Light atmosphere regulation method, light control system and electronic device

Abstract

The application provides a light atmosphere regulation method, a light control system and an electronic device. The method comprises: acquiring light atmosphere guide information and basic configuration information of a smart light device cluster located in a target regulation area; the light atmosphere guide information is described in natural language; based on a generative artificial intelligence model, taking the light atmosphere guide information and the basic configuration information as inputs, a matching experience scheme of a target light atmosphere suitable for the target regulation area is generated; the matching experience scheme comprises: light atmosphere physical configuration parameters corresponding to a device control surface, and light atmosphere semantic description text corresponding to an audio-visual broadcast surface; a light control instruction is generated based on the light atmosphere physical configuration parameters, and the light control instruction is sent to the smart light device cluster to control the smart light device cluster to present the target light atmosphere; and the light atmosphere semantic description text is presented to a user to enable the user to obtain complete audio-visual experience.

Description

Technical Field

[0001] This application mainly relates to the field of intelligent lighting technology, and in particular to a lighting atmosphere control method, a lighting control system, and electronic equipment. Background Technology

[0002] Existing smart lighting devices largely rely on preset scene libraries or limited keyword triggering effects. For example, users pre-configure the required scene parameters for "reading mode," and the smart lighting device can then call these parameters to reproduce the lighting atmosphere required for that "reading mode." However, this approach results in a fixed response from the smart lighting device, making it unable to generate more diverse lighting atmospheres based on real-time context or personalized user needs. Furthermore, existing technologies generally lack semantic descriptions of lighting atmospheres, failing to provide users with a more diverse sensory experience and resulting in a poor immersive experience. Summary of the Invention

[0003] The purpose of this invention is to provide a lighting atmosphere control method, a lighting control system, and an electronic device to solve the problems of fixed response effects and lack of semantic description of lighting atmosphere in the prior art.

[0004] In a first aspect, this application provides a method for controlling lighting atmosphere, comprising: Acquire lighting atmosphere guidance information and basic configuration information of a cluster of intelligent lighting devices located in the target control area; the lighting atmosphere guidance information is described in natural language; the basic configuration information includes the physical attributes and protocol specifications of each intelligent lighting device in the intelligent lighting device cluster. Based on a generative artificial intelligence model, using the lighting atmosphere guidance information and the basic configuration information as input, a matching experience scheme for the target lighting atmosphere adapted to the target control area is generated; wherein, the matching experience scheme includes: physical configuration parameters of the lighting atmosphere corresponding to the device control surface, and semantic description text of the lighting atmosphere corresponding to the audiovisual broadcast surface; Based on the physical configuration parameters of the lighting atmosphere, a lighting control command is generated and sent to the intelligent lighting device cluster to control the intelligent lighting device cluster to present the target lighting atmosphere; and, The semantic description of the lighting atmosphere is presented to the user so that the user can have a complete audiovisual experience.

[0005] In some embodiments, the generative artificial intelligence model is trained through a reinforcement learning phase to acquire the semantic understanding and structured generation capability to map the lighting atmosphere guidance information and the basic configuration information into the supporting experience scheme; The reinforcement learning phase includes a reward function and a value function. The reward function is used to predict the comprehensive evaluation effect of different model outputs, and the value function is used to predict the long-term aesthetic value of different model outputs. The model outputs include the physical configuration parameters of the lighting atmosphere and the semantic description text of the lighting atmosphere.

[0006] In some embodiments, the reward function consists of any or a combination of the following components: A semantic alignment reward is used to provide positive feedback to the model training process based on the correlation between the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere. The consistency reward is used to provide positive feedback to the model training process based on the degree of consistency of multiple model outputs; The physical constraint penalty term is used to provide negative feedback to the model training process when the color temperature and color feature values ​​are outside the reasonable range; Human factors lighting rewards are used to provide positive feedback during model training based on the degree of matching between brightness and color temperature.

[0007] In some embodiments, the value function is a weighted sum of long-term cumulative reward and semantic entropy; the semantic entropy is calculated based on a diversity function, the probability distribution of all possible color temperature combinations, and a value coefficient.

