Lighting device regulation method and apparatus, and lighting device and storage medium

Abstract

A lighting device regulation method and apparatus, and a lighting device and a storage medium. The lighting device regulation method comprises: acquiring user expression information (S11); inputting the user expression information into a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information (S12); and regulating the lighting device on the basis of the target lighting instruction (S13). In the lighting device regulation method, a lighting device is regulated by means of user expression information, and direct interaction between a user and the lighting device is realized, thereby simplifying a control operation of the lighting device, and thus improving the control efficiency of the lighting device.

Description

Lighting equipment adjustment method, device, lighting equipment and storage medium Technical Field

[0001] The present application belongs to the field of lighting technology, and in particular relates to a lighting equipment adjustment method, device, lighting equipment and storage medium. Background Art

[0002] With the continuous development of lighting technology, healthy and energy-saving smart lighting has become a trend. For lighting equipment, in order to adapt to different scene requirements, lighting equipment is usually equipped with multiple adjustable lighting modes, allowing users to adjust the lighting mode of the lighting equipment according to their needs to suit the corresponding scene requirements.

[0003] However, in the related art, it is often necessary to control multiple lighting devices through touch switches, output direct voice control commands, etc., which is complicated to operate and affects the control efficiency of the lighting devices.

[0004] Summary of the Invention

[0005] Embodiments of the present application provide a lighting device adjustment method, apparatus, lighting device, and storage medium to improve the problem of low control efficiency of lighting devices.

[0006] A first aspect of an embodiment of the present application provides a lighting device adjustment method, which is applied to a lighting device, and the method includes: obtaining user expression information; inputting the user expression information into a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information; and adjusting the lighting device according to the target lighting instruction.

[0007] Furthermore, in the above method provided in the embodiment of the present application, the user expression information includes at least one of the following: voice expression, text expression, picture expression, facial expression, body expression and musical expression.

[0008] Furthermore, in the above method provided in the embodiment of the present application, the lighting instruction generation model includes a word segmenter, an embedding layer, a core operation layer and a multi-layer perception network, and the user expression information is input into the lighting instruction generation model to obtain the target lighting instruction corresponding to the user expression information, including: inputting the user expression information into the word segmenter to obtain digital expression information; inputting the digital expression information into the embedding layer to obtain an expression vector; inputting the expression vector into the core operation layer to obtain implicit lighting features; and inputting the implicit lighting features into the multi-layer perception network to obtain target lighting instructions.

[0009] Furthermore, in the above method provided in the embodiment of the present application, if the user expression information includes expression information of multiple users, the method also includes: inputting the user expression information corresponding to each user into the lighting instruction generation model to obtain the target lighting instruction corresponding to each user; determining the lighting area corresponding to each target lighting instruction; and adjusting the lighting equipment in the lighting area according to the target lighting instruction.

[0010] Furthermore, in the above method provided in the embodiment of the present application, if the user expression information includes expression information of multiple users, the method also includes: determining the client corresponding to each user expression information; selecting a target client from the clients, and inputting the user expression information corresponding to the target client into the lighting instruction generation model; or determining the voiceprint feature corresponding to each user expression information; selecting a target voiceprint feature from the voiceprint features, and inputting the user expression information corresponding to the target voiceprint feature into the lighting instruction generation model.

[0011] Furthermore, in the above method provided in the embodiment of the present application, after adjusting the lighting device according to the target lighting instruction, the method also includes: obtaining supplementary user expression information corresponding to the user expression information; inputting the supplementary user expression information into the lighting instruction generation model to obtain an updated target lighting instruction corresponding to the supplementary user expression information; and adjusting the lighting device according to the updated target lighting instruction.

[0012] Furthermore, in the above method provided in an embodiment of the present application, after adjusting the lighting device according to the updated target lighting instruction, the method also includes: using the user expression information and the updated target lighting instruction as training data; training the lighting instruction generation model according to the training data to obtain an updated lighting instruction generation model.

[0013] The second aspect of an embodiment of the present application also provides a lighting equipment adjustment device, which includes: an expression information receiving module for obtaining user expression information sent by a client; a lighting instruction generation module for inputting the user expression information into a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information; and a lighting equipment adjustment module for adjusting the lighting equipment according to the target lighting instruction.

[0014] A third aspect of an embodiment of the present application further provides a lighting device, which includes a controller and a memory, and the controller is configured to implement any one of the above-mentioned lighting device adjustment methods when executing a computer program stored in the memory.

[0015] A fourth aspect of the embodiments of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a controller, any one of the above-mentioned lighting device adjustment methods is implemented.

[0016] The lighting device adjustment method provided in the embodiments of the present application obtains user expression information, inputs the user expression information into a lighting command generation model, obtains a target lighting command, and then adjusts the lighting device according to the target lighting command. Adjusting the lighting device based on the user expression information enables direct interaction between the user and the lighting device, simplifies lighting device control operations, and thus improves lighting device control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a diagram showing an application scenario of a lighting equipment adjustment method provided in an embodiment of the present application.

[0018] FIG2 is a flow chart of a lighting equipment adjustment method provided in an embodiment of the present application.

[0019] FIG3 is a flow chart of determining a target lighting instruction provided in an embodiment of the present application.

