Electronic device for identifying electronic device to perform speech recognition and method for thereof

Abstract

According to various embodiments, an electronic device may be provided comprising: a communication circuit; a memory; and at least one processor; wherein, when instructions stored in the memory are executed, the instructions are such that the at least one processor: establishes a communication connection with a plurality of external electronic devices for providing an intelligent voice service; receives at least one piece of information associated with a user utterance including a specific word from at least some of the plurality of external electronic devices; identifies a device among at least some of the plurality of external electronic devices to be woken up based on at least one piece of first information received during a time interval for identifying a device to be woken up; and, when at least one piece of second information is received after the time interval, changes the time interval to a first time interval longer than the time interval based on the time of receiving the at least one piece of second information. Various other embodiments are possible.

Description

Technology Field

[0001] Various embodiments of the present disclosure relate to an electronic device for identifying an electronic device for performing voice recognition and a method of operating the same. Background Technology

[0003] Various types of electronic devices are being distributed to consumers living in the modern era.

[0004] Various types of electronic devices can provide intelligent voice services by performing voice recognition and performing various operations based on the recognized voice. Furthermore, based on the Internet of Things, which connects electronic devices in various environments via wired and wireless networks, an environment is being established where electronic devices can provide intelligent voice services based on information sharing among themselves.

[0005] With the recent increase in the number of electronic devices capable of providing intelligent voice services, it is becoming difficult to select a device that offers such services in accordance with the user's intent. Therefore, it is necessary to implement technology to select a device among various electronic devices that provides intelligent voice services aligned with the user's intent. The problem to be solved

[0007] Various types of electronic devices capable of providing intelligent services (e.g., intelligent voice services) may be provided within various environments. When said electronic devices receive a user utterance (e.g., a wake-up utterance) containing a specific word to initiate the provision of intelligent voice services from a user, they recognize a user utterance for control (e.g., a control utterance) and enter a state (e.g., a listening state) in which they perform at least one action corresponding to the recognized utterance (i.e., become woken up). However, due to the wake-up utterance, numerous electronic devices among those provided in the environment that differ from the user's intention may enter the listening state (i.e., become woken up). Consequently, an operational burden may arise in which numerous other electronic devices unnecessarily enter the listening state. Furthermore, the user may face the inconvenience of having to release the listening state of other electronic devices, issue a wake-up utterance again, and switch the electronic device that matches the user's intention back to the listening state.

[0008] According to various embodiments, an electronic device and a method of operation thereof can reduce the operational burden and inconvenience caused by numerous other electronic devices waking up by receiving information related to the wake-up ignition from other external electronic devices when a wake-up ignition occurs and identifying the optimal device to be woken up (i.e., switched to a listening state) based on the received information. Also, according to various embodiments, an electronic device and a method of operation thereof can enable the optimal device to be woken up by setting or changing a value (e.g., time-out, priority) used when performing an operation to identify the device to be woken up based on information generated within the environment (e.g., information about the time of reception of information received during one session obtained when performing an operation to identify the device to be woken up, or information about a device re-identified as the device to be woken up). means of solving the problem

[0010] According to various embodiments, an electronic device may be provided comprising: a communication circuit; a memory; and at least one processor; wherein, when instructions stored in the memory are executed, the instructions are configured such that the at least one processor: establishes a communication connection with a plurality of external electronic devices for providing an intelligent voice service; receives at least one piece of information associated with a user utterance including a specific word from at least some of the plurality of external electronic devices; identifies a device to be woken up among at least some of the plurality of external electronic devices based on at least one piece of first information received during a time interval for identifying a device to be woken up; and, when at least one piece of second information is received after the time interval, changes the time interval to a first time interval longer than the time interval based on the time of receiving the at least one piece of second information.

[0011] According to various embodiments, a method of operation of an electronic device may be provided, comprising: establishing a communication connection with a plurality of external electronic devices for providing an intelligent voice service; receiving at least one piece of information associated with a user utterance including a specific word from at least some of the plurality of external electronic devices; identifying a device to be woken up among at least some of the plurality of external electronic devices based on at least one piece of first information received during a time interval for identifying a device to be woken up; and, if at least one piece of second information is received after the time interval, changing the time interval to a first time interval longer than the time interval based on the time of receiving the at least one piece of second information.

[0012] According to various embodiments, an electronic device may be provided comprising: a communication circuit; a memory; and at least one processor; wherein, when instructions stored in the memory are executed, the instructions are such that the at least one processor: forms a network with a plurality of external electronic devices for providing an intelligent voice service, and while performing an operation to wake up some of the plurality of external electronic devices that form the network, accumulates information associated with the plurality of external electronic devices, sets a time interval for obtaining information associated with the user voice and a priority for each of the plurality of external electronic devices based on the accumulated information, receives at least one piece of information associated with a user utterance including a specific word for waking up from at least some of the plurality of external electronic devices, and identifies a device among at least some of the plurality of external electronic devices to be woken up based on the at least one piece of information and at least one of the set time interval or the priority.

[0013] The means for solving the problem according to various embodiments are not limited to the means for solving the problem described above, and unmentioned means for solving the problem will be clearly understood by those skilled in the art from this specification and the attached drawings. Effects of the invention

[0015] According to various embodiments, an electronic device and a method of operation thereof may be provided, which reduce the operational burden and inconvenience caused by numerous other electronic devices waking up by receiving information related to the wake-up ignition from other external electronic devices when a wake-up ignition occurs and identifying the optimal device to be woken up (i.e., switched to a listening state) based on the received information.

