Electronic device for generating personalized sound and control method therefor

Abstract

This electronic device comprises: at least one processor including processing circuitry; and a memory storing instructions, wherein, when the instructions are individually or collectively executed by the at least one processor, the electronic device obtains at least one parameter value corresponding to an attribute of a sound, obtains a prompt for generating a sound reflecting the attribute on the basis of the parameter value, obtains the sound by inputting the obtained prompt into an artificial intelligence model, and transmits the obtained sound to at least one external device.

Description

Electronic device for generating personalized sound and method for controlling the same

[0001] The present disclosure relates to an electronic device and a method for controlling the same, and more specifically, to an electronic device for generating personalized sound and a method for controlling the same.

[0002] IoT (Internet of Things) devices can output system sounds, such as a power sound indicating that the power is turned on or an operation sound indicating a notification or the completion of an operation. It is common for IoT devices to output standardized system sounds. These standardized system sounds limit the user experience and have the disadvantage of failing to satisfy diverse user preferences.

[0003] Accordingly, as the demand for improving the user experience increases, the demand for personalized system sounds is steadily rising. Users require the ability to set and adjust the system sounds provided by IoT devices to suit their personal preferences, and thus there is a need for technology that provides personalized system sounds.

[0004] An electronic device according to the present disclosure comprises at least one processor and a memory for storing at least one instruction, and when the at least one instruction is executed individually or collectively by the at least one processor, the electronic device may acquire at least one parameter value corresponding to an attribute of sound, acquire a prompt for generating a sound reflecting the attribute based on the parameter value, input the acquired prompt into an artificial intelligence model to acquire the sound, and transmit the acquired sound to at least one external device.

[0005] In this case, one of the above at least one parameter value may include a value based on at least one of the attributes of the environment in which the sound is output, the mood of the sound, the type of the sound, information about music preferred by the user, identification information corresponding to the external device in which the sound is output, or a detected event.

[0006] In this case, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device can transmit the acquired sound to the above at least one external device when the event is detected.

[0007] Meanwhile, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device can obtain information about music preferred by the user from a music application running on an external device.

[0008] In this case, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device can acquire a feature vector of the music preferred by the user based on information about the music preferred by the user, and input the prompt and the feature vector of the music liked by the user into the artificial intelligence model to acquire the sound.

[0009] In this case, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device may acquire a plurality of sounds reflecting the above attributes, determine a similarity score between each of the plurality of sounds and a feature vector corresponding to the user's situation, identify the sound having the highest similarity score among the plurality of sounds, and transmit the identified sound to the above at least one external device.

[0010] Meanwhile, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device can obtain the sound by removing the noise from the data based on a Gaussian distribution.

[0011] Meanwhile, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device can acquire information about the speaker performance of a plurality of external devices and transmit the acquired sound to an external device having a higher speaker performance than other external devices.

[0012] Meanwhile, when the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device may transmit the acquired sound to the above at least one external device located in the space where the user's terminal device is located among a plurality of external devices when the condition for outputting the acquired sound is satisfied.

[0013] A control method for an electronic device according to the present disclosure may include the steps of: obtaining at least one parameter value corresponding to an attribute of sound; obtaining a prompt for generating a sound reflecting the attribute based on the parameter value; inputting the obtained prompt into an artificial intelligence model to obtain the sound; and transmitting the obtained sound to at least one external device.

[0014] In this case, one of the above at least one parameter value may include a value based on at least one of the attributes of the environment in which the sound is output, the mood of the sound, the type of the sound, information about music preferred by the user, identification information corresponding to the external device in which the sound is output, or a detected event.

[0015] In this case, the step of transmitting the acquired sound to the external device may transmit the acquired sound to the at least one external device when the event is detected.

[0016] In this case, the step of obtaining user input corresponding to a parameter value for determining the attributes of the sound output by the external device may involve obtaining information about the music preferred by the user from a music application running on the external device.

[0017] Meanwhile, the above control method further includes the step of obtaining a feature vector of music preferred by the user based on information about music preferred by the user, and the step of obtaining the sound can be obtained by inputting the prompt and the feature vector of music liked by the user into the artificial intelligence model.

[0018] Meanwhile, the step of acquiring the sound comprises acquiring a plurality of sounds reflecting the attribute, and the control method further includes the step of determining a similarity score between each of the plurality of sounds and a feature vector corresponding to the user's situation, and the step of identifying the sound having the highest similarity score among the plurality of sounds, and the step of transmitting the acquired sound to the external device may transmit the identified sound to the at least one external device.

[0019] The step of acquiring the sound above can be performed by removing the noise from data containing noise following a Gaussian distribution based on the generated prompt as a condition to acquire the sound.

[0020] The step of transmitting the acquired sound to the external device may involve acquiring information regarding the speaker performance of a plurality of external devices and transmitting the acquired sound to an external device with higher speaker performance than the external device, for the sound to be output by the external device.

[0021] The step of transmitting the acquired sound to the external device may, when a condition for outputting the acquired sound is detected, transmit the acquired sound to an external device located in the space where the user's terminal device is located among a plurality of external devices.

[0022] A non-transient computer-readable recording medium comprising a program for executing a method of controlling an electronic device according to one or more embodiments of the present disclosure comprises: a step of obtaining a user input for setting a parameter value for determining the attribute of a sound output by an external device; a step of obtaining a prompt for generating a sound reflecting the determined attribute based on the set parameter value; a step of inputting the obtained prompt into an artificial intelligence model to obtain a sound reflecting the attribute; and a step of transmitting the obtained sound to the external device.

[0023] The above parameter value may include at least one of the sound output environment, the atmosphere of the sound, the type of the sound, the music preferred by the user, and the type of the external device.

[0024] FIG. 1 is a drawing for illustrating a system for generating personalized sound according to one or more embodiments of the present disclosure.

[0025] FIG. 2 is a block diagram for explaining the configuration of an electronic device according to one embodiment of the present disclosure.

[0026] FIG. 3 is a block diagram for explaining the configuration of a terminal device according to one embodiment of the present disclosure.

[0027] FIG. 4 is a block diagram illustrating the configuration of an external device according to one embodiment of the present disclosure.

[0028] FIG. 5 is a sequence diagram for explaining the operation of an electronic device, a terminal device, and an external device according to one embodiment of the present disclosure.

[0029] FIGS. 6 to 10 are drawings for illustrating a method of personalizing sound using an electronic device according to one embodiment of the present disclosure.

[0030] FIG. 11 is a diagram illustrating a method for an electronic device to train an artificial intelligence model according to one embodiment of the present disclosure.

[0031] FIG. 12 is a diagram illustrating the process of generating sound using an artificial intelligence model according to one embodiment of the present disclosure.

[0032] FIG. 13 is a sequence diagram for explaining the operation of an electronic device, a terminal device, and an external device according to one embodiment of the present disclosure.

[0033] FIG. 14 is a sequence diagram for explaining the operation of an electronic device, a terminal device, and an external device according to one embodiment of the present disclosure.

