Control method and apparatus, electronic device, and storage medium

Abstract

The present application provides a control method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring user information; inputting the user information into a multi-modal model to obtain suggestion information corresponding to the user information; and controlling at least one target device on the basis of the suggestion information. By using the method, light effects and / or sound effects can be accurately controlled, so that scenario requirements match the light effects and / or the sound effects, thereby providing a comfortable sensory experience for users.

Description

Control method, device, electronic device and storage medium Technical Field

[0001] The present application belongs to the field of smart home technology, and in particular relates to a control method, device, electronic device and storage medium. Background Art

[0002] With the continuous development of lighting technology, intelligent lighting has become a trend. Faced with tens of millions of lighting effects on lighting devices and a variety of sound effects on audio playback devices, users may feel confused and have difficulty finding the lighting and / or sound effects that suit specific scene requirements. This will lead to a mismatch between scene requirements and lighting and / or sound effects, making it difficult to effectively control lighting and / or sound, and thus failing to provide users with a comfortable sensory experience.

[0003] Summary of the Invention

[0004] In view of the above, it is necessary to provide a control method, device, electronic device and storage medium that can improve the technical problems of difficulty in effectively controlling light and / or sound and poor user experience caused by the mismatch between lighting scene requirements and light effects and / or sound effects.

[0005] On the one hand, the present application provides a control method, which includes: obtaining user information, inputting the user information into a multimodal model, obtaining suggestion information corresponding to the user information, and controlling at least one target device based on the suggestion information.

[0006] In some embodiments of the present application, the category of the user information includes at least one of text, video, image and sound.

[0007] In some embodiments of the present application, controlling at least one target device based on the suggestion information includes: analyzing the semantics of the suggestion information, and extracting lighting effect key information and / or sound effect key information from the suggestion information, controlling at least one lighting device according to the lighting effect key information, and / or controlling at least one audio playback device according to the sound effect key information.

[0008] In some embodiments of the present application, the method also includes: sending the lighting effect key information and / or the sound effect key information to a terminal device, and receiving a selection instruction for the lighting effect key information and / or the sound effect key information sent from the terminal device, controlling the at least one lighting device according to the lighting effect key information corresponding to the selection instruction, and / or controlling the at least one audio playback device according to the sound effect key information corresponding to the selection instruction.

[0009] In some embodiments of the present application, controlling at least one lighting device according to the lighting effect key information, and / or controlling at least one audio playback device according to the sound effect key information includes: combining different types of lighting effect key information to obtain multiple lighting effects, and controlling the at least one lighting device according to the multiple lighting effects, and / or combining different types of sound effect key information to obtain multiple sound effects, and controlling the at least one audio playback device according to the multiple sound effects.

[0010] In some embodiments of the present application, controlling the at least one lighting device according to the multiple lighting effects, and / or controlling the at least one audio playback device according to the multiple sound effects includes: sending the multiple lighting effects and / or the multiple sound effects to a terminal device, receiving selection instructions for the multiple lighting effects and / or the multiple sound effects sent from the terminal device, controlling the at least one lighting device according to the lighting effect corresponding to the selection instruction, and / or controlling the at least one audio playback device according to the sound effect corresponding to the selection instruction.

[0011] In some embodiments of the present application, the method also includes: controlling at least one smart device and / or at least one lighting device based on the lighting effect key information, and / or controlling at least one smart device and / or at least one audio playback device based on the sound effect key information, wherein the at least one smart device has at least one lighting function and / or at least one audio playback function.

[0012] In some embodiments of the present application, the method further includes: when it is detected that the suggestion information includes preset information, outputting a voice to interact with the user.

[0013] The present application provides a control device, which includes: an acquisition unit for acquiring user information, an input unit for inputting the user information into a multimodal model to obtain recommendation information corresponding to the user information, and a control unit for controlling at least one target device based on the recommendation information.

[0014] On the other hand, the present application provides an electronic device, which includes: a memory storing at least one instruction; and a processor executing at least one instruction to implement the control method.

[0015] On the other hand, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the control method.

[0016] Through the above-described embodiments, user information can be used to clarify user behavior, control requirements, or the user's current scenario. By learning the implicit connections between information from different input modalities and the common features that require output of recommended information, the system can respond to any user's expressed information. Furthermore, the multimodal model is trained using the user's expressed information to output recommended information. Therefore, even if the user information does not include control requirements, the multimodal model can output recommended information consistent with the user information, thereby accurately controlling the target device based on the recommended information. When the recommended information includes information related to lighting and / or sound effects, the target device includes one or more of a lighting device, an audio playback device, and a smart device with lighting and / or audio playback functions. Based on the information related to the lighting and / or sound effects, the lighting device and / or audio playback device can be accurately controlled, thereby matching the scene requirements with the lighting and / or sound effects, providing the user with a comfortable sensory experience. Furthermore, by matching the scene requirements with the lighting and / or sound effects, a suitable atmosphere can be created, increasing the flexibility of controlling the ambient device. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a diagram showing an application environment of a lighting device control method provided in an embodiment of the present application.

[0018] FIG2 is a diagram showing an application environment of a lighting device control method provided in another embodiment of the present application.

[0019] FIG3 is a flow chart of a control method provided in an embodiment of the present application.

[0020] FIG4 is a flow chart of a control method provided by another embodiment of the present application.

[0021] FIG5 is a flow chart of a control method provided in yet another embodiment of the present application.

[0022] FIG6 is a flow chart of a control method provided in yet another embodiment of the present application.

[0023] FIG7 is a functional module diagram of a control device provided in an embodiment of the present application.