[0016] According to various embodiments, an electronic device and a method of operation thereof may be provided, which enable an optimal device to be woken up by setting or changing a value (e.g., time-out, priority) used when performing an operation to identify a device to be woken up based on information generated within an environment (e.g., information about the time of reception of information received during one session obtained when performing an operation to identify a device to be woken up, or information about a device re-identified as a device to be woken up). Brief explanation of the drawing

[0018] FIG. 1 illustrates an IoT (internet of things) system according to one embodiment. FIG. 2 is a block diagram showing an integrated intelligence system according to various embodiments. FIG. 3 is a diagram showing the form in which relationship information between concepts and operations is stored in a database according to various embodiments. FIG. 4 is a diagram showing a screen in which a user terminal processes voice input received through an intelligent app according to various embodiments. FIG. 5a is a drawing showing examples of devices included in an IoT system according to various embodiments. FIG. 5b is a diagram illustrating an environment in which an IoT system is implemented according to various embodiments. FIG. 6 is a diagram showing an example of the configuration of an electronic device included in an IoT system according to various embodiments. FIG. 7 is a diagram illustrating an example of an operation for setting values ​​used in the wake-up operation of an electronic device according to various embodiments. FIG. 8 is a flowchart illustrating an example of the operation of electronic devices included in an IoT system according to various embodiments. FIG. 9a is a diagram illustrating an example of an operation in which a main device according to various embodiments receives information about a user utterance from sub-devices. FIG. 9b is a diagram illustrating an example of an operation in which a sub-device according to various embodiments provides voice services. FIG. 10 is a flowchart illustrating an example of the operation of an electronic device according to various embodiments. FIG. 11 is a diagram illustrating an example of an operation to identify a device to be woken up of an electronic device according to various embodiments. FIG. 12 is a diagram illustrating an example of an operation for processing information associated with a user's utterance of an electronic device according to various embodiments. FIG. 13 is a flowchart illustrating an example of the operation of an electronic device according to various embodiments. FIG. 14 is a drawing for illustrating an example of an operation to extend a designated time interval of an electronic device according to various embodiments. FIG. 15 is a drawing for illustrating an example of an operation to shorten a specified time interval of an electronic device according to various embodiments. FIG. 16 is a flowchart illustrating an example of the operation of an electronic device according to various embodiments. FIG. 17 is a diagram illustrating an example of an operation to identify a device to be finally woken up of an electronic device according to various embodiments. FIG. 18 is a diagram illustrating an example of an operation to change the priority of a plurality of external electronic devices of an electronic device according to various embodiments. FIG. 19 is a flowchart illustrating an example of the operation of an electronic device according to various embodiments. FIG. 20a is a diagram illustrating an example of an operation to generate an artificial intelligence model based on various information accumulated when performing an operation to identify a device to be woken up of an electronic device according to various embodiments. FIG. 20b is a diagram illustrating an example of an operation to identify a device to be woken up based on an artificial intelligence model of an electronic device according to various embodiments. FIG. 21 is a flowchart illustrating an example of the operation of an electronic device configured according to various embodiments. FIG. 22 is a diagram illustrating an example of an operation to generate an artificial intelligence model based on various information accumulated when performing an operation to identify a device to be woken up of an electronic device according to various embodiments. FIG. 23 is a diagram illustrating an example of an operation to identify a device to be woken up based on an artificial intelligence model of an electronic device according to various embodiments. FIG. 24 is a flowchart illustrating an example of the operation of an electronic device configured according to various embodiments. FIG. 25 is a diagram illustrating an example of an operation to generate an artificial intelligence model based on various information accumulated when performing an operation to identify a device to be woken up of an electronic device according to various embodiments. FIG. 26 is a block diagram of an electronic device in a network environment according to various embodiments. Specific details for implementing the invention

[0019] FIG. 1 illustrates an IoT (internet of things) system (100) according to one embodiment. Meanwhile, at least some of the components of FIG. 1 may be omitted, and the system may be implemented to include additional components not illustrated.

[0020] Referring to FIG. 1, an IoT system (100) according to one embodiment includes a plurality of electronic devices that can be connected to a data network (116 or 146). For example, the IoT system (100) may include at least one of a first IoT server (110), a first node (120), a voice assistance server (130), a second IoT server (140), a second node (150), or devices (121, 122, 123, 124, 125, 136, 137, 151, 152, 153).

[0021] According to one embodiment, the first IoT server (110) may include at least one of a communication interface (111), a processor (112), or a storage unit (113). The second IoT server (140) may include at least one of a communication interface (141), a processor (142), or a storage unit (143). An “IoT server” in this document may remotely control and / or monitor one or more devices (e.g., devices (121, 122, 123, 124, 125, 151, 152, 153)) based on, for example, a data network (e.g., data network (116) or data network (146)), through a relay device (e.g., first node (120) or second node (150)), or directly without a relay device. The term "device" as used herein refers to sensors, home appliances, office electronic devices, or devices for performing processes deployed (or located) within a local environment, such as a home, office, factory, building, external branch, or other types of sites, without any limitations on their type. A device that receives a control command and performs an action corresponding to that command may be referred to as a "target device." An IoT server may also be referred to as a central server in that it selects a target device from among multiple devices and provides control commands.

[0022] According to one embodiment, the first IoT server (110) can communicate with devices (121, 122, 123) through a data network (116). The data network (116) may mean a network for long-distance communication, such as the Internet, or a computer network (e.g., LAN or WAN), or may include a cellular network.

[0023] According to one embodiment, the first IoT server (110) may be connected to a data network (116) through a communication interface (111). The communication interface (111) may include a communication device (or communication module) for supporting communication of the data network (116), and may be integrated into a single component (e.g., a single chip) or implemented as separate components (e.g., multiple chips). The first IoT server (110) may communicate with devices (121, 122, 123) through a first node (120). The first node (120) may receive data from the first IoT server (110) through the data network (116) and transmit the received data to at least some of the devices (121, 122, 123). Alternatively, the first node (120) may receive data from at least some of the devices (121, 122, 123) and transmit the received data to the first IoT server (110) via the data network (116). The first node (120) may function as a bridge between the data network (116) and the devices (121, 122, 123). Meanwhile, although FIG. 1 is illustrated as having only one first node (120), this is merely illustrative and there is no limit to the number.

[0024] In this document, "node" may be an edge computing system or a hub device. According to one embodiment, the first node (120) supports wired and / or wireless communication of the data network (116) and may also support wired and / or wireless communication with devices (121, 122, 123). For example, the first node (120) may be connected to the devices (121, 122, 123) via a short-range communication network such as Bluetooth, Wi-Fi, Wi-Fi Direct, Z-wave, Zig-bee, INSETEON, X10, etc., or IrDA (infrared data association), but there are no restrictions on the type of communication. The first node (120) may be placed (or located) within an environment such as, for example, a home, office, factory, building, external branch, or other types of sites. Accordingly, the devices (121, 122, 123) may be monitored and / or controlled by a service provided by the first IoT server (110), and the devices (121, 122, 123) may not be required to have the capability of full network communication (e.g., Internet communication) for direct connection to the first IoT server (110). The devices (121, 122, 123) are illustrated as being implemented as electronic devices in a home environment, such as light switches, proximity sensors, temperature sensors, etc., but this is exemplary and not limited to this.

