A method for selecting a light scene from a plurality of light scenes

Abstract

A method for selecting a light scene from a plurality of light scenes for controlling a lighting system. The method comprising the steps of receiving a user input indicative of a light scene selection criterium, selecting a set of light scenes from the plurality of light scenes based on the user input and determining at least two color palettes based on the set of light scenes, wherein each color palette is associated with a subset of the set of light scenes, the subsets at least partially non-overlapping. The method further comprises displaying to the user the at least two color palettes, receiving input from the user indicating a selection of at least one of the at least two color palettes, determining a selected subset of the set of light scenes associated with the selected at least one of the at least two color palettes, and displaying to the user images associated with the selected subset of the set of light scenes. The method further comprises receiving input indicating a selection of an image from the displayed associated images and determining light settings of the light scene based on the selected image.

Description

[0001] 2024PF80247 1

[0002] A method for selecting a light scene from a plurality of light scenes

[0003] FIELD OF THE INVENTION

[0004] The invention relates to method for selecting a light scene from a plurality of light scenes. The invention further relates to a lighting control device for selecting a light scene from a plurality of light scenes. The invention further relates to a lighting arrangement for selecting a light scene from a plurality of light scenes.

[0005] BACKGROUND OF THE INVENTION

[0006] Lighting control systems have been in use for many years to create different lighting scenes for different situations, such as work, relaxation, or entertainment. These systems are designed to provide users with more control over their lighting and create a more personalized experience. Regarding the control of a lighting arrangement, there have been some efforts to control luminaires using natural language processing (NLP). Voice-activated smart home systems like Amazon’s Alexa, Google Home, and Apple’s Siri utilize NLP to understand and execute user commands.

[0007] However, despite the advancements in NLP, users of lighting systems often struggle to express what they are looking for in a lighting scene. They may use generic requests that can be satisfied with many different light scenes. This presents a challenge for lighting systems as they are unable to provide real-time feedback on the range of possible outcomes based on user inputs.

[0008] SUMMARY OF THE INVENTION

[0009] The inventors have realized that a generic user request may be satisfied with a plurality of light scenes. It is therefore an object to provide a system that can help the users of a lighting system select a lighting scene from a plurality of lighting scenes.

[0010] According to a first aspect, the object is achieved by a method for selecting a light scene from a plurality of light scenes for controlling a lighting system. The method comprises the steps of receiving a user input indicative of a light scene selection criterium and selecting a set of light scenes from the plurality of light scenes based on the user input. For example, a user types “I would like to relax” and a set of light scenes that match the user input (light scenes that may provide a relaxing lighting experience) may be selected. 2024PF80247 2

[0011] However, It may not be possible to immediately display the full set of light scenes that match the initial selection criteria. The method further comprises determining at least two color palettes based on the set of light scenes, wherein each color palette is associated with a respective subset of the set of light scenes, the subsets at least partially non-overlapping. A color palette is a grouping of a plurality of individual colors (that may create a theme). For example, a first color palette may comprise a number of warm reds and orange colours and may be associated with light scenes corresponding to sunsets (first subset) e.g., sunset on the beach, sunset in the dessert, etc. A second color palette may comprise a number of hues of green and may be associated with light scenes corresponding to nature (second subset), e.g., a forest, a park, a tropical island, etc. Both the first and the second subset are comprised in the initially selected set of light scenes. A number of palettes (or overall number of colors presented to the user) may indirectly be indicative of the spread and number of scenes that fits or matches with said input (i.e. more colors / palettes are shown for larger number of scenes even if the scenes are all more or less have similar colors. The method further comprises receiving an input from the user indicating a selection of at least one of the at least two color palettes. For example, the user may click on the second color palette to indicate his / her selection, the input may be a voice input indicating the selection of at least one of the color palettes, etc. The method further comprises determining a selected subset from the respective subsets of the set of light scenes, said selected subset associated with the selected at least one of the at least two color palettes and displaying to the user images associated with the selected subset of the set of light scenes that corresponds to the selected at least one of the least two color palettes. That is, after the selection of the preferred at least one color palette, the method comprises displaying to the user images that are associated with the subset of light scenes that correspond to this selected color palette. The method further comprises receiving input from the user indicating a selection of an image from the displayed associated images and determining light settings of the light scene based on the selected image. If a single image is associated with the selected color palette, said single image is considered automatically selected by the user. The method may further comprise controlling the lighting system according to the determined light settings of the light scene.

