Self-adaptive lighting control method and device based on large model and electronic equipment

Abstract

The invention provides an adaptive lighting control method and device based on a large model and electronic equipment, and the method comprises the steps: receiving an initial input indicating a preset lighting effect; processing the initial input using a large model to generate a plurality of initial lighting effect parameter values; re-evaluating the plurality of initial lighting effect parameter values based on real-time environmental conditions fed back by at least one environmental sensor; and generating a plurality of updated lighting effect parameter values according to the re-evaluation result so as to maintain the lighting effect adaptive to the real-time environment condition. Automatic process design is adopted, the technical threshold of a user is lowered, and the safety and adaptability of the lighting effect are ensured.

Description

Technical Field

[0001] This disclosure relates to the field of ambient lighting technology, and more specifically, to an adaptive lighting control method, device, and electronic device based on a large model. Background Technology

[0002] In the field of ambient lighting, traditional methods typically rely on pre-programmed built-in lighting modes to achieve lighting effects, such as gradients, flashing, or scrolling bars. These preset effects are directly configured into the luminaire's firmware, limiting users to a limited selection of options. While this manufacturer-based approach is simple and inexpensive, its closed and fixed nature severely restricts the depth and breadth of the user experience, making it difficult to meet the growing personalized, intelligent, and interactive lighting needs of modern users.

[0003] Furthermore, while manually configuring lighting effects (DIY lighting effects) offers a high degree of freedom and creative space, it also presents significant technical challenges and reliability risks for ordinary users. Users need to understand complex lighting control logic, parameter meanings, and programming concepts, which limits the widespread adoption of personalized lighting experiences. Manually designing complex lighting effects may require repeated adjustments, which is time-consuming and demands considerable patience and hands-on skills, making the creation of nuanced dynamic lighting effects impractical for most users. More seriously, inappropriate parameter settings can lead to problems such as overheating, abnormal flickering, or conflicts with other devices in the physical lighting system, affecting the reliability, safety, and stable operation of the lighting facilities.

[0004] Therefore, there is an urgent need in this field for an intelligent lighting control solution that can automatically generate personalized lighting effects. Summary of the Invention

[0005] This disclosure provides at least one adaptive lighting control method, apparatus, and electronic device based on a large model to solve the aforementioned technical problems.

[0006] In a first aspect, embodiments of this disclosure provide an adaptive lighting control method based on a large model, comprising:

[0007] Receive initial input indicating a preset lighting effect; The initial input is processed using a large model to generate multiple initial lighting effect parameter values; The multiple initial lighting effect parameter values ​​are re-evaluated based on real-time environmental conditions fed back by at least one environmental sensor. Based on the re-evaluation results, multiple updated lighting effect parameter values ​​are generated to maintain the preset lighting effect adapted to the real-time environmental conditions.

[0008] In one possible implementation, the re-evaluation of the plurality of initial lighting effect parameter values ​​includes: Based on the real-time environmental conditions, calculate the deviation between the current environment and the environment required for the preset lighting effect; The plurality of initial lighting effect parameter values ​​are adjusted according to the deviation to generate a plurality of updated lighting effect parameter values, thereby compensating for the deviation.

[0009] In one possible implementation, the re-evaluation of the plurality of initial lighting effect parameter values ​​includes: In response to the fulfillment of preset triggering conditions, the values ​​of the plurality of initial lighting effect parameters are re-evaluated; The preset triggering conditions include the real-time environmental conditions deviating from preset conditions, or the time interval exceeding a predetermined time interval since the last adjustment of multiple initial lighting effect parameter values.

[0010] In one possible implementation, the reassessment includes at least one of the following adjustments: Adjusting the intensity, color temperature, or spatial distribution of emitted light to compensate for environmental changes; Synchronize the flicker rate, brightness modulation, or color change of the emitted light with the rhythm or spectrum of the ambient sound data.

[0011] In one possible implementation, the initial input includes natural language input representing desired emotional or environmental characteristics.

[0012] In one possible implementation, processing the initial input using a large model includes: The natural language input is processed using a large language model (LLM) to identify at least one color category associated with the desired emotional or environmental characteristics. Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the natural language input based on the identified color category; Multiple initial lighting effect parameter values ​​are generated based on the target emotional tendency.

[0013] In one possible implementation, generating multiple initial lighting effect parameter values ​​based on the target emotional tendency includes: Access the lighting effect mapping table to find the association between multiple sentiment tendencies and multiple lighting effect rules, and find the target lighting effect rule corresponding to the target sentiment tendency; Based on the target lighting effect rules, one or more lighting effect parameters, including chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and lighting state, are assigned values, and multiple initial lighting effect parameter values ​​are generated.

[0014] In one possible implementation, the initial input includes a digital image input representing a desired scene, subject, or environmental context.

[0015] In one possible implementation, processing the initial input using a large model includes: The digital image input is processed using a large visual model (LVM) to identify multiple color categories associated with the desired scene, subject, or environmental context. Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the digital image input based on the identified color categories; Multiple initial lighting effect parameter values ​​are generated based on the target emotional tendency.

[0016] In one possible implementation, the step of finding the target sentiment corresponding to the digital image input based on the identified color category includes: The target object data within the digital image input is weighted and aggregated; wherein the weighting is based on at least one of the following: the size of the target object in the image, the proximity of the target object to the center of interest, or a predefined level of emotional influence on the target object; Based on the identified color category and weighted aggregation results, the target sentiment tendency corresponding to the target object in the digital image input is found.

[0017] In one possible implementation, it also includes: Each time a lighting effect parameter value is generated, the lighting system operation constraints are accessed. Verify whether the generated lighting effect parameter values ​​meet the operating constraints of the lighting system to ensure that the output control signal will not cause the lighting system to malfunction.

[0018] In one possible implementation, it also includes: Obtain the user's physiological information in the current environment; The lighting effect parameter values ​​are adjusted based on the physiological information.

[0019] Secondly, this disclosure also provides an adaptive lighting control device based on a large model, comprising: The receiving module is used to receive initial input indicating a preset lighting effect; The generation module is used to process the initial input using a large model and generate multiple initial lighting effect parameter values. An evaluation module is used to re-evaluate the multiple initial lighting effect parameter values ​​based on real-time environmental conditions fed back by at least one environmental sensor. An update module is used to generate multiple updated lighting effect parameter values ​​based on the re-evaluation results, so as to maintain the preset lighting effect adapted to the real-time environmental conditions.