[0025] According to one embodiment, the first IoT server (110) may support direct communication with devices (124, 125). Here, "direct communication" means communication without passing through a relay device, such as a first node (120), for example, and may mean communication through a cellular communication network and / or a data network, for example.

[0026] According to one embodiment, the first IoT server (110) may transmit a control command to at least some of the devices (121, 122, 123, 124, 125). Here, "control command" may mean data that causes a controllable device to perform a specific action, and the specific action is an action performed by the device, which may include outputting information, sensing information, reporting information, and managing information (e.g., deletion, or creation), and there is no limitation on the type thereof. For example, the processor (112) may obtain information (or a request) for generating a control command from an external source (e.g., a voice assistant server (130), a second IoT server (140), an external system (126), or at least some of the devices (121, 122, 123, 124, 125), and generate a control command based on the obtained information. Alternatively, the processor (112) may generate a control command based on the fact that the monitoring results of at least some of the devices (121, 122, 123, 124, 125) satisfy a specified condition. The processor (112) may control the communication interface (111) to transmit the control command to the target device.

[0027] According to one embodiment, the processor (112), or the processor (132) or the processor (142) may be implemented as a combination of one or more general-purpose processors such as a CPU (central processing unit), a DSP (digital signal processor), an AP (application processor), a CP (communication processor), a graphics-dedicated processor such as a GPU (graphical processing unit) or a VPU (vision processing unit), or an artificial intelligence-dedicated processor such as an NPU (neural processing unit). The processing units described above are merely exemplary, and those skilled in the art will understand that the processor (112) is not limited to any means of computation capable of executing instructions stored in memory (113), for example, and outputting the result of the execution.

[0028] According to one embodiment, the processor (112) may configure a web-based interface based on an API (114) or expose a resource managed by the first IoT server (110) to the outside. The web-based interface may support communication, for example, between the first IoT server (110) and an external web service. The processor (112) may allow, for example, an external system (126) to control and / or access the devices (121, 122, 123). The external system (126) may, for example, be an independent system that is not associated with or part of the system (100). The external system (126) may, for example, be an external server or a website. However, security is required for access to the devices (121, 122, 123) or the resources of the first IoT server (110) from the external system (126). According to one embodiment, the processor (112) may expose an API endpoint (e.g., a URL (universal resource locator)) based on the API (114) of the automation application to the outside. As described above, the first IoT server (110) may transmit control commands to a target device among the devices (121, 122, 123). Meanwhile, the description of the communication interface (141), processor (142), API (144) of the storage unit (143), and database (145) of the second IoT server (140) may be substantially the same as the description of the communication interface (111), processor (112), API (114) of the storage unit (113), and database (115) of the first IoT server (110). Additionally, the description of the second node (150) may be substantially the same as the description of the first node (120). The second IoT server (140) can transmit control commands to a target device among the devices (151, 152, 153).The first IoT server (110) and the second IoT server (140) may be operated by the same service provider in one embodiment, but may be operated by different service providers in another embodiment.

[0029] According to one embodiment, the voice assistant server (130) can transmit and receive data with the first IoT server (110) through a data network (116). The voice assistant server (130) according to one embodiment may include at least one of a communication interface (131), a processor (132), or a storage unit (133). The communication interface (131) can communicate with a smartphone (136) or an AI speaker (137) through a data network (not shown) and / or a cellular network (not shown). The smartphone (136) or the AI ​​speaker (137) may include a microphone and can acquire a user voice, convert it into a voice signal, and transmit the voice signal to the voice assistant server (130). The processor (132) can receive a voice signal from the smartphone (136) or the AI ​​speaker (137) through the communication interface (131). The processor (132) can process the received voice signal based on the stored model (134). The processor (132) can generate (or verify) a control command using the processing result based on the information stored in the database (135).According to one embodiment, the storage unit (113, 133, 143) may include at least one type of non-transitory storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, a magnetic disk, and an optical disk, and there is no limitation on the type.

[0032] FIG. 2 is a block diagram showing an integrated intelligence system according to various embodiments. The description of the integrated intelligence system (10) described below may be applied to the description of the IoT system described above in FIG. 1.

[0033] Referring to FIG. 2, an integrated intelligent system (10) of one embodiment may include a user terminal (160), an intelligent server (200), and a service server (300).

[0034] The user terminal (160) of one embodiment may be a terminal device (or electronic device) capable of connecting to the internet, and for example, the user terminal (160) may be a mobile phone, smartphone, PDA (personal digital assistant), laptop computer, TV, home appliance, wearable device, HMD, or smart speaker.

[0035] According to the illustrated embodiment, the user terminal (160) may include a communication interface (161), a processor (162), a display (163), a speaker (164), a microphone (165), or a memory (170). The listed components may be operatively or electrically connected to each other.

[0036] A communication interface (161) of one embodiment may be configured to be connected to an external device to transmit and receive data. A microphone (165) of one embodiment may receive sound (e.g., user speech) and convert it into an electrical signal. A speaker (164) of one embodiment may output the electrical signal as sound (e.g., voice). A display (163) of one embodiment may be configured to display an image or video. A display (163) of one embodiment may also display a graphic user interface (GUI) of an app (or application program) being executed.

[0037] In one embodiment, the memory (170) can store a client module (171), an SDK (software development kit) (173), and a plurality of apps (175_1, 175_2). The client module (171) and the SDK (173) can form a framework (or solution program) for performing general-purpose functions. Additionally, the client module (171) or the SDK (173) can form a framework for processing voice input.

[0038] In one embodiment, the memory (170) may be a program for performing a designated function, wherein the plurality of apps (175_1, 175_2) may be a program. According to one embodiment, the plurality of apps (175_1, 175_2) may include a first app (175_1) and a second app (175_2). According to one embodiment, each of the plurality of apps (175_1, 175_2) may include a plurality of operations for performing a designated function. For example, the apps may include an alarm app, a message app, and / or a schedule app. According to one embodiment, the plurality of apps (175_1, 175_2) may be executed by a processor (162) to sequentially execute at least some of the plurality of operations.