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

[0025] In order to make the objectives, technical solutions and advantages of this application clearer, this application is described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0027] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0028] With the continuous development of lighting technology, intelligent lighting has become a trend. Faced with tens of millions of lighting effects on lighting devices and a variety of sound effects on audio playback devices, users may feel confused and have difficulty finding the lighting and / or sound effects that suit specific scene requirements. This will lead to a mismatch between scene requirements and lighting and / or sound effects, making it difficult to effectively control lighting and / or sound, and thus failing to provide users with a comfortable sensory experience.

[0029] To address the above technical issues, the present application provides a control method, device, electronic device, and storage medium that can accurately control lighting effects and / or sound effects, so that scene requirements match the lighting effects and / or sound effects, providing users with a comfortable sensory experience. The control method provided in the embodiments of the present application can be executed by one or more electronic devices.

[0030] Figure 1 illustrates an application environment for a lighting device control method according to an embodiment of the present application. In Figure 1 , an electronic device 10 communicates with multiple lighting devices 20 and multiple audio playback devices 30. The electronic device 10 can connect to the multiple lighting devices 20 and multiple audio playback devices 30 via Bluetooth, hotspots, Wi-Fi, or other methods, enabling the electronic device 10 to control the multiple lighting devices 20 and multiple audio playback devices 30.

[0031] The electronic device 10 may be a mobile phone, a tablet computer, a laptop computer, an intelligent interactive device, an intelligent remote control, an intelligent central control device, a computer or other electronic device. The embodiment of the present application does not impose any restrictions on the specific type of the electronic device 10.

[0032] The lighting device 20 may be any type of lamp that can provide lighting functions, for example, an LED lamp, an energy-saving lamp, a floodlight, a security lamp, a stage lamp, a light string, a light strip, or a light bead.

[0033] The audio player 30 can be any device with a sound playback function. For example, the audio player 30 can be a smart speaker, a radio, a Bluetooth headset, a player, a speaker, etc.

[0034] FIG2 illustrates an application environment for a lighting device control method according to another embodiment of the present application. In FIG2 , an electronic device 10 communicates with multiple smart devices 40. The electronic device 10 can communicate with the multiple smart devices 40 via Bluetooth, hotspots, Wi-Fi, or other methods, thereby enabling the electronic device 10 to control the multiple smart devices 40.

[0035] The electronic device 10 may be a mobile phone, a tablet computer, a laptop computer, a smart remote control, a smart central control device, a computer or other electronic device. The embodiment of the present application does not impose any restrictions on the specific type of the electronic device 10.

[0036] The smart device 40 has at least one lighting function and / or at least one audio playback function. One smart device 40 has lighting and / or audio playback functions; or one smart device 40 corresponds to one function. For example, the smart device 40 can be a smart lighting and audio system, a light and audio projector, or a smart home system.

[0037] FIG3 is a flow chart of a control method according to an embodiment of the present application. The order of the steps in the flow chart may be adjusted according to actual requirements, and some steps may be omitted. The method is performed by an electronic device, such as the electronic device 10 shown in FIG1 or FIG2 .

[0038] S11, obtain user information.

[0039] In some embodiments of the present application, the category of user information includes at least one of text, video, image, and sound, wherein sound includes instant voice and audio files. User information may include information related to lighting effects and sound effects, or user information may also be information unrelated to lighting effects and sound effects. User information may include text, video, image, and sound input by the user. User information may be obtained through various methods such as user typing on a keyboard, user handwriting input on an interactive interface of an electronic device, electronic device converting voice recorded by a microphone, or electronic device analyzing images, and the present application does not impose any restrictions on this.

[0040] User information can be any one or more of various types of information such as expressing the user's behavior, life needs, lighting effect needs, sound effect needs, emotions, the scene the user is in, and basic attributes. For example, if the user information is related to lighting effects and / or sound effects, the user information can be a text message or voice message describing "I am dancing, what color and effect of light is suitable?", "I am very happy, what kind of light color and light brightness should I choose?", "I am having a party, red and orange lights", "Hi singing, loud volume", "What kind of environment is suitable for me to read?", a text or voice message, or a picture or video describing lighting effects and / or sound effects. Alternatively, if the user information is not related to lighting effects and / or sound effects, the user information can be a text message or voice message describing "female, 23 years old, undergraduate, Guangdong" and "the indoor scene is white". Alternatively, the user information can be an image or video describing a person singing, a person dancing, or a gray scene in the rain. The above examples of user information are only examples, and this application does not limit user information.

[0041] In some embodiments of the present application, the electronic device may obtain user information in various ways. For example, the electronic device may receive text or voice information input by the user as user information, or the electronic device may receive an image or video selected by the user from a preset database as user information, where the preset database may be a local database or a cloud disk database, which is not limited in this application.

[0042] In this embodiment, the user's behavior, life needs, lighting effect needs, sound effect needs, emotions, or the scene in which the user is located can be clarified through user information.

[0043] S12: Input the user information into the multimodal model to obtain recommendation information corresponding to the user information.

[0044] In some embodiments of the present application, a multimodal model refers to a model that can recognize and process multiple different types of information (for example, text, voice, audio, video, and images). For example, the multimodal model may be the AliceMind-PLUG model, the AliceMind-mPLUG model, the M6-OFA model, and the ChatGPT series model. The suggestion information may include information related to lighting effects and / or sound effects, and the lighting effects may include one or more of the following information: lighting color, lighting change speed, lighting change time, lighting brightness, lighting direction, lighting operation, lighting angle, and lighting change effect. For example, lighting colors include but are not limited to: red, blue, and yellow. Light change effects include flowing lighting effects, flashing lighting effects, lighting effects that change with the rhythm of music, lighting effects that quickly switch between light and dark, and slowly changing lighting effects.

[0045] Sound effects can be special sound effects and / or music. These effects can include one or more of the following: loudness, pitch, rhythm, spatial characteristics, sound manipulation, music title, and melody. For example, tones include heavy and soft, rhythms include slow, tense, relaxed, and cheerful, and spatial characteristics include stereo and surround. Special sound effects include wind, rain, animal sounds, and mechanical sounds, while music can include classical music, pop music, rock music, electronic music, and hip-hop music.