[0012] By initially displaying color palettes associated with subsets of light scenes, the method allows users to see the breadth of available light scenes (corresponding to his input) without overwhelming them with all the available light scenes, i.e., with the full set of initially selected light scenes. The user may consequently select a preferred color palette, and images associated with this selection are displayed. This approach helps the user to 2024PF80247 3 efficiently and user-friendly select a light scene from a plurality of light scenes associated with their input.

[0013] The method may further comprise receiving a further portion of the user input, said further portion indicative of the light scene selection criterium, and updating the set of light scenes based on the further portion of the user input resulting in an updated set of light scenes, wherein said updated set of light scenes is a subset of the (initially selected) set of light scenes. For example, a user types a first portion of the user input “A sunset” and a set of light scenes from the plurality of light scenes is selected based on the first portion. The user continues typing a second portion of the user input “A sunset on the beach”. A further subset from the initially selected set of light scenes is selected corresponding to the second portion (light scenes corresponding to beach sunsets). This allows the selected set of light scenes to be continuously updated based on the user input received so far, providing a more personalized and refined set of light scenes for the user to choose from.

[0014] Preferably, each light scene from the plurality of light scenes may be associated with a textual description and / or an image representing the scene. The step of selecting the set of light scenes from the plurality of light scenes based on the user input may comprise selecting the set of light scenes for which a semantic similarity metric between the user input and the corresponding textual description and / or image of the plurality of light scenes is above a similarity threshold. For example, light scenes for which a semantic similarity between the user input and the corresponding textual description is above a similarity threshold are selected or light scenes for which a keyword or phrase in the user input matches a keyword or phrase in the corresponding textual description are selected.

[0015] The step of determining the at least two color palettes based on the set of light scenes may comprise determining a first color palette and a second color palette, wherein the first color palette has a higher color contrast from the second color palette. Color contrast in a color palette may refer to a degree of visual difference between colors comprising the palette. It is a measure of how much the colors in a palette stand out from each other, and is based on factors such as brightness, saturation, and hue. A higher color contrast in a palette means that the colors used are more distinct from each other, while a lower color contrast means that the colors are more similar and may be harder to distinguish. Presenting to the user color palettes with different degrees of color contrast facilitate the user to select a scene with a desired level of contrast, e.g., the user may say “I would like to have mild color variations”.

[0016] Each light scene from the plurality of light scenes may be associated with an image, and the step of determining the at least two color palettes based on the set of light 2024PF80247 4 scenes may comprise extracting colors from the images associated with the subset of the set of light scenes such that a first color palette from the at least two color palettes comprises colors extracted from a first subset of the set of light scenes and a second color palette from the at least two color palettes comprises colors extracted from a second subset of the set of light scenes. The subsets are at least partially non-overlapping.

[0017] The method may further comprise determining the subsets of the set of light scenes using a machine learning model on the corresponding images. For example, an unsupervised image clustering algorithm may be used on the images associated with the plurality of light scenes to determine clusters (subsets) of similar images.

[0018] A subset from the subsets of the set of light scenes may comprise a first and a second light scene, wherein the first light scene is associated with a first set of colors and the second light scene is associated with a second set of colors and wherein a color distance metric between the first and the second sets of colors is above a color threshold. For example, a subset of the set of light scenes according to a “relaxing” criterium may comprise a first “crocus” light scene associated with colours purple, lavender, yellow and a second “Narcissa” light scene associated with colours purple, yellow, light blue. Those light scenes were grouped together to form a subset of light scenes as the color distance between the first and second sets of colors is below a color distance threshold. The color palette associated with the subset from the subsets of the sets of light scenes comprises colours from the first and the second sets of colours. For example, a random selection, the most dominant colours, all colours from the first and second sets, etc.