[0020] FIG4 is a flowchart of determining an updated target lighting instruction provided in an embodiment of the present application.

[0021] FIG5 is a flowchart of adjusting the lighting instruction generation model provided in an embodiment of the present application.

[0022] FIG6 is a flowchart of determining a lighting area provided in an embodiment of the present application.

[0023] FIG7 is a schematic structural diagram of a lighting equipment adjustment device provided in an embodiment of the present application.

[0024] FIG8 is a schematic structural diagram of a lighting device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] It should be noted that the terms "first" and "second" in the description, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0026] It should also be noted that the method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0027] The following will describe some embodiments with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0028] Combined with Figure 1, the application scenario of the embodiment of the present application is illustrated. The user expression information can come from the display selection interface of the lighting device (for example, the display selection interface contains multiple expression information, and the user expression information is determined by monitoring the user's selection of expression information), or a client installed on a mobile device, or a mobile terminal on an electronic device, etc., which does not restrict user input operations, and is not limited here. The embodiment of the present application only takes the user expression information coming from the client as an example, and the client is communicatively connected with the lighting device. The client can be a mobile device, a camera device, a video doorbell or door lock, or other devices with text collection, voice collection and image recording functions to ensure that the user expression information can be obtained. A lighting device refers to a lighting device that can provide a lighting function.

[0029] In some embodiments, the client is used to collect user expression information, and the expression methods may include but are not limited to voice expression, text expression, picture expression, expression, body expression, and music expression, etc. For example, the user expression information may be information in the form of voice expression such as "I'm having a party", "I want to read a book", "I want to sleep", and "I want to cook"; or the user expression information may be information in the form of text expression such as "I'm having a party", "I want to read a book", "I want to sleep", and "I want to cook"; or the user expression information may be information in the form of photo expression such as "birthday cake", "book", and "kitchen supplies"; or the user expression information may be information in the form of expression pictures or videos such as "smiling", "crying", and "laughing"; or the user expression information may be information in the form of body pictures or videos such as specific hand gestures and specific body postures; or the user expression information may be information in the form of music expression such as music type (for example, rock, sad, light music, etc.), music volume, and music rhythm.

[0030] A lighting instruction generation model is stored in the lighting device. The lighting instruction generation model is used to analyze the user's expression information to obtain the lighting instruction. The lighting device then adjusts and controls the lighting effect at the current moment according to the lighting instruction.

[0031] FIG2 is a flow chart of a lighting device adjustment method provided in an embodiment of the present application, which is applied to lighting devices. As shown in FIG2 , the order of the steps in the flow chart can be changed and some steps can be omitted according to different requirements.

[0032] S11, obtaining user expression information.

[0033] In some embodiments, user expression information refers to information in the form of voice, text, pictures, expressions, body language, and music sent by a user. The number of users corresponding to the user expression information can be one or multiple, that is, the user expression information can be output by a single user or by multiple users, and this is not limited here. For example, when the user expression information is the user expression information of a single user, the user expression information is output by user a; or, when the user expression information includes the user expression information of multiple users, user a and user b output the same user expression information, and "the same" here can mean that user a and user b output expression information with the same semantics, for example, user a and user b both output the user expression information "I am having a party"; or, user a and user b output different user expression information, and "different" here can mean that user a and user b output expression information with different semantics, for example, user a outputs the user expression information "I am having a party" and user b outputs the user expression information "I want to read a book".

[0034] In some embodiments, the number of user expression information can be one or more. It can be one user expression information sent by a single user, or multiple user expression information sent by a single user, or multiple user expression information sent by multiple users, and there is no limitation here. When the client sends one user expression information sent by a single user, the user expression information can be processed to adjust the lighting equipment; when the client sends multiple user expression information sent by a single user, if the multiple user expression information are of different information types, the multiple user expression information can be combined to form a user expression information group, and then the user expression information group can be processed to adjust the lighting equipment; when the client sends multiple user expression information sent by a single user, if the multiple user expression information are of the same information type, it indicates that the information the user wants to express has been updated. At this time, the multiple user expression information needs to be filtered, and then the filtered user expression information is processed to adjust the lighting equipment; when the client sends multiple user expression information sent by multiple users, if at the same time, multiple users send user expression information for different areas on their respective clients. expression information, then the lighting equipment of the corresponding area is adjusted accordingly according to the user expression information; if at the same time, multiple users send user expression information for the same area on their respective clients, the lighting instructions corresponding to each user expression information and the usage frequency corresponding to each lighting instruction are determined, and the lighting instruction with the highest usage frequency is selected to adjust the lighting equipment; or, a master device is selected from multiple clients, and the lighting equipment is adjusted according to the user expression information corresponding to the master device; or, a prompt is output for multiple users to select user expression information, and then the lighting equipment is adjusted according to the selected user expression information; or, for different lighting instructions, there are corresponding lighting areas. In one embodiment, a mapping relationship between lighting instructions and lighting areas is pre-set, and by traversing the mapping relationship, the lighting area corresponding to each lighting instruction can be obtained; then, the lighting effect of the corresponding lighting area is adjusted according to the lighting instruction. Wherein, the information type includes but is not limited to voice type, text type, picture type, expression type, and body type.