[0034] FIG. 15 is a flowchart illustrating a method for controlling an electronic device according to one embodiment of the present disclosure.

[0035] The embodiments described herein are subject to various modifications and may have various forms; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope of specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present disclosure. In relation to the description of the drawings, similar reference numerals may be used for similar components.

[0036] In describing the present disclosure, if it is determined that a detailed description of related known functions or configurations could unnecessarily obscure the essence of the present disclosure, such detailed description is omitted.

[0037] Additionally, the following embodiments may be modified in various other forms, and the scope of the technical concept of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided to make the present disclosure more faithful and complete and to fully convey the technical concept of the present disclosure to those skilled in the art.

[0038] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of the rights. The singular expression includes the plural expression unless the context clearly indicates otherwise.

[0039] In the present disclosure, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, actions, or components such as parts) and do not exclude the presence of additional features.

[0040] In the present disclosure, expressions such as “A or B,” “at least one of A or / and B,” or “one or more of A or / and B” may include all possible combinations of items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B.

[0041] Expressions such as "first," "second," "first," or "second" used in this disclosure may modify various components regardless of order and / or importance, and are used only to distinguish one component from another and do not limit said components.

[0042] Where it is stated that a certain component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the said certain component may be directly connected to the said other component or connected through another component (e.g., a third component).

[0043] On the other hand, when it is stated that a certain component (e.g., a first component) is "directly connected" or "directly coupled" to another component (e.g., a second component), it may be understood that no other component (e.g., a third component) exists between said certain component and said other component.

[0044] As used in this disclosure, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware.

[0045] Instead, in some situations, the expression “device configured to do something” may mean that the device is “capable of doing something” together with other devices or components. For example, the phrase “processor configured (or set) to perform A, B, and C” may mean a dedicated processor for performing those operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or application processor) capable of performing those operations by executing one or more software programs stored in a memory device.

[0046] In the embodiments, a 'module' or 'part' performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of 'modules' or a plurality of 'parts' may be integrated into at least one module and implemented by at least one processor, except for the 'module' or 'part' that needs to be implemented in specific hardware.

[0047] Meanwhile, the various elements and areas in the drawings are depicted schematically. Accordingly, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0048] Hereinafter, embodiments according to the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement them.

[0049] FIG. 1 is a drawing for illustrating a system for generating personalized sound according to one embodiment of the present disclosure.

[0050] Referring to FIG. 1, a system (1) for generating personalized sound may include an electronic device (100), a terminal device (200), and an external device (300).

[0051] According to one embodiment of the present disclosure, the electronic device (100) may be implemented as a server, the terminal device (200) may be implemented as a smartphone, and the external device (300) may be implemented as a home appliance such as a refrigerator, TV, microwave oven, etc. The electronic device (100) may communicate with the terminal device (200) through a network. As will be understood by those skilled in the art, the embodiments of the present invention are not limited to a single electronic device (101). For example, the embodiments of the present invention may be implemented on a distributed architecture including a plurality of processors. Additionally, the embodiments of the present invention may be implemented in such a way that one or more tasks are distributed and performed on a plurality of servers in the cloud.

[0052] In particular, the external device (300) can be implemented as an IoT device that is connected to the Internet or a network and can transmit and / or receive data based on Internet of Things technology.

[0053] In one or more examples, the implementation examples of each device described above are merely one embodiment, and each device may be implemented in various forms such as a server, smartphone, mobile phone, TV, smart TV, set-top box, refrigerator, washing machine, microwave oven, dishwasher, PDA (personal digital assistant), laptop, media player, e-book reader, digital broadcasting terminal, navigation, kiosk, MP3 player, wearable device, home appliance, and other mobile or non-mobile computing devices.

[0054] The external device (300) may output a system sound to convey to the user the operating status of the external device (300), interaction through the user interface of the external device (300), warning notifications, etc. The system sound may be used to indicate the status of the external device (300) or to provide feedback to the user when the user performs a specific task through the external device (300). For example, when the operation of the external device (300) begins, the external device (300) may output a sound indicating the start of operation. In one or more examples, the external device (300) may output a confirmation sound when a button is pressed. Alternatively, the external device (300) may output a sound indicating the completion of a specific task when a specific task is completed.

[0055] In the present disclosure, the "system sound" of an external device may be replaced with terms of the same or similar concept, such as "output sound," "notification sound," "operation sound," "feedback sound," "signal sound," "function sound," "status sound," "warning sound," "interface sound," or "control sound." Furthermore, as will be understood by those skilled in the art, embodiments of the present invention are not limited to system sounds. For example, embodiments of the present invention may include tactile or visual feedback that is output together with the system sound or output instead of the system sound.

[0056] The system (1) according to the present disclosure can personalize the system sound of an external device (300). The system (1) can generate a sound having attributes preferred by the user and / or attributes suitable for the user's environment by reflecting the user's preferences, the user's environment, etc. For example, user preferences may specify a predetermined volume level, a predetermined frequency range (e.g., high or low), or a preferred language (e.g., English, Spanish, etc.).

[0057] The terminal device (200) can run an application for personalizing the system sound of an external device (300). The terminal device (200) can obtain user input to set parameter values ​​for determining the attributes of the system sound through the run application.

[0058] When a parameter value is set, the terminal device (200) can transmit the set parameter value to the electronic device (100). At this time, the terminal device (200) can transmit a request to the electronic device (100) to generate a personalized sound using the parameter value.

[0059] The electronic device (100) can obtain a prompt for generating a sound that reflects a determined attribute based on a received parameter value. The prompt may include information about the parameter value for determining the attribute of the sound.

[0060] A prompt may refer to an input for initiating interaction with an artificial intelligence model that generates personalized sounds. A prompt may be a text input containing one or more words and / or one or more sentences. In one or more examples, the prompt may be displayed on a graphical user interface of a terminal device (300). The prompt may be displayed as an application that causes the prompt to be displayed is executed. The prompt may include text or audio requesting user input. The input may be text, or it may be an input for selecting one of multiple options.

[0061] When a prompt is obtained, the electronic device (100) can input the obtained prompt into an artificial intelligence model to obtain a sound that reflects the determined attributes. The generated sound may be a sound with attributes personalized to the user. The generated sound may be replaced with terms such as "personalized sound" or "AI sound".

[0062] An artificial intelligence model may be a generative AI model that generates personalized sound based on input prompts. As will be understood by those skilled in the art, a generative AI model may be a type of AI model configured to generate new content, such as images, text, music, and audio, based on existing data. A generative AI model learns from data and can generate new samples or instances based on that learned knowledge. Examples of generative AI models may include, but are not limited to, Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs).

[0063] The electronic device (100) can transmit the acquired sound to a terminal device (200). The terminal device (200) can transmit the received sound to an external device (300). The external device (300) can output the received sound when conditions for outputting the received sound are satisfied. In one or more examples, each of these devices may be connected via a short-range communication technology such as Bluetooth, or may be connected via Wi-Fi or the Internet.

[0064] The configuration and detailed operation of each device constituting the system (1) will be explained with reference to the drawings below.