[0039] A processor (162) of one embodiment can control the overall operation of a user terminal (160). For example, the processor (162) can be electrically connected to a communication interface (161), a microphone (165), a speaker (164), and a display (163) to perform a specified operation.

[0040] The processor (162) of one embodiment may also perform a specified function by executing a program stored in the memory (170). For example, the processor (162) may execute at least one of the client module (171) or the SDK (173) to perform the following operations for processing voice input. The processor (162) may, for example, control the operation of a plurality of apps (175_1, 175_2) through the SDK (173). The following operations described as the operation of the client module (171) or the SDK (173) may be operations performed by the execution of the processor (162).

[0041] A client module (171) of one embodiment can receive voice input. For example, the client module (171) can receive a voice signal corresponding to a user utterance detected through a microphone (165). The client module (171) can transmit the received voice input to an intelligent server (200). Along with the received voice input, the client module (171) can transmit status information of the user terminal (160) to the intelligent server (200). The status information may be, for example, execution status information of an app.

[0042] A client module (171) of one embodiment can receive a result corresponding to a received voice input. For example, if the client module (171) can produce a result corresponding to the received voice input from an intelligent server (200), the client module (171) can receive a result corresponding to the received voice input. The client module (171) can display the received result on a display (163).

[0043] In one embodiment, the client module (171) can receive a plan corresponding to the received voice input. The client module (171) can display the results of executing multiple actions of the app according to the plan on the display (163). The client module (171) can, for example, display the results of executing multiple actions sequentially on the display. The user terminal (160) can, for another example, display only some of the results of executing multiple actions (e.g., the result of the last action) on the display.

[0044] According to one embodiment, the client module (171) may receive a request from the intelligent server (200) to obtain information necessary to produce a result corresponding to a voice input. According to one embodiment, the client module (151) may transmit the necessary information to the intelligent server (200) in response to the request.

[0045] A client module (171) of one embodiment can transmit result information of executing a plurality of operations according to a plan to an intelligent server (200). The intelligent server (200) can use the result information to confirm that the received voice input has been processed correctly.

[0046] A client module (171) of one embodiment may include a voice recognition module. According to one embodiment, the client module (171) may recognize voice input that performs a limited function through the voice recognition module. For example, the client module (171) may perform an intelligent app for processing voice input to perform an organic action through a specified input (e.g., Wake Up!).

[0047] An intelligent server (200) of one embodiment can receive information related to user voice input from a user terminal (160) via a communication network. According to one embodiment, the intelligent server (200) can convert the data related to the received voice input into text data. According to one embodiment, the intelligent server (200) can generate a plan for performing a task corresponding to the user voice input based on the text data.

[0048] According to one embodiment, a plan may be generated by an artificial intelligence (AI) system. The AI ​​system may be a rule-based system or a neural network-based system (e.g., a feedforward neural network (FNN), a recurrent neural network (RNN)). Alternatively, it may be a combination of the foregoing or a different AI system. According to one embodiment, the plan may be selected from a set of predefined plans or may be generated in real time in response to a user request. For example, the AI ​​system may select at least one plan from a plurality of predefined plans.

[0049] An intelligent server (200) of one embodiment may transmit a result according to a generated plan to a user terminal (160) or transmit a generated plan to a user terminal (160). According to one embodiment, the user terminal (160) may display a result according to a plan on a display. According to one embodiment, the user terminal (160) may display a result of executing an action according to a plan on a display.

[0050] An intelligent server (200) of one embodiment may include a front end (210), a natural language platform (220), a capsule database (230), an execution engine (240), an end user interface (250), a management platform (260), a big data platform (270), or an analytic platform (280).

[0051] A front end (210) of one embodiment can receive voice input received from a user terminal (160). The front end (210) can transmit a response corresponding to the voice input.

[0052] According to one embodiment, the natural language platform (220) may include an automatic speech recognition module (ASR module) (221), a natural language understanding module (NLU module) (223), a planner module (225), a natural language generator module (NLG module) (227), or a text to speech module (TTS module) (229).

[0053] An automatic speech recognition module (221) of one embodiment can convert voice input received from a user terminal (160) into text data. A natural language understanding module (223) of one embodiment can identify the user's intention using the text data of the voice input. For example, the natural language understanding module (223) can identify the user's intention by performing a syntactic analysis or a semantic analysis. A natural language understanding module (223) of one embodiment can identify the meaning of a word extracted from the voice input using linguistic features (e.g., grammatical elements) of a morpheme or phrase, and determine the user's intention by matching the identified meaning of the word to the intention.

[0054] A planner module (225) of one embodiment can generate a plan using intentions and parameters determined by a natural language understanding module (223). According to one embodiment, the planner module (225) can determine multiple domains necessary to perform a task based on the determined intention. The planner module (225) can determine multiple actions included in each of the multiple domains determined based on the intention. According to one embodiment, the planner module (225) can determine parameters necessary to execute the determined multiple actions or result values ​​output by the execution of the multiple actions. The parameters and result values ​​may be defined as concepts of a specified format (or class). Accordingly, the plan may include multiple actions and multiple concepts determined by the user's intention. The planner module (225) can determine the relationship between the multiple actions and the multiple concepts in a stepwise (or hierarchical) manner. For example, the planner module (225) can determine the execution order of multiple actions determined based on the user's intentions based on multiple concepts. In other words, the planner module (225) can determine the execution order of multiple actions based on parameters required for the execution of multiple actions and results output by the execution of multiple actions. Accordingly, the planner module (225) can generate a plan that includes association information (e.g., ontology) between multiple actions and multiple concepts. The planner module (225) can generate the plan using information stored in a capsule database (230) in which a set of relationships between concepts and actions is stored.

[0055] A natural language generation module (227) of one embodiment can change specified information into a text form. The information changed into a text form may be in the form of natural language utterance. A text-to-speech conversion module (229) of one embodiment can change information in a text form into information in a speech form.

[0056] According to one embodiment, some or all functions of the natural language platform (220) may also be implemented on a user terminal (160).