[0035] In some embodiments, after obtaining the user expression information sent by the client, the method further includes: verifying the user expression information to determine whether the user expression information meets the requirements of the model processing, thereby improving the accuracy of the model processing and, in turn, improving the accuracy of the lighting device adjustment. In one embodiment, when the user expression information is of a voice type, a voice clarity verification can be performed on the user expression information so that the voice clarity of the user expression information meets a preset voice clarity threshold. The voice clarity verification method can be a method of calling a voice clarity determination model, which is not limited here. The preset voice clarity threshold is a preset value used to identify that the user expression information meets the voice clarity requirements. In another embodiment, when the user expression information is of a picture type, an expression type, or a body type, an image clarity verification can be performed on the user expression information so that the image clarity of the user expression information meets a preset image clarity threshold. The image clarity verification method can be a method of calling an image clarity determination model, which is not limited here. The preset image clarity threshold is a preset value used to identify that the user expression information meets the image clarity requirements.

[0036] S12: Input the user expression information into a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information.

[0037] In some embodiments, the lighting command generation model is a generative algorithm that eliminates the need for manual pre-defined lighting effects. Based on the user's expression information, the model directly generates the lighting effect that best suits the user's expression information. The lighting command generation model can be a neural network model, and the training data includes user expression information and lighting commands. In one embodiment, the training data can include historical user expression information associated with the current lighting device and the lighting commands ultimately displayed based on that historical expression information. For example, if the user's expression information is "I'm having a party," the corresponding lighting command is "red, purple, and orange lights, pulsating in 0.5-second intervals." If the user's expression information is "I want to read," the corresponding lighting command is "bright white light, pulsating in a constant manner." The neural network model is trained using the user's expression information as input vectors and the corresponding lighting commands as output vectors until the model converges, resulting in a fully trained lighting command generation model. By collecting model training data in this manner, different users, even if they input the same information, can still receive lighting effects that suit their individual characteristics and habits, adapting the lighting effects to their actual needs and improving the accuracy of lighting device control.

[0038] In other embodiments, the training data may also be the user expression information of other users who are similar to the user profile of the user corresponding to the current lighting device, as well as the lighting instructions that are finally displayed corresponding to the user expression information. The user profile can be constructed based on the user attribute information. The user attribute information may include but is not limited to information such as age, gender, education level, region of origin, and type of lighting device. The types of lighting devices include simple, retro, and internet celebrity types. The lighting devices of different users are used as blockchain nodes to build a blockchain network. With the authorization of the user, each lighting device can provide the corresponding relationship between the user expression information and the lighting instructions. For example, it is assumed that there are blockchain nodes A, blockchain node B, and blockchain node C in the blockchain network, where blockchain node A corresponds to the lighting device of user A, blockchain node B corresponds to the lighting device of user B, and blockchain node C corresponds to the lighting device of user C. In one embodiment, the number of blockchain nodes in the blockchain network may be large. Therefore, a first user portrait corresponding to user D (for example, user age, user gender, user education, region, model of lighting equipment selected by the user, etc.) and a second user portrait of each user in the blockchain network can also be constructed. Users who are similar or identical to the first user portrait are selected from multiple second user portraits as users with similar behavioral preferences to user D. Historical user expression information whose similarity with the user expression information is higher than a preset similarity threshold is determined from such users to improve the accuracy of determining the historical user expression information, thereby improving the accuracy of training the lighting instruction generation model, so that the lighting effect is adapted to the actual needs of the user.

[0039] In one embodiment, historical user expression information is determined from the blockchain network whose similarity to user expression information exceeds a preset similarity threshold. The preset similarity threshold is a pre-set value used to identify the similarity between user expression information. For example, the user expression information corresponding to user D is {I'm having a party; singing}, the user expression information corresponding to user A stored in blockchain node A is {I'm having a party}, the user expression information corresponding to user B stored in blockchain node B is {I'm reading; light music}, and the user expression information corresponding to user C stored in blockchain node C is {I'm cooking; light music}. Therefore, user A's user expression information is most similar to user D's. User A's user expression information is used as historical user expression information whose similarity to user D's user expression information exceeds the preset similarity threshold. In one embodiment, similarity can be determined by vectorizing the user expression information and then calculating the Euclidean distance between the vectors.

[0040] A lighting command is a command composed of lighting parameters used to adjust the lighting effects of a lighting device. The lighting parameters may include, but are not limited to, one or more of light color parameters, color rhythm parameters, and light brightness parameters. In one embodiment, the lighting parameters may be expressed in a coded form, with each of the light color parameters, color rhythm parameters, and light brightness parameters being assigned a unique code to produce a light color code, a color rhythm code, and a light brightness code. The codes may be in the form of numeric codes, alphabetic codes, or color codes. The lighting command may be the set of light color codes, color rhythm codes, and light brightness codes with the highest probability.

[0041] S13: Adjust the lighting equipment according to the target lighting instruction.

[0042] In some embodiments, the lighting parameters within the target lighting instruction are obtained, and the lighting effect of the lighting device is directly switched according to the lighting parameters to achieve the lighting effect adjustment. This application directly switches the lighting effect of the lighting device according to the lighting parameters corresponding to the target lighting instruction, without having to analyze the current lighting parameters of the lighting device, thereby achieving rapid adjustment of the lighting effect.