[0008] In some embodiments, generating the lighting control command based on the physical configuration parameters of the lighting atmosphere includes: The color ratio required for the target lighting atmosphere is determined from the physical configuration parameters of the lighting atmosphere; Color boundaries are generated based on the color ratio and cumulative distribution function; The visual abrupt changes in the color boundary are corrected using a linear interpolation method based on spline functions to obtain the target color space; Mapping the target color space to the cluster of smart lighting devices yields the target color feature value for each smart lighting device; and... The lighting control command is generated based on the target color feature value, brightness, and color temperature of each smart lighting device.

[0009] In some embodiments, the cumulative distribution function is obtained by normalizing the multidimensional fusion result; The multi-dimensional fusion result is composed of the color ratio, spatial preference function, and temperature coefficient, and the multi-dimensional fusion result is directly proportional to the color ratio and the spatial preference function, and inversely proportional to the temperature coefficient.

[0010] In some embodiments, it also includes: The diurnal rhythm deviation and energy efficiency of the intelligent lighting equipment cluster applied to the target lighting atmosphere were statistically analyzed. Based on the diurnal rhythm deviation, the energy efficiency, and the semantic matching degree of the semantic description text of the lighting atmosphere relative to the target lighting atmosphere, a comprehensive evaluation score for the target lighting atmosphere is obtained; and, Record the overall evaluation score.

[0011] In a second aspect, this application provides a lighting control system, comprising: Internet of Things (IoT) devices are used to collect user input information in real time; A cloud server, communicatively connected to the IoT device, is used to perform the method as described in any one of the first aspects; and, The intelligent lighting equipment cluster communicates with the cloud server and the IoT device to present the target lighting atmosphere according to the received lighting control instructions.

[0012] In a third aspect, an electronic device is provided. The electronic device includes: one or more processors; and one or more memories coupled to the one or more processors and storing instructions thereon. When the instructions are executed individually or jointly by the one or more processors, the electronic device performs the methods described above.

[0013] In a fourth aspect, a non-transitory computer-readable storage medium is provided that stores machine-executable instructions. When executed by one or more processors of a machine, the machine-executable instructions cause the machine to perform any of the methods described above.

[0014] The beneficial effects of this application's embodiments are as follows: By introducing a generative artificial intelligence model, personalized lighting atmospheres can be generated autonomously without requiring users to preset any scene, thus lowering the barrier to entry; a closed loop of user experience is completed on the device control surface and audiovisual broadcast surface, enabling users to have an immersive experience and aesthetic atmosphere perception; the required control area is decoupled from the user's real environment, allowing users to customize and select the target control area they need, and realizing the collaborative control of intelligent lighting device clusters within the area; based on the physical configuration parameters of the lighting atmosphere, the gradual change requirement of the lighting range is met, thereby effectively improving the user's sensory experience.

[0015] It should be understood that the summary section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0016] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of some embodiments thereof in the accompanying drawings, in which: Figure 1 This is a schematic diagram of a typical application scenario of the lighting atmosphere control method in the embodiments of this application; Figure 2 This is a flowchart of the lighting atmosphere control method provided in the embodiments of this application; Figure 3 This is a logical diagram of an exemplary instance of a lighting atmosphere control method; Figure 4 This is a simplified block diagram of an electronic device suitable for implementing exemplary embodiments of the present disclosure. Detailed Implementation

[0017] The principles of this disclosure will now be described with reference to some embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and implementing this disclosure, and do not impose any limitation on the scope of this disclosure. The disclosure described herein may be implemented in ways other than those described below.

[0018] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0019] References to "an embodiment," "embodiment," "exemplary embodiment," etc., in this disclosure indicate that the described embodiments may include specific features, structures, or characteristics, but not every embodiment needs to include specific features, structures, or characteristics. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when a specific feature, structure, or characteristic is described in connection with an exemplary embodiment, whether explicitly described or not, those skilled in the art will recognize that such a feature, structure, or characteristic affects its connection to other embodiments.

[0020] It should be understood that while the terms “first” and “second”, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term “and / or” as used herein includes any and all combinations of one or more of the listed terms.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. The singular forms “a,” “an,” and “the” used herein also include the plural forms unless the context clearly indicates otherwise. The terms “a group of elements” or “a collection of elements” as used herein are intended to include one or more elements. It should also be understood that the terms “comprising,” “including,” “having,” “possessing,” “including,” and / or “comprising,” when used herein, specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0022] Generative artificial intelligence models (LLMs) refer to large language models that possess contextual understanding and structured output capabilities.