[0020] Thirdly, this disclosure also provides an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executed by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, they perform the large-model-based adaptive lighting control method as described in any one of the first aspects and various embodiments thereof.

[0021] Fourthly, this disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the large-model-based adaptive lighting control method as described in any one of the first aspects and various embodiments thereof.

[0022] The aforementioned adaptive lighting control method, apparatus, and electronic device based on a large model receive an initial input indicating a preset lighting effect; process the initial input using a large model to generate multiple initial lighting effect parameter values; re-evaluate the multiple initial lighting effect parameter values ​​based on real-time environmental conditions fed back by at least one environmental sensor; and generate multiple updated lighting effect parameter values ​​based on the re-evaluation results to maintain the preset lighting effect adapted to the real-time environmental conditions. Therefore, this disclosure employs an automated process design, lowers the technical threshold for users, and ensures the safety and adaptability of the lighting effect.

[0023] Other advantages of this disclosure will be explained in more detail in conjunction with the following description and accompanying drawings.

[0024] It should be understood that the above description is merely an overview of the technical solution of this disclosure, so as to provide a general understanding of the technical means of this disclosure and to implement it in accordance with the contents of the specification. In order to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are illustrated below. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. The accompanying drawings are incorporated in and constitute a part of this specification. These drawings illustrate embodiments conforming to this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure. It should be understood that the drawings only illustrate certain embodiments of this disclosure and should not be considered as a limitation on the scope of protection. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. Furthermore, the same reference numerals denote the same components throughout the drawings. In the drawings: Figure 1 A flowchart of an adaptive lighting control method based on a large model provided in an embodiment of this disclosure is shown; Figure 2 This illustration shows the intention of constructing a mapping representation in the large-model-based adaptive lighting control method provided in the embodiments of this disclosure; Figure 3 A schematic diagram of an adaptive lighting control device based on a large model provided in an embodiment of this disclosure is shown; Figure 4 The diagram shows the architecture of the system environment in which the large-model-based adaptive lighting control method provided in this embodiment of the present disclosure is applied; Figure 5 A schematic diagram of the memory in the system environment to which the large-model-based adaptive lighting control method provided in this embodiment of the present disclosure is applied is shown; Figure 6 A schematic diagram of an electronic device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0026] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0027] In the description of embodiments disclosed herein, it should be understood that terms such as “comprising” or “having” are intended to indicate the presence of the disclosed features, figures, steps, behaviors, components, portions or combinations thereof in this specification, and do not exclude the possibility of the presence of one or more other features, figures, steps, behaviors, components, portions or combinations thereof.

[0028] Unless otherwise stated, " / " means "or". For example, A / B can mean A or B. In this article, "and / or" is merely a way of describing the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A alone, A and B at the same time, and B alone.

[0029] The terms "first," "second," etc., are used only for ease of description to distinguish identical or similar technical features and should not be construed as indicating or implying the relative importance or number of these technical features. Therefore, a feature defined by "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, the term "multiple" means two or more.

[0030] Research has shown that manually designing complex lighting effects can require repeated adjustments, which is time-consuming and demands considerable patience and manual dexterity, making it impractical for most users to achieve nuanced dynamic lighting effects. More seriously, inappropriate parameter settings can lead to problems such as overheating, abnormal flickering, or conflicts with other equipment in the physical lighting system, affecting the reliability, safety, and stable operation of the lighting facilities.

[0031] To at least partially address one or more of the aforementioned problems and other potential issues, this disclosure provides an adaptive lighting control method, apparatus, and electronic device based on a large model to continuously maintain the desired lighting effect that adapts to real-time environmental conditions.

[0032] To facilitate understanding of this embodiment, a detailed description of the large-model-based adaptive lighting control method disclosed in this disclosure is provided first. The execution entity of the large-model-based adaptive lighting control method provided in this disclosure is generally an electronic device with a certain computing capability. This electronic device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, this large-model-based adaptive lighting control method can be implemented by a processor calling computer-readable instructions stored in memory.

[0033] See Figure 1 The diagram illustrates a flowchart of an adaptive lighting control method based on a large model provided in this disclosure, the method comprising the following steps S101-S104: S101: Receive initial input indicating a preset lighting effect; S102: Use a large model to process the initial input and generate multiple initial lighting effect parameter values; S103: Based on real-time environmental conditions fed back by at least one environmental sensor, re-evaluate multiple initial lighting effect parameter values; S104: Generate multiple updated lighting effect parameter values ​​based on the re-evaluation results to maintain the preset lighting effect adapted to real-time environmental conditions.

[0034] To facilitate understanding of the adaptive lighting control method provided in this disclosure, a brief introduction to its application scenarios is given first. This adaptive lighting control method can be applied to any scenario requiring ambient lighting, such as stage performances, restaurant ambiance, festival celebrations; medical spaces, meditation spaces, nighttime architectural views; exhibition hall background lighting, commercial spaces; concert special effects, advertising light boxes; luxury hotels, spas, home lighting, etc. This disclosure does not impose specific limitations on these applications.

[0035] Considering that in real-world lighting scenarios, users' technical limitations often prevent the provision of more personalized, intelligent, and interactive solutions, this disclosure provides an adaptive lighting control method based on a large model. By using a large model to process user input and combining it with an adaptive feedback loop to re-evaluate lighting effect parameters, a more reliable and safer lighting effect can be maintained.

[0036] Depending on the application requirements, the initial input received here will also be different. For example, it can be natural language input, digital image input, or ambient environment input (including but not limited to ambient light intensity, ambient temperature, etc.). In practical applications, it can also be other input data forms or a fusion of various data forms. No specific restrictions are made here.

[0037] Different large models can be used to process different input data formats to determine the initial lighting effect parameter values ​​corresponding to the initial input. Taking natural language input as an example, the large model used here can be a Large Language Model (LLM); taking digital image input as an example, the large model used here can be a Large Vision Model (LVM), or it can be a large model for other input formats, without specific restrictions.