[0043] The above-mentioned lighting equipment adjustment method provided in the embodiment of the present application uses user expression information to input the user expression information into the lighting instruction generation model to obtain the target lighting instruction, and then adjusts the lighting equipment according to the target lighting instruction. By adjusting the lighting equipment through the user expression information, direct interaction between the user and the lighting equipment end is achieved, avoiding the problem of low lighting equipment control efficiency caused by the user operating the lighting equipment multiple times; and directly using the user expression information as the model input and the lighting instruction as the model output, there is no need to judge other indirect information such as the emotional information corresponding to the user expression information, which can avoid the problem of low lighting equipment control accuracy caused by emotional misjudgment due to factors such as human individuality. In summary, the embodiment of the present application can improve the efficiency and accuracy of lighting equipment control.

[0044] In some embodiments, the lighting instruction generation model can be a neural network model based on a self-attention mechanism, including a tokenizer, an embedding layer, a core computing layer, and a multi-layer perception network. Figure 3 is a flow chart for determining target lighting instructions provided in an embodiment of the present application. The target lighting instruction determination process is applied to lighting equipment. As shown in Figure 3, the following steps are included:

[0045] S21, inputting the user expression information into the word segmenter to obtain digital expression information.

[0046] In some embodiments, a tokenizer refers to the process of converting user expression information into a format that the model can understand (in this application, digital expression information), which may include the steps of segmentation, tokenization, and encoding. The segmentation step refers to dividing the user expression information into words or subwords; the tokenization step refers to converting each word or subword into a unique identifier so that the model can distinguish between different words or subwords; and the encoding step refers to converting each word or subword into a fixed-length encoded representation.

[0047] For example, when the user's expression information is voice, the received voice data can be converted into text data through a word segmenter, and then the text data can be segmented to obtain multiple word segments, and the word segmentation code corresponding to each word segmentation is determined. The corresponding digital expression information can be obtained by combining the multiple word segmentation codes. When the user's expression information is a picture, expression, or body expression, the received picture data can be converted into a digital matrix through a word segmenter, and each element in the digital matrix represents a pixel value in the picture. When the user's expression information is a combination of voice and picture, the voice expression can be converted into first digital expression information and the picture expression can be converted into second digital expression information through a word segmenter. The first expression information and the second expression information are then combined as input information for the embedding layer.

[0048] S22, inputting the digital expression information into the embedding layer to obtain an expression vector.

[0049] In some embodiments, the embedding layer is used to convert each word segment or character into a vector representation (user expression vector in this application), that is, the embedding layer will map each word segment or character to a vector space of fixed length, so that the distance between different word segments or characters in the vector space is as close as possible, thereby embedding discrete word segments or characters into a continuous vector space, obtaining low-dimensional dense vector data, and thus improving the accuracy of model processing. This process usually includes a word embedding layer and a position encoding layer, wherein the word embedding layer is used to map each word segment or character in the digital expression information to a vector to obtain a word vector, and the position encoding layer is used to calculate the position vector of each word segment or character in the digital expression information so that the model can distinguish the differences between different positions. Afterwards, the word vector and the position vector are spliced ​​as the output of the embedding layer, that is, the expression vector is obtained.

[0050] S23, inputting the expression vector into the core operation layer to obtain implicit lighting features.

[0051] In some embodiments, the core computing layer can extract text features based on the expression vectors obtained by the embedding layer to obtain feature vectors, i.e., implicit lighting features. The specific structure of the core computing layer can be configured based on actual conditions. For example, the core computing layer may include a multi-layer core computing structure composed of transformers based on the attention mechanism.

[0052] S23, inputting the implicit lighting features into a multi-layer perception network to obtain target lighting instructions.

[0053] In some embodiments, after the implicit lighting features are input into the multi-layer perception network and activated by an activation function for calculating probabilities, the probability of the lighting parameters corresponding to the lighting device can be obtained, wherein the lighting parameters may include but are not limited to light color parameters, color rhythm parameters, and light brightness parameters. The light color parameters, color rhythm parameters, and light brightness parameters with high probabilities are selected to form the target lighting instructions. In one embodiment, the lighting instructions can be expressed in the form of an attribute set, for example, the lighting instructions can be an attribute set such as {light color parameters, color rhythm parameters, light brightness parameters}; in another embodiment, the lighting instructions can also be expressed in the form of a graph, for example, the light color parameters are used as nodes in the graph, and the color rhythm parameters are used as edges in the graph. The target lighting instructions expressed in the above form are input into the lighting device, and the lighting device displays the corresponding lighting effect.

[0054] The embodiment of the present application trains the core operation layer and the multi-layer perception network based on user expression information, and jointly constructs a lighting instruction generation model with the trained core operation layer and the multi-layer perception network, which can improve the accuracy of model processing and thus improve the accuracy of target lighting instruction determination.

[0055] FIG4 is a flowchart of determining an updated target lighting instruction according to an embodiment of the present application. The determination process of the updated target lighting instruction is applied to a lighting device. As shown in FIG4 , the process includes the following steps:

[0056] S41, obtaining supplementary user expression information corresponding to the user expression information.