[0023] Structured IoT commands refer to structured control commands for specific smart lighting devices, which typically include device ID, actions (on / off / dimming / color adjustment), parameters (RGB values, color temperature, brightness), etc.

[0024] The lighting atmosphere control method in this application embodiment can be applied to home or commercial scenarios, such as home theaters, music parties, and exhibitions. The typical application scenario below uses a home environment as an example; its beneficial effect is that it enables users to have an immersive experience and aesthetic atmosphere perception, thereby effectively enhancing the user's sensory experience.

[0025] Figure 1 This is a schematic diagram illustrating a typical application scenario of the lighting atmosphere control method in the embodiments of this application. For example... Figure 1 As shown, IoT device 10 communicates with cloud server 20, and smart lighting device cluster 30 communicates with both cloud server 20 and IoT device 10. When lighting atmosphere adjustment is needed, the user can open the built-in client (such as an APP) in IoT device 10, so that the client can collect lighting atmosphere guidance information and target control area information (such as area ID) in real time in the current scene. The lighting atmosphere guidance information is described in natural language, and the information type can be voice or text. For example, the user can verbally say, "Give me an aurora feel." The target control area can be one or more specific areas in the home specified by the user (such as a combination of the living room and dining room), or it can default to the area where smart lighting device cluster 30 is located. After real-time data collection, IoT device 10 sends the collected lighting atmosphere guidance information and target control area information to cloud server 20 for further processing.

[0026] The cloud server 20 stores metadata and generative artificial intelligence models of all smart lighting devices in the user's home. Specifically, after receiving lighting atmosphere guidance information and area information of the target control area, the cloud server 20 queries the metadata based on the area information to retrieve the basic configuration information of the smart lighting device cluster located in the target control area, including the physical attributes and protocol specifications of each smart lighting device in the smart lighting device cluster.

[0027] Physical attributes include device ID, supported functions, actions (such as on / off, dimming, color adjustment), location, and range of function parameters (such as color temperature range, RGB value range). Protocol specifications include WiFi protocol, etc.

[0028] The IoT device 10 in this embodiment may include mobile terminals such as mobile phones and tablets, or non-mobile terminals such as smart TVs and desktop computers. The cloud server 20 may include distributed servers, etc. For ease of description, the IoT device 10 in the following embodiments is exemplified as a mobile terminal, and the cloud server 20 is exemplified as a distributed server.

[0029] Figure 2 This is a flowchart of a lighting atmosphere control method provided in an embodiment of this application. In this embodiment, the cloud server 20 can serve as the execution entity of the lighting atmosphere control method, which includes: S201, Obtain lighting atmosphere guidance information and basic configuration information of the cluster of intelligent lighting devices located in the target control area.

[0030] Specifically, the lighting atmosphere guidance information is described using natural language. For example, a user could verbally say, "Give me an aurora feel." Physical attributes include device ID, supported functions, location, and range of function parameters (such as color temperature range and RGB value range). Protocol specifications include Wi-Fi protocols.

[0031] S202, based on a generative artificial intelligence model, takes lighting atmosphere guidance information and basic configuration information as input to generate a matching experience scheme for the target lighting atmosphere that is adapted to the target control area.

[0032] Specifically, the supporting experience solution includes: physical configuration parameters of the lighting atmosphere corresponding to the device control surface, and semantic description text of the lighting atmosphere corresponding to the audiovisual broadcast surface.

[0033] The device control interface reflects the control requirements of the intelligent lighting equipment cluster, enabling hardware control of the cluster through physical configuration parameters of the lighting atmosphere. The audiovisual broadcast interface reflects the user's audiovisual broadcast requirements, providing user-facing audiovisual broadcasts through semantic descriptions of the lighting atmosphere. These semantic descriptions include the lighting atmosphere name and explanatory text, with no restrictions on their content.