[0019] Additionally, and or alternatively, a subset from the subsets of the set of light scenes may comprise a first and a second light scene, wherein the first light scene is associated with a first textual description and the second light scene is associated with a second textual description and wherein a semantic similarity metric between the first and the second textual description is above a semantic similarity threshold. Each light scene from the plurality of light scenes may be associated with a textual description. For example, a light scene may be associated with a textual description of the mood that the light scene evokes to the user or may be associated with a description of an image associated with the light scene, etc. The method may comprise determining a subset of the set of light scenes based on a semantic similarity metric between the textual descriptions associated with each light scene. In that way, light scenes from the set of light scenes for which a semantic similarity metric between the corresponding textual descriptions is above a threshold are grouped together to form the subset of the set of light scenes. 2024PF80247 5

[0020] The method may comprise refraining from displaying to the user the images associated with the selected subset of the set of light scenes if a number of images associated with said selected subset is above an image threshold. Said image threshold may depend on a type of display device. For example, if the user is accessing the information through a mobile device with a smaller screen, the image threshold may be lower than if the user is accessing the information through a larger computer screen or projector. The number of images associated with the selected subset may be too high to be displayed to the user in some cases. This may occur if the subset is particularly large or if the images are of a high resolution. In these instances, it may be beneficial to implement the refraining method to ensure a smooth and efficient user experience.

[0021] If the number of images associated with the selected subset is above the image threshold, it may not be possible to display them to the user. In such cases, it may be beneficial to determine at least two further color palettes based on the selected subset. Each updated palette may be associated with a further subset of the selected subset of the set of light scenes. This can be achieved by dividing the selected subset into smaller subsets, each associated with an updated palette. By splitting the selected subset into further subsets, users can still access the relevant information, but in a more organized and manageable way. This approach can help to optimize the user experience and ensure that the information is presented in a clear and concise manner.

[0022] According to a second aspect, the object is achieved by a lighting control system for controlling operation of a lighting system according to a selected light scene. The lighting control system comprises an input interface, an output interface and a controller. The controller is configured to receive a user input indicative of a light scene selection criterium, select a set of light scenes from a plurality of light scenes based on the user input, determine at least two color palettes based on the set of light scenes, wherein each color palette is associated with a subset of the set of light scenes, the subsets at least partially nonoverlapping, display to the user the at least two color palettes, receive input from the user indicating a selection of at least one of the at least two color palettes. The controller is further configured to determine a selected subset of the set of light scenes associated with the selected at least one of the at least two color palettes, display to the user images associated with the selected subset of the set of light scenes, receive input from the user indicating a selection of an image from the displayed associated image, and determine light settings of the light scene based on the selected image and provide control signals indicative of the 2024PF80247 6 respective light settings for controlling the lighting system. Thus, the lighting control device of the second aspect of the invention shares the advantages of the method of the first aspect.

[0023] The input indicating the selection of the at least one color palette comprises one or more of: a voice input indicative of an explicit selection of the at least one color palette (e.g., user explicitly saying “I prefer the first color palette”), a voice input indicative of an implicit selection of the at least one color palette (e.g., a voice input that refers to a characteristic or property of the at least one color palette), a button press, etc. For example, the user may click on the selected color palette (button click) to indicate his / her selection or may refer to properties of his / her selected color palette. For example, user may request a relaxing scene with blue hues (indicating the selection of the color palette that displays blue hues).

[0024] According to a third aspect, the object is achieved by a lighting arrangement. The lighting arrangement comprises a lighting control device in accordance with the second aspect and a lighting system configured to receive control signals indicative of the respective light settings and to operate in dependence thereof. Thus, the lighting arrangement of the third aspect of the invention shares the advantages of the lighting control device of the second aspect.

[0025] According to a fourth aspect, the object is achieved by a computer program comprising instruction which, when executed by a lighting control device, cause the lighting control device to perform the steps of the method of the first aspect.

[0026] As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a device, a method or a computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a "circuit", "module" or "system." Functions described in this disclosure may be implemented as an algorithm executed by a processor / microprocessor of a computer. Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied, e.g., stored, thereon.

[0027] Any combination of one or more computer readable medium(s) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or 2024PF80247 7 semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer readable storage medium may include, but are not limited to, the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of the present invention, a computer readable storage medium may be any tangible medium that can contain, or store, a program for use by or in connection with an instruction execution system, apparatus, or device.

[0028] A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0029] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber, cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java(TM), Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0030] Aspects of the present invention are described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood 2024PF80247 8 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 may be provided to a processor, in particular a microprocessor or a central processing unit (CPU), of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer, other programmable data processing apparatus, or other devices create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0031] These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0032] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0033] The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of devices, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. 2024PF80247 9

[0034] BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above, as well as additional objects, features and advantages of the disclosed systems, devices and methods will be better understood through the following illustrative and non-limiting detailed description of embodiments of devices and methods, with reference to the appended drawings, in which:

[0036] Fig. 1 shows schematically an example of a lighting arrangement for controlling operation of a lighting system according to a selected light scene;

[0037] Fig. 2 shows schematically an example of color palettes determined based on a set of light scenes;

[0038] Fig. 3 shows schematically an example of color palettes determined based on a set of light scenes;

[0039] Fig. 4 shows schematically a method of controlling operation of a lighting system according to a selected light scene.