[0046] In one embodiment of the present application, the multimodal model can be obtained through pre-training. Before inputting user information into the multimodal model, the method also includes: the electronic device obtains training expression information, and trains a preset multimodal learner based on the training expression information to obtain the multimodal model.

[0047] Multimodal models possess both adaptive learning and transfer learning capabilities. Transfer learning refers to the ability of multimodal models to adapt to and learn from the characteristics of training data from multiple domains, enabling them to achieve robust performance across diverse domains. Adaptive learning refers to the ability of multimodal models to continuously adjust their parameters based on user feedback, thereby improving their performance in practical applications. Furthermore, to enhance the performance of multimodal models, knowledge graphs can be used to train them and optimize their performance.

[0048] The training expression information includes at least one type of information for instructing the multimodal learner to output lighting effects and / or sound effects. In order for the multimodal model to learn the implicit connections between information of different input modalities and the common features that require output of recommended information, the training expression information can be a combination of multiple types of (multimodal) expression information. For example, taking the training expression information as information instructing the multimodal learner to output lighting effects as an example, the training expression information can include text information describing "I am dancing, what color and lighting effect is suitable?" and an image depicting a dancing person. Alternatively, the training expression information can include voice information describing "I am happy, what lighting color and brightness should I choose?" and an image depicting a smiling face. Alternatively, the training expression information can include text information describing "I am dancing, what color and lighting effect is suitable?" and an image and video depicting a dancing person. The above examples of training expression information are only examples and are not limited to these. The multimodal learner corresponds to the multimodal model. For example, if the multimodal models are the AliceMind-PLUG model, the AliceMind-mPLUG model, the M6-OFA model, and the ChatGPT series models, the multimodal learners are the AliceMind-PLUG learner, the AliceMind-mPLUG learner, the M6-OFA learner, and the ChatGPT series learner.

[0049] In some embodiments of the present application, a multimodal learner is trained through various training expression information, so that the trained multimodal model learns the implicit connection between information of different input modalities and the common features that need to output suggestion information. When faced with new user information, the multimodal model can use previously learned knowledge and trained patterns to generate suggestion information corresponding to the user information. Therefore, even if the user information does not include information indicating that the multimodal model outputs information related to lighting effects or sound effects, the multimodal model can generate suggestion information corresponding to the user information. After obtaining the suggestion information corresponding to the user information through the multimodal model, the trained multimodal model can be directly called, and there is no need to train the multimodal model.

[0050] For example, if the user information is a text message such as "I am dancing, what color and lighting effect is suitable for me?", the recommended information output by the multimodal model for the above user information may be: "Red and orange: can create an atmosphere of passion and vitality, suitable for expressing strong emotions and dynamics; blue and purple: can create a mysterious and romantic atmosphere, suitable for expressing deep emotions or dreamy dances; white and light colors can create a pure and fresh atmosphere, suitable for expressing light, smooth or elegant dances. Chasing effect: by allowing the lights to move with the dance movements, the dynamics and continuity of the dance can be enhanced; sweeping effect: by allowing the lights to quickly sweep across the stage or a specific area, the key points can be highlighted or a tense atmosphere can be created; gradient effect: by allowing the lights to gradually change color or brightness, a gradient effect can be created, making the dance more smooth and natural."

[0051] If the user information is a text message or voice message asking "What kind of environment is suitable for me to read?", the recommended information output by the multimodal model for the above user information may be: "With soft background music and a quiet atmosphere, the library or bookstore is an ideal place to read. There, we can sit by the window in bright light, holding a book in hand, and let our thoughts wander freely among the words. The warmth and tranquility of home provide us with a comfortable reading space. Cafes or teahouses are also good places for us to read. The relaxing music and comfortable atmosphere there seem to soothe our inner anxiety and uneasiness, and enjoy the unique tranquility and beauty. The spacious nature is also a good choice for reading. In parks, beaches, gardens and other places, you can immerse yourself in the embrace of nature and feel tranquility and harmony."

[0052] If the user information is a picture of several people wearing Christmas hats, the recommendation information output by the multimodal model for the above user information may be: "Several friends or family members get together, wearing cute Christmas hats, the warmth and affection of home, adding joy and warmth to the festival. At this special moment, let us share happiness together, leave beautiful memories, and feel the joy and blessings that Christmas brings us."

[0053] The above examples of suggested information are only examples and are not limited to these.

[0054] S13: Control at least one target device based on the suggestion information.

[0055] In some embodiments of the present application, the target device may include any one or more of a lighting device (e.g., the lighting device 20 in FIG. 1 ), an audio playback device (e.g., the audio playback device 30 in FIG. 1 ), and a smart device (e.g., the smart device 40 in FIG. 2 ). Among them, the lighting device may be various types of lamps that can provide lighting functions and effects. For example, the lighting device may be an LED lamp, an energy-saving lamp, a floodlight, a security lamp, a stage lamp, a light string, a light strip, and a light bead, etc. The audio playback device may be various types of devices that can provide audio playback functions, for example, the audio playback device may be a smart speaker, a radio, a Bluetooth headset, a player, a speaker, and a device in a smart home that can have a central control function through authorization, etc. The smart device has at least one lighting function and / or at least one audio playback function, and a smart device has a lighting function and / or an audio playback function. When the smart device has both lighting function and audio playback function, the smart device may be a smart lighting audio, a light and audio projector, and a smart home system, etc.

[0056] In some embodiments of the present application, the electronic device controls at least one target device based on the suggestion information, including: the electronic device analyzes the semantics of the suggestion information, and extracts lighting effect key information and / or sound effect key information from the suggestion information, the electronic device controls at least one lighting device according to the lighting effect key information, and / or controls at least one audio playback device according to the sound effect key information.