[0065] FIG. 2 is a block diagram for explaining the configuration of an electronic device according to one embodiment of the present disclosure.

[0066] Referring to FIG. 2, the electronic device (100) may include at least one of a memory (110), a communication interface (120), and a processor (130). The electronic device (100) may include additional components in addition to the above components.

[0067] The memory (110) can store at least one instruction regarding the electronic device (100). The memory (110) can store an operating system (O / S) for operating the electronic device (100). Additionally, the memory (110) can store various software programs or applications for the electronic device (100) to operate according to various embodiments of the present disclosure. Furthermore, the memory (110) may include semiconductor memory such as flash memory or magnetic storage media such as a hard disk.

[0068] Specifically, the memory (110) may store various software modules for the operation of the electronic device (100) according to various embodiments of the present disclosure, and the processor (130) may control the operation of the electronic device (100) by executing the various software modules stored in the memory (110). That is, the memory (110) is accessed by the processor (130), and reading / writing / modifying / deleting / updating of data by the processor (130) may be performed.

[0069] Meanwhile, in the present disclosure, the term memory (110) may be used to include memory (110), ROM, RAM, or a memory card mounted in the processor (130).

[0070] The communication interface (120) includes a circuitry and is configured to communicate with an external device and a server. The communication interface (120) can perform communication with an external device or server based on a wired or wireless communication method. The communication interface (120) may include a Bluetooth module, a Wi-Fi module, an IR (infrared) module, a LAN (Local Area Network) module, an Ethernet module, etc. Here, each communication module may be implemented in the form of at least one hardware chip. In addition to the communication method described above, the wireless communication module may include at least one communication chip that performs communication according to various wireless communication standards such as Zigbee, USB (Universal Serial Bus), MIPI CSI (Mobile Industry Processor Interface Camera Serial Interface), 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), LTE-A (LTE Advanced), 4G (4th Generation), 5G (5th Generation), etc. However, this is merely one example, and the communication interface (120) may use at least one communication module among various communication modules.

[0071] The processor (130) can control the overall operation and function of the electronic device (100). Specifically, the processor (130) is connected to the configuration of the electronic device (100) including memory (110), and can control the overall operation of the electronic device (100) by executing at least one instruction stored in the memory (110) as described above.

[0072] The processor (130) can be implemented in various ways. For example, the processor (130) can be implemented as at least one of an Application Specific Integrated Circuit (ASIC), a Logic Integrated Circuit, an embedded processor, a Microcomputer (Micom), a microprocessor, hardware control logic, a hardware Finite State Machine (FSM), and a Digital Signal Processor (DSP).

[0073] In particular, the processor (130) may include one or more processors. Specifically, one or more processors may include one or more of a CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), MIC (Many Integrated Core), DSP (Digital Signal Processor), NPU (Neural Processing Unit), MPU (Main Processing Unit), hardware accelerator, or machine learning accelerator. One or more processors may control one or any combination of other components of the electronic device and may perform operations or data processing related to communication. One or more processors may execute one or more programs or instructions stored in memory. For example, when instructions stored in memory (110) are executed individually or collectively by one or more processors, the electronic device (100) may perform operations according to the present disclosure.

[0074] When a method according to one or more embodiments of the present disclosure includes a plurality of operations, the plurality of operations may be performed by a single processor or by a plurality of processors. That is, when a first operation, a second operation, and a third operation are performed by a method according to one or more embodiments, the first operation, the second operation, and the third operation may all be performed by a first processor, or the first operation and the second operation may be performed by a first processor (e.g., a general-purpose processor) and the third operation may be performed by a second processor (e.g., an artificial intelligence dedicated processor).

[0075] One or more processors may be implemented as a single-core processor comprising one core, or as one or more multicore processors comprising multiple cores (e.g., homogeneous multicore or heterogeneous multicore). When one or more processors are implemented as multicore processors, each of the multiple cores included in the multicore processor may include internal processor memory such as cache memory or on-chip memory, and a common cache shared by multiple cores may be included in the multicore processor. Additionally, each of the multiple cores included in the multicore processor (or some of the multiple cores) may independently read and execute program instructions for implementing a method according to one or more embodiments of the present disclosure, or all (or some) of the multiple cores may be linked together to read and execute program instructions for implementing a method according to one or more embodiments of the present disclosure.

[0076] When a method according to one or more embodiments of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one of the plurality of cores included in a multi-core processor, or may be performed by a plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to one or more embodiments, the first operation, the second operation, and the third operation may all be performed by a first core included in a multi-core processor, or the first operation and the second operation may be performed by a first core included in a multi-core processor and the third operation may be performed by a second core included in a multi-core processor.

[0077] In embodiments of the present disclosure, the processor (130) may mean a system-on-chip (SoC) in which one or more processors and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, GPU, APU, MIC, DSP, NPU, hardware accelerator or machine learning accelerator, etc., but the embodiments of the present disclosure are not limited thereto.

[0078] FIG. 3 is a block diagram for explaining the configuration of a terminal device according to one embodiment of the present disclosure.

[0079] Referring to FIG. 3, the terminal device (200) may include a memory (210), a communication interface (220), a display (230), a user interface (240), a speaker (250), and a processor (260). Some of the above components may be omitted, and the terminal device (200) may include additional components in addition to the above components.

[0080] Meanwhile, the description of the memory (210), communication interface (220), and processor (260) among the configurations of the terminal device (200) shown in FIG. 3 may overlap with the description in FIG. 2, and any description that overlaps with the content of FIG. 2 is omitted.

[0081] The display (230) can be implemented as various types of displays such as an LCD (Liquid Crystal Display), an OLED (Organic Light Emitting Diodes) display, and a PDP (Plasma Display Panel). The display (230) may also include a driving circuit, a backlight unit, etc., which can be implemented in forms such as an a-si TFT (amorphous silicon thin film transistor), an LTPS (low temperature poly silicon) TFT, and an OTFT (organic TFT). Meanwhile, the display (230) can be implemented as a touch screen combined with a touch sensor, a flexible display, a 3D display, a three-dimensional display, etc. Additionally, according to one embodiment of the present disclosure, the display (230) may include not only a display panel that outputs an image, but also a bezel that houses the display panel. In particular, according to one embodiment of the present disclosure, the bezel may include a touch sensor for detecting user interaction.

[0082] The user interface (240) may be implemented as a device such as a button, touchpad, mouse, and keyboard, or as a touch screen capable of performing the aforementioned display function and operation input function. Here, the button may be a various type of button, such as a mechanical button, touchpad, or wheel, formed in any area such as the front, side, or back of the main body exterior of the electronic device (100).

[0083] The speaker (250) is configured to output an audio signal. In particular, the speaker (250) may include an audio output mixer, an audio signal processor, and an audio output module. The audio output mixer may synthesize a plurality of audio signals to be output into at least one audio signal. For example, the audio output mixer may synthesize an analog audio signal and another analog audio signal (e.g., an analog audio signal received from an external source) into at least one analog audio signal. The audio output module may include a speaker or an output terminal.