[0040] All the figures are schematic, not necessarily to scale, and generally only show parts which are necessary in order to elucidate the invention, wherein other parts may be omitted or merely suggested.

[0041] DETAILED DESCRIPTION

[0042] Fig. 1 shows an example of a lighting arrangement 100 comprising a lighting control system 105 and a lighting system 150. The lighting control system 105 comprises an input interface 102, e.g., a receiver, an input port, etc., an output interface 104, e.g., a transmitter, an output port for a display, etc. and a controller 106. The lighting control system 105 may further comprise at least one data repository or storage or memory 108 for storing computer program code instructions. The controller 106 may further be communicatively coupled to the cloud 120. Said memory module 108 may be comprised in the cloud 120. The lighting control system 105 may be comprised in a single device, for example, a smart phone device or parts of the system 105 may be comprised in multiple devices, e.g., a voice assistant device and a mobile phone device, etc.

[0043] The lighting control system 105 is for controlling operation of the lighting system 150 according to a selected light scene. A light scene may be defined by a respective set of light settings (light scene data set) for a lighting system comprising one or more light sources (luminaires). Each light setting contains information on which luminaires belong to it and defines one or more lighting parameters for those luminaires, such as colour parameter(s) 2024PF80247 10 and / or brightness parameter (s), i.e., a colour point and / or a brightness level at which each of the luminaire is set.

[0044] The lighting control system 105 is configured to receive, via the input interface 102, a user input indicative of a light scene selection criterium. Said user input may be a voice input e.g., user speaking to a voice assistant device such as Siri or Alexa, a text input e.g., user typing on a personal device. It may be a direct indication of the user’s intention such as “I want to create a light scene that resembles a sunset” , or a more abstract text such as “I want to relax” from which a light scene can be inferred.

[0045] The controller 106 is configured to select a set of light scenes from a plurality of light scenes based on the user input. The plurality of light scenes may be stored in a light scene repository or database (e.g., memory 108). In another embodiment, the plurality of light scenes may be generated, e.g., using a generative machine learning model.

[0046] In an embodiment, the selection of the set of light scenes is based on a semantic similarity metric. Semantic similarity refers to the degree to which two inputs are similar in terms of their meaning. Each light scene from the plurality of light scenes may be associated with a textual description. For example, an “Energize” light scene may be stored in the scene database together with a textual description describing the light scene e.g., “Get energized with cool, blue-toned light. This light recipe helps you add a little pep to your morning or an extra punch to your workout”. A “Yoga” light scene may be stored in the scene database together with a textual description describing the light scene e.g., “This light scene is designed to create a serene and relaxing atmosphere that is perfect for your yoga practice. It can also be used to enhance your morning routine or your workout”. The controller 106 may be configured to select the set of light scenes for which a semantic similarity metric between the (text) user input and the corresponding textual description of the plurality of light scenes is above a similarity threshold. In an example, the user input may be “I am starting a workout”. Said user input may be a text user input, or a voice input converted to text. The “Energize” and “Yoga” light scenes may be selected as a semantic similarity metric between the textual description associated with the scenes and the user input is above the threshold. Several methods and techniques are known in prior art for determining semantic similarity between text, e.g., word embeddings word embeddings, Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA), etc.

[0047] Additionally, and or alternatively, each light scene from the plurality of light scenes may be associated with an image. The controller 106 may be configured to select the set of light scenes for which a semantic similarity metric between the user input and the 2024PF80247 11 corresponding image of the plurality of light scenes is above a similarity threshold. For example, a Convolutional Neural Network can be used to extract visual features from images, such as color, texture, and shape, while a Recurrent Neural Network can be used to extract semantic features from text input. These features can then be compared to identify a semantic similarity between the text and the images. In another embodiment, the images associated with the plurality of light scenes may be converted into an associated textual description, e.g., by computer vision techniques to extract key visual features and convert them into a textual description.

[0048] In embodiments, the controller may be configured to select the set of light scenes by selecting light scenes for which a semantic similarity metric between the user input and textual description and / or image of the plurality of light scenes is above a first threshold and for which a semantic similarity between the scenes in the set (inter-scene similarity) is above a second threshold.