[0057] Among them, the key information of lighting effects and / or key information of sound effects include but are not limited to: words, phrases and sentences, etc., and the key information of lighting effects and / or key information of sound effects can be interpreted and analyzed by a natural language processing model (Natural Language Processing, NLP). The electronic device can call the natural language processing model to perform semantic analysis on the suggestion information, and extract the key information of lighting effects and / or key information of sound effects from the suggestion information. The natural language processing model can be a pre-set model, or the natural language processing model can be a model that is closer to the needs after being pre-set and pre-trained, and this application does not limit this. For example, the natural language processing model can be a recurrent neural network (RNN), a long short-term memory network (LSTM), a text convolutional neural network (TextCNN) and a Transformer model, etc.

[0058] Key lighting effect information includes key information about light color and light change effects. For example, key information about light colors that an electronic device can extract from suggestion information includes: red, orange, blue, purple, white, and pastel colors. Key information about light change effects that an electronic device can extract from suggestion information includes: a chasing effect where the light follows dance movements, a sweeping effect where the light quickly sweeps across, and a gradient effect where the light gradually changes color or brightness.

[0059] For example, the multimodal model's suggestion information for dancing lights can extract lighting effect keywords such as red, orange, white, pale, chasing, sweeping, and gradient. The multimodal model's suggestion information for the environment can extract sound effect keywords such as soft background music, tranquility, serene atmosphere, warmth, tranquility, relaxing music, and harmony, as well as lighting effect keywords such as bright and comfortable. The multimodal model's suggestion information for a picture of several people wearing Santa hats can extract lighting and sound effect keywords such as joy, happiness, warmth, and warmth. The lighting effect keywords and sound effect keywords extracted from the suggestion information can be the same. For example, keywords such as "happy" and "joyful" can be sound effect keywords as well as lighting effect keywords. Keywords such as "happy" and "joyful" can be used to control both lighting and sound effects.

[0060] In some embodiments of the present application, the electronic device controls at least one lighting device according to lighting effect key information, and / or controls at least one audio playback device according to sound effect key information, including: the electronic device combines different types of lighting effect key information to obtain multiple lighting effects, and controls at least one lighting device according to the multiple lighting effects, and / or combines different types of sound effect key information to obtain multiple sound effects, and controls at least one audio playback device according to the multiple sound effects.

[0061] The combination of key lighting effect information and / or key sound effect information can be free or based on preset rules. For example, if there are six key lighting effect information for light color and three key lighting effect information for light change effects, free combination of the six key lighting effect information for light effects and the three key lighting effect information for light change effects can produce at least 18 lighting effects. By combining different types of key lighting effect information, the number of lighting effects can be increased, and by combining different types of key sound effect information, the number of sound effects can be increased.

[0062] In some embodiments of the present application, the method also includes: the electronic device controls at least one smart device and / or at least one lighting device based on the lighting effect key information, and / or controls at least one smart device and / or at least one audio playback device based on the sound effect key information, and the at least one smart device has at least one lighting function and / or at least one audio playback function.

[0063] Among them, a smart device can have both lighting and / or audio playback functions, or it can have one of the lighting function and audio playback function. The smart device can have corresponding components to support the functions of the smart device. For example, the spotlights and light-emitting diodes in the smart device can support the lighting function of the smart device, and the speakers, audio drivers or audio modules in the smart device can support the audio playback function of the smart device. When the key information of lighting effects and key information of sound effects are extracted, and the smart device has lighting function and audio playback function, the electronic device can control the lighting function and audio playback function of the smart device respectively according to the key information of lighting effects and key information of sound effects, or the electronic device can control the lighting function or audio playback function of the smart device according to one of the information between the key information of lighting effects and key information of sound effects, and then control other corresponding devices (such as lighting devices or audio playback devices) according to the other information between the key information of lighting effects and key information of sound effects.

[0064] In some examples, in a smart device, lighting effect key information may correspond to sound effect key information. When only one of the lighting effect key information and the sound effect key information is extracted, the corresponding function may be activated based on the correspondence between the lighting effect key information and the sound effect key information. For example, the smart device has a lighting function and an audio playback function. The extracted lighting effect key information is "red," and the sound effect key information corresponding to "red" in the smart device is classical music. The electronic device can control the smart device to turn on the red spotlight and activate the audio module to play classical music. Or if the extracted sound effect key information is classical music, and the lighting effect key information corresponding to classical music in the smart device is blue, the electronic device can control the smart device to turn on the blue spotlight and activate the audio module to play classical music.

[0065] In this embodiment, the use of the functions of the smart device and the combination of the smart device with lighting devices, audio playback devices and other devices are flexible and can be set by yourself. This application does not impose any restrictions on this.

[0066] In other embodiments of the present application, user information may include user profile information, which refers to various types of information related to the user. User profile information may include basic user information and user authorization information. Basic user information includes, but is not limited to, gender, current mood, date of birth, age, marital status, hobbies, education, occupation, location, weather conditions at the user's location, and scene images of the user's area (e.g., images of grayscale walls and whitescale walls). User authorization information is a user's historical usage records on multiple devices. Historical usage records can be obtained from the device logs. The multiple devices can be devices used by the user, such as lighting devices and audio playback devices. Historical usage records of the user on multiple devices include, but are not limited to, information on the current and / or historical music types played by the user on audio playback devices, sound devices, or music players, current and / or historical music volumes, current and / or historical music rhythms, and other musical expression forms, as well as the current and / or historical air conditioning temperatures set by the user on air conditioning devices. Furthermore, the user's previous usage habits for lighting devices (e.g., the user's historical expression information and the lighting effects of the historical expression information on the lighting device) can also be part of the user authorization information.

[0067] Key lighting effect information and / or key sound effect information can be extracted from the user profile information. For example, if the user's historical usage records indicate that the user used yellow lights and listened to classical music, the key lighting information in the user profile information would be yellow, and the key sound effect information would be classical music.