[0084] FIG. 4 is a block diagram for explaining the configuration of an external device (300) according to one embodiment of the present disclosure.

[0085] Referring to FIG. 4, the external device (300) may include a memory (310), a communication interface (320), a display (330), a user interface (340), a speaker (350), and a processor (360). Some of the above components may be omitted, and the terminal device (200) may include additional components in addition to the above components.

[0086] Meanwhile, the description of the memory (310), communication interface (320), display (330), user interface (340), speaker (350), and processor (360) among the components of the external device (300) shown in FIG. 4 may overlap with the descriptions in FIG. 2 and FIG. 3, and descriptions that overlap with FIG. 2 and FIG. 3 are omitted.

[0087] FIG. 5 is a sequence diagram for explaining the operation of an electronic device, a terminal device, and an external device according to one embodiment of the present disclosure.

[0088] Referring to FIG. 5, the terminal device (200) can execute an application when user input for executing an application is obtained (S510). The executed application may be an application installed on the terminal device (200) to personalize the sound output by an external device.

[0089] When the application is executed, the terminal device (200) can obtain user input for setting parameter values ​​to determine the attributes of the system sound of the external device (300) (S520). For example, the application may be configured to display a prompt to the terminal device (200) requesting the user to input information corresponding to the parameter values.

[0090] Parameter values ​​that can be set by user input may include parameter values ​​for at least one of the sound output environment, sound mood, sound type, music preferred by the user, and identification information of an external device.

[0091] In one or more embodiments, one of the at least one parameter value may include a value based on at least one of the attributes of the environment in which the sound is output (or the environment for outputting the sound), the mood of the sound, the type of the sound, information about music preferred by the user, identification information corresponding to the external device in which the sound is output, or a detected event.

[0092] The sound output environment may refer to an environment suitable for outputting personalized sound. That is, when the sound output environment is set, the system (1) can generate a sound having attributes suitable for the output environment.

[0093] The sound output environment may include continuous and temporary environments. A continuous environment may refer to an environment within the sound output environment that is continuously maintained. A temporary environment may refer to an environment within the sound output environment that is temporarily maintained.

[0094] That is, a continuous environment may refer to an environment that must always be reflected whenever a personalized sound is generated. A temporary environment may refer to an environment where the user must choose whether to reflect it whenever the system sound of the external device (300) is personalized. In one or more examples, the continuous environment may be a private space primarily used by the user, or an environment where the conditions of the environment rarely change. The temporary environment may be a public environment used by many people, or an environment where the conditions of the environment change frequently.

[0095] For example, among the sound output environments, the parameter value for a continuous environment may include at least one of "having a baby," "using with an elderly person," and "living in a house with poor sound insulation." However, while at least one parameter value for a continuous environment as described above may be selected, this is merely one embodiment and no parameter value for a continuous environment may be selected.

[0096] For example, a parameter value for a temporary environment among the sound output environments may include at least one of "a baby is sleeping," "using home appliances at night," and "being with a guest." However, while at least one parameter value for a temporary environment as described above may be selected, this is merely one embodiment and no parameter value for a temporary environment may be selected.

[0097] When user input for setting parameter values ​​for a continuous environment is obtained, the terminal device (200) can set the parameter values ​​for the continuous environment to default. The parameter values ​​for the continuous environment set to default can be reapplied whenever a personalized sound is generated, even if the user does not reset them.

[0098] "Continuous environment" can be replaced with terms such as "general environment," "general state," or "environment to always reflect," and "temporary environment" can be replaced with terms such as "special environment," "special state," or "environment to reflect only this time."

[0099] The mood of sound can refer to the emotional or sensory feelings generated or conveyed by the sound. The mood of sound can be determined by factors such as timbre, rhythm, volume, and harmony, and can evoke specific emotions in the listener or create a specific atmosphere.

[0100] For example, parameter values ​​for the mood of the sound that can be set by user input may include at least one of "colorful," "romantic," "hip," "fresh," "calm," "warm," "playful," "splendid," "luxurious," "simple," "lively," "fresh," "dignified," "calm," "classic," and "fresh."

[0101] Information about the music preferred by the user may include at least one of the title of the music preferred by the user, the singer preferred by the user, and the genre preferred by the user.

[0102] For example, the parameter value for the music preferred by the user may be "song by singer A", "B sung by singer A", or "classical".

[0103] "Music preferred by the user" can be replaced with "music set by the user," "music specified by the user," "music searched by the user," "music frequently listened to by the user," "music listened to by the user more than a set frequency," etc.

[0104] The identification information of an external device may include at least one of the model name, model number, type, function, role, and characteristics of the external device. The system according to the present disclosure may personalize the system sound of the external device corresponding to the selected identification information.

[0105] For example, the parameter value for the identification information of an external device can be implemented as the type of the external device, such as "washing machine," "refrigerator," or "TV."

[0106] For example, the parameter value for the identification information of an external device can be implemented as a product name such as "Bespoke AI Steam", "Bespoke Cuckoo Oven", or "Bespoke AI Windless Classic".

[0107] According to one or more embodiments, parameter values ​​corresponding to the characteristics of the sound may include parameter values ​​based on a detected event. In this case, the detected event may refer to an event for the electronic device (100) to transmit sound to an external device. That is, when the electronic device (100) detects an event, it may transmit the acquired sound to an external device so that the external device outputs the acquired sound. The detected event may also be referred to as a detection event, a trigger event, etc.

[0108] Meanwhile, the terminal device (200) can obtain parameter values ​​that are not set by the user by using parameter values ​​set by the user. Specifically, when identification information of an external device is selected, the terminal device (200) can obtain parameter values ​​for specification information of the external device corresponding to the selected identification information. In one or more examples, the specification information of the external device may be stored in memory (210). The specification information of the external device may include performance information of the speaker, such as the output wattage of the external device's speaker and the output channel of the speaker. That is, parameter values ​​for the specification information of the external device can be obtained without the user having to set them separately when the type or identification information of the external device is set.

[0109] The terminal device (200) can display a UI on the display (230) to obtain user input for setting parameter values ​​through an executed application. The terminal device (200) can obtain user input for setting parameter values ​​through the displayed UI.

[0110] For example, the UI displayed by the terminal device (200) may be as illustrated in FIG. 6. Referring to FIG. 6, the UI (600) displayed by the terminal device (200) may include a UI element (610) for setting parameter values ​​for the mood of the sound, a UI element (620) for setting parameter values ​​for a continuous environment among the sound output environments, a UI element (630) for setting parameter values ​​for a temporary environment among the sound output environments, a UI element (640) for setting parameter values ​​for music preferred by the user, a UI element (650) for selecting identification information of an external device for personalizing the sound, and a UI element (660) for starting an operation to generate a personalized sound using the set parameter values.

[0111] At this time, some of the displayed UI elements may be omitted, and the UI (600) may include other UI elements in addition to the UI elements described above.

[0112] A UI element (640) for setting parameter values ​​for music preferred by the user may include an element for not selecting music preferred by the user, an element for searching for music preferred by the user, and an element for selecting a music listening application for listening to music preferred by the user.

