation marks (such as commas and periods) or segmentation marks. For example, it can convert speech text without punctuation into "turn up the color temperature of the headlights and turn down the brightness of the taillights", providing a clear foundation for subsequent semantic parsing and intent segmentation.

[0085] Next, the smart wearable device 100 can perform deep analysis of the text information converted in step S810 through its built-in Natural Language Understanding (NLU) module or large model. First, intent segmentation is performed. For complex text containing multiple light control requirements, independent instruction intents are extracted (e.g., splitting the complex text into two sub-intents: "Increase the color temperature of the leftmost light" and "Decrease the brightness of the rightmost light"). Then, according to preset parsing rules, key elements of each sub-intent are extracted, including target device selection conditions (e.g., "rightmost," "leftmost," etc.), control actions (e.g., "increase to," "increase," "decrease"), adjustment parameters (e.g., brightness, color temperature, color, light focus, light rotation / tilt angle, etc.), and parameter values ​​(e.g., 88%, default step size 10%). During the parsing process, synonym conversion (e.g., "warm up," "increase" is parsed as "decrease color temperature," "cool down," "cool down" is parsed as "increase color temperature") and complex multi-parameter instruction splitting are also supported. Simultaneously, combined with the device capability model defined in the network configuration phase, parameter adaptability is verified (e.g., determining whether the light fixture supports color temperature adjustment). Finally, the analysis results are integrated into clear and executable user instructions, providing a precise basis for subsequent target luminaire determination, dimming parameter calculation, and control instruction generation.

[0086] In step S640, the smart wearable device determines the target camera light to be dimmed based on the user's instructions and the scene distribution information of multiple camera lights.

[0087] In this step, after the smart wearable device completes user voice signal acquisition, preprocessing, ASR conversion, and NLU semantic parsing, it can first extract at least one user intent from the extracted user commands, clarifying the target device filtering conditions (such as semantic keywords like "leftmost" and "rightmost"), control actions, and adjustment parameters contained in each intent. Then, the filtering conditions in the semantic parsing results are aligned with the parameter dimensions (such as relative distance values ​​and azimuth angles) in the scene distribution information. For example, "closest to me" is mapped to "minimum relative distance (MIN)," and "rightmost" is mapped to "maximum value within the azimuth angle range of 0°-90°." After the format alignment, the target camera light to be dimmed is selected. Specifically, if the command is "the nearest light," the system extracts the relative distance parameters of all camera lights from the logical mapping relationship and filters out the light ID corresponding to the minimum distance. If the command is "the rightmost light," the system uses the user's field of vision center as the reference 0° and filters out the light ID with the largest azimuth angle within the range of 0°-90°. If the command is "the light to the left rear," the system filters out lights with an azimuth angle within the range of 270°-360° to ensure that the spatial positioning is consistent with the user's intuitive perception. For characteristic commands such as "P1200R model light," "long bar light," and "largest COB light," filtering can be achieved by combining the light model and shape / volume estimation parameters in the scene distribution information. For example, the model specified in the command (such as P1200R, GodoxMG4KR) can be directly matched through the "light ID-model" mapping table in the logical mapping relationship. For shape feature descriptions such as "long bar" and "largest volume," the shape estimation parameters (such as "long bar" or "flat") or volume values ​​of the light can be called to filter out light IDs that meet the characteristics.

[0088] In some embodiments, after filtering candidate light IDs, the position and relative relationship of the candidate light IDs can be verified a second time by combining scene distribution information to avoid positioning deviations caused by parameter errors. For example, if the filtered "nearest light" is actually located behind the user in the scene distribution map, which is consistent with the intuitive perception of "closest to me", the light ID is confirmed as a valid target. If the position of the candidate light in the distribution map is obviously contradictory to the instruction description (such as the filtered "rightmost light" actually being located on the left), the filtering is retried or the user is prompted to confirm the instruction. If only one light ID meets the conditions after filtering and verification, the light is directly determined as the target to be dimmed, and its corresponding unicast address is associated with it from the address mapping table (for individual control). If the instruction is a group control or a multi-device instruction (such as "turn on the leftmost light and the rightmost light simultaneously"), the multiple filtered light IDs are integrated into a target device set, associated with their corresponding multicast addresses (for synchronous control), and it is ensured that all lights in the set support the control actions in the instruction. If no matching light fixture is found after filtering (e.g., the "far right" but there are no lights in the 0°-90° range in the scene), the system will mark it as "no target device" and prepare a prompt message for the subsequent feedback process (e.g., "No matching light fixture found, please check the lighting scene").