[0038] After processing the large model, initial lighting effect parameter values ​​can be generated. These lighting effect parameters include, but are not limited to, chromaticity, saturation, brightness, color temperature, flicker rate, and light intensity distribution.

[0039] Here, given the real-time environmental conditions fed back by the environmental sensors, we can first determine whether the current lighting effect parameter values ​​can meet the real-time environmental conditions, and then further re-evaluate multiple initial lighting effect parameter values ​​to determine updated lighting effect parameter values, thereby maintaining adaptation to the real-time environment.

[0040] The real-time environmental conditions can be obtained based on feedback from environmental sensors, which include at least one of the following: a photodiode or photoresistor for detecting ambient light intensity; a thermistor or thermocouple for detecting ambient temperature; a passive infrared (PIR) sensor or ultrasonic sensor for detecting human presence; or a microphone array for detecting ambient sound level and characteristics. Other environmental sensors are also possible, without specific limitations.

[0041] The reassessment can be achieved through the following steps: Step 1: Based on real-time environmental conditions, calculate the deviation between the current environment and the environment required for the preset lighting effect; Step 2: Adjust multiple initial lighting effect parameter values ​​based on the deviation to generate multiple updated lighting effect parameter values, thereby compensating for the deviation.

[0042] Here, we first identify the deviation between the current environment and the environment required for the preset lighting effect. The greater the deviation, the greater the lighting effect parameter value that needs to be adjusted to some extent, and vice versa. Based on the deviation, we can determine the updated lighting effect parameter value to compensate for the lighting deviation that the current environment may bring, thereby providing data support for the subsequent continuous adaptation of the lighting effect.

[0043] In practical applications, reassessment can be triggered when real-time environmental conditions deviate from preset conditions, i.e., environment-triggered reassessment; or it can be triggered when a predetermined time interval has elapsed since the last adjustment of multiple initial lighting effect parameter values, i.e., periodic reassessment to further ensure the reliability of the lighting effect.

[0044] In the process of generating updated lighting effect parameter values ​​based on the reassessment results, for example, multiple updated lighting effect parameter values ​​can be generated by adjusting the light intensity, color temperature, or spatial distribution of the emitted light. Among these adjustments, the emitted light can be made to compensate for changes in ambient light intensity detected by the light sensor, thereby maintaining a constant brightness level. Alternatively, it can be an adjustment made when a sensor detects human occupancy, with the aim of adapting the lighting effect to the presence or absence of a person.

[0045] Alternatively, multiple updated lighting effect parameter values ​​can be generated by synchronizing the flicker rate, brightness modulation, or color change of the emitted light with the rhythm or spectrum of ambient sound data.

[0046] Considering that the initial inputs in this embodiment mainly include natural language inputs and digital image inputs, and that different large model processing schemes will be used for different types of inputs, the following will elaborate on this from two aspects.

[0047] Firstly, when the initial input includes natural language input, the natural language input here can represent the desired emotional or environmental characteristics.

[0048] In this embodiment of the disclosure, the initial input can be processed according to the following steps: Step 1: Use a Large Language Model (LLM) to process the natural language input and identify at least one color category that is associated with the desired emotional or environmental characteristics; Step 2: Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the natural language input based on the identified color categories; Step 3: Generate multiple initial lighting effect parameter values ​​based on the target's emotional tendency.

[0049] Specifically, generating multiple initial lighting effect parameter values ​​based on the target's emotional tendency can be achieved through the following steps: Step 1: Access the association between multiple sentiment tendencies and multiple lighting effect rules in the lighting effect mapping table, and find the target lighting effect rule corresponding to the target sentiment tendency; Step 2: Based on the target lighting effect rules, assign values ​​to one or more of the lighting effect parameters, including chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and lighting state, and generate multiple initial lighting effect parameter values.

[0050] like Figure 2 The table shown illustrates an example of a sentiment mapping table and a lighting effect mapping table. The sentiment mapping table stores the associations between multiple color categories and multiple sentiment tendencies, while the lighting effect mapping table stores the associations between multiple sentiment tendencies and multiple lighting effect rules. Based on this, the target sentiment tendency corresponding to the natural language input can be found, and the target lighting effect rule corresponding to the target sentiment tendency can be determined, thereby determining the initial lighting effect parameter values.

[0051] In the actual implementation process, the lighting effect rules can also be determined directly based on the entire summary table, without specific restrictions.

[0052] The color categories can include warm colors (red, orange, yellow), cool colors (blue, cyan, purple), neutral colors (gray, white, black, beige), highly saturated colors, and low-saturation colors; the emotional tendencies can be, for example, enthusiasm, warmth, excitement, intimacy; calmness, rationality, stability, mystery; balance, neutrality, and strong contrast; strong stimulation and impact, softness and soothingness; and the lighting effect rules are specifically integrated into specific application examples according to chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and lighting conditions.

[0053] based on Figure 2 It is understood that the embodiments of this disclosure can also adjust the lighting effect parameter values ​​by combining the user's physiological information in the current environment. The physiological information here includes relevant information on physical and psychological aspects, such as increased blood pressure, increased heart rate, visual relaxation / tension, etc.

[0054] Secondly, when the initial input includes digital image input, the natural language input here can represent the desired scene, topic, or environmental context.

[0055] In this embodiment of the disclosure, the initial input can be processed according to the following steps: Step 1: Use Large Visual Model (LVM) to process digital image input and identify multiple color categories related to the desired scene, subject, or environmental context; Step 2: Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the digital image input based on the identified color categories; Step 3: Generate multiple initial lighting effect parameter values ​​based on the target's emotional tendency.

[0056] The relevant description of generating multiple initial lighting effect parameter values ​​based on the target's emotional tendency can be found in the first aspect, and will not be repeated here.

[0057] Furthermore, this can be combined with Figure 2 The table shown illustrates the process of determining the values ​​of the lighting effect parameters. For details, please refer to the relevant description in the first section, which will not be repeated here.

[0058] It should be emphasized that, in the actual process of finding the target sentiment tendency corresponding to the digital image input, relevant information from the weighted aggregation of the target object data within the digital image input can be used to better determine the target sentiment tendency corresponding to the target object in the digital image input.