[0049] The controller 106 is configured to determine at least two color palettes based on the set of light scenes. Each color palette is associated with a subset of the set of light scenes, the subsets at least partially non-overlapping. The at least two color palettes may be generated using a generative Al model, e.g., GAN, LLM, stable diffusion model, based on the user input. Each light scene from the plurality of light scenes may be associated with a set of colors representing the scene. Each determined color palette from the one or more color palettes may comprise colours of respective sets of colors associated with subsets of the set of light scenes. The colours comprising each color palette from the at least two determined color palettes may be selected (e.g., randomly) from the sets of colors associated with the respective subset of the set of light scenes.

[0050] Fig. 2 shows an example of two color palettes 201 and 202 determined based on an initial set A of light scenes. For example, a user requests a “party” light scene, and an initial set A of 4 light scenes is selected that matches the users criterium. A first color palette 201 comprising colors associated with a first subset B of the set of light scenes and a second color palette 202 comprising colors associated with a second subset C of the set of light scenes. Each light scene from the set of light scenes may be associated with a set of colours. In the example of Fig. 2, a first light scene “Motown” is associated with a first set of colours, a second light scene “Tokyo” is associated with a second set of colours, a third light scene “Ibiza” is associated with a third set of colours, and a fourth light scene “Miami” is associated with a fourth set of colours. The controller 106 may determine the first subset B of light scenes comprising the first and second light scenes based on a color distance metric. 2024PF80247 12

[0051] That is, the first and second light scenes may be grouped to form the first subset B as the color distance metric between the first and second color palette is below a distance threshold. The third and fourth light scenes may be grouped to form the second subset C as the color distance metric between the third and fourth color palette is below a distance threshold. There are several methods for quantifying the distance between colors in a color space, such as Euclidean distance or Delta E of their RGB or HEX values, which may also take into account different aspects of color perception, such as hue, saturation, and brightness.

[0052] The controller 106 may determine the color palettes 201, 202 by randomly selecting colors of respective sets of colors associated with the first and second subsets. Alternatively, the most dominant colors from the respective sets of colors may be selected. In another embodiment, the colours that best represent the range and spread of colours in the respective subset are selected, i.e., colours that have a maximum distance from the rest of colours in the subsets. In embodiments, a clustering algorithm may be applied on the colours of the subset and the central color of each cluster may be selected. In embodiments, the colours comprised in each subset may be sorted in the color space and a predetermined locations in the sorted colours may be selected, e.g., each 10th color may be selected.

[0053] In an embodiment, the colours are selected such that the first color palette has a higher color contrast from the second color palette.

[0054] In another embodiment, each light scene from the plurality of light scenes may be associated with an image representing the scene. Fig. 3 shows an example of 4 light scenes and associated images. The controller 106 may determine the at least two color palettes by extracting colors from the images associated with the subset of the set of light scenes. For example, a first color palette 301 is determined by extracting colors from the first and second image associated with a first subset B and a second color palette 302 is determined by extracting colors from the third and fourth image associated with a second subset C.

[0055] In embodiments, the subsets of the set of light scenes may be determined using a machine learning model on the associated images. For example, an unsupervised image clustering algorithm may be used on the images associated with the plurality of light scenes to determine clusters (subsets) of similar images. The clustering may be based on semantic similarity, color similarity, etc. In the example of Fig. 3, images are grouped to form subsets (e.g., subsets B and C) of the initially selected set of light scenes A based on color similarity.

[0056] In embodiments, the subsets of the set of light scenes may be determined based on a semantic similarity metric. Each light scene from the plurality of light scenes may be associated with a textual description. For example, a first “Storybook” light scene may be 2024PF80247 13 associated with a first textual description describing the light scene “Curl up with a good book in your reading nook.”, a second “Read” light scene may be associated with a second textual description “Get the right shade of bright, warm light to read in.”. Alternatively, said descriptions may comprise the title of the light scenes. The first and second light scenes may be grouped to form a first subset of the set of light scenes as the semantic similarity metric between the first and second descriptions is above the similarity threshold.