[0089] In step S650, the smart wearable device generates a corresponding dimming control command based on the user's instruction and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation.

[0090] In this step, after identifying the target camera light to be dimmed, the smart wearable device 100 can perform precise calculations of the dimming parameters based on the user instructions extracted through semantic parsing (including key information such as control actions, adjustment parameters, and parameter values). Specifically, if the instruction is a "adjust to a specified value" type (such as "adjust brightness to 80%)", the adjusted parameter value can be obtained by multiplying the maximum brightness value by a specified ratio according to the brightness quantization range commonly used in Mesh models of 0-255 or 0-100%. If the instruction is a "adjust up" or "adjust down" type step adjustment instruction (such as "adjust brightness up"), the current parameter status of the target camera light can be obtained through Mesh status query or local cache, and the target parameter value can be calculated by combining it with a preset adjustment step size (such as 10%). At the same time, it can verify whether the target camera light supports the adjustment parameter (such as determining whether the lamp supports color temperature adjustment). Subsequently, based on the calculated target parameter value and the unicast address (or multicast address) corresponding to the target camera light, a dimming control instruction conforming to the communication protocol (such as the BLE Mesh protocol) specification can be constructed. Finally, the smart wearable device uses its built-in wireless communication module to precisely send the control command to the target photography light, thereby driving the target photography light to perform corresponding lighting adjustment operations such as brightness, color temperature, color, light focus, rotation or tilt angle, completing the closed-loop control from command generation to execution.

[0091] Specifically, refer to Figure 9 , Figure 9 This application provides a flowchart of the steps of a smart wearable device generating a corresponding dimming control command according to a user instruction and sending the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation, including but not limited to steps S910 to S940.

[0092] In step S910, the smart wearable device obtains the target parameter adjustment information corresponding to the target photography light to be dimmed according to the user's instructions.

[0093] In this step, after completing voice recognition and semantic analysis, the smart wearable device 100 can accurately filter out the target parameter adjustment information corresponding to the target photographic light to be dimmed from the extracted user commands. This target parameter adjustment information covers core control elements: first, control actions, including types such as "adjust to," "adjust up," and "adjust down." If it is color temperature adjustment, it also includes the action logic corresponding to synonyms such as "warm up" and "cool down" ("warm up" corresponds to a decrease in color temperature value, and "cool down" corresponds to an increase in color temperature value); second, adjustment parameters, specifying specific adjustment dimensions such as brightness, color temperature, color, light focus, and the rotation or tilt angle of the light; and third, associated parameter values. For commands like "adjust to," it includes specific values ​​(e.g., 88%), while commands like "adjust up" and "adjust down" correspond to preset adjustment steps (e.g., 10%). For complex multi-parameter commands, they have been broken down into single sets of adjustment information during the semantic analysis stage to ensure that the content obtained in this step accurately corresponds to a single adjustment requirement.

[0094] Step S920: The smart wearable device acquires the current value of the target parameters of the target photography light.

[0095] In this step, the smart wearable device 100 can obtain the current values ​​of the adjustment parameters corresponding to the target photography light in two ways: first, by sending a status query command to the target photography light through the wireless communication module to obtain its current parameter data in real time; second, by directly calling the historical parameter information of the photography light stored in the local cache (this cache will be updated synchronously after each dimming to ensure data timeliness). The obtained current values ​​need to be compatible with parameter quantification standards. For example, the brightness value needs to correspond to the 0-255 or 0-100% range commonly used in Mesh models to provide a unified data foundation for subsequent calculations. At the same time, if the target parameter is an adjustment dimension not supported by the device capability model (such as the color adjustment of white light fixtures), it will be identified and marked synchronously at this stage to prepare for subsequent feedback of fault information.