[0057] The capsule database (230) can store information regarding the relationships between multiple concepts and actions corresponding to multiple domains. A capsule according to one embodiment may include multiple action objects (or action information) and concept objects (or concept information) included in a plan. According to one embodiment, the capsule database (230) may store multiple capsules in the form of a CAN (concept action network). According to one embodiment, multiple capsules may be stored in a function registry included in the capsule database (230).

[0058] The above capsule database (230) may include a strategy registry in which strategy information necessary for determining a plan corresponding to a voice input is stored. The strategy information may include reference information for determining one plan when there are multiple plans corresponding to the voice input. According to one embodiment, the capsule database (230) may include a follow-up registry in which information of a follow-up action is stored for suggesting a follow-up action to a user in a specified situation. The follow-up action may include, for example, a follow-up utterance. According to one embodiment, the capsule database (230) may include a layout registry in which layout information of information output through a user terminal (160) is stored. According to one embodiment, the capsule database (230) may include a vocabulary registry in which vocabulary information included in the capsule information is stored. According to one embodiment, the capsule database (230) may include a dialogue registry in which information regarding a conversation (or interaction) with a user is stored. The capsule database (230) may update stored objects through a developer tool. The developer tool may include, for example, a function editor for updating action objects or concept objects. The developer tool may include a vocabulary editor for updating vocabulary. The developer tool may include a strategy editor for creating and registering strategies for determining plans. The developer tool may include a dialogue editor for creating conversations with a user.The above developer tool may include a follow-up editor capable of activating a follow-up goal and editing a follow-up utterance that provides a hint. The follow-up goal may be determined based on a currently set goal, user preferences, or environmental conditions. In one embodiment, the capsule database (230) may also be implemented within the user terminal (160).

[0059] An execution engine (240) of one embodiment can produce a result using the generated plan. An end-user interface (250) can transmit the produced result to a user terminal (160). Accordingly, the user terminal (160) can receive the result and provide the received result to the user. A management platform (260) of one embodiment can manage information used in the intelligent server (200). A big data platform (270) of one embodiment can collect user data. An analysis platform (280) of one embodiment can manage the quality of service (QoS) of the intelligent server (200). For example, the analysis platform (280) can manage the components and processing speed (or efficiency) of the intelligent server (200).

[0060] A service server (300) of one embodiment may provide a service designated to a user terminal (160), such as food ordering or hotel reservation. According to one embodiment, the service server (300) may be a server operated by a third party. A service server (300) of one embodiment may provide information to an intelligent server (200) for generating a plan corresponding to a received voice input. The provided information may be stored in a capsule database (230). Additionally, the service server (300) may provide result information according to the plan to the intelligent server (200).

[0061] In the integrated intelligent system (10) described above, the user terminal (160) can provide various intelligent services to the user in response to user input. The user input may include, for example, input via a physical button, touch input, or voice input.

[0062] In one embodiment, the user terminal (160) may provide a voice recognition service through an intelligent app (or voice recognition app) stored internally. In this case, for example, the user terminal (160) may recognize a user utterance or voice input received through the microphone and provide a service to the user corresponding to the recognized voice input.

[0063] In one embodiment, the user terminal (160) may perform a specified action, either alone or together with the intelligent server and / or service server, based on the received voice input. For example, the user terminal (160) may execute an app corresponding to the received voice input and perform a specified action through the executed app.

[0064] In one embodiment, when a user terminal (160) provides services together with an intelligent server (200) and / or a service server, the user terminal can detect user speech using the microphone (165) and generate a signal (or voice data) corresponding to the detected user speech. The user terminal can transmit the voice data to the intelligent server (200) using a communication interface (161).

[0065] An intelligent server (200) according to one embodiment may generate, in response to a voice input received from a user terminal (160), a plan for performing a task corresponding to the voice input, or a result of performing an operation according to the plan. The plan may include, for example, a plurality of operations for performing a task corresponding to the user's voice input, and a plurality of concepts related to the plurality of operations. The concepts may define parameters input to the execution of the plurality of operations or result values ​​output by the execution of the plurality of operations. The plan may include association information between the plurality of operations and the plurality of concepts.

[0066] A user terminal (160) of one embodiment can receive the response using a communication interface (161). The user terminal (160) can output a voice signal generated inside the user terminal (160) to the outside using the speaker (164), or output an image generated inside the user terminal (160) to the outside using the display (163).

[0067] FIG. 3 is a diagram showing the form in which relationship information between concepts and operations is stored in a database according to various embodiments.

[0068] The capsule database (e.g., capsule database (230)) of the intelligent server (200) can store capsules in the form of a CAN (concept action network) (400). The capsule database can store actions for processing tasks corresponding to the user's voice input, and parameters required for said actions, in the form of a CAN (concept action network) (400).

[0069] The above capsule database may store a plurality of capsules (capsule(A)(401), capsule(B)(404)) corresponding to each of a plurality of domains (e.g., application). According to one embodiment, one capsule (e.g., capsule(A)(401)) may correspond to one domain (e.g., location (geo), application). Additionally, one capsule may correspond to at least one service provider (e.g., CP 1 (402), CP 2 (403), CP 3 (406), or CP 4 (405)) for performing functions for the domain associated with the capsule. According to one embodiment, one capsule may include at least one operation (410) and at least one concept (420) for performing a specified function.

[0070] The above natural language platform (220) can generate a plan for performing a task corresponding to a received voice input using capsules stored in a capsule database. For example, the planner module (225) of the natural language platform can generate a plan using capsules stored in a capsule database. For example, a plan (407) can be generated using the actions (4011, 4013) and concepts (4012, 4014) of capsule A (410) and the actions (4041) and concepts (4042) of capsule B (404).

[0071] FIG. 4 is a diagram showing a screen in which a user terminal processes voice input received through an intelligent app according to various embodiments.

[0072] The user terminal (160) can run an intelligent app to process user input through the intelligent server (200).

[0073] According to one embodiment, on the screen 310, the user terminal (160) can execute an intelligent app for processing voice input when it recognizes a designated voice input (e.g., Wake up!) or receives input via a hardware key (e.g., a dedicated hardware key). The user terminal (160) can execute the intelligent app while, for example, a schedule app is running. According to one embodiment, the user terminal (160) can display an object (e.g., an icon) (311) corresponding to the intelligent app on the display (163). According to one embodiment, the user terminal (160) can receive voice input by user speech. For example, the user terminal (160) can receive voice input saying "Tell me this week's schedule!" According to one embodiment, the user terminal (160) can display a UI (user interface) (313) (e.g., an input window) of the intelligent app on the display, in which text data of the received voice input is displayed.