[0068] In other embodiments of the present application, before controlling at least one lighting device according to the key lighting effect information, the method also includes: the electronic device detects whether there is at least one lighting device in the environment, and when it is detected that there is no at least one lighting device in the environment, stores the key lighting effect information; when it is detected that there is at least one lighting device in the environment, controls the at least one lighting device according to the stored key lighting effect information; or, by inquiring the user, determines whether to use the stored key lighting effect information, and when it is determined to use the stored key lighting effect information, controls the at least one lighting device according to the stored key lighting effect information.

[0069] In other embodiments of the present application, before the sound effect key information controls at least one audio playback device, it is possible to first detect whether there is at least one audio playback device in the environment. When it is detected that there is no at least one audio playback device in the environment, the sound effect key information is stored. When it is detected that there is at least one audio playback device in the environment, the at least one audio playback device is controlled based on the stored sound effect key information; or, by inquiring with the user, it is determined whether to use the stored sound effect key information. When it is determined to use the stored sound effect key information, the at least one audio playback device is controlled based on the stored sound effect key information.

[0070] In other embodiments of the present application, the electronic device may invoke a built-in artificial intelligence algorithm to generate lighting effects and sound effects that match the user's expression information based on the key lighting effect information and / or key sound effect information. Alternatively, the electronic device may extract the key lighting effect information and / or key sound effect information from a preset database to generate lighting effects and sound effects that match the user's expression information.

[0071] The artificial intelligence algorithm may be a generative algorithm that automatically generates lighting effects and / or sound effects based on lighting effect keywords and / or sound effect key information. The artificial intelligence algorithm may use natural language processing technology and machine learning models to analyze lighting effect keywords and / or sound effect key information in user information and generate lighting effects and / or sound effects that are tailored to the user information. A database stores information on various lighting effects and / or sound effects that match the lighting effect keywords and / or sound effect key information. By matching the extracted lighting effect keywords and / or sound effect keywords, the electronic device can retrieve the lighting effects and / or sound effects corresponding to the user information from the database.

[0072] In other embodiments of the present application, if the electronic device is a device with a voice output function, such as an intelligent interactive device, the method further includes: upon detecting that the suggestion information includes preset information, outputting voice to interact with the user. The preset information is a condition that triggers the voice output, and the preset information can be set arbitrarily, and this application does not impose any restrictions on this. The voice can be a preset voice or a natural language interactive voice. The process of the electronic device outputting voice to interact with the user can be a continuous process.

[0073] The relationship between outputting voice to interact with the user, controlling the lighting effects of the lighting device, and controlling the sound effects of the audio playback device is an AND / OR relationship. Based on actual needs, one or more of the steps of outputting voice to interact with the user, controlling the lighting effects of the lighting device, and controlling the sound effects of the audio playback device can be flexibly performed. For example, during voice interaction with the user, the lighting effects of the lighting device and the sound effects of the audio playback device can be controlled simultaneously. Alternatively, during voice interaction with the user, to ensure voice clarity and voice interaction quality, only the lighting effects of the lighting device can be controlled.

[0074] If a user is accustomed to using a certain device (such as a mobile phone) for a long time, when the user has needs such as communication and chatting, he or she may forget that there are other devices at home that can meet the user's needs. When it is detected that the suggestion information includes preset information, the electronic device can interact with the user by outputting voice, which can increase the path for the use of smart interactive devices and make reasonable use of smart interactive devices that are not often used in the user's home. For example, the user information is "I want to talk to someone now", and the suggestion information output by the multimodal model for the user information is "Find someone to talk to: You can have a conversation with anyone, whether it is a stranger or a friend. Or you can communicate with the smart interactive devices at home", then the preset information can be "smart interactive device". When it is detected that the suggestion information includes "smart interactive device", the electronic device can output voice such as "Do you have any specific questions or needs?" or "I am listening, please tell me how you need help" to interact with the user.

[0075] In this embodiment, when it is detected that the suggestion information includes preset information, voice is output to interact with the user, which can meet the diversified needs of the user.

[0076] Through the above-described embodiments, user information can be used to clarify user behavior, control requirements, or the user's current scenario. By learning the implicit connections between information from different input modalities and the common features that require output of recommended information, the system can respond to any user's expressed information. Furthermore, the multimodal model is trained using the user's expressed information to output recommended information. Therefore, even if the user information does not include control requirements, the multimodal model can output recommended information consistent with the user information, thereby accurately controlling the target device based on the recommended information. When the recommended information includes information related to lighting and / or sound effects, the target device includes one or more of a lighting device, an audio playback device, and a smart device with lighting and / or audio playback functions. Based on the information related to the lighting and / or sound effects, the lighting device and / or audio playback device can be accurately controlled, thereby matching the scene requirements with the lighting and / or sound effects, providing the user with a comfortable sensory experience. Furthermore, by matching the scene requirements with the lighting and / or sound effects, a suitable atmosphere can be created, increasing the flexibility of controlling the ambient device.

[0077] In some embodiments of the present application, as shown in FIG4 , which is a flow chart of a control method provided by another embodiment of the present application, the method includes the following steps:

[0078] S131 : Send the lighting effect key information and / or the sound effect key information to the terminal device, and receive a selection instruction for the lighting effect key information and / or the sound effect key information sent from the terminal device.

[0079] In some embodiments of the present application, terminal devices include but are not limited to mobile phones, smart watches, computers and other devices. The selection instruction may correspond to a type of lighting effect key information and / or a type of sound effect key information selected by the user, or may correspond to a combination of multiple lighting effect key information and / or a combination of multiple sound effect key information selected by the user. If there is a contradiction in displaying multiple combinations of lighting effect key information and / or multiple combinations of sound effect key information at the same time, the multiple combinations of lighting effect key information and / or multiple combinations of sound effect key information may be displayed intermittently, or the user may be prompted to select only one of the multiple combinations of lighting effect key information, and / or the user may be prompted to select only one of the multiple combinations of sound effect key information.