[0096] In step S930, the smart wearable device calculates the target value of the target parameter corresponding to the target photography light based on the current value of the target parameter and the target parameter adjustment information.

[0097] In this step, the smart wearable device 100 calculates the target value according to the current value of the target parameter and the target parameter adjustment information, following the corresponding rules. Specifically, for a "raise to" type of instruction, the specific value in the instruction can be directly used as the target value (brightness needs to be converted according to the quantization range, such as converting 80% to the corresponding value in the 0-255 range); for a "raise" or "lower" type of step adjustment instruction, the current value is used as the base, and a preset step size is added or subtracted (e.g., if the current brightness is 50%, after raising it by 10%, the target value is 60%), ensuring that the adjustment range meets the user's expectations. During the calculation process, it will check whether the target value is within the maximum adjustable range of the parameter to avoid exceeding the device's adjustment limits. If it exceeds the limits, the maximum or minimum value will be automatically used as the target value.

[0098] In step S940, the smart wearable device generates a corresponding dimming control command based on the target value of the target parameter corresponding to the target photography light, and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation.

[0099] In this step, the smart wearable device 100 combines the calculated target value of the target parameter with the unicast address (or multicast address, for group control scenarios) of the target lighting light to construct a dimming control command conforming to the communication protocol (such as the BLE Mesh protocol), clearly defining the recipient and execution standard of the command. Subsequently, the control command is precisely sent to the target lighting light via its built-in wireless communication module. Upon receiving the command, the target lighting light performs the corresponding light adjustment operation to ensure the parameters are adjusted to the target value. If the adjustment fails (e.g., signal timeout, device offline), it will report the fault information to the smart wearable device, which will then notify the user via voice or display.

[0100] In some embodiments, refer to Figure 10 , Figure 10 This is a flowchart of another step of the smart wearable device provided in one embodiment of the present application, which generates a corresponding dimming control command according to the user's instruction and sends the dimming control command to the target photography light to drive the target photography light to perform a corresponding light adjustment operation, including but not limited to steps S1010 to S1020.

[0101] Step S1010: The smart wearable device obtains the target parameter adjustment information corresponding to the target photography light to be dimmed according to the user's instructions; In step S1020, the smart wearable device generates a corresponding dimming control command based on the target parameter adjustment information of the target photography light, and sends the dimming control command to the target photography light so that the target photography light calculates the target value of the target parameter corresponding to the target photography light based on the current value of the target parameter and the target parameter adjustment information, and performs the corresponding light adjustment operation based on the target value of the target parameter.