[0074] According to one embodiment, on a 320 screen, the user terminal (160) can display a result corresponding to the received voice input on the display. For example, the user terminal (160) can receive a plan corresponding to the received user input and display 'this week's schedule' on the display according to the plan.

[0076] Hereinafter, with reference to FIGS. (932)a to FIGS. 5b, an example of a device included in an IoT system will be described. For the IoT system described below, the description of the IoT system described in FIG. 1 and the description of the integrated intelligence system described in FIGS. 2 to 3 may be applied, so redundant descriptions will be omitted.

[0077] FIG. 5a is a diagram illustrating examples of devices included in an IoT system according to various embodiments. According to various embodiments, the IoT system may be implemented to include more or fewer devices, not limited to the devices shown in FIG. 5.

[0078] FIG. 5b is a diagram illustrating an environment in which an IoT system is implemented according to various embodiments.

[0079] According to various embodiments, the IoT system is implemented in a specific environment (500) and may include a plurality of electronic devices (510) and an intelligent server (530). The IoT system may be implemented in a home as shown in FIG. 5a, or in various environments (e.g., an office, a factory, a building, the interior of a means of transportation, an outdoor environment) without being limited to those shown.

[0080] Below, a plurality of electronic devices (510) will be described first.

[0081] According to various embodiments, the plurality of electronic devices (510) may include various types of electronic devices that can be installed within the environment (500) where the IoT system is implemented. For example, the plurality of electronic devices (510) may include not only electronic devices installed at a fixed location (e.g., refrigerator (501), air conditioner (502), speaker (503), TV (504) shown in FIG. 5a), but also electronic devices whose location is constantly changing (M (movable), e.g., smartphone (505), wearable device (506) shown in FIG. 5). Without being limited to those described, the plurality of electronic devices (510) may further include various types of devices installed within the environment (500) where the IoT system is implemented (e.g., robot vacuum cleaner, smart window, smart light, various products).

[0082] According to various embodiments, each of the plurality of electronic devices (510) may establish a communication connection with one another. For example, the plurality of electronic devices (510) may establish communication connections (511, 512, 513, 514, 515, 516) using a wireless communication scheme (e.g., Wi-Fi) utilizing an access point (AP) (540) or a repeater as illustrated in FIG. 5a. Without being limited to the description, each of the plurality of electronic devices (510) may also establish a communication connection using a wireless communication scheme (e.g., Bluetooth) for direct connection with one another. The plurality of electronic devices (510) that have established communication connections with one another may form at least one communication network. At this time, some of the plurality of electronic devices (510) may detach from the formed communication network, or other electronic devices may join the formed communication network. For example, if some of the plurality of electronic devices (510) are moved to a location where it is impossible to form a communication connection with the remaining electronic devices (or a location outside the environment (500) where the IoT system is implemented), the communication connection of some of the plurality of electronic devices (510) may be disconnected, and the plurality of electronic devices (510) may be removed from the communication network. Also, if another external electronic device is located (or provided) at a location where it is possible to form a communication connection with the plurality of electronic devices (510) (or a location within the environment where the IoT system is implemented), the other external electronic device may establish a communication connection with the plurality of electronic devices (510) and participate in the communication network. Each of the plurality of electronic devices (510) may transmit information (e.g., information related to user utterance, information regarding the status of the electronic device) to other electronic devices included in the communication network based on the communication connection, which will be described later.

[0083] According to various embodiments, at least some of the plurality of electronic devices (510) may provide various intelligent services (e.g., voice recognition services). For example, at least some of the plurality of electronic devices (510) may include a program for providing intelligent services (e.g., an intelligent service provision module (613) to be described later). At least some of the plurality of electronic devices (510) may receive a user utterance based on the execution and / or operation of the program, process the received user utterance, and provide a voice recognition service corresponding to the user utterance according to the processing result. For example, at least some of the plurality of electronic devices (510) may perform an operation to identify a device to be woken up when receiving a first user utterance containing a specific word (or trigger word) for executing the voice recognition service (or executing a program for providing intelligent voice services). The meaning of the above electronic device being “wake-up” may mean that the state of the above electronic device is transitioned to a state capable of acquiring and processing a user’s utterance for control (in other words, a state capable of providing voice recognition and voice recognition-based services, or a listening state for recognizing and processing user utterances for control). Also, for example, among the plurality of electronic devices (510), the woke-up electronic device may receive a second user utterance for control and transmit the second user utterance to an intelligent server (530) to be described later. Some of the plurality of electronic devices (510) may receive information regarding the result of processing the second user utterance from the intelligent server (530) and provide a service corresponding to the second user utterance (e.g., perform a specific function of the electronic device) based on the received information.The voice recognition service provision operation of at least some of the plurality of electronic devices (510) can be performed as described in FIGS. 2 to 4, so a redundant description is omitted. At this time, at least some of the other remaining parts of the plurality of electronic devices (510) equipped in the IoT system may not be able to provide the intelligent service. For example, at least some of the other remaining parts of the plurality of electronic devices (510) may not have a program installed to provide the intelligent service.

[0084] According to various embodiments, the respective roles of a plurality of electronic devices (510) within an IoT system may be set. For example, at least one device (e.g., 503) among the plurality of electronic devices (510) may be set as a “main device” (520) (or, master device), and the other remaining devices may be set as “sub devices” (or, slave devices). The electronic device (e.g., 503) set as the main device (520) may receive information (e.g., information related to user utterances) from the other remaining sub devices (e.g., 501, 502, 504, 505, 506) and may control the intelligent service provision operation of the plurality of electronic devices (510) based on the received information. For example, the main device (520) may receive information related to the user utterance (e.g., information about the intensity of the user utterance) from at least some of the sub-devices when a user utterance occurs (e.g., a user utters in an environment where an IoT system is implemented), and may identify a device among the sub-devices to be woken up based on the received information. For example, the main device (520) may accumulate information obtained during the operation of identifying a device among the sub-devices to be woken up (e.g., information on the time of reception to be described later, information on the device re-identified as the device to be woken up, device-specific status information, SNR information, priority information), and may change values ​​used during the operation of identifying a device to be woken up (e.g., time interval to be described later, priority) based on the accumulated information. Each of the accumulated information will be described later. The main device (520) may transmit some of the accumulated information to an intelligent server (530) so that it accumulates in the intelligent server (530).