[0034] By combining the device control panel with the audiovisual broadcast panel, users can not only have a good visual experience—seeing the range of lights—but also a corresponding auditory experience (such as hearing narration), thereby further enhancing the sense of immersion.

[0035] Generative AI models are typically not usable from the outset. They can only be used after being trained through reinforcement learning to acquire the semantic understanding and structured generation capabilities to map lighting and ambient guidance information and basic configuration information into matching experience solutions.

[0036] The reinforcement learning phase includes a reward function and a value function. The reward function is used to predict the comprehensive evaluation effect of different model outputs, and the value function is used to predict the long-term aesthetic value of different model outputs. The model outputs include physical configuration parameters of the lighting atmosphere and semantic description text of the lighting atmosphere.

[0037] The reward function of a generative artificial intelligence model consists of any or a combination of the following components: The semantic alignment reward is used to provide positive feedback to the model training process based on the correlation between the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere.

[0038] The consistency reward is used to provide positive feedback to the model training process based on the degree of consistency of multiple model outputs.

[0039] The physical constraint penalty term is used to provide negative feedback to the model training process when the color temperature and color feature values ​​are outside the reasonable range.

[0040] Human factors lighting rewards are used to provide positive feedback during model training based on the degree of matching between brightness and color temperature.

[0041] As an example, the reward function may include a semantic alignment reward, a consistency reward, a physical constraint penalty, and a human factors lighting reward, and the expression for the reward function is as follows:

[0042] R=w1R semantic +w2R human +w3R consistency +w4R constraint

[0043] Where R represents the reward function value, and w1, w2, w3, and w4 represent weighting coefficients. semantic R human R consistency R constraint These represent semantic alignment reward, human factors lighting reward, consistency reward, and physical constraint penalty, respectively.

[0044] In the semantic alignment reward item, the correlation between the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere can be described using cosine similarity. For example, after converting the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere into vector representations, the cosine similarity between the two vectors is calculated to measure the correlation between the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere. The expression for this semantic alignment reward item is as follows: R semantic =cos(Vector(Action Description),Vector(Scene Name)) Where Vector(Action Description) and Vector(Scene Name) are vector representations of the physical configuration parameters of the lighting atmosphere and the semantic description text of the lighting atmosphere, respectively, and cos(.) represents the cosine similarity.

[0045] In the human factors lighting reward category, the degree of matching between brightness and color temperature can be calculated using the Krusov curve. The Krusov curve reflects the specific matching range between brightness and color temperature that provides comfortable lighting, thereby avoiding a cold and gloomy scene characterized by "high color temperature + extremely low brightness." The expression for this human factors lighting reward category is as follows: R human =exp( ) in, This represents the ideal median luminance at a given color temperature. The standard deviation of brightness is represented by L, the current brightness value is represented by exp(.), and the natural exponential function is represented by exp(.).

[0046] In the physical constraint penalty item, different reasonable ranges can be set for color temperature and color feature values. For example, the reasonable range for color temperature can be 2700K-5700K. When the color temperature exceeds the reasonable range, negative feedback should be given. The reasonable range for color feature values ​​(such as RGB values) can be ≤70%. When the color feature values ​​exceed the reasonable range, it will lead to excessive saturation, and therefore negative feedback should be given.

[0047] In the consistency reward item, the difference between the model state and the reference state during the current model training process can be calculated, and appropriate negative feedback can be given to the difference. For example, the larger the difference, the greater the negative feedback. When the difference is less than a preset threshold, appropriate positive feedback can also be given to the model training process, thereby ensuring the robustness of the model.

[0048] Furthermore, the value function of the generative artificial intelligence model is a weighted sum of long-term cumulative reward and semantic entropy; the semantic entropy is calculated based on the diversity function, the probability distribution of all possible color temperature combinations, and the value coefficient.

[0049] As an example, the expression for this value function is as follows: V innovative (s)=V(s)+ . H (LLM Output Distribution) Among them, V innovative Let V(s) represent the value function, and V(s) represent the long-term cumulative reward. β.H (LLM OutputDistribution) represents semantic entropy, and LLM Output Distribution represents the probability distribution of all possible color temperature combinations. This represents the value coefficient.