[0113] When an element for the user to search for music preferred by the user is selected, the terminal device (200) can display a UI for searching for music preferred by the user. Through the displayed UI, the terminal device (200) can obtain information about music preferred by the user.

[0114] Alternatively, when an element for selecting a music listening application that the user listens to is selected, the electronic device (100) can obtain parameter values ​​for the music preferred by the user by linking with the selected music listening application. At this time, the terminal device (200) can display a UI to obtain the user's consent to link with the selected music listening application. Once the user's consent is obtained through the displayed UI, the terminal device (200) can obtain parameter values ​​for the music preferred by the user by linking with the music listening application.

[0115] A UI element (650) for selecting identification information of an external device may include a list of external devices linked to the terminal device (200). An external device linked to the terminal device (200) may refer to a device connected through the same home network as the terminal device (200). Alternatively, an external device (300) linked to the terminal device (200) may refer to a device currently performing a communication connection with the terminal device (200). Alternatively, an external device linked to the terminal device (200) may refer to a device already registered to a user account logged into the terminal device (200). Alternatively, an external device (300) linked to the terminal device (200) may refer to a device registered to the terminal device (200).

[0116] The terminal device (200) can obtain user input selecting at least one of a plurality of external devices included in a displayed list. The terminal device (200) can obtain user input selecting at least one device for personalizing system sound among the external devices linked to the terminal device (200) through a displayed UI element (650). The sound personalization system according to the present disclosure can personalize the system sound of an external device corresponding to identification information selected by the user.

[0117] When a parameter value for determining the properties of the sound is obtained, the terminal device (200) can transmit the obtained parameter value to the electronic device (100) (S530). That is, the electronic device (100) can receive the parameter value set by the user from the terminal device (200).

[0118] In one or more embodiments, the electronic device (100) can obtain at least one parameter value corresponding to the attribute of the sound. For example, the electronic device (100) can receive at least one parameter value corresponding to the attribute of the sound from the terminal device (200). Alternatively, the electronic device (100) can obtain a parameter value not set by the user by using a parameter value set by the user.

[0119] When a parameter value for determining the properties of a sound is received, the electronic device (100) can obtain a prompt for generating a sound that reflects the determined properties (S540).

[0120] According to one embodiment of the present disclosure, the electronic device (100) can generate a prompt in a rule-based manner. That is, the electronic device (100) can generate a prompt using parameter values ​​obtained according to a set rule. However, generating a prompt in a rule-based manner is merely one embodiment, and the prompt can be generated using other methods. For example, the electronic device (100) can generate a prompt using an artificial intelligence model trained for prompt generation. That is, the electronic device (100) can generate a prompt by inputting parameter values ​​into a trained artificial intelligence model.

[0121] The electronic device (100) can generate a prompt by inputting a parameter value obtained into a predetermined prompt format. The predetermined prompt format may include multiple input fields. The electronic device (100) can generate a prompt by inputting a parameter value obtained into a format that includes multiple input fields.

[0122] For example, a defined prompt format may correspond to "a {Mood} {SoundType} system sound {Situation} {FavoriteMusic} for {Type} {Speaker Quality} speaker". In this case, the input fields included in the defined prompt format may be {Mood}, {SoundType}, {Situation} {FavoriteMusic}, {Type}, and {Speaker Quality}.

[0123] The electronic device (100) can input parameter values ​​for the mood of the sound in the {Mood} field in a defined prompt format. The electronic device (100) can input parameter values ​​for the type of sound set by the user in the {SoundType} field. The electronic device (100) can input parameter values ​​for the environment set by the user in the {Situation} field. The electronic device (100) can input parameter values ​​for the song preferred by the user in the {FavoriteMusic} field. The electronic device (100) can input parameter values ​​for the type of external device set by the user in the {Type} field. The electronic device (100) can input parameter values ​​for the speaker performance of the external device in {Speaker Quality}.

[0124] Meanwhile, the parameter value set by the user and the parameter value entered into the prompt's input field may be different. That is, the electronic device (100) can convert the parameter value set by the user into a parameter value suitable for input into the prompt's input field. The electronic device (100) can convert the parameter value set by the user into a parameter value in a language and / or a suitable format suitable for input into an artificial intelligence model.

[0125] In one or more examples, the parameter value set by the user may be expressed in language A, and the artificial intelligence model may be a model trained based on language B. In this case, the electronic device (100) can convert the parameter value expressed in language A into a parameter value expressed in language B. The matching relationship between the parameter value expressed in language A and the parameter value expressed in language B may be stored in memory (110) in the form of a lookup table. The electronic device (100) can convert the parameter value expressed in language A into a parameter value expressed in language B.

[0126] For example, the matching relationship between a parameter value expressed in language A and a parameter value expressed in language B may be the same as the matching table (710, 720) shown in FIG. 7. In relation to the sound output environment set by the user, a parameter value such as "baby is sleeping" expressed in language A may correspond to a parameter value such as "that baby likes" expressed in language B. And, in relation to the performance of the external device's speaker, a parameter value such as "40W or more and 4.2ch or more" expressed in language A may correspond to a parameter value such as "with high quality" expressed in language B.

[0127] The electronic device (100) can generate a prompt by inputting the converted parameter value into a specified prompt format.

[0128] For example, the parameter value for the mood of the sound set by the user may be "fresh," the parameter value for the type of sound may be "warning sound," the parameter value for the identification information of the external device may be "washing machine," the parameter value for the music preferred by the user may be "song B by singer A," the parameter value for the sound output environment may be "baby is sleeping," and the parameter value for the speaker performance of the external device may be "40W or more and 4.2ch or more."

[0129] At this time, the prompt generated by the electronic device (100) may be "a refreshing warning system sound which is joyful and similar with 'B, A' for microwave with high quality speaker".

[0130] Meanwhile, the electronic device (100) can obtain a prompt using only some of the obtained parameter values. Specifically, the electronic device (100) can obtain a prompt by inputting only some of the obtained parameter values ​​into an input field of the prompt format.

[0131] For example, the electronic device (100) can generate a prompt by inputting parameter values, excluding parameter values ​​for music preferred by the user, into a predetermined prompt format. At this time, the prompt generated by the electronic device (100) may be "a refreshing warning system sound that baby likes for microwave with high quality speaker".

[0132] When a prompt is obtained, the electronic device (100) can input the obtained prompt into an artificial intelligence model to obtain a sound that reflects the determined attributes (S550).

[0133] For example, referring to FIG. 8, the electronic device (100) can obtain a prompt (820) using the obtained parameter value (810) and input the obtained prompt (820) into an artificial intelligence model (10) to generate a personalized sound (830). The artificial intelligence model (10) may be a model trained to generate a sound corresponding to the input data. That is, the artificial intelligence model (10) may be a model trained to generate a sound having attributes determined by the parameter value set by the user.