[0059] The weighting factors can be, for example, the size of the target object in the image, the proximity of the target object to the center of interest, or a predefined level of emotional influence on the target object. In other words, the greater the weighting information, the clearer the corresponding emotional tendency of the target will be.

[0060] In practical applications, the adaptive lighting control method based on a large model provided in this disclosure generates control signals for controlling the lighting system based on the generated lighting effect parameter values. In specific applications, each time a lighting effect parameter value is generated, the operating constraints of the lighting system are accessed, and it is verified whether the generated lighting effect parameter value meets the operating constraints of the lighting system, so as to ensure that the output control signal will not cause the lighting system to malfunction.

[0061] The operational constraints of the lighting system include, for example, rules to prevent overheating, abnormal flickering, or equipment conflicts.

[0062] In addition to natural language input and digital image input mentioned above, input can also be environmental data.

[0063] In practical applications, when user inputs environmental data into the system, the system first uses intent recognition to determine whether the user's input is to generate a new lighting effect or to modify the previous lighting effect.

[0064] If it's a new lighting effect, it's necessary to further determine whether it falls under one of the following categories: holiday, sports, or mood. The lighting effect will then be adjusted based on this determination. If the user's input is a modification to the previous lighting effect, the modification process will proceed directly.

[0065] Regarding the generation process of new lighting effects, user input is fed into a vector database for matching. The database categorizes lighting effects, and the system outputs the top 5 scenes that best match the user input. These 5 scenes are then fed into a large model for further processing, where the model selects the best-matching scene.

[0066] Here, the matching scenario selected by the model must have a matching degree greater than 0.7 with the user input. If the matching degree is lower than this threshold, 'none' is returned.

[0067] Furthermore, based on environmental data, the system will adjust the results matched from the database to ensure that the lighting effect meets the actual needs of the current environment.

[0068] Regarding the modification process of the previous lighting effect, or if the user's input does not involve special scenarios such as holidays, teams, or emotions, the system will directly send the user input and environmental data into the large model.

[0069] Here, the large model first determines the appropriate colors and rhythms for the scene based on user input and environmental data. Based on the determined colors and rhythms, the system passes this data to the lighting effect generation large model to generate the corresponding lighting effects.

[0070] The color, rhythm, and lighting effect generation models retain historical records for future lighting effect adjustments or modifications.

[0071] In practical applications, data from environmental sensors is synchronously input into the model as part of the user input. It is mainly used to adjust the color brightness and rhythm speed of the lighting effect. In addition, environmental sensor data can be dynamically acquired in real time (e.g., the environmental sensor sends data every 5 minutes, and the rhythm and color models are modified according to this data and then input into the lighting effect generation model).

[0072] In the description of this specification, references to terms such as "some possible implementations," "some implementations," "example," "specific example," or "some examples" indicate that a specific feature, structure, material, or characteristic described in connection with that implementation or example is included in at least one implementation or example of this disclosure, and the aforementioned terms do not necessarily refer to the same implementation or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more implementations or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different implementations or examples described in this specification, as well as the features of different implementations or examples.

[0073] Regarding the method flowcharts of embodiments of this disclosure, certain operations are described as different steps performed in a certain order. Such flowcharts are illustrative and not restrictive. Some steps described herein may be grouped together and performed in a single operation, or some steps may be divided into multiple sub-steps, and some steps may be performed in an order different from that shown herein. The various steps shown in the flowcharts may be implemented in any way by any circuit structure and / or tangible mechanism (e.g., software running on a computer device, hardware (e.g., logic functions implemented by a processor or chip), and / or any combination thereof).

[0074] Those skilled in the art will understand that in the methods described in the above specific embodiments, the order in which the steps are written does not imply a strict execution order, and the specific execution order of each step should be determined by its function and possible internal logic.

[0075] Based on the same inventive concept, this disclosure also provides a large-model-based adaptive lighting control device corresponding to the large-model-based adaptive lighting control method. Since the principle of the device in this disclosure for solving the problem is similar to the large-model-based adaptive lighting control method described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0076] Reference Figure 3 The diagram shown is a schematic of an adaptive lighting control device based on a large model according to an embodiment of this disclosure. The device includes: a receiving module 201, a generating module 202, an evaluation module 203, and an updating module 204; wherein: The receiving module 201 is used to receive initial input indicating a preset lighting effect; The generation module 202 is used to process the initial input using a large model and generate multiple initial lighting effect parameter values; Evaluation module 203 is used to re-evaluate multiple initial lighting effect parameter values ​​based on real-time environmental conditions fed back by at least one environmental sensor; The update module 204 is used to generate multiple updated lighting effect parameter values ​​based on the re-evaluation results, so as to maintain the preset lighting effect adapted to real-time environmental conditions.

[0077] The aforementioned large-model-based adaptive lighting control device receives an initial input indicating a preset lighting effect; processes the initial input using a large model to generate multiple initial lighting effect parameter values; re-evaluates these initial lighting effect parameter values ​​based on real-time environmental conditions fed back by at least one environmental sensor; and generates multiple updated lighting effect parameter values ​​based on the re-evaluation results to maintain the preset lighting effect adapted to real-time environmental conditions. Therefore, this disclosure employs an automated process design, lowers the technical threshold for users, and ensures the safety and adaptability of the lighting effect.

[0078] In one possible implementation, the evaluation module 203 is configured to re-evaluate the plurality of initial lighting effect parameter values ​​according to the following steps: Based on the real-time environmental conditions, calculate the deviation between the current environment and the environment required for the preset lighting effect; The plurality of initial lighting effect parameter values ​​are adjusted according to the deviation to generate a plurality of updated lighting effect parameter values, thereby compensating for the deviation.

[0079] In one possible implementation, the evaluation module 203 is configured to re-evaluate the plurality of initial lighting effect parameter values ​​according to the following steps: In response to the fulfillment of preset triggering conditions, the values ​​of the plurality of initial lighting effect parameters are re-evaluated; The preset triggering conditions include the real-time environmental conditions deviating from preset conditions, or the time interval exceeding a predetermined time interval since the last adjustment of multiple initial lighting effect parameter values.