[0102] In this embodiment, after completing voice recognition and semantic parsing, the smart wearable device 100 can accurately extract the target parameter adjustment information corresponding to the target photography light to be dimmed from the extracted user commands. Next, based on the target parameter adjustment information obtained in step S910, the smart wearable device 100, combined with the unicast address (or multicast address, for group control scenarios) of the target photography light, constructs a dimming control command conforming to a communication protocol (such as the BLE Mesh protocol). The command clearly includes key information such as control actions, adjustment parameters, and associated parameter values, but does not need to carry the current and target values ​​of the parameters. Subsequently, the smart wearable device 100 can accurately send the control command to the target photography light through its built-in wireless communication module. After receiving the command, the target photography light first calls its own stored target parameter current value (or obtains the real-time current value through device status self-check), and then calculates the target value according to preset rules and the adjustment information in the command. Specifically, for commands like "increase to," the target light directly uses the specific value in the command as the target value (brightness must be compatible with the quantization range of the Mesh model, which is 0-255 or 0-100%). For step commands like "increase" or "decrease," the target light uses the current value as a base, adding or subtracting a preset step size to calculate the target value. During the calculation, it checks whether the target value is within its maximum adjustable range to avoid exceeding the device's adjustment limits. Finally, based on the calculated target parameter values, the target light executes the corresponding light adjustment operation, completing precise adjustments to dimensions such as brightness, color temperature, and color. If signal abnormalities or parameters exceeding the range occur during the adjustment process, the target light will report fault information to the smart wearable device 100, which will then inform the user via voice broadcast or display module (e.g., "Adjustment failed, please check if the light is online"). Understandably, smart wearable devices can pre-configure the light adjustment operation type, adjustment step size, and maximum adjustable value for each type of photographic light. Specifically, the smart wearable device 100 can target different types of photographic lights, such as stick lights, board lights, COB lights, gas lights, and flashes, based on their light source characteristics (e.g., dual-color temperature LED, RGB). Standardized configurations are pre-completed for LED, RGBW, RGBWW, and other supported control channels. Specifically, this includes configuring corresponding light adjustment operation types (such as basic brightness adjustment, color temperature adjustment for dual-color temperature lights, color adjustment for RGB series lights, and focal length, rotation, and tilt angle adjustment for lights with mechanical functions) according to the hardware capabilities of each type of photography light. Adjustment step sizes are preset for each adjustment type to adapt to the characteristics of the device (such as a default step size of 10% for brightness and color temperature adjustment, and a reasonable step size preset according to the mechanical precision of the device) and the maximum adjustable value range is configured according to the hardware parameter limits of each type of photography light (such as brightness following the quantization standard of 0-255 or 0-100% of the Mesh model, color temperature preset with upper and lower limits according to the actual coverage of the device, and angle adjustment with the physical limits of the mechanical structure as the boundary). These configurations are associated with the device identifier of each type of photography light and stored locally. They can be automatically matched and called after subsequent networking to ensure that the dimming operation is accurate, efficient, and in line with the characteristics of the device.

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0104] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0105] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0106] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0107] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

Claims

1. A voice-controlled light dimming method, characterized in that, Applied to smart wearable devices, the method includes: The smart wearable device and multiple camera lights are networked together, enabling the multiple camera lights to subscribe to the message publication of the smart wearable device. The smart wearable device collects visual information of the lighting scene and generates scene distribution information of the multiple camera lights based on the visual information. The smart wearable device collects the user's voice signal and performs speech recognition and semantic parsing on the user's voice signal to extract user commands; The smart wearable device determines the target photography light to be dimmed based on the user's instructions and the scene distribution information of the multiple photography lights. The smart wearable device generates a corresponding dimming control command based on the user's instruction and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation.

2. The method according to claim 1, characterized in that, The scene distribution information includes a scene distribution map and / or a logical mapping relationship used to characterize the distribution information of the photography lights. Correspondingly, the smart wearable device collects visual information of the lighting scene and generates scene distribution information of the multiple photography lights based on the visual information, including: The smart wearable device captures images of the current lighting scene to obtain scene images; The smart wearable device identifies the type of each camera light in the scene image and outputs a bounding box representing the position of the camera light; The smart wearable device generates a scene distribution map of each camera light and / or a logical mapping relationship to characterize the distribution information of the camera lights based on the depth information of the scene image and the bounding boxes corresponding to each camera light.

3. The method according to claim 2, characterized in that, The logical mapping relationship used to characterize the distribution information of the photography lights is the mapping relationship between each photography light and a set of position association parameters. The set of position association parameters includes the relative distance between the photography light and the scene reference point, the azimuth angle of the photography light relative to the scene reference point, the volume or shape estimation parameters of the photography light, the relative height of the photography light relative to the ground reference, or the angle of the optical axis of the photography light relative to the target being photographed.

4. The method according to claim 2, characterized in that, The smart wearable device identifies the types of various photography lights in the scene image, including: The smart wearable device determines the type of each photography light by recognizing the logos and / or QR code information on each photography light in the scene image; Alternatively, the smart wearable device can identify the type of each of the photography lights based on a pre-trained feature library that maps photography light types to shape and volume.