[0134] Meanwhile, if a prompt is generated using only some of the acquired parameter values, the electronic device (100) can acquire a sound with reflected attributes by separately inputting parameter values, excluding some of the acquired parameter values, into an artificial intelligence model. In this case, the electronic device (100) can input some of the parameter values ​​set by the user into the artificial intelligence model in the form of separate feature vectors rather than prompts.

[0135] For example, referring to FIG. 9, the electronic device (100) can generate a prompt (920) using parameter values ​​(910) excluding parameter values ​​(930) for music preferred by the user. The electronic device (100) can convert parameter values ​​(930) for music preferred by the user into feature vectors (940) for music preferred by the user. At this time, the electronic device (100) can generate a sound (950) by inputting the generated prompt (920) and the feature vectors (940) of music preferred by the user together into an artificial intelligence model (10). Meanwhile, FIG. 8 and FIG. 9 describe the artificial intelligence model (10) as directly outputting the sound, but this is merely one embodiment. The electronic device (100) can obtain inferred noise by inputting the generated prompt (920) and the feature vectors (940) of music preferred by the user together into the artificial intelligence model (10), and can obtain a sound (950) using the inferred noise. This will be explained in more detail later with reference to Figs. 11 and 12.

[0136] Meanwhile, the electronic device (100) can generate a prompt using only some of the acquired parameter values ​​and acquire multiple sounds using the generated prompt. Additionally, the electronic device (100) can select one of the acquired multiple sounds using the remainder of the acquired parameter values.

[0137] For example, referring to FIG. 10, the electronic device (100) can obtain a prompt (1020) using a parameter value (1010) excluding a parameter value (1060) for a temporary environment among the obtained parameter values ​​for the sound output environment.

[0138] Additionally, the electronic device (100) can acquire multiple sounds (1050) by inputting the acquired prompt (1020) and the feature vector (1040) of the music (1030) preferred by the user into the artificial intelligence model (10). At this time, the electronic device (100) may also input only the prompt (1020) into the artificial intelligence model (10) excluding the feature vector (1040).

[0139] The electronic device (100) can identify a sound among a plurality of generated sounds (1050) that corresponds to a parameter value (1060) for a set temporary environment. The electronic device (100) can identify a sound among a plurality of generated sounds that is most similar to a parameter value for a temporary environment.

[0140] Specifically, the electronic device (100) can calculate a similarity (1070) between each of the plurality of sounds (1050) and a parameter value (1060) for a transient environment. The electronic device (100) can obtain a feature vector for each of the plurality of sounds and a feature vector for the parameter value for a transient environment. The electronic device (100) can calculate a cosine similarity between the feature vector for each of the plurality of sounds and the feature vector for the parameter value for a transient environment. In one or more examples, cosine similarity may be an indicator that measures the similarity between two vectors by calculating the cosine of the angle between the two vectors. Cosine similarity focuses on the direction (or slope) rather than the magnitude of the vectors. The calculated cosine value has a range from -1 to 1, where 1 indicates perfect similarity, 0 indicates no similarity (vectors are orthogonal to each other), and -1 indicates perfect dissimilarity (vectors are in opposite directions).

[0141] For example, if an artificial intelligence model generates three sounds, the electronic device (100) can calculate the cosine similarity between the feature vector of the first sound and the feature vector of the parameter value for the temporary environment, calculate the cosine similarity between the feature vector of the second sound and the feature vector of the parameter value for the temporary environment, and calculate the cosine similarity between the feature vector of the third sound and the feature vector of the parameter value for the temporary environment. Meanwhile, as described above, calculating the similarity (1070) between each of the plurality of sounds (1050) and the parameter value (1060) for the temporary environment using cosine similarity is merely one embodiment, and it is obvious that the similarity (1070) between each of the plurality of sounds (1050) and the parameter value (1060) for the temporary environment can be calculated using other methods.

[0142] The electronic device (100) can identify the feature vector with the highest cosine similarity with the feature vector of parameter values ​​for a transient environment among the feature vectors of each of the plurality of acquired sounds.

[0143] When a sound is generated using a prompt as described above, the electronic device (100) can transmit the generated sound to a terminal device (200). The terminal device (200) can transmit the generated sound to an external device (300).

[0144] In particular, when multiple sounds are generated and one of the multiple sounds is identified, the electronic device (100) can transmit the identified sound to the terminal device (200).

[0145] The external device (300) can output the received sound when the conditions for outputting the received sound are satisfied. For example, when the external device (300) is turned on, it can output a sound indicating that the power of the external device (300) has been turned on. At this time, the sound output may be a sound personalized to the user.

[0146] Meanwhile, the artificial intelligence model according to the present disclosure can be implemented as a diffusion model. That is, the artificial intelligence model can be implemented as a generative artificial intelligence model that generates output data based on input data from data containing noise.

[0147] The electronic device (100) can train an artificial intelligence model to generate a sound corresponding to a prompt based on input data, specifically a prompt.

[0148] This will be explained with reference to the drawings below.

[0149] FIG. 11 is a diagram illustrating a method for an electronic device to train an artificial intelligence model according to one embodiment of the present disclosure.

[0150] The electronic device (100) can acquire a training data set. Referring to FIG. 11, the training data set may include data in which a prompt (1110) and audio data (1120) are paired. Alternatively, the training data set may include data in which a feature vector (1160) of a prompt (1110), audio data (1120), and music (1170) preferred by the user are paired.

[0151] At this time, the first audio data (1120) may be a feature vector of the first audio signal (1110). The training data may include audio data. Alternatively, the electronic device (100) may obtain audio data by extracting features of the audio signal included in the training data.

[0152] Referring to FIG. 11, the electronic device (100) can obtain second audio data (1140) with noise added n times by performing a Forward Process operation that randomly adds noise (1130) n times sequentially to first audio data (1120) that is free of noise.

[0153] The electronic device (100) can train an artificial intelligence model (10) to perform a Backward Process operation to infer a first audio data (1120) from which noise (1130) has been removed from second audio data (1140) to which noise has been added n times.

[0154] "Forward Process" can be replaced with "Diffusion Process," and "Backward Process" can be replaced with "Reverse Process."

[0155] Specifically, the noise (1130) added to the first audio data (1120) may be Gaussian noise following a Gaussian distribution. The magnitude and distribution of the noise may be adjusted to optimize the performance of the artificial intelligence model during the training process.

[0156] That is, the electronic device (100) can sequentially add noise (1130) to the first audio data (1120) so that the distribution of the noise-added data follows a Gaussian distribution. Specifically, the electronic device (100) can obtain the second audio data (1140) by adding noise to the first audio data (1120) so that the mean of the second audio data approaches 0 and the variance approaches 1.

[0157] The electronic device (100) can infer audio data from which noise has been removed from the second audio data (1140). That is, the artificial intelligence model can infer noise (1150) contained in the second audio data (1140). The electronic device (100) can infer the first audio data by removing the noise inferred by the artificial intelligence model (10) from the second audio data (1140).

[0158] The electronic device (100) can train an artificial intelligence model (10) based on a loss function (1190) that includes the difference between noise (1130) added to the first audio data (1120) and noise (1150) inferred from the second audio data (1140). That is, the electronic device (100) can train the artificial intelligence model (10) so that the difference between the noise (1130) added to the first audio data (1120) and the noise (1150) inferred from the second audio data (1140) becomes smaller.