[0080] In one possible implementation, the reassessment includes at least one of the following adjustments: Adjusting the intensity, color temperature, or spatial distribution of emitted light to compensate for environmental changes; Synchronize the flicker rate, brightness modulation, or color change of the emitted light with the rhythm or spectrum of the ambient sound data.

[0081] In one possible implementation, the initial input includes natural language input representing desired emotional or environmental characteristics.

[0082] In one possible implementation, the generation module 202 is configured to process the initial input using a large model according to the following steps: The natural language input is processed using a large language model (LLM) to identify at least one color category associated with the desired emotional or environmental characteristics. Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the natural language input based on the identified color category; Multiple initial lighting effect parameter values ​​are generated based on the target emotional tendency.

[0083] In one possible implementation, the generation module 202 is configured to generate multiple initial lighting effect parameter values ​​based on the target emotional tendency according to the following steps: Access the lighting effect mapping table to find the association between multiple sentiment tendencies and multiple lighting effect rules, and find the target lighting effect rule corresponding to the target sentiment tendency; Based on the target lighting effect rules, one or more lighting effect parameters, including chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and lighting state, are assigned values, and multiple initial lighting effect parameter values ​​are generated.

[0084] In one possible implementation, the initial input includes a digital image input representing a desired scene, subject, or environmental context.

[0085] In one possible implementation, the generation module 202 is configured to process the initial input using a large model according to the following steps: The digital image input is processed using a large visual model (LVM) to identify multiple color categories associated with the desired scene, subject, or environmental context. Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the digital image input based on the identified color categories; Multiple initial lighting effect parameter values ​​are generated based on the target emotional tendency.

[0086] In one possible implementation, the generation module 202 is configured to search for a target sentiment tendency corresponding to the digital image input based on the identified color category, according to the following steps: The target object data within the digital image input is weighted and aggregated; wherein the weighting is based on at least one of the following: the size of the target object in the image, the proximity of the target object to the center of interest, or a predefined level of emotional influence on the target object; Based on the identified color category and weighted aggregation results, the target sentiment tendency corresponding to the target object in the digital image input is found.

[0087] In one possible implementation, it also includes: The verification module is used to access the lighting system operation constraints every time a lighting effect parameter value is generated; to verify whether the generated lighting effect parameter value meets the lighting system operation constraints, so as to ensure that the output control signal will not cause the lighting system to malfunction.

[0088] In one possible implementation, it also includes: An adjustment module is used to acquire the user's physiological information in the current environment and adjust the lighting effect parameter values ​​based on the physiological information.

[0089] It should be noted that the apparatus in this embodiment can implement the various processes of the aforementioned method and achieve the same effects and functions, which will not be elaborated here.

[0090] Based on the large-model-based adaptive lighting control method and apparatus provided in the above embodiments, this disclosure provides an example system environment 100. For example... Figure 4 As shown, the system environment 100 includes a client device 102, a network 104, and a computer system 106. Other implementations may use... Figure 4 The diagram shows more or fewer or different systems. The functionality of the various modules and systems described herein can be implemented by other modules and / or systems besides those described herein.

[0091] Client device 102 is a computing device capable of receiving user input and sending and / or receiving data via network 104. In one embodiment, client device 102 is a conventional computer system, such as a desktop computer or laptop computer. Alternatively, client device 102 may be a device with computer functionality, such as a personal digital assistant (PDA), mobile phone, smartwatch, or another suitable device. Client device 102 is configured to communicate via network 104.

[0092] In one embodiment, client device 102 executes an application that allows a user of client device 102 to interact with computer system 106. In another embodiment, client device 102 interacts with computer system 106 via an Application Programming Interface (API) running on the native operating system of client device 102, such as iOS® or Android™.

[0093] In another embodiment, the client device 102 launches an application (app) to enable interaction between the client device 102 and the computer system 106 via the network 104.

[0094] In some embodiments, the client device 102 is a computing device through which the user can provide desired mood and environmental characteristics, scenes, or themes. In some embodiments, user input includes dialogue. In some other embodiments, user input includes images.

[0095] Client device 102 may include a physical microphone (for natural language processing requirements) or text input interface (e.g., keyboard, touchscreen) for receiving spoken or typed natural language user input. Client device 102 may also include a physical camera module (for image processing requirements) or interface for receiving digital image files, capturing or photographing digital image data. Client device 102 may also include a graphical user interface (GUI) providing display and / or touchscreen functionality for user interaction, input confirmation, and system status display. Client device 102 provides user input to computer system 106 via network 104.

[0096] In some implementations, the client device 102 receives natural language input representing desired emotions or environmental characteristics via an interface; in other implementations, the client device 102 receives digital image input representing desired scenes, themes, or environmental contexts via an interface.

[0097] Computer system 106 in the system environment is the system's computing and control unit, containing various interconnected hardware and software components. Computer system 106 includes a physical processor 108 (or multiple processors, including a Central Processing Unit (CPU) and / or a Graphics Processing Unit (GPU)) responsible for overall system coordination, executing software instructions, managing data flow, and performing general computing tasks. Computer system 106 also includes physical computer memory 110 (e.g., random access memory (RAM)) for storing operating system instructions, application software, temporary data, and critical knowledge bases.

[0098] Figure 5 A block diagram of a physical computer memory according to one embodiment is shown. The physical computer memory 110 stores the parameters and architecture 132 of a pre-trained deep learning model (e.g., a large language model (LLM) or a large vision model (LVM), or a multimodal LLM, etc.) loaded into memory for semantic understanding or image analysis.

[0099] It should be understood that while the various implementations described herein may involve using LLM or LVM to process user input and extract relevant features, this disclosure is not limited to these specific types of deep learning models. As used herein, the terms “large model” or “deep learning model” are intended to encompass any artificial intelligence model, particularly those based on deep neural networks, capable of processing complex data (e.g., natural language, images, audio, or multimodal data) to extract semantics, identify features, classify content, or infer context and sentiment.

[0100] The physical memory 110 also includes a semantic information extraction unit 134, which is configured to receive user dialogue content as input and provide the user input to the LLM for processing to derive higher-level semantic features. Using the LLM, the semantic information extraction unit 134 can identify and extract keywords, concepts, and contextual cues from the dialogue input. These extracted semantic features may include, but are not limited to, time-based references (e.g., identifying specific events or periods), environmental descriptors (e.g., indicating location or setting), and emotional or thematic elements (e.g., conveying desired mood or atmosphere). The output of the semantic information extraction unit 134 may include structured data representing the user's potential intentions or preferences.