[0085] According to various embodiments, the configuration of the “main device” and the “sub device” may be performed automatically or manually. For example, when registering a plurality of electronic devices (510), the intelligent server (503) may automatically configure the main device (520) based on information regarding the plurality of electronic devices (e.g., information regarding processing capability, information regarding priority to be identified as a device to be woken up). For example, the intelligent server (503) may configure the device with the highest processing capability as the main device (520). For another example, the intelligent server (503) may configure the device with the lowest (or highest) priority to be identified as a device to be woken up as the main device (520). For example, when a user registers a plurality of electronic devices (510), one of the plurality of electronic devices (510) may be configured as the main device (520). When a main device (520) is configured among the plurality of electronic devices (510), the remaining devices among the plurality of electronic devices can be automatically configured as sub-devices. The intelligent server (530) stores information regarding the roles (main device and sub-device) configured for each of the plurality of electronic devices (510) and can transmit the stored information to the main device (520).

[0086] If there are multiple electronic devices that have received a wake-up utterance, a situation may arise where the intelligent server (530) must process all voice information transmitted by multiple electronic devices (510). If all voice information transmitted by multiple electronic devices (510) is processed, the load on the intelligent server (530) may increase, and the time required for the intelligent server (530) to process the voice information may increase. As described above, the load on the intelligent server (530) can be reduced by the electronic device set as the “main device” (520) identifying the device to provide voice recognition services (e.g., the device to be woken up). Additionally, devices that are not woken up may not provide voice recognition services (e.g., do not switch to a listening state).

[0087] The following describes an intelligent server (530).

[0088] According to various embodiments, the intelligent server (530) may receive information regarding user utterances from a plurality of electronic devices (510) and process the received user utterances to generate information for providing services. For example, the intelligent server (530) may convert user utterances into text based on a text conversion algorithm (e.g., an auto speech recognition (ASR) algorithm) and analyze the meaning of the converted text based on a natural language understanding algorithm (e.g., a natural language understanding (NLU) algorithm). The intelligent server (530) may identify information for providing services corresponding to the analyzed meaning (e.g., a plan for performing a plurality of actions) and transmit the identified information to the plurality of electronic devices (510). For example, as described above, the plan may include a plurality of actions for performing a task corresponding to the user's voice input, and a plurality of concepts related to the plurality of actions. Accordingly, the plurality of electronic devices (510) may sequentially provide at least one function based on the identified information. Since the description of the intelligent server (200) described in FIGS. 2 to 4 can be applied to the intelligent server (530) above, redundant descriptions are omitted.

[0089] According to various embodiments, the intelligent server (530) may register a plurality of electronic devices (510). For example, when each electronic device establishes a communication connection, the intelligent server (530) may automatically receive identification information (e.g., IMEI (international mobile equipment identity), MAC address (media access control address), IP address (internet protocol address)) for identifying the electronic device from each electronic device, and register each electronic device based on the received identification information. Alternatively, the intelligent server (530) may receive identification information for a plurality of electronic devices (510) from a user terminal (e.g., smartphone) used by a user (e.g., a user using an IoT system), and register the electronic devices based on the received identification information.

[0090] At this time, the intelligent server (530) can classify and register and / or manage multiple electronic devices (510) by location. For example, as shown in FIG. 5b, multiple electronic devices (510) may be provided by location (e.g., rooms (551, 554, 555), kitchen (552), living room (553)) in an environment (e.g., home) where the IoT system is implemented. When registering multiple electronic devices (510), the intelligent server (530) may request information regarding the location where the multiple electronic devices (510) are provided from the multiple electronic devices (510) and receive information regarding the location based on the request. For example, the multiple electronic devices (510) may receive and store information regarding the location of the multiple electronic devices (510) by inputting it from a user, and the intelligent server (530) may request information regarding the location from each of the multiple electronic devices (510) and receive information regarding the location. For example, the plurality of electronic devices (510) may request information regarding the location of the plurality of electronic devices (510) from a user terminal used by a user, and may receive information regarding the location of the plurality of electronic devices (510) input by the user on the user terminal from the user terminal. Accordingly, the intelligent server (530) may classify or group the plurality of electronic devices (510) by location (e.g., master bedroom, living room) and enroll and / or manage information regarding the plurality of electronic devices (510) by location.

[0091] According to various embodiments, the intelligent server (530) may transmit information about a plurality of registered electronic devices (510) to the main device (520) so that the main device (520) can identify the registered sub-devices. Alternatively, without being limited to the description, the main device (520) may not receive information about a plurality of electronic devices (510) from the intelligent server (530), but may directly receive and store identification information about the sub-devices from other sub-devices.

[0093] Below, an example of the components included in the electronic device (510) included in the IoT system is described. Meanwhile, in addition to the components included in the electronic device (510) described in FIG. 6, the components of the electronic device (101) described in FIG. 25 may also be included.

[0094] FIG. 6 is a diagram illustrating an example of the configuration of an electronic device included in an IoT system according to various embodiments. According to various embodiments, the electronic device may be implemented to include more or fewer configurations, not limited to the devices shown in FIG. 6. FIG. 6 will be further described below with reference to FIG. 7. For example, the electronic device (510) may be implemented not to include at least one configuration (e.g., microphone (601), wake-up device identification module (611)) depending on the purpose of implementation. As an example, the electronic device (510) may be implemented not to include the wake-up device identification module (611).

[0095] FIG. 7 is a diagram illustrating an example of an operation for setting values ​​used in a wake-up operation of an electronic device set as a “main device” according to various embodiments.

[0096] According to various embodiments, the electronic device (510) may include a microphone (601), a speaker (603), a communication circuit (605), a processor (610) including a wake-up device identification module (611) and an intelligent service provision module (613), and a memory (620).

[0097] According to various embodiments, the electronic device (510) can receive user speech using the microphone (601).