[0159] Specifically, the electronic device (100) can train an artificial intelligence model (10) to infer the nth added noise from audio data (1140) in which noise has been added n times.

[0160] At this time, the electronic device (100) can train an artificial intelligence model (10) to infer the nth added noise by taking the audio data with noise added n times, a prompt, and a feature vector of music preferred by the user as inputs. The electronic device (100) can obtain audio data with noise added (n-1) times by removing the nth added noise from the audio data with noise added n times. Meanwhile, when training the artificial intelligence model (10), the feature vector of music preferred by the user may be omitted. That is, the electronic device (100) can train an artificial intelligence model to infer the nth added noise by taking the audio data with noise added n times and the prompt as inputs.

[0161] That is, during the training process, the electronic device (100) can train an artificial intelligence model using a prompt paired with audio data as a condition. Alternatively, during the training process, the electronic device (100) can train an artificial intelligence model using a prompt paired with audio data and a feature vector of music preferred by the user as a condition.

[0162] Accordingly, in the inference phase of the artificial intelligence model, the AI ​​model can infer the nth added noise from audio data to which noise has been added n times, using the prompt and the feature vector of the music preferred by the user as conditions. In this case, the feature vector of the music preferred by the user may be omitted. That is, the AI ​​model can infer the nth added noise from audio data to which noise has been added n times, using the prompt as a condition.

[0163] The detailed inference process of the artificial intelligence model according to the present disclosure will be explained with reference to FIG. 12.

[0164] FIG. 12 is a diagram illustrating the process of generating sound using an artificial intelligence model according to one embodiment of the present disclosure.

[0165] Referring to FIG. 12, the electronic device (100) can input a prompt (1210) and randomly generated noise (1220) into an artificial intelligence model (10).

[0166] At this time, the electronic device (100) can perform a concatenation operation on the noise (1220) and the feature vector (1230) of the music preferred by the user, and input the result of the concatenation operation into the artificial intelligence model (10) along with the prompt (1210).

[0167] The artificial intelligence model (10) may be a model with a cross-attention mechanism applied to learn the correlation between the result value of the input connection operation and the prompt (1210).

[0168] The artificial intelligence model can infer added noise from audio data with added noise based on input prompts and feature vectors. In particular, the electronic device (100) can infer noise by inputting the prompt (1210), noise (1220), and feature vector (1230) of music preferred by the user into the artificial intelligence model. Here, as shown in FIG. 12, the electronic device (100) can infer noise (1240) by repeating the above-described operation a preset number of times or a number at which the change in inferred noise is minimized. Then, the electronic device (100) can obtain sound by removing the inferred noise (1240) from the noise (1220) input into the artificial intelligence model (10).

[0169] Meanwhile, the electronic device (100) of the present disclosure may infer noise in a single step without repeating the noise removal operation as described above a preset number of times. That is, the artificial intelligence model (10) may infer noise included in audio data with added noise in a single step. At this time, the electronic device (100) may obtain a noise-removed sound by removing the noise inferred by the artificial intelligence model (10) from the input noise.

[0170] Meanwhile, as described above, the electronic device (100) may generate personalized sound, but this is merely one embodiment, and the terminal device (200) or external device (300) may also generate and output personalized sound.

[0171] This will be explained with reference to FIGS. 13 and FIGS. 14.

[0172] FIG. 13 is a sequence diagram for explaining the operation of an electronic device, a terminal device, and an external device according to one embodiment of the present disclosure.

[0173] Referring to FIG. 13, the terminal device (200) can execute an application (S1310). The terminal device (200) can obtain parameter values ​​through the executed application (S1320). The operation of S1310 and S1320 may be the same as the operation of S510 and S520 described in FIG. 5.

[0174] The terminal device (200) can generate a prompt using the acquired parameter value (S1330). The terminal device (200) can acquire a sound using the generated prompt (S1340). The operation of the terminal device (200) according to S1330 and S1340 may be the same as the operation of the electronic device (100) described in S540 and S550 described in FIG. 5.

[0175] The terminal device (200) can transmit the acquired sound to an external device (300) (S1350). When the condition for outputting the received sound is satisfied, the external device (300) can output the received sound (S1360).

[0176] FIG. 14 is a sequence diagram for explaining the operation of an electronic device, a terminal device, and an external device according to one embodiment of the present disclosure.

[0177] Referring to FIG. 14, the terminal device (200) can execute an application (S1410). The terminal device (200) can obtain parameter values ​​through the executed application (S1420). The operations of S1410 and S1420 may be the same as the operations of S510 and S520 described in FIG. 5.

[0178] The terminal device (200) can transmit the acquired parameter value to an external device (300) (S1430).

[0179] The external device (300) can obtain a prompt using the obtained parameter value (S1440). The external device (300) can obtain a personalized sound using the obtained prompt (S1450). When the condition for outputting the obtained sound is satisfied, the external device (300) can output the obtained sound (S1460).

[0180] FIG. 15 is a flowchart illustrating a method for controlling an electronic device according to one embodiment of the present disclosure.

[0181] Referring to FIG. 15, the electronic device (100) can obtain at least one parameter value corresponding to the properties of sound (S1510).

[0182] The parameter value may include at least one of the sound output environment, sound mood, sound type, user-preferred music, and external device type.

[0183] One of the at least one parameter value may include a value based on at least one of the attributes of the environment in which the sound is output, the mood of the sound, the type of sound, information about music preferred by the user, identification information corresponding to the external device in which the sound is output, or a detected event.

[0184] The electronic device (100) can obtain information about music preferred by the user by linking with a music application installed on the user's terminal device. Alternatively, the electronic device (100) can obtain information about music preferred by the user from a music application running on an external device.

[0185] The electronic device (100) can obtain a prompt to generate a sound with attributes reflected based on parameter values ​​(S1520).

[0186] The electronic device (100) can acquire sound by inputting the acquired prompt into an artificial intelligence model (S1530).

[0187] According to one embodiment of the present disclosure, an electronic device (100) can obtain a feature vector of music preferred by a user based on information about music preferred by a user. Then, the electronic device (100) can obtain a sound by inputting a prompt and the feature vector of music preferred by the user into an artificial intelligence model.

[0188] According to one embodiment of the present disclosure, an electronic device (100) can acquire a plurality of sounds that reflect attributes. The electronic device (100) can identify the similarity between each feature vector of the plurality of sounds and a feature vector corresponding to the user's situation. The electronic device (100) can identify a sound having the feature vector with the highest similarity to the feature vector corresponding to the user's situation. The electronic device (100) can transmit the identified sound to at least one external device.

[0189] According to one embodiment of the present disclosure, an electronic device (100) can obtain sound by removing noise based on a prompt generated from data containing noise that follows a Gaussian distribution.

[0190] The electronic device (100) can transmit the sound obtained from the external device to at least one external device (S1540).