[0057] In some embodiments, after adjusting the lighting device according to the target lighting instruction, it is possible to monitor whether there is supplementary user expression information corresponding to the user expression information within a preset time interval. If there is no supplementary user expression information corresponding to the user expression information, it indicates that the current lighting effect is adapted to the user's actual needs; if there is supplementary user expression information corresponding to the user expression information, it indicates that the current lighting effect is not adapted to the user's actual needs. The preset time interval is pre-set, for example, the preset time interval is 1 minute. There is at least one identical preset keyword or other expression information with the same meaning as the preset keyword between the supplementary user expression information and the user expression information. The preset keywords may include, but are not limited to, words such as "party", "read", "cook", and "rest", and can be set according to actual needs. For example, the user expression information output by the client is "I am having a party", and the corresponding lighting instruction is "red light, green light, the rhythmic mode is to change at an interval of 0.5 seconds." If within 1 minute, the user expresses "blue light, white light, I am having a party" again, and the preset keyword "party" exists in both of the above two user expression information, then the user expression will be used as the supplementary user expression information corresponding to the user expression information; if within 1 minute, the user expresses "blue light, white light, have a party" or "blue light, red light, I am having a party" again, party”, and the language type of the above user expression information is different but expresses the same meaning, then the user expression information shall be regarded as the supplementary user expression information corresponding to the user expression information; if within one minute, the user again expresses “blue light, white light” by voice and makes a body expression of dancing, and the body expression of dancing is associated with “having a party”, then the voice expression and body expression shall be regarded as the supplementary user expression information corresponding to the user expression information; if within one minute, the user again expresses “blue light, white light” by voice and holds a photo of a birthday cake in his hand, and the photo of the birthday cake is associated with “having a party”, then the voice expression and photo shall be regarded as the supplementary user expression information corresponding to the user expression information; if within one minute, the user again expresses “I want to read a book”, and there is no identical preset keyword in the above two user expression information, and the meanings of “reading a book” and “having a party” are different, then it is considered that the user has not updated the previous user expression information, but has output new user expression information, and there is no need to regard the user expression as the supplementary user expression information corresponding to the user expression information.

[0058] In some embodiments, after adjusting the lighting device according to the target lighting instruction, while monitoring whether there is supplementary user expression information corresponding to the user expression information within a preset time interval, the user's feedback information can also be combined to assist in evaluating whether the current lighting effect is adapted to the user's actual needs, thereby avoiding missing supplementary user expression information and improving the accuracy of lighting device control. Feedback information can be text feedback, voice feedback, expression feedback or touch feedback. For example, the feedback information can be feedback in the form of text or voice, such as "NO", "too bright", "too dark", or in the form of expression, such as "crying face, frowning", or in the form of a specified control in the touch client (for example, a control marked NO, a control marked to reduce brightness, a control marked to adjust color, etc.). If the above-mentioned feedback information of the user is collected within a preset time interval after adjusting the lighting device according to the target lighting instruction, it indicates that the probability of the user expressing again is relatively high, and the terminal continues to monitor whether it outputs supplementary user expression information.

[0059] S42: Input the supplementary user expression information into the lighting instruction generation model to obtain an updated target lighting instruction corresponding to the supplementary user expression information.

[0060] In some embodiments, the supplementary user expression information is used as input data and input into a lighting instruction generation model to obtain an updated target lighting instruction corresponding to the supplementary user expression information.

[0061] S43: Adjust the lighting device according to the updated target lighting instruction.

[0062] In an embodiment of the present application, after adjusting the lighting device according to the target lighting instruction, if supplementary user expression information corresponding to the user expression information is received, the lighting instruction generation model is used to obtain an updated target lighting instruction corresponding to the supplementary user expression information, and the lighting device is adjusted according to the updated target lighting instruction, so that the final target lighting instruction meets the user's personalized needs, thereby improving the accuracy of lighting device control.

[0063] FIG5 is a flowchart of adjusting the lighting instruction generation model provided in an embodiment of the present application. The adjustment process of the lighting instruction generation model is applied to lighting equipment. As shown in FIG5, the steps include:

[0064] S51: Use the user expression information and the updated target lighting instruction as training data.

[0065] S52: Train the lighting instruction generation model according to the training data to obtain an updated lighting instruction generation model.

[0066] In some embodiments, user expression information and updated target lighting instructions are collected as new training data to retrain the lighting instruction generation model, so that the actual output results of the lighting instruction generation model are increasingly close to the user's personally expected output results, thereby improving the accuracy of the lighting instruction generation model and thereby improving the accuracy of lighting device control.

[0067] FIG6 is a flowchart of determining a lighting area according to an embodiment of the present application. The lighting area determination process is applied to a lighting device. As shown in FIG6 , the process includes the following steps:

[0068] S61: If the user expression information includes user expression information of multiple users, the user expression information corresponding to each user is input into the lighting instruction generation model to obtain a target lighting instruction corresponding to each user.