[0101] The physical computer memory 110 also stores a structured database 136 of color knowledge pool, which contains sentiment mapping tables that associate predefined color categories with corresponding sentiment tendencies.

[0102] Physical computer memory 110 stores lighting effect rules 138, which include a set of predefined rules or algorithms that map emotional tendencies and color categories to specific physical lighting attributes and control parameters.

[0103] The physical computer memory 110 also includes an object-emotion matching table 140 that associates objects identified from digital images with their extracted emotional tendencies, in order to determine the emotional tendencies corresponding to target objects and their lighting effect rules, etc.

[0104] The computer system 106 also includes a lighting effects controller 112 (e.g., a neural processing unit, digital signal processor, or dedicated GPU core) configured to perform natural language processing tasks (for LLM inference) or image processing tasks (for LVM inference, object detection, and segmentation).

[0105] LLM can be configured to extract relevant keywords, key terms, or semantic features from explicit statements and implicit or latent semantic meanings in received session content. The extracted information can provide a refined representation of the user's intent, topic, or preferences for subsequent processing.

[0106] LLM may include a contextual keyword recognition module configured to process user conversations using LLM to perform deep semantic analysis. The functionality of this contextual keyword recognition module may include identifying and extracting keywords and concepts, regardless of whether they are explicitly stated or implied through context, nuance, or subtext in the conversational input. This contextual keyword recognition module can output a set of high-level semantic tags derived from a comprehensive understanding of the user's communication.

[0107] The computer system 106 also includes a lighting effect parameter generator 114 executed by the processor 108, which is configured to apply lighting effect rules and calculate values ​​of physical lighting parameters.

[0108] Computer system 106 also includes a lighting control output interface 116 that converts digital lighting effect parameters into electrical or wireless control signals compatible with the physical lighting system. Examples of lighting control output interfaces 116 include wired digital multiplexing (DMX) controllers, wireless Zigbee / Wi-Fi modules, and dedicated general purpose input / output (GPIO) ports.

[0109] System environment 100 includes lighting system 118, which is a physical device that includes multiple lighting devices (lamp fixtures) and associated control circuits, capable of dynamically adjusting various physical lighting attributes such as chromaticity, saturation, brightness, color temperature, flicker rate, and light intensity distribution.

[0110] The lighting system 118 is configured to control the lighting system using the output generated by the lighting effect parameter generator 114 to achieve the desired lighting effect in the physical space based on the parameter information.

[0111] The lighting effects controller 112 can be configured to dynamically control a physical multi-parameter lighting system based on the emotions expressed by the user. The lighting effects controller 112 can operate using Natural Language Processing (NLP) to perform the methods detailed below.

[0112] In some implementations, the lighting effects controller 112 (e.g., an NLP engine) uses LLM to process natural language input to extract and identify multiple color categories associated with desired mood or environmental characteristics. In some embodiments, the NLP engine uses LLM to process natural language input to extract at least one of the following: primary hue, secondary hue, and gradient color distribution of different color categories.

[0113] In some implementations, the lighting effects controller 112 accesses a color pool from memory, which includes an emotion mapping table that associates multiple color categories with multiple emotion tendencies.

[0114] In some implementations, the lighting effects controller 112 determines the sentiment tendency associated with the natural language input based on multiple color categories. In some embodiments, the lighting effects controller 112 performs a computational lookup within a sentiment map.

[0115] In some embodiments, the lighting effect controller 112 generates a plurality of lighting effect parameters based on emotional tendencies. In some embodiments, the lighting effect controller 112 associates emotional tendencies and a plurality of color categories with predefined lighting effect rules stored in a memory. The lighting effect controller 112 calculates values ​​for a plurality of lighting effect parameters selected from the group consisting of: chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and transition speed between lighting states of a plurality of lighting devices.

[0116] In some implementations, the lighting effect parameter generator 114 generates multiple lighting effect parameters based on emotional tendencies.

[0117] In some implementations, the processor 108 transmits control signals representing multiple lighting effect parameters to the physical multi-parameter lighting system via the lighting control output interface 116, thereby dynamically adjusting the emitted light according to the desired mood or environmental characteristics.

[0118] In some implementations, these multiple lighting effect parameters are associated with physical reactions and psychological feelings.

[0119] The lighting effects controller 112 can also be configured to dynamically control a physical multi-parameter lighting system to reflect atmospheric characteristics derived from visual input. The lighting effects controller 112 can operate in conjunction with a Visual Processing Unit (VPU) and an LVM to perform the methods detailed below.

[0120] In some embodiments, the lighting effects controller 112 uses an LVM to process digital image data to extract and identify multiple color categories associated with a desired scene, theme, or environmental context. In some embodiments, the lighting effects controller 112 uses a VPU to process digital image data to extract at least one of the following: primary hue, secondary hue, and gradient color distribution of different color categories.

[0121] In some implementations, the lighting effects controller 112 generates an object-emotion matching table in memory. In some embodiments, the lighting effects controller 112 associates color categories with emotional tendencies.

[0122] In some implementations, the lighting effects controller 112 determines multiple color categories and sentiment tendencies associated with a desired scene, theme, or environmental context based on an object-sentiment matching table. In some embodiments, when determining multiple color categories and sentiment tendencies, the lighting effects controller 112 applies a weighted aggregation to the sentiment tendencies of objects within the digital image data, wherein the weights of the weighted aggregation are based on at least one of the following: the size of the object within the digital image data; the proximity of the object to a center point of interest; or a predefined level of emotional impact on the object.

[0123] In some embodiments, the lighting effect parameter generator 114 generates a plurality of physical lighting effect parameters. In some embodiments, the lighting effect parameter generator 114 associates mood and multiple color categories with predefined lighting effect rules stored in memory, and then calculates values ​​for a plurality of physical lighting effect parameters selected from a group of items including: chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and transition speed between lighting states of a plurality of lighting devices.