[0057] The controller 106 is further configured to display to the user, via the output interface, the at least two color palettes, for example on a display unit such a mobile phone. That is, the controller 106 is configured to provide, via the output interface 104, image data indicative of the at least two color palettes for displaying the corresponding at least two color palettes to the user. For example, the controller 106 is configured to transmit the image data indicative of the at least two color palettes to an image providing unit 160 for displaying the corresponding at least two color palettes to the user. The image providing unit 160 is signally connected to the output interface 104 for receiving the image data and comprises a display for displaying the at least two color palettes. The image providing unit can be, for instance a television, a smart phone, a tablet, a digital frame, a computer including a monitor, or any other device that can receive image data and display the corresponding image. The at least two color palettes may be sorted when displayed to the user in terms of semantic distance to the user request (e.g., color palettes assosiated with light scenes that better match user input are presented first), average color temperature, colorfulness of the scenes assosiated with the color palettes, etc.

[0058] The controller 106 is further configured to receive, via the input interface 102, input from the user indicating a selection of at least one of the at least two color palettes. Said input may, in embodiments, comprise a voice input indicative an explicit selection of the at least one color palette, e.g., user says “I prefer the first color palette” or a voice input indicative of an implicit selection of the at least one color palette. For example, the voice input may be indicative of a reference to a property or characteristic of at least one color palette from the at least two color palettes e.g., user says “I prefer vibrant colors” or “I prefer neutral tones”. Said input may comprise a button press, for example user clicks on the color palette to select it.

[0059] The controller 106 is further configured to determine a selected subset from the subsets of the set of light scenes, said selected subset associated with the selected at least one of the at least two color palettes. Each color palette is associated with a respective subset 2024PF80247 14 of the set of light scenes. When the user selects a color palette, the subset associated with the selected color palette is determined to be selected.

[0060] The controller 106 is further configured to display to the user images (static or animated images (GIF) or video associated with the selected subset of the set of light scenes (images associated with the selected at least one of the at least two color palettes). That is, the controller 106 is configured to provide, via the output interface, image data indicative of images associated with the selected subset of the set of light scenes (images associated with the selected at least one of the at least two color palettes) for displaying the corresponding images to the user. For example, the controller 106 is configured to transmit the image data indicative of the images to an image providing unit 160 for displaying the corresponding images to the user. The image providing unit 160 is signally connected to the output interface 104 for receiving the image data and comprises a display for displaying the images. In the example of Fig. 3, if color palette 302 is selected by the user, images 306 and 307 associated with the “Ibiza” and “Miami” light scene (images associated with subset C) are displayed to the user. The images associated with the selected subset may be generated using a generative Al model. This could be the same generative Al model used for generating the at least two colour palettes or a different generative Al model. For example, a first simpler generative model may be used to generate the at least two palettes and a second more complex model may be used to generate the associated images. The images may be generated based on the selected at least one of the at least two colour palettes and the user input. This is beneficial as it allows for unique and customized elements and colors in the images presented to the user, even if the themes are the same. For example, using the input "savannah sunset" with mostly orange colors would generate an image focusing on the sun, while using a similar palette with added green would generate an image with both the sun and vegetation.

[0061] The controller 106 is further configured to receive, via the input interface 102, input from the user indicating a selection of an image from the displayed associated images. Said input indicating the selection of an image may comprise a voice input, a button press, etc. In embodiments, if the selected subset consists of a single image, said image is automatically selected.

[0062] The controller 106 is further configured to determine light settings of the light scene based on the selected image. For example, the controller 106 may extract color data from the selected image, determine respective light settings indicative of lighting operation parameters for the one or more lighting devices of the lighting system 150 using the color data. The controller 106 may provide control signals CS indicative of the respective light 2024PF80247 15 settings for controlling the lighting devices of the lighting system 150. The light settings may specify a color palette and a distribution of the colors and color temperatures among the available lighting devices of the lighting system 150. Further, the light settings may optionally specify how the colors change over time. For example, the user selects image 307 from the displayed images 306 and 307 assosiated with color palette 302. The controller 106 may determine a light setting rendering pink for a first (centrally located) lighting device based on the color of the pink swan represented in the selected image 307 and a blue light for the surounding lighting devices based on the sea represented in the selected image 307. Colors from the selecred image may be mapped to lighting devices by determining colors at locations in the image which correspond to the locations of the lighting device. When mapping colors from the selected image to lighting devices of the lighting system 150, it may be taken into account whether a lighting device is capable of rendering color or white-only.