[0080] In other embodiments of the present application, the electronic device may combine multiple lighting effect key information and / or multiple sound effect key information to obtain multiple lighting effects and / or multiple sound effects for the user to select one or more. If multiple lighting effects and / or sound effects are selected, and there is a conflict in displaying the multiple lighting effects and / or multiple sound effects simultaneously, the multiple lighting effects and / or multiple sound effects may be displayed intermittently, or the user may be prompted to select only one of the multiple lighting effects and / or the user may be prompted to select only one of the multiple sound effects.

[0081] Among them, the key information of multiple lighting effects and the multiple lighting effects are different.

[0082] For example, multiple lighting effects, such as "red," "green," "white," and "gradient," are directly displayed on the terminal device for user selection. This allows for greater flexibility in selecting key lighting effects. Multiple lighting effects, such as "red, gradient," "green, gradient," and "white, gradient," are displayed directly on the terminal device for user selection. This direct display of multiple lighting effects increases user clarity regarding the lighting effect they desire.

[0083] Among them, multiple sound effect key information and multiple sound effects are different.

[0084] For example, a variety of sound effect key information refers to the key information extracted such as "wind", "rain", and "classical music" being directly presented on the terminal device for the user to choose. By displaying it in this way, the user's flexibility in selecting the key sound effect information can be improved. A variety of sound effects refers to "wind, classical music", "rain, classical music", "wind, rain", and "wind, rain, and classical music" being presented on the terminal device for the user to choose. By displaying a variety of sound effects on the terminal device, the clarity of the sound effects that the user wants to display can be improved.

[0085] In this embodiment, the lighting effect key information and / or sound effect key information is directly sent to the terminal device for user selection, which can improve the user's selection flexibility and make the selected lighting effect key information and / or sound effect key information meet the user's needs.

[0086] In other embodiments of the present application, the electronic device may first classify the key lighting effect information and / or key sound effect information, and then send the classified key lighting effect information and / or key sound effect information to the terminal device. For example, when classifying the key lighting effect information, the light brightness may be classified into one category, the light color may be classified into one category, the light change effect may be classified into one category, and the light operation may be classified into one category. When classifying the key sound effect information, the sound tone may be classified into one category, the sound rhythm may be classified into one category, the music title may be classified into one category, and the sound operation may be classified into one category.

[0087] In this embodiment, since the classified lighting effect key information and / or sound effect key information are more organized and logical, the classified lighting effect key information and / or sound effect key information are sent to the terminal device, which can improve the user experience.

[0088] S132: Control at least one lighting device according to the lighting effect key information corresponding to the selection instruction, and / or control at least one audio playback device according to the sound effect key information corresponding to the selection instruction.

[0089] In some embodiments of the present application, if key information on lighting effects and key information on sound effects are extracted from the suggestion information, the electronic device can send the key information on lighting effects to at least one lighting device, and send the key information on sound effects to at least one audio playback device, or the electronic device can send the key information on lighting effects and key information on sound effects to a smart device that has both lighting and audio playback functions, thereby achieving dual control of lighting effects and sound effects.

[0090] In some embodiments of the present application, the electronic device may generate a lighting effect control instruction based on the lighting effect key information corresponding to the selection instruction, and control at least one lighting device to emit a lighting effect corresponding to the lighting effect key information according to the lighting effect control instruction, and / or, the electronic device may generate a sound effect control instruction based on the sound effect key information corresponding to the selection instruction, and control at least one audio playback device to emit a sound effect corresponding to the sound effect key information according to the sound effect control instruction.

[0091] In other embodiments of the present application, if key information on lighting effects and key information on sound effects are extracted from the suggestion information, the electronic device can generate a lighting effect control instruction based on the key information on lighting effects corresponding to the selection instruction, and generate a sound effect control instruction based on the key information on sound effects corresponding to the selection instruction. The electronic device controls the smart device with both lighting and audio playback functions to emit lighting effects corresponding to the key information on lighting effects and sound effects corresponding to the key information on sound effects based on the lighting effect control instruction and the sound effect control instruction.

[0092] In other embodiments of the present application, if the terminal device is an electronic device, for example: the electronic device receives user information input by the user in the electronic device, and generates corresponding suggestion information based on the user information, the electronic device extracts lighting effect key information and / or sound effect key information, and directly displays the extracted lighting effect key information and / or sound effect key information on the visual interface of the electronic device, receives the lighting effect key information and / or sound effect key information selected by the user on the visual interface, and generates lighting effect control instructions and / or sound effect control instructions based on the lighting effect key information and / or sound effect key information selected by the user to control one or more of the lighting device, audio playback device and smart device with both lighting and audio playback functions.

[0093] In this embodiment, the lighting effect and / or sound effect are controlled by using the lighting effect key information and / or sound effect key information selected by the user, which can improve the control accuracy of the lighting effect and / or sound effect.

[0094] In some embodiments of the present application, as shown in FIG5 , which is a flow chart of a control method provided by another embodiment of the present application, the control method includes the following steps:

[0095] S133: Send the multiple lighting effects and / or multiple sound effects to the terminal device, and receive a selection instruction for the multiple lighting effects and / or multiple sound effects sent from the terminal device.

[0096] In some embodiments of the present application, terminal devices include but are not limited to mobile phones, smart watches, and computers. The selection instruction may correspond to a single lighting effect and / or a single sound effect selected by the user, or may correspond to a combination of multiple lighting effects and / or a combination of multiple sound effects selected by the user. If there is a conflict in displaying the multiple lighting effect combinations and / or the multiple sound effect combinations simultaneously, the multiple lighting effect combinations and / or the multiple sound effect combinations may be displayed intermittently, or the user may be prompted to select only one of the multiple lighting effect combinations and / or the multiple sound effect combinations.