[0191] According to one embodiment of the present disclosure, the electronic device (100) can transmit the acquired sound to at least one external device when an event is detected.

[0192] Specifically, when the electronic device (100) detects an event, it can acquire a sound that reflects an attribute corresponding to the detected event. Subsequently, the electronic device (100) can transmit the sound corresponding to the detected event to an external device.

[0193] For example, the electronic device (100) can detect an event called a 'guest visit'. If the electronic device (100) detects a voice other than that of a user registered in the electronic device (100), it can identify that a guest has visited. Alternatively, if the electronic device (100) detects the voices of multiple people, it can identify that a guest has visited. Afterward, the electronic device (100) can transmit a sound corresponding to the detected event to an external device.

[0194] The electronic device (100) can generate a prompt using a parameter value corresponding to a detected event and obtain a sound corresponding to a detected event using the generated prompt. In one embodiment, when an event is detected, the electronic device (100) can generate a sound corresponding to the detected event and transmit it to an external device. For example, when an event called 'guest visit' is detected, the electronic device (100) can generate a sound corresponding to the detected event called 'guest visit' and transmit it to an external device.

[0195] In another embodiment, the electronic device (100) may generate and store a sound corresponding to a detected event, and then transmit the sound to an external device when the event is detected. For example, the electronic device (100) may generate and store a sound corresponding to a detected event called 'guest visit', and then transmit the sound to an external device when the event is detected.

[0196] Through this, the electronic device (100) can provide a sound corresponding to the detected event when a specific event is detected, thereby providing a customized sound suitable for the user's environment.

[0197] According to one embodiment of the present disclosure, when a sound output environment is detected, the acquired sound can be transmitted to an external device so that the external device outputs the acquired sound.

[0198] According to one embodiment of the present disclosure, an electronic device (100) can obtain information regarding the speaker performance of a plurality of external devices. The electronic device (100) can transmit the obtained sound to an external device with higher speaker performance than other external devices.

[0199] According to one embodiment of the present disclosure, when a condition for outputting the acquired sound is satisfied, the electronic device (100) can transmit the acquired sound to at least one external device located in the space where the user's terminal device is located among a plurality of external devices.

[0200] Although various embodiments have been described above, each embodiment is not necessarily implemented individually, and may be combined with at least one other embodiment, either wholly or partially, to be implemented together in a single product.

[0201] Meanwhile, the terms “part” or “module” as used in this disclosure include a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A “part” or “module” may be a component formed integrally, or a minimum unit or part thereof that performs one or more functions. For example, a module may be composed of an application-specific integrated circuit (ASIC).

[0202] Various embodiments of the present disclosure may be implemented as software comprising instructions stored on machine-readable storage media (e.g., a computer). The machine may include an electronic device (100) according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage media and operating according to the called instructions. When the instructions are executed by a processor, the processor may perform a function corresponding to the instructions directly or using other components under the control of the processor. The instructions may include code generated or executed by a compiler or an interpreter. The machine-readable storage media may be provided in the form of non-transitory storage media. Here, "non-transitory" means only that the storage media does not contain a signal and is tangible, and does not distinguish whether data is stored semi-permanently or temporarily in the storage media.

[0203] According to one or more embodiments, the method according to the various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a storage medium such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0204] Each component (e.g., module or program) according to various embodiments may consist of a singular or multiple entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be further included in various embodiments. Generally or additionally, some components (e.g., module or program) may be integrated into a single entity to perform the same or similar functions as those performed by each of the respective components prior to integration. The operations performed by the module, program, or other components according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations added.

Claims

In electronic devices, At least one processor; and Memory for storing at least one instruction; including, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, Obtain at least one parameter value corresponding to the properties of the sound, and Obtain a prompt to generate a sound reflecting the above attributes based on the above parameter values, and The above-mentioned obtained prompt is input into an artificial intelligence model to obtain the above-mentioned sound, and An electronic device that transmits the above-mentioned acquired sound to at least one external device. In paragraph 1, An electronic device wherein one of the above at least one parameter value comprises a value based on at least one of the attributes of the environment in which the sound is output, the mood of the sound, the type of the sound, information about music preferred by the user, identification information corresponding to the external device in which the sound is output, or a detected event. In paragraph 2, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, An electronic device that transmits the acquired sound to at least one external device when the above event is detected. In paragraph 2, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, An electronic device that obtains information about music preferred by the user from a music application running on an external device. In paragraph 4, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, Based on information about the music preferred by the user, a feature vector of the music preferred by the user is obtained, and An electronic device that acquires the sound by inputting the above prompt and the feature vector of the music liked by the user into the above artificial intelligence model. In paragraph 1, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, Acquire multiple sounds reflecting the above attributes, and Determining a similarity score between each of the above-mentioned feature vectors of the plurality of sounds and the feature vector corresponding to the user's situation, Identify the sound having the highest similarity score from the above plurality of sounds, and An electronic device that transmits the identified sound to at least one external device. In paragraph 1, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, An electronic device that obtains the sound by removing the noise from the data based on a Gaussian distribution. In paragraph 1, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, Acquire information on the speaker performance of multiple external devices, and An electronic device that transmits the above-mentioned acquired sound to an external device with higher speaker performance than other external devices. In paragraph 1, When the above at least one instruction is executed individually or collectively by the above at least one processor, the electronic device, An electronic device that transmits the acquired sound to at least one external device located in the space where the user's terminal device is located among a plurality of external devices when the condition for outputting the acquired sound is satisfied. In a method for controlling an electronic device, A step of obtaining at least one parameter value corresponding to the properties of the sound; A step of obtaining a prompt to generate a sound reflecting the above attributes based on the above parameter values; A step of acquiring the sound by inputting the above-mentioned acquired prompt into an artificial intelligence model; and A control method comprising the step of transmitting the acquired sound to at least one external device. In Paragraph 10, A control method wherein one of the above at least one parameter value comprises a value based on at least one of the attributes of the environment in which the sound is output, the mood of the sound, the type of the sound, information about music preferred by the user, identification information corresponding to the external device in which the sound is output, or a detected event. In Paragraph 11, The step of transmitting the acquired sound to the external device is, A control method for transmitting the acquired sound to at least one external device when the above event is detected. In Paragraph 10, The step of obtaining user input corresponding to parameter values ​​for determining the properties of the sound output by the above external device is: A control method for obtaining information about music preferred by the user from a music application running on an external device. In Paragraph 10, The above control method is, The method further includes the step of obtaining a feature vector of the music preferred by the user based on information about the music preferred by the user; The step of acquiring the above sound is, A control method for acquiring the sound by inputting the above prompt and the feature vector of the music liked by the user into the above artificial intelligence model. In Paragraph 10, The step of acquiring the above sound is, Acquire multiple sounds reflecting the above attributes, and The above control method is, A step of determining a similarity score between each of the above plurality of sound feature vectors and a feature vector corresponding to the user's situation; The method further includes the step of identifying the sound having the highest similarity score among the plurality of sounds; and The step of transmitting the acquired sound to the external device is, A control method for transmitting the identified sound to at least one external device.

Images