[0063] In embodiments, the controller 106 may be configured to receive, via the input interface 102, a further portion of the user input. For example, the user may have typed “A sunset” and based on the first user input an initial set of light scenes from the plurality of light scenes is selected. If a further portion of the user input is received, e.g., user continues typing “A sunset on the beach”, the controller 106 may update the initally selected set of light scenes based on the further portion of the user input. That is, the controller 106 may determine a subset of the initially selected set of light scenes, said subset selected based on the further portion of the user input resulting in an updated set of light scenes.

[0064] In embodiments, if a number of images comprised in the selected subset is above an image threshold, the controller 106 refrains from displaying to the user the images assosiated with the selected subset. In such case, the controller 106 may be configured to determine at least two further color palettes based on the selected subset of the set of light scenes. Each color palette may be associated with a further subset of the selected subset of the set of light scenes. The image threshold may depend on a display type. For example, if the number of images associated with the subset associated with the selected color palettes is above a threshold, say 4, the controller 106 may determine further subsets of the selected subset (determine groups for the light scenes comprised in the selected subset) and determine at least two further color palettes associated with the further subsets. The further subsets may be determined by grouping the light scenes comprised in the selected subset based on a semantic similarity metric, based on textual description, color distance metric, etc.

[0065] Fig. 4 shows a method 400 for selecting a light scene from a plurality of light scenes for controlling a lighting system. The method comprises the steps of receiving 402, 2024PF80247 16 via an input interface, a user input indicative of a light scene selection criterium, selecting 404 a set of light scenes from the plurality of light scenes based on the user input, and determining 406 at least two color palettes based on the set of light scenes, wherein each color palette is associated with a subset of the set of light scenes, the subsets at least partially non-overlapping.

[0066] The method further comprises displaying 408 to the user, via an output interface, the at least two color palettes. That is the method comprises providing, via an output interface, image data indicative of the at least two color palettes to an image providing unit for displaying the corresponding at least two color palettes to the user.

[0067] The method further comprises receiving 410, via an input interface, input from the user indicating a selection of at least one of the at least two color palettes, determining 412 a selected subset of the set of light scenes associated with the selected at least one of the at least two color palettes, and displaying 414 to the user, via the output interface, images associated with the selected subset of the set of light scenes. That is, the method comprises providing, via the output interface, image data indicative of the images associated with the selected subset to an image providing unit for displaying the corresponding images to the user.

[0068] The method further comprises receiving 416, via an input interface, input indicating a selection of an image from the displayed associated images; and determining 418 light settings of the light scene based on the selected image.

[0069] The method 400 may be executed by computer program code of a computer program product when the computer program product is run on a processing unit of a computing device, such as the processor 106 of the lighting control system 105.

[0070] Various embodiments of the invention may be implemented as a program product for use with a computer system, where the program(s) of the program product define functions of the embodiments (including the methods described herein). In one embodiment, the program(s) can be contained on a variety of non-transitory computer-readable storage media, where, as used herein, the expression “non-transitory computer readable storage media” comprises all computer-readable media, with the sole exception being a transitory, propagating signal. In another embodiment, the program(s) can be contained on a variety of transitory computer-readable storage media. Illustrative computer-readable storage media include, but are not limited to: (i) non-writable storage media (e.g., read-only memory devices within a computer such as CD-ROM disks readable by a CD-ROM drive, ROM chips or any type of solid-state non-volatile semiconductor memory) on which information is 2024PF80247 17 permanently stored; and (ii) writable storage media (e.g., flash memory, floppy disks within a diskette drive or hard-disk drive or any type of solid-state random-access semiconductor memory) on which alterable information is stored. The computer program may be run on the processor 302 described herein.

[0071] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0072] The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The description of embodiments of the present invention has been presented for purposes of illustration but is not intended to be exhaustive or limited to the implementations in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the present invention. The embodiments were chosen and described to best explain the principles and some practical applications of the present invention, and to enable others of ordinary skill in the art to understand the present invention for various embodiments with various modifications as are suited to the particular use contemplated.