[0097] In this embodiment, by sending multiple lighting effects and / or multiple sound effects to the terminal device, the probability that the multiple lighting effects and / or multiple sound effects meet the user's needs can be increased.

[0098] S134: Control at least one lighting device according to the lighting effect corresponding to the selection instruction, and / or control at least one audio playback device according to the sound effect corresponding to the selection instruction.

[0099] In this embodiment, the electronic device can generate a lighting effect control instruction based on the lighting effect corresponding to the selection instruction, and control at least one lighting device to emit the lighting effect corresponding to the selection instruction based on the lighting effect control instruction, and / or, the electronic device can generate a sound effect control instruction based on the sound effect corresponding to the selection instruction, and control at least one audio playback device to emit the sound effect corresponding to the selection instruction based on the sound effect control instruction.

[0100] In other embodiments of the present application, if the terminal device is an electronic device, for example: the electronic device receives user information input by the user in the electronic device, and generates corresponding suggestion information based on the user information, the electronic device extracts lighting effect key information and / or sound effect key information, combines different types of lighting effect key information to obtain a variety of lighting effects, and / or combines different types of sound effect key information to obtain a variety of sound effects, directly displays a variety of lighting effects and / or a variety of sound effects on the visual interface of the electronic device, receives at least one lighting effect and / or at least one sound effect selected by the user on the visual interface, and generates lighting effect control instructions and / or sound effect control instructions based on the at least one lighting effect and / or at least one sound effect selected by the user to control one or more of the lighting device, audio playback device and smart devices with both lighting and audio playback functions.

[0101] In some embodiments of the present application, as shown in FIG6 , which is a flow chart of a control method provided by another embodiment of the present application, the control method includes the following steps:

[0102] S136, determining a target lighting effect from a plurality of lighting effects according to the user portrait information, and / or determining a target sound effect from a plurality of sound effects according to the user portrait information.

[0103] In some embodiments of the present application, in addition to obtaining user portrait information from user information, the electronic device may also obtain user portrait information through other means. For example, the electronic device may be connected to a device such as a smartphone or tablet computer used by the user and, through authorization, obtain user portrait information from various applications on the smartphone or tablet computer, including, but not limited to, social applications and weather applications.

[0104] In some embodiments of the present application, the electronic device determines a target lighting effect from a plurality of lighting effects based on user portrait information, and / or determines a target sound effect from a plurality of sound effects based on user portrait information, including: the electronic device inputs the user portrait information, the plurality of lighting effects and / or the plurality of sound effects into a pre-trained machine learning model, obtains a first probability of the user portrait information corresponding to each lighting effect and / or a second probability of the user portrait information corresponding to each sound effect, selects a first preset number of lighting effects from the first probabilities arranged from high to low as the target lighting effect, and / or selects a second preset number of sound effects from the second probabilities arranged from high to low as the target sound effect.

[0105] The first preset number and the second preset number may be the same or different, and the first preset number and the second preset number may be set arbitrarily, and this application does not impose any restrictions thereon. For example, the first preset number may be 1, and the second preset number may be 2.

[0106] In some embodiments of the present application, a machine learning model can be obtained by pre-training a machine learning algorithm using training data. The training data includes multiple user profile information and lighting effects. During the process of training the machine learning model based on the user profile information, multiple lighting effects, and / or multiple sound effects, the parameters of the machine learning algorithm are repeatedly optimized so that the trained machine learning model can accurately predict the relationship between the user profile information and the lighting effects and / or the relationship between the user profile information and the sound effects.

[0107] Machine learning algorithms include, but are not limited to, decision trees and support vector machines. A machine learning model may include a classifier, which can be used to determine a first probability of each lighting effect corresponding to user profile information and / or a second probability of each sound effect corresponding to user profile information. The classifier may be a softmax function.

[0108] S137: Control at least one lighting device according to the target light effect, and / or control at least one audio playback device according to the target sound effect.

[0109] In this embodiment, the electronic device can generate a lighting effect control instruction based on the target lighting effect, and control at least one lighting device to emit the target lighting effect based on the lighting effect control instruction, and / or, the electronic device can generate a sound effect control instruction based on the target sound effect, and control at least one audio playback device to emit the target sound effect based on the sound effect control instruction.

[0110] Figure 7 shows a functional block diagram of a control device according to an embodiment of the present application. The control device 11 includes an acquisition unit 110, an input unit 111, and a control unit 112. A module / unit as referred to herein refers to a series of computer-readable instruction segments that can be acquired by the processor 103 in Figure 8 and that can perform a fixed function, and is stored in the memory 102 in Figure 8. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0111] The acquiring unit 110 is configured to acquire user information.

[0112] In some embodiments of the present application, the category of the user information includes at least one of text, video, image and sound.

[0113] The input unit 111 is used to input the user information into the multimodal model to obtain suggestion information corresponding to the user information.

[0114] The control unit 112 is configured to control at least one target device based on the suggestion information.

[0115] In some embodiments of the present application, the control unit 112 is further used to analyze the semantics of the suggestion information, and extract lighting effect key information and / or sound effect key information from the suggestion information, control at least one lighting device according to the lighting effect key information, and / or control at least one audio playback device according to the sound effect key information.

[0116] In some embodiments of the present application, the control unit 112 is further used to send the lighting effect key information and / or the sound effect key information to the terminal device, and receive a selection instruction for the lighting effect key information and / or the sound effect key information sent from the terminal device, and control the at least one lighting device according to the lighting effect key information corresponding to the selection instruction, and / or control the at least one audio playback device according to the sound effect key information corresponding to the selection instruction.

[0117] In some embodiments of the present application, the control unit 112 is further used to combine different types of lighting effect key information to obtain multiple lighting effects, and control the at least one lighting device according to the multiple lighting effects, and / or combine different types of sound effect key information to obtain multiple sound effects, and control the at least one audio playback device according to the multiple sound effects.