[0124] In some embodiments, when generating multiple physical lighting effect parameters, the lighting effect parameter generator 114 accesses a set of lighting system operation constraints from memory; and verifies the values ​​of the multiple physical lighting effect parameters as being below a predetermined threshold by referring to the set of lighting system operation constraints.

[0125] In some implementations, the lighting effect controller 112 transmits electronic control signals representing multiple physical lighting effect parameters to the physical multi-parameter lighting system, thereby dynamically adjusting the emitted light according to the desired scene, theme, or environmental context.

[0126] In some implementations, the lighting effect controller 112 extracts the emotional tendency of objects within digital image data based on at least one of the following: the semantic meaning of the object; the primary color or texture associated with the object; or a predefined emotional dictionary or visual emotional dictionary stored in memory.

[0127] The lighting effects controller 112 can be configured with an adaptive / feedback loop for real-time environmental adjustment.

[0128] In some embodiments, the lighting effects controller 112 receives initial input indicating a desired lighting effect. In some embodiments, the initial input includes natural language text input processed by an NLP engine to extract semantic meaning. In some embodiments, the initial input includes digital image data processed by a vision processing unit to identify visual features.

[0129] In some implementations, the lighting effect controller 112 uses an LLM to determine multiple initial lighting effect parameters based on the initial input.

[0130] In some implementations, the processor 108 transmits electronic control signals representing multiple initial physical lighting effect parameters to the physical multi-parameter lighting system via the lighting control output interface 116.

[0131] In some embodiments, the lighting effect controller 112 monitors real-time environmental conditions within the physical multi-parameter lighting system via at least one environmental sensor. In some embodiments, the at least one environmental sensor includes at least one of the following devices: a photodiode or photoresistor for detecting ambient light intensity; a thermistor or thermocouple for detecting ambient temperature; a PIR sensor or ultrasonic sensor for detecting human occupancy; or a microphone array for detecting ambient sound level and characteristics.

[0132] In some embodiments, the lighting effect controller 112 re-evaluates multiple initial physical lighting effect parameters based on real-time environmental conditions and initial inputs. In some embodiments, when re-evaluating the multiple initial physical lighting effect parameters, the lighting effect controller 112 calculates the deviation between the current state of the emitted light and the desired lighting effect; and adjusts the multiple initial physical lighting effect parameters to generate multiple updated lighting effect parameters to adapt to real-time environmental conditions.

[0133] In some other embodiments, when re-evaluating multiple initial physical lighting effect parameters, the lighting effect controller 112 detects a trigger event based on at least one of the following: real-time environmental conditions deviate from a predetermined threshold; or a predetermined time interval has elapsed since the last adjustment of the multiple initial physical lighting effect parameters.

[0134] In some embodiments, when adjusting multiple initial physical lighting effect parameters, the lighting effect controller 112 increases or decreases the brightness of the emitted light to compensate for changes in ambient light intensity detected by the light sensor, thereby maintaining a constant brightness level.

[0135] In some embodiments, when adjusting a plurality of initial physical lighting effect parameters, the lighting effect controller 112 modifies the light intensity, color temperature, or spatial distribution of emitted light in response to detecting human occupancy via an occupancy sensor, so that the lighting effect adapts to the presence or absence of a human.

[0136] In some embodiments, when adjusting a plurality of initial physical lighting effect parameters, the lighting effect controller 112 synchronizes at least one of the following: flicker rate, brightness modulation, color change of emitted light with a detected rhythm, rhythm, or spectrum of ambient sound data received from a microphone array.

[0137] In some implementations, the processor 108 transmits updated electronic control signals representing multiple updated physical lighting effect parameters to the physical multi-parameter lighting system via an interface, thereby continuously maintaining the desired lighting effect adapted to real-time environmental conditions.

[0138] like Figure 2 An emotion mapping table according to one embodiment is shown. The emotion mapping table, stored in memory 110, associates predefined color categories with corresponding emotional tendencies. Different colors trigger different physiological responses (e.g., heart rate, muscle relaxation or tension) and psychological feelings (e.g., warmth, calmness, passion, hesitation).

[0139] The emotion mapping table associates color category 202 with emotional tendency 204, physiological response 206, and application examples in lighting design 208.

[0140] For example, referring to the first entry of the Emotion Map, the Emotion Map associates warm colors (from color category column 202) with passion, warmth, excitement, intimacy (from emotional tendency column 204), increased blood pressure, increased heart rate, stimulated appetite (from physiological response column 206), as well as the climax of a stage performance, restaurant atmosphere, and festive celebrations (application examples in lighting design column 208).

[0141] The processor 108 accesses the sentiment map from the memory 110 and calculates and determines the sentiment tendency 204 and color category / class 202 related to the user's input based on the output of the AI ​​model.

[0142] The lighting effect parameter generator 114, executed by the processor 108, associates emotional tone and color category with lighting effect rules stored in the memory 110 through calculation. The lighting effect parameter generator 114 then calculates the values ​​of physical lighting parameters (such as chromaticity, saturation, brightness, flicker rate, etc.).

[0143] This disclosure also provides an electronic device, such as... Figure 6 The diagram shown is a schematic representation of an electronic device structure provided in an embodiment of this disclosure. This electronic device can be, for example, the computer system 106 in the system environment 100 described above, including: a processor 301, a memory 302, and a bus 303. The memory 302 stores machine-readable instructions executable by the processor 301 (e.g., ...). Figure 3 The device includes the receiving module 201, the generating module 202, the evaluating module 203, and the updating module 204 (and their corresponding execution instructions). When the electronic device is running, the processor 301 and the memory 302 communicate via the bus 303. When a machine-readable instruction is executed by the processor 301, the following processing is performed: Receive initial input indicating a preset lighting effect; The initial input is processed using a large model to generate multiple initial lighting effect parameter values; Based on real-time environmental conditions fed back by at least one environmental sensor, multiple initial lighting effect parameter values ​​are re-evaluated. Based on the re-evaluation results, multiple updated lighting effect parameter values ​​are generated to maintain the preset lighting effect adapted to real-time environmental conditions.

[0144] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the large-model-based adaptive lighting control method described in the above-described method embodiments. The storage medium can be either volatile or non-volatile computer-readable storage.