[0069] In some embodiments, user expression information may be output by only one user or by multiple users. When the number of user expression information is one, it can be determined that the user expression information is output by only one user; when the number of user expression information is multiple, it can be determined whether there are multiple users through voiceprint recognition, account recognition, and face recognition. Accordingly, when the number of users corresponding to the user expression information is multiple, the user expression information corresponding to each user can be determined through voiceprint features, user accounts, and face features. Taking the user expression information as a voice expression as an example, when there are multiple voice expressions, the multiple voice expressions can be processed by a pre-trained voiceprint recognition model to determine the voiceprint features corresponding to each voice expression; when the voiceprint features are the same, the number of users corresponding to the user expression is determined to be one, that is, one user outputs multiple voice expressions; when the voiceprint features are different, it is determined that the number of users corresponding to the user expression is multiple. Taking the user expression information as a text expression as an example, each user has a corresponding client, and their respective user expression information is output through the client. Each client has a corresponding user account. When the number of user accounts is one, the number of users corresponding to the user expression is determined to be one, that is, one user outputs multiple text expressions. When the user accounts are different, the number of users corresponding to the user expression is determined to be multiple. Taking the user expression information as an example of facial expressions, multiple facial expressions can be processed through a pre-trained facial recognition model to determine the facial features corresponding to each facial expression. When the facial features are the same, the number of users corresponding to the user expression is determined to be one, that is, one user outputs multiple facial expressions. When the facial features are different, the number of users corresponding to the user expression is determined to be multiple.

[0070] In some embodiments, a corresponding thread can be set for each user, each thread being used to input the user expression information corresponding to each user into the lighting instruction generation model to obtain the target lighting instruction corresponding to each user. By setting up multiple threads, the user expression information corresponding to each user can be processed synchronously, thereby improving the processing speed of the model.

[0071] S62: Determine the lighting area corresponding to each target lighting instruction.

[0072] In some embodiments, a mapping relationship between lighting commands and lighting zones is pre-set. By traversing this mapping relationship, the lighting zone corresponding to each lighting command can be obtained. For example, if user A sends user expression information A in lighting zone A, and user B sends user expression information B in lighting zone A, target lighting commands A and B are then derived based on user expression information A and user expression information B. Traversing this mapping relationship reveals that target lighting command A corresponds to lighting zone A, and target lighting command B corresponds to lighting zone B. Lighting device A in lighting zone A is then adjusted according to target lighting command A, and lighting device B in lighting zone B is adjusted according to target lighting command B. Different lighting commands have preferred corresponding lighting zones. For example, if the lighting command is "red, purple, and orange lights, with a 0.5s interval transition," the preferred lighting zone may be the living room; if the lighting command is "bright white light, with a constant rhythm," the preferred lighting zone may be the study; and if the lighting command is "soft warm light, with a constant rhythm," the preferred lighting zone may be the bedroom. In one embodiment, a mapping relationship between lighting instructions and lighting areas is preset, and the lighting area corresponding to each lighting instruction can be obtained by traversing the mapping relationship.

[0073] S63: Adjust the lighting equipment in the lighting area according to the target lighting instruction.

[0074] In some embodiments, lighting parameters of the lighting device at the current moment are acquired, and the lighting parameters of the lighting device at the current moment are adjusted according to the lighting parameters in the target lighting instruction to achieve an adjusted lighting effect.

[0075] When there are multiple users corresponding to user expression information, this embodiment of the application determines the user expression information corresponding to each user and the target lighting instructions corresponding to the user expression information, then determines the lighting area corresponding to each target lighting instruction, and adjusts and controls the lighting equipment within the lighting area according to the target lighting instructions. This embodiment of the application can improve the accuracy of lighting equipment control in scenarios involving multiple people in a family, so that the lighting effects are adapted to the actual needs of multiple users.

[0076] In other embodiments, if the user expression information includes user expression information of multiple users, the method further includes: determining the client corresponding to the user expression information; if the client is a target client, executing the user expression information corresponding to the target client. Multiple users send user expression information through their respective clients. In actual application scenarios, the main client corresponding to the lighting device (also referred to as the target client in this application) can be bound. When the main client outputs user expression information, the user expression information is executed first. In other embodiments, it can also be determined whether it is a multi-user output by voiceprint recognition or other methods. Afterwards, a main user (also referred to as the target user in this application, for example, the head of the household) is selected from multiple users, and the user expression information of the main user is executed first. Exemplarily, when the user expression information is voice expression, and there are multiple voice expressions, the multiple voice expressions can be processed by a pre-trained voiceprint recognition model to determine the voiceprint features corresponding to each voice expression; when the voiceprint features are the same, the number of users corresponding to the user expression is determined to be one, that is, one user outputs multiple voice expressions; when the voiceprint features are different, the number of users corresponding to the user expression is determined to be multiple; then, the target voiceprint feature is selected from the multiple voiceprint features, and the user expression information corresponding to the target voiceprint feature is input into the lighting instruction generation model.

[0077] In some embodiments, when the client sends multiple pieces of user expression information sent by a single user, the following steps are also included:

[0078] Step 1: If the user expression information is user expression information of a single user, determine multiple information types corresponding to the user expression information.

[0079] In some embodiments, information types may include voice, text, images, emoticons, body language, and music. When the number of users corresponding to the user expression information is one, the number of user expression information for the same information type may be one or more. When there are multiple user expression information of the same information type, it indicates that the information the user wishes to express has been updated; when there is only one user expression information of the same information type, it indicates that the information the user wishes to express does not need to be updated.