[0050] The beneficial effect of semantic entropy is that it can prevent the model from getting stuck in local optima (such as only recommending a color temperature of 3000K), thereby encouraging the model to explore more artistic lighting combinations (such as the warm and cool contrast between RGB ambient light and the main light) while satisfying the basic lighting logic, thus improving the diversity of supporting experience solutions.

[0051] S203 generates a lighting control command based on the physical configuration parameters of the lighting atmosphere and sends the lighting control command to the intelligent lighting device cluster to control the intelligent lighting device cluster to present the target lighting atmosphere.

[0052] The lighting control command refers to a structured IoT command set for all smart lighting devices in the smart lighting device cluster, and this structured IoT command set has been converted into a communication protocol (such as MQTT) that the smart lighting devices can receive.

[0053] The cloud server can send corresponding structured IoT commands to the smart lighting device step by step according to the lighting control command, so as to control the smart lighting device to display the specified color temperature, brightness and color characteristic values ​​(such as RGB values).

[0054] When the target lighting range is gradient, the generative artificial intelligence model can usually output the color ratio required for the target lighting atmosphere (such as the ratio of primary, secondary, and accent colors), and then calculate the target color feature value of each smart lighting device based on the color ratio.

[0055] In some embodiments, generating lighting control commands based on physical configuration parameters of the lighting atmosphere includes: Step 1: Determine the required color ratio for the target lighting atmosphere from the physical configuration parameters of the lighting atmosphere.

[0056] Step 2: Generate color boundaries based on color ratio and cumulative distribution function.

[0057] Step 3: Correct visual abrupt changes in color boundaries using a linear interpolation method based on spline functions to obtain the RGB color space.

[0058] Step 4: Map the target color space to the cluster of smart lighting devices to obtain the RGB values ​​of each smart lighting device.

[0059] Step 5: Generate lighting control instructions based on the target color feature values, brightness, and color temperature of each smart lighting device.

[0060] The beneficial effect of the above methods is that they allow the color gradient within the target light range to blend naturally, avoiding visual abrupt changes and thus providing users with a more aesthetically pleasing visual experience.

[0061] In some embodiments, the cumulative distribution function is obtained by normalizing the multi-dimensional fusion result; wherein the multi-dimensional fusion result consists of color ratio, spatial preference function, and temperature coefficient, and the multi-dimensional fusion result is directly proportional to the color ratio and spatial preference function, and inversely proportional to the temperature coefficient. The expression for the cumulative distribution function is as follows: P(x) = Softmax( ) Where P(x) represents the cumulative distribution function, and Softmax(.) represents the normalization function. This indicates the result of multi-dimensional fusion. Indicates color proportions. Represents the spatial preference function, This represents the temperature coefficient.

[0062] S204 presents the semantic description text of the lighting atmosphere to the user so that the user can have a complete audiovisual experience.

[0063] The semantic description text of the lighting atmosphere can be presented in two ways: voice broadcast (e.g., via voice modules in IoT devices or smart lighting devices) or text display (e.g., via an app interface). Furthermore, when a cluster of smart lighting devices presents the target lighting atmosphere, users can choose whether to simultaneously display the semantic description text of that atmosphere via IoT devices, thus meeting their personalized needs.

[0064] Furthermore, this method for controlling the lighting atmosphere may also include: Step 6: Analyze the diurnal rhythm deviation and energy efficiency of the intelligent lighting equipment cluster application in the target lighting atmosphere.

[0065] Step 7: Based on the semantic matching degree of the text describing the circadian rhythm deviation, energy efficiency, and lighting atmosphere relative to the target lighting atmosphere, obtain the comprehensive evaluation score of the target lighting atmosphere.

[0066] Step 8: Record the comprehensive evaluation score for subsequent model optimization.

[0067] As an example, the expression for this comprehensive evaluation score is as follows: Score =αSim( Emb text , Emb params )-η| CT target - CT biological |-λEnergy(L) in, Score This represents the overall evaluation score. Emb text , Emb params Sim( represents the vectorized representation of the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere, respectively.) Emb text , Emb params ) represents the semantic matching degree, | CT target - CT biological | represents the diurnal rhythm deviation, Energy(L) represents energy efficiency, and α, η, and λ represent weighting coefficients. 。

[0068] The overall evaluation score can be combined with user satisfaction with the target lighting atmosphere for subsequent model optimization. This overall evaluation score can be calculated and recorded by a cloud server, or it can be calculated by an IoT device and then uploaded to the cloud server.