[0145] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the large-model-based adaptive lighting control method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0146] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0147] The various embodiments in this disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments. In particular, the description of the apparatus, device, and computer-readable storage medium embodiments is simplified because they are basically similar to the method embodiments, and the relevant parts can be referred to the description of the method embodiments.

[0148] The apparatus, device, and computer-readable storage medium provided in this disclosure correspond one-to-one with the method. Therefore, the apparatus, device, and computer-readable storage medium also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the apparatus, device, and computer-readable storage medium will not be repeated here.

[0149] Those skilled in the art will understand that embodiments of this disclosure can be implemented as methods and apparatus (devices or systems), or as computer-readable storage media. Therefore, this disclosure can be implemented entirely in hardware, entirely in software, or in a combination of software and hardware. Furthermore, this disclosure can be implemented as a computer-readable storage medium on one or more computer-readable storage media containing computer-usable program code (including, but not limited to, disk storage, read-only optical disc storage (CD-ROM), optical storage, etc.).

[0150] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices or systems), and computer-readable storage media according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to create a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0151] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article including instruction means, wherein the instruction means implement the functions specified in one or more flowcharts and / or one or more blocks in a block diagram.

[0152] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram.

[0153] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0154] Memory can include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0155] Computer-readable media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory, read-only memory, electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. Furthermore, although the operations of the methods of this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally, certain steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple sub-steps.

[0156] While the spirit and principles of this disclosure have been described above with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. An adaptive lighting control method based on a large model, characterized in that, include: Receive initial input indicating a preset lighting effect; The initial input is processed using a large model to generate multiple initial lighting effect parameter values; The multiple initial lighting effect parameter values ​​are re-evaluated based on real-time environmental conditions fed back by at least one environmental sensor. Based on the re-evaluation results, multiple updated lighting effect parameter values ​​are generated to maintain the preset lighting effect adapted to the real-time environmental conditions.

2. The method according to claim 1, characterized in that, The re-evaluation of the plurality of initial lighting effect parameter values ​​includes: Based on the real-time environmental conditions, calculate the deviation between the current environment and the environment required for the preset lighting effect; The initial lighting effect parameter values ​​are adjusted based on the deviation to generate multiple updated lighting effect parameter values.

3. The method according to claim 1, characterized in that, The re-evaluation of the plurality of initial lighting effect parameter values ​​includes: In response to the fulfillment of preset triggering conditions, the values ​​of the plurality of initial lighting effect parameters are re-evaluated; The preset triggering conditions include the real-time environmental conditions deviating from preset conditions, or the time interval exceeding a predetermined time interval since the last adjustment of multiple initial lighting effect parameter values.

4. The method according to claim 1, characterized in that, The generation of multiple updated lighting effect parameter values ​​based on the re-evaluation results includes at least one of the following methods: Multiple updated lighting effect parameter values ​​can be generated by adjusting the intensity, color temperature, or spatial distribution of the emitted light. Multiple updated lighting effect parameter values ​​are generated by synchronizing the flicker rate, brightness modulation, or color change of the emitted light with the rhythm or spectrum of ambient sound data.

5. The method according to any one of claims 1 to 4, characterized in that, The initial input includes natural language input, representing the desired emotional or environmental characteristics.

6. The method according to claim 5, characterized in that, The process of using a large model to process the initial input includes: The natural language input is processed using a large language model (LLM) to identify at least one color category associated with the desired emotional or environmental characteristics. Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the natural language input based on the identified color category; Multiple initial lighting effect parameter values ​​are generated based on the target emotional tendency.

7. The method according to claim 6, characterized in that, The generation of multiple initial lighting effect parameter values ​​based on the target emotional tendency includes: Access the lighting effect mapping table to find the association between multiple sentiment tendencies and multiple lighting effect rules, and find the target lighting effect rule corresponding to the target sentiment tendency; Based on the target lighting effect rules, one or more lighting effect parameters, including chromaticity, saturation, brightness, color temperature, flicker rate, light intensity distribution, and lighting state, are assigned values, and multiple initial lighting effect parameter values ​​are generated.

8. The method according to any one of claims 1 to 4, characterized in that, The initial input includes digital image input, representing the desired scene, subject, or environmental context.

9. The method according to claim 8, characterized in that, The process of using a large model to process the initial input includes: The digital image input is processed using a large visual model (LVM) to identify multiple color categories associated with the desired scene, subject, or environmental context. Access the sentiment mapping table to find the association between multiple color categories and multiple sentiment tendencies, and find the target sentiment tendency corresponding to the digital image input based on the identified color categories; Multiple initial lighting effect parameter values ​​are generated based on the target emotional tendency.

10. The method according to claim 9, characterized in that, The method of finding the target sentiment tendency corresponding to the digital image input based on the identified color category includes: The target object data within the digital image input is weighted and aggregated; wherein the weighting is based on at least one of the following: the size of the target object in the image, the proximity of the target object to the center of interest, or a predefined level of emotional influence on the target object; Based on the identified color category and weighted aggregation results, the target sentiment tendency corresponding to the target object in the digital image input is found.

11. The method according to any one of claims 1 to 4, characterized in that, Also includes: Each time a lighting effect parameter value is generated, the lighting system operation constraints are accessed. Verify whether the generated lighting effect parameter values ​​meet the operating constraints of the lighting system to ensure that the output control signal will not cause the lighting system to malfunction.

12. The method according to any one of claims 1 to 4, characterized in that, Also includes: Obtain the user's physiological information in the current environment; The lighting effect parameter values ​​are adjusted based on the physiological information.

13. An adaptive lighting control device based on a large model, characterized in that, include: The receiving module is used to receive initial input indicating a preset lighting effect; The generation module is used to process the initial input using a large model and generate multiple initial lighting effect parameter values. An evaluation module is used to re-evaluate the multiple initial lighting effect parameter values ​​based on real-time environmental conditions fed back by at least one environmental sensor. An update module is used to generate multiple updated lighting effect parameter values ​​based on the re-evaluation results, so as to maintain the preset lighting effect adapted to the real-time environmental conditions.

14. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions that the processor executes. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the adaptive lighting control method based on a large model as described in any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the adaptive lighting control method based on a large model as described in any one of claims 1 to 12.

Images