[0118] In some embodiments of the present application, the control unit 112 is further used to send the multiple lighting effects and / or the multiple sound effects to a terminal device, receive selection instructions for the multiple lighting effects and / or the multiple sound effects sent from the terminal device, control at least one lighting device according to the lighting effects corresponding to the selection instructions, and / or control at least one audio playback device according to the sound effects corresponding to the selection instructions.

[0119] In some embodiments of the present application, the control unit 112 is also used to control at least one smart device and / or at least one lighting device based on the lighting effect key information, and / or, based on the sound effect key information, to control at least one smart device and / or at least one audio playback device, wherein the at least one smart device has at least one lighting function and / or at least one audio playback function.

[0120] In some embodiments of the present application, the control unit 112 is further configured to output a voice message to interact with the user when detecting that the suggestion information includes preset information.

[0121] FIG8 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. As shown in FIG8 , the electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102, and the input / output interface 104 via the bus 105.

[0122] The communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as universal serial bus (USB) and controller area network (CAN). The wireless communication module may provide one or more wireless communication solutions such as wireless fidelity (Wi-Fi), Bluetooth (BT), mobile communication network, frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0123] The memory 102 may include one or more random access memories (RAMs) and one or more non-volatile memories (NVMs). The RAM can be directly read and written by the processor 103 and can be used to store executable programs (e.g., machine instructions) of other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0124] The non-volatile memory can also store executable programs and user and application data, etc., and can be pre-loaded into the random access memory for direct reading and writing by the processor 110. The non-volatile memory can include disk storage devices and flash memory.

[0125] The memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include multiple instructions. When the multiple instructions are executed by the processor 103, the control method executed on the electronic device 10 can be implemented.

[0126] In other embodiments, the electronic device 10 shown in FIG8 further includes an external memory interface for connecting to an external memory to expand the storage capacity of the electronic device 10 .

[0127] The processor 103 may include one or more processing units. For example, the processor 103 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0128] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute a computer program stored in the memory 102 to implement the above-mentioned control method.

[0129] The input / output interface 104 is used to provide a channel for user input or output. For example, the input / output interface 104 can be used to connect various input and output devices, such as a mouse, keyboard, touch device, display screen, etc., so that the user can enter information or visualize information.

[0130] The bus 105 is at least used to provide a channel for mutual communication among the communication module 101 , the memory 102 , the processor 103 , and the input / output interface 104 in the electronic device 10 .

[0131] It should be understood that the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the electronic device 10. In other embodiments of the present application, the electronic device 10 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0132] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the methods in the above-mentioned embodiments of the present application.

[0133] The computer-readable storage medium may be the internal memory of the electronic device described in the above embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash memory card, etc. equipped on the electronic device.

[0134] In some embodiments, the computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, applications required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc.

[0135] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0136] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0137] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0138] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0139] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A control method, characterized in that, The method includes: Obtaining user information; Inputting the user information into a multi-modal model to obtain recommended information corresponding to the user information; Controlling at least one target device based on the recommended information.

2. The control method according to claim 1, characterized in that The category of the user information includes at least one of text, video, image, and sound.

3. The control method according to claim 1, characterized in that The controlling at least one target device based on the recommended information includes: Analyzing the semantics of the recommended information and extracting lighting effect key information and / or sound effect key information from the recommended information; Controlling at least one lighting device according to the lighting effect key information, and / or controlling at least one audio playback device according to the sound effect key information.

4. The control method according to claim 3, wherein The method further includes: Sending the lighting effect key information and / or the sound effect key information to a terminal device and receiving a selection instruction for the lighting effect key information and / or the sound effect key information sent from the terminal device; Controlling the at least one lighting device according to the lighting effect key information corresponding to the selection instruction, and / or controlling the at least one audio playback device according to the sound effect key information corresponding to the selection instruction.

5. The control method according to claim 3, characterized in that The controlling at least one lighting device according to the lighting effect key information, and / or controlling at least one audio playback device according to the sound effect key information includes: Combining different types of lighting effect key information to obtain multiple lighting effects and controlling the at least one lighting device according to the multiple lighting effects, and / or combining different types of sound effect key information to obtain multiple sound effects and controlling the at least one audio playback device according to the multiple sound effects.

6. The control method according to claim 5, wherein The controlling the at least one lighting device according to the multiple lighting effects, and / or controlling the at least one audio playback device according to the multiple sound effects includes: Sending the multiple lighting effects and / or the multiple sound effects to a terminal device and receiving a selection instruction for the multiple lighting effects and / or the multiple sound effects sent from the terminal device; Controlling the at least one lighting device according to the lighting effect corresponding to the selection instruction, and / or controlling the at least one audio playback device according to the sound effect corresponding to the selection instruction.

7. The control method according to claim 3, wherein The method further includes: Controlling at least one smart device and / or the at least one lighting device according to the lighting effect key information, and / or controlling the at least one smart device and / or the at least one audio playback device according to the sound effect key information, where the at least one smart device has at least one lighting function and / or at least one audio playback function.

8. The control method according to claim 1, wherein, The method further includes: When it is detected that the recommended information includes preset information, outputting voice to interact with the user.

9. A control device, characterized in that, The control device includes: An obtaining unit for obtaining user information; An input unit for inputting the user information into a multi-modal model to obtain recommended information corresponding to the user information; A control unit for controlling at least one target device based on the recommended information.

10. An electronic device, characterized in that, The electronic device includes: A memory storing at least one instruction; and A processor for executing the at least one instruction to implement the control method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: At least one instruction is stored in the computer-readable storage medium, and when the at least one instruction is executed by a processor in an electronic device, the control method described in any one of claims 1 to 8 is implemented.

Images