[0080] Step 2: Determine the timestamp of the user expressing the information corresponding to each information type.

[0081] In some embodiments, each user expression information is associated with a timestamp that identifies the time when the user expression information was collected. The closer the timestamp is to the current time, the more recently the user expression information was collected. For example, if the current time is 02:24:21, timestamp A corresponding to user expression information 1 is 02:24:15, and timestamp B corresponding to user expression information 2 is 02:24:19, indicating that user expression information 2 was recently collected.

[0082] Step 3: Select the user expression information corresponding to the timestamp closest to the current time as the target user expression information.

[0083] In some embodiments, the user expression information with the latest timestamp refers to the updated information of the user.

[0084] Step 4: Combine the target user expression information corresponding to each information type as updated user expression information.

[0085] In some embodiments, the target user expression information corresponding to each information type is combined according to a preset data format as updated user expression information. For example, the preset data format may be {target user expression information 1, target user expression information 2, target user expression information 3}.

[0086] In this embodiment of the present application, when the number of users corresponding to user expression information is one, the information type corresponding to the user expression information and the timestamp of the user expression information corresponding to each information type are determined. The user expression information corresponding to the timestamp closest to the current time is then selected as the target user expression information. The target user expression information corresponding to each information type is then combined to form the updated user expression information. This embodiment of the present application can identify the latest user expression information sent by a user and then adjust the lighting equipment based on the latest user expression information, thereby improving the accuracy of lighting equipment adjustment.

[0087] Please refer to Figure 7, which is a schematic diagram of the structure of a lighting device adjustment device provided in an embodiment of the present application. In some embodiments, the lighting device adjustment device 20 may include multiple functional modules composed of computer program segments. The computer programs for each program segment in the lighting device adjustment device 20 may be stored in the memory of a computer device 30 and executed by at least one controller to perform the lighting device adjustment function (see Figure 2 for details).

[0088] In this embodiment, the lighting device adjustment device 20 can be divided into multiple functional modules based on their functions. When used in a host device, the functional modules may include: an expression information receiving module 201, a lighting instruction generation module 202, and a lighting device adjustment module 203. A module, as referred to herein, refers to a series of computer program segments that can be executed by at least one controller and perform fixed functions, stored in memory. The functions of each module in this embodiment will be described in detail in subsequent embodiments.

[0089] The expression information receiving module 201 is used to obtain the user expression information sent by the client.

[0090] The lighting instruction generation module 202 is configured to use a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information.

[0091] The lighting device adjustment module 203 is configured to adjust the lighting device according to the target lighting instruction.

[0092] In some embodiments, the lighting instruction determination module 202 is also used to input the user expression information into the word segmenter to obtain digital expression information; input the digital expression information into the embedding layer to obtain an expression vector; input the expression vector into the core operation layer to obtain implicit lighting features; input the implicit lighting features into the multi-layer perception network to obtain target lighting instructions.

[0093] In some embodiments, the lighting equipment adjustment module 203 is also used to input the user expression information corresponding to each user into the lighting instruction generation model to obtain the target lighting instruction corresponding to each user; determine the lighting area corresponding to each target lighting instruction; and adjust the lighting equipment in the lighting area according to the target lighting instruction.

[0094] In some embodiments, the expression information receiving module 201 is also used to determine the client corresponding to each user expression information; select a target client from the clients, and input the user expression information corresponding to the target client into the lighting instruction generation model; or determine the voiceprint feature corresponding to each user expression information; select a target voiceprint feature from the voiceprint features, and input the user expression information corresponding to the target voiceprint feature into the lighting instruction generation model.

[0095] In some embodiments, the lighting device adjustment module 203 is also used to obtain supplementary user expression information corresponding to the user expression information; input the supplementary user expression information into the lighting instruction generation model to obtain an updated target lighting instruction corresponding to the supplementary user expression information; and adjust the lighting device according to the updated target lighting instruction.

[0096] In some embodiments, the lighting device adjustment module 203 is further configured to use the user expression information and the updated target lighting instruction as training data; and train the lighting instruction generation model according to the training data to obtain an updated lighting instruction generation model.

[0097] In some embodiments, the lighting device adjustment module 203 is also used to determine the user attribute information of the user corresponding to the user expression information; input the user expression information and the user attribute information into the lighting instruction generation model to obtain the target lighting instruction; and adjust the lighting device according to the target lighting instruction.

[0098] It can be understood that the lighting equipment adjustment device 20 and the lighting equipment adjustment method of the above embodiment belong to the same inventive concept. The specific implementation method of each module of the lighting equipment adjustment device 20 corresponds to the various steps of the lighting equipment adjustment method in the above embodiment, and this application will not go into details here.

[0099] The module division described above is a logical functional division, and other division methods may be used in actual implementation. In addition, the functional modules in the various embodiments of the present application can be integrated into the same processing unit, or each module can exist physically separately, or two or more modules can be integrated into the same unit. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0100] Figure 8 is a schematic diagram of the structure of a lighting device provided in an embodiment of the present application. As shown in Figure 8, the lighting device 30 includes a memory 31, at least one controller 32, and at least one communication bus 33. The controller 32 is configured to implement the lighting device adjustment method when executing a computer program stored in the memory 31. The at least one communication bus 33 is configured to enable communication between the memory 31 and the at least one controller 32.