[0069] Figure 3 This is a logical diagram illustrating an exemplary instance of a lighting atmosphere control method. For example... Figure 3 At 12:00, the user selects the "living room + dining room" as the target control area through the client built into the IoT device, and simultaneously speaks the lighting atmosphere guidance message: "Give me an aurora feeling." The cloud server then receives this information from the IoT device and executes the steps of the aforementioned lighting atmosphere control method. Then, at 12:05, the cloud server generates a corresponding experience plan and controls the cluster of smart lighting devices located in the user's "living room + dining room" to present the target lighting atmosphere according to the plan. At this time, the IoT device simultaneously plays the voice prompt: "Aurora environment, using a mix of cool emerald green, ice blue, and violet...", providing the user with a complete audiovisual experience.

[0070] In summary, the beneficial effects of this lighting atmosphere control method are as follows: by introducing a generative artificial intelligence model, it can autonomously generate personalized lighting atmospheres without requiring users to preset any specific scenarios, thus lowering the barrier to entry; it completes a closed loop of user experience across the device control and audiovisual broadcasting aspects, enabling users to enjoy an immersive experience and aesthetic atmosphere perception; it decouples the required control area from the user's real environment, allowing users to customize and select the target control area, and achieves collaborative control of a cluster of intelligent lighting devices within the area; and it satisfies the gradual change requirement of the lighting range based on the physical configuration parameters of the lighting atmosphere, thereby effectively enhancing the user's sensory experience.

[0071] Furthermore, this embodiment also provides a lighting control system. The implementation principle and technical effects of this lighting control system are the same as those in the aforementioned method embodiments. Specifically, the lighting control system includes IoT devices, a cloud server, and a smart lighting device cluster. The IoT devices are communicatively connected to the cloud server, and the cloud server and IoT devices are communicatively connected to the smart lighting device cluster. The cloud server can act as the execution entity to perform the corresponding content as described in the aforementioned method embodiments. For ease of description and brevity, the specific working process of the cloud server executing the lighting atmosphere control method can be referred to the corresponding process in the above method embodiments, and will not be repeated here.

[0072] Furthermore, such as Figure 4 An exemplary embodiment of this application also provides an electronic device including one or more memories 401 and one or more processors 402, wherein the one or more memories 401 are coupled to and store instructions thereon on the one or more processors 402, the instructions being executable individually or jointly by the one or more processors 402, causing the electronic device to perform the method as described in any of the first aspects.

[0073] It should be understood that the processor mentioned in the embodiments of this application can be a CPU, or other general-purpose processors, DSPs, ASICs, FPGAs, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0074] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronous linked dynamic random access memory, and direct memory bus random access memory.

[0075] This application also provides a non-transitory computer-readable storage medium storing machine-executable instructions that can be executed by one or more processors of a machine. The machine may include electronic devices as mentioned above. When the machine-executable instructions are executed by one or more processors, the machine performs any of the methods mentioned above.

[0076] Computer-readable storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. The computer-readable storage medium can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or similar media, or any combination of the above media.

[0077] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0078] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0079] Some aspects of this application can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The aforementioned hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." The processor may be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. Furthermore, aspects of this application may manifest as computer products residing in one or more computer-readable media, including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), optical discs (e.g., compressed CDs, digital multifunction DVDs, etc.), smart cards, and flash memory devices (e.g., cards, sticks, key drives, etc.).

[0080] A computer-readable medium may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. A computer-readable medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or similar media, or any combination of the above media.