Claims

2024PF80247 18CLAIMS:

1. A method for selecting a light scene from a plurality of light scenes for controlling a lighting system, wherein each light scene from the plurality of light scenes is associated with a textual description and / or image, the method comprising the steps of: receiving (402) a user input indicative of a light scene selection criterium; selecting (402) a set of light scenes from the plurality of light scenes based on the user input by selecting the set of light scenes for which a semantic similarity metric between the user input and the corresponding textual description and / or image of the plurality of light scenes is above a similarity threshold; determining (404) at least two color palettes based on the set of light scenes, wherein each color palette is associated with a respective subset of the set of light scenes, the subsets at least partially non-overlapping; displaying (406) to the user the at least two color palettes; receiving input from the user indicating a selection of at least one of the at least two color palettes; determining (408) a selected subset from the respective subsets of the set of light scenes associated with the selected at least one of the at least two color palettes; displaying (410) to the user images associated with the selected subset of the set of light scenes, wherein the images are associated with the selected at least one of the at least two color palettes; receiving (412) input indicating a selection of an image from the displayed associated images; and determining (414) light settings of the light scene based on the selected image.

2. The method according to claim 1, wherein the method further comprises controlling the lighting system according to the determined light settings of the light scene.

3. The method according to claim 1, wherein the method further comprises receiving a further portion of the user input indicative of the light scene selection criterium;2024PF80247 19 updating the set of light scenes based on the further portion of the user input.

4. The method according to any preceding claim, wherein the step of determining the at least two color palettes based on the set of light scenes comprises determining a first color palette and a second color palette, wherein the first color palette has a higher color contrast from the second color palette.

5. The method according to any preceding claim, wherein each light scene from the plurality of light scenes is associated with an image, and wherein the step of determining the at least two color palettes based on the set of light scenes comprises extracting colors from the images associated with the subset of the set of light scenes.

6. The method according to any preceding claim, wherein each light scene from the plurality of light scenes is associated with an image, and wherein the subsets of the set of light scenes are determined using a machine learning model on the associated images.

7. The method according to claim 1, wherein a subset from the subsets of the set of light scenes comprises a first and a second light scene, wherein the first light scene is associated with a first set of colors and the second light scene is associated with a second set of colors and wherein a color distance metric between the first and the second sets of colors is below a color distance threshold, and wherein the color palette associated with the subset from the subsets of the sets of light scenes comprises colours from the first and the second sets of colours.

8. The method according to claim 1, wherein a subset from the subsets of the set of light scenes comprises a first and a second light scene, wherein the first light scene is associated with a first textual description and the second light scene is associated with a second textual description and wherein a semantic similarity metric between the first and the second textual description is above a semantic similarity threshold.

9. The method according to any preceding claim, wherein the method comprises refraining from displaying to the user the images associated with the selected subset of the set of light scenes if a number of images associated said selected subset is above an image threshold.2024PF80247 2010. The method according to claim 9, wherein the method comprises determining at least two further color palettes based on the selected subset of the set of light scenes, wherein each further color palette is associated with a further subset of the selected subset of the set of light scenes.

11. A lighting control system (105) for controlling operation of a lighting system (150) according to a selected light scene, the lighting control system comprising: an input interface (102), an output interface (104), and a controller (106), said controller configured to: receive, via the input interface, a user input indicative of a light scene selection cri terium; select a set of light scenes from a plurality of light scenes based on the user input, wherein each light scene from the plurality of light scenes is associated with a textual description and / or image and wherein the controller is configured to select the set of light scenes for which a semantic similarity metric between the user input and the corresponding textual description and / or image of the plurality of light scenes is above a similarity threshold; determine at least two color palettes based on the set of light scenes, wherein each color palette is associated with a respective subset of the set of light scenes, the subsets at least partially non-overlapping; display to the user, via the output interface, the at least two color palettes; receive, via the input interface, input from the user indicating a selection of at least one of the at least two color palettes; determine a selected subset from the respective subsets of the set of light scenes associated with the selected at least one of the at least two color palettes; display to the user, via the output interface, images associated with the selected subset of the set of light scenes, wherein the images are associated with the selected at least one of the at least two color palettes; receive, via the input interface, input from the user indicating a selection of an image from the displayed associated images; and determine light settings of the light scene based on the selected image and provide control signals indicative of the respective light settings for controlling the lighting system.2024PF80247 2112. The lighting control system according to claim 11, wherein the input indicating the selection of the at least one color palette comprises one or more of: a voice input indicative of an explicit selection of the at least one color palette, a voice input indicative of an implicit selection of the at least one color palette, a button press.

13. A lighting arrangement (100) comprising:- a lighting control system (105) in accordance with any of the claims 11-12; and - a lighting system (150) configured to receive control signals indicative of the respective light settings and to operate in dependence thereof.

14. A computer program product for a computing device, the computer program product comprising computer program code to perform the method of claim 1 when the computer program product is run on a processing unit of the computing device.

Images