[0101] The structure of the lighting device shown in FIG8 does not constitute a limitation on the embodiments of the present application. The lighting device 30 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0102] In some embodiments of the present application, the lighting device 30 can also be connected to a client device, which includes but is not limited to any electronic product that can interact with a user through a keyboard, mouse, remote control, touchpad or voice control device, such as a personal computer, tablet computer, smart phone, digital camera, etc.

[0103] It should be noted that the lighting device 30 is only an example. Other existing or future electronic products that are suitable for this application should also be included in the scope of protection of this application and included here by reference.

[0104] In some embodiments, the lighting device 30 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0105] The memory 31 stores a computer program that, when executed by at least one controller 32, implements all or part of the steps in the lighting device adjustment method. The memory 31 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0106] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the lighting device 30, etc.

[0107] In some embodiments, at least one controller 32 is the control core (Control Unit) of the lighting device 30, which uses various interfaces and lines to connect the various components of the entire lighting device 30, and executes various functions and processes data of the lighting device 30 by running or executing programs or modules stored in the memory 31, and calling data stored in the memory 31. For example, when the at least one controller 32 executes the computer program stored in the memory, it implements all or part of the steps of the lighting device adjustment method in the embodiment of the present application; or implements all or part of the functions of the lighting device adjustment device. The at least one controller 32 can be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microcontrollers, digital processing chips, graphics controllers, and a combination of various control chips.

[0108] The above-mentioned integrated unit implemented in the form of a software functional module can be stored in a computer-readable storage medium. The above-mentioned software functional module stored in a storage medium includes a number of instructions for causing a lighting device (which can be a personal computer, lighting device, or network device, etc.) or a controller (processor) to execute portions of the methods of various embodiments of the present application.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is only a logical function division, and other division methods may be used in actual implementation.

[0110] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, and may be located in one place or distributed across multiple network elements. Some or all of these modules may be selected to achieve the objectives of this embodiment based on actual needs.

[0111] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0112] It is obvious to those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "including" does not exclude other units or, and the singular does not exclude the plural. Multiple units or devices stated in the specification may also be implemented by one unit or device through software or hardware. Words such as first, second, etc. are used to indicate names and do not indicate any particular order.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A lighting equipment adjustment method, applied to lighting equipment, characterized in that: The method comprises: Obtain user expression information; Inputting the user expression information into a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information; The lighting device is adjusted according to the target lighting instruction.

2. The method according to claim 1, characterized in that The user expression information includes at least one of the following: voice expression, text expression, picture expression, facial expression, body expression and music expression.

3. The method according to claim 1, characterized in that The lighting instruction generation model includes a word segmenter, an embedding layer, a core computing layer, and a multi-layer perception network. The step of inputting the user expression information into the lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information includes: Inputting the user expression information into the word segmenter to obtain digital expression information; Inputting the digital expression information into the embedding layer to obtain an expression vector; Inputting the expression vector into the core computing layer to obtain implicit lighting features; The implicit lighting features are input into the multi-layer perception network to obtain target lighting instructions.

4. The method according to claim 1, characterized in that If the user expression information includes expression information of multiple users, the method further includes: Inputting the user expression information corresponding to each user into the lighting instruction generation model to obtain the target lighting instruction corresponding to each user; Determine the lighting area corresponding to each target lighting instruction; The lighting equipment in the lighting area is adjusted according to the target lighting instruction.

5. The method according to claim 1, characterized in that If the user expression information includes expression information of multiple users, the method further includes: Determine the client corresponding to each user expression information; select a target client from the clients, and input the user expression information corresponding to the target client into the lighting instruction generation model; or Determine the voiceprint features corresponding to each user expression information; select a target voiceprint feature from the voiceprint features, and input the user expression information corresponding to the target voiceprint feature into the lighting instruction generation model.

6. The method according to claim 1, characterized in that After adjusting the lighting device according to the target lighting instruction, the method further includes: Acquire supplementary user expression information corresponding to the user expression information; Inputting the supplementary user expression information into the lighting instruction generation model to obtain an updated target lighting instruction corresponding to the supplementary user expression information; The lighting device is adjusted according to the updated target lighting instructions.

7. The method according to claim 6, characterized in that After adjusting the lighting device according to the updated target lighting instruction, the method further includes: using the user expression information and the updated target lighting instruction as training data; The lighting instruction generation model is trained according to the training data to obtain an updated lighting instruction generation model.

8. A lighting equipment adjustment device, characterized in that: The device comprises: An expression information receiving module, used to obtain user expression information; A lighting instruction generation module, used for inputting the user expression information into a lighting instruction generation model to obtain a target lighting instruction corresponding to the user expression information; A lighting device adjustment module is used to adjust the lighting device according to the target lighting instruction.

9. A lighting device, characterized in that: The lighting device comprises a controller and a memory, and the controller is used to implement the lighting device adjustment method according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the controller, the lighting device adjustment method according to any one of claims 1 to 7 is implemented.

Images