[0081] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0082] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of scope in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

Claims

1. A method for controlling lighting atmosphere, characterized in that, include: Obtain lighting atmosphere guidance information and basic configuration information of the intelligent lighting device cluster located in the target control area; The lighting atmosphere guidance information is described using natural language. The basic configuration information includes the physical attributes and protocol specifications of each smart lighting device in the smart lighting device cluster; Based on a generative artificial intelligence model, using the lighting atmosphere guidance information and the basic configuration information as input, a matching experience scheme for the target lighting atmosphere adapted to the target control area is generated; wherein, the matching experience scheme includes: physical configuration parameters of the lighting atmosphere corresponding to the device control surface, and semantic description text of the lighting atmosphere corresponding to the audiovisual broadcast surface; Based on the physical configuration parameters of the lighting atmosphere, a lighting control command is generated and sent to the intelligent lighting device cluster to control the intelligent lighting device cluster to present the target lighting atmosphere; and, The semantic description of the lighting atmosphere is presented to the user so that the user can have a complete audiovisual experience.

2. The lighting atmosphere control method as described in claim 1, characterized in that, The generative artificial intelligence model, after being trained through a reinforcement learning phase, acquires the semantic understanding and structured generation capability to map the lighting atmosphere guidance information and the basic configuration information into the supporting experience scheme. The reinforcement learning phase includes a reward function and a value function. The reward function is used to predict the comprehensive evaluation effect of different model outputs, and the value function is used to predict the long-term aesthetic value of different model outputs. The model outputs include the physical configuration parameters of the lighting atmosphere and the semantic description text of the lighting atmosphere.

3. The lighting atmosphere control method as described in claim 2, characterized in that, The reward function consists of any or a combination of the following components: A semantic alignment reward is used to provide positive feedback to the model training process based on the correlation between the semantic description text of the lighting atmosphere and the physical configuration parameters of the lighting atmosphere. The consistency reward is used to provide positive feedback to the model training process based on the degree of consistency of multiple model outputs; The physical constraint penalty term is used to provide negative feedback to the model training process when the color temperature and color feature values ​​are outside the reasonable range; Human factors lighting rewards are used to provide positive feedback during model training based on the degree of matching between brightness and color temperature.

4. The lighting atmosphere control method as described in claim 2, characterized in that, The value function is a weighted sum of long-term cumulative reward and semantic entropy; the semantic entropy is calculated based on the diversity function, the probability distribution of all possible color temperature combinations, and the value coefficient.

5. The lighting atmosphere control method according to any one of claims 1-4, characterized in that, The generation of lighting control commands based on the physical configuration parameters of the lighting atmosphere includes: The color ratio required for the target lighting atmosphere is determined from the physical configuration parameters of the lighting atmosphere; Color boundaries are generated based on the color ratio and cumulative distribution function; The visual abrupt changes in the color boundary are corrected using a linear interpolation method based on spline functions to obtain the target color space; Mapping the target color space to the cluster of smart lighting devices yields the target color feature value for each smart lighting device; and... The lighting control command is generated based on the target color feature value, brightness, and color temperature of each smart lighting device.

6. The lighting atmosphere control method as described in claim 5, characterized in that, The cumulative distribution function is obtained by normalizing the multi-dimensional fusion result; The multi-dimensional fusion result is composed of the color ratio, spatial preference function, and temperature coefficient, and the multi-dimensional fusion result is directly proportional to the color ratio and the spatial preference function, and inversely proportional to the temperature coefficient.

7. The lighting atmosphere control method as described in claim 1, characterized in that, Also includes: The diurnal rhythm deviation and energy efficiency of the intelligent lighting equipment cluster applied to the target lighting atmosphere were statistically analyzed. Based on the circadian rhythm deviation, the energy efficiency, and the semantic matching degree of the semantic description text of the lighting atmosphere relative to the target lighting atmosphere, a comprehensive evaluation score for the target lighting atmosphere is obtained; as well as, Record the overall evaluation score.

8. A lighting control system, characterized in that, include: Internet of Things (IoT) devices are used to collect user input information in real time; A cloud server, communicatively connected to the IoT device, is used to execute the method as described in any one of claims 1-7; as well as, The intelligent lighting equipment cluster communicates with the cloud server and the IoT device to present the target lighting atmosphere according to the received lighting control instructions.

9. An electronic device, characterized in that, include: One or more processors; as well as, One or more memories coupled to one or more processors and storing instructions thereon, which, when executed by one or more processors individually or jointly, cause the electronic device to perform the method as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing machine-executable instructions, characterized in that, When executed by one or more processors of the machine, the machine-executable instructions cause the machine to perform the method as described in any one of claims 1-7.

Images