5. The method according to claim 1, characterized in that, After the smart wearable device generates a corresponding dimming control command based on the user instruction and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation, the method further includes: The smart wearable device announces the result of the light adjustment operation through a voice broadcast module, and / or the smart wearable device displays the result of the light adjustment operation through a display module.

6. The method according to claim 1, characterized in that, The smart wearable device collects the user's voice signal and performs speech recognition and semantic parsing on the user's voice signal to extract user commands, including: The smart wearable device collects the user's voice signal and converts the user's voice signal into text information through a local or cloud-based automatic speech recognition engine; The smart wearable device uses a natural language understanding module or a large model to perform semantic parsing on the text information in order to extract user instructions.

7. The method according to claim 1 or 6, characterized in that, The user instructions include at least one user intent, which represents a lighting adjustment operation on one of the plurality of camera lights.

8. The method according to claim 1 or 7, characterized in that, The lighting adjustment operation includes at least one of the following: lighting brightness adjustment, lighting color temperature adjustment, lighting color adjustment, lighting focal length adjustment, lighting rotation, and lighting tilt angle adjustment.

9. The method according to claim 1, characterized in that, The smart wearable device generates a corresponding dimming control command based on the user instruction, and sends the dimming control command to the target photography light to drive the target photography light to perform corresponding light adjustment operations, including: The smart wearable device obtains target parameter adjustment information corresponding to the target photography light to be dimmed according to the user's instructions; The smart wearable device acquires the current values ​​of the target parameters of the target photography light; The smart wearable device calculates the target value of the target parameter corresponding to the target photography light based on the current value of the target parameter of the target photography light and the target parameter adjustment information; The smart wearable device generates a corresponding dimming control command based on the target value of the target parameter corresponding to the target photography light, and sends the dimming control command to the target photography light to drive the target photography light to perform the corresponding light adjustment operation.

10. The method according to claim 1, characterized in that, The smart wearable device generates a corresponding dimming control command based on the user instruction, and sends the dimming control command to the target photography light to drive the target photography light to perform corresponding light adjustment operations, including: The smart wearable device obtains target parameter adjustment information corresponding to the target photography light to be dimmed according to the user's instructions; The smart wearable device generates a corresponding dimming control command based on the target parameter adjustment information corresponding to the target photography light, and sends the dimming control command to the target photography light, so that the target photography light calculates the target value of the target parameter corresponding to the target photography light based on the current value of the target parameter of the target photography light and the target parameter adjustment information, and performs corresponding light adjustment operation based on the target value of the target parameter.

11. The method according to claim 1, characterized in that, The method further includes: The smart wearable device pre-configures the lighting adjustment operation type, adjustment step size, and maximum adjustable value for each type of photographic light.

12. A smart wearable device, characterized in that, include: A wireless communication module is provided, through which the smart wearable device communicates with each photographic light; An image acquisition module, used to acquire visual information about the lighting scene; A voice acquisition module, which is used to acquire user voice signals; The main control module is connected to the wireless communication module, the voice acquisition module, and the image acquisition module, respectively, and the main control module is used to execute the method according to any one of claims 1-11.

13. The smart wearable device according to claim 12, characterized in that, The smart wearable device also includes: A voice broadcast module, which is connected to the main control module, is used to broadcast the results of the lighting adjustment operation; and / or a display module, the display module being connected to the main control module, the display module being used to display the result of the light adjustment operation.

14. The smart wearable device according to claim 12, characterized in that, The smart wearable device also includes: An NFC module is connected to the main control module. When the smart wearable device approaches the photography light, the NFC module performs NFC communication and triggers the smart wearable device to establish a communication connection with the photography light.

15. A voice-controlled lighting dimming system, characterized in that, include: The smart wearable device according to any one of claims 12-14; Multiple photographic lights are connected to the smart wearable device, wherein the smart wearable device is configured to send messages to the multiple photographic lights.

Images