[0098] According to various embodiments, the electronic device (510) may output sound using the speaker (603). For example, the electronic device (510) may output sound through the speaker (603) to notify the wake-up when it is woke-up. Also, for example, when the electronic device (510) receives sound information from the intelligent server (530) based on the processing result of a user's speech, it may output sound through the speaker (603) based on the received sound information.

[0099] According to various embodiments, a plurality of electronic devices (510) may establish a communication connection with other electronic devices (510) included in the IoT system using a communication circuit (605) and transmit and / or receive information (e.g., information associated with user utterances). The information associated with user utterances may include information indicating the intensity of the user utterances. For example, the information indicating the intensity of the user utterances may include information regarding the signal-to-noise ratio (SNR) of the user utterances, or information regarding the quality of the user utterances. The quality of the user utterances may indicate the clarity of the user utterances.

[0100] Hereinafter, a processor (610) included in each of the plurality of electronic devices (510) will be described. According to various embodiments, modules included in the processor (610) of the plurality of electronic devices (510) (e.g., a wake-up device identification module (611) and an intelligent service provision module (613)) may be stored in the electronic device (510) (e.g., memory (620)) in the form of an application, program, computer code or instructions, routine, or process that can be executed by the processor (610) of the electronic device (510). When the modules are executed by the processor (610), the modules may cause the processor (610) to perform an operation associated with the module. Hereinafter, each component included in the processor (610) will be described.

[0101] The wake-up device identification module (611) and intelligent service provision module (613) described below may be implemented as at least part of the client module (171) described above.

[0102] According to various embodiments, the wake-up device identification module (611) can identify a device to be woken up among sub-devices included in the IoT system. For example, the wake-up device identification module (611) can identify a device to be woken up among the external electronic devices (510) based on information received from external electronic devices (510) (e.g., information related to user utterance) and values ​​(710) used in the operation of identifying a device to be woken up. The values ​​(710) used in the operation of identifying a device to be woken up are stored in memory (620) as shown in FIG. 7 and may include information about time (711) and information about the priority of a plurality of electronic devices (712). The information regarding the time (711) may include information regarding at least one of a session, a first time-out for identifying a device to be woken up included in the session, or a second guard time other than the first time-out. The information regarding the priority (712) indicates the preference for being identified as a device to be woken up for each of the plurality of external electronic devices, and the higher the priority, the higher the probability of being identified as a device to be woken up. Specific examples of the operation to identify a device to be woken up among the external electronic devices (510) based on the information received from the external electronic devices (510) of the wake-up device identification module (e.g., information related to user utterance) and the values ​​(710) used in the operation to identify a device to be woken up will be described later.

[0103] According to various embodiments, the wake-up device identification module (611) may set and / or change values ​​(710) (e.g., information on time intervals (710), information on priority (712)) for identifying a device to be woken up based on accumulated information (720). Referring to FIG. 7, the accumulated information (720) may include information on the time of reception of information received from external electronic devices obtained during the execution of operations to identify a wake-up device (not shown), device-specific status information (e.g., power status, battery status, temperature status, app execution status), SNR information, information on priority, initial selection information (e.g., a device initially identified as a device to be woken up in an operation to identify a device to be woken up), and final selection information (e.g., a device finally identified as a device to be woken up in an operation to identify a device to be waken up). The wake-up device identification module (611) can set information on the time interval (710) and information on the priority (712) based on the accumulated information (720), which will be described later.

[0104] For example, the above accumulated information (720) is as follows [Table 1] It can be like that.

[0105] Wake-up operation number TV cell phone air conditioning Initial selection device Final selection device power vol SNR priority app_state SNR priority Current temperature Set temperature SNR priority #1 on 10 -10db 0.3 YouTube -98db 0.8 20 20 -48db 0.4 Speaker Speaker #2 off N / A -98db 0.3 sleep -10db 0.8 30 18 -105db 0.4 air conditioning air conditioning

[0106] According to various embodiments, the intelligent service providing module (613) may be implemented to provide a voice recognition service. When the intelligent service providing module (613) is implemented and executed in the form of a program or application, it may perform the operation of providing a voice recognition service. Since the voice recognition service is as described above, a redundant description is omitted.

[0108] Hereinafter, an example of the operation of electronic devices included in an IoT system according to various embodiments is described.

[0109] According to various embodiments, among the electronic devices included in the IoT system, the main device (520) receives information regarding user utterances from other sub-devices (521), identifies a device to be woken up based on the received information, and can transmit a message (or signal) to wake up the identified device. The woke-up device receives a user utterance for control from the user and can provide intelligent services based on transmitting the received user utterance to an intelligent server (530). The electronic device (901) described below is the “main device (520),” and the external electronic devices (e.g., the first external electronic device (902), the second external electronic device (903), the third external electronic device (904)) are described as “sub-devices (521).”

[0110] FIG. 8 is a flowchart illustrating an example of the operation of electronic devices included in an IoT system according to various embodiments. According to various embodiments, the operations illustrated in FIG. 8 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 8, or at least one fewer operation may be performed. FIG. 8 will be described below with reference to FIG. 9a and 9b.

[0111] FIG. 9a is a diagram illustrating an example of an operation in which a main device according to various embodiments receives information about a user utterance from sub-devices. FIG. 9b is a diagram illustrating an example of an operation in which a sub-device according to various embodiments provides a voice service.

[0112] According to various embodiments, an electronic device (901) (e.g., main device (520)) may establish a communication connection with other external electronic devices (e.g., sub device (521), first to third external electronic devices (902, 903, 904)) in operation 801. For example, referring to FIG. 9a, a plurality of electronic devices (901, 902, 903, 904) may be provided within an environment (500) (e.g., a home). Among the plurality of electronic devices (901, 902, 903, 904), one electronic device (e.g., 901) may be set as the "main device (520)" and the other remaining electronic devices (e.g., 902, 903, 904) may be set as "sub devices (521)". The operation of setting one of the plurality of electronic devices (901, 902, 903, 904) as the "main device (520)" and the operation of setting the remaining electronic devices as "sub devices (521)" can be performed automatically or manually, and since this is as described in the description of FIG. 5b, a redundant description is omitted. The "main device (520)" can establish a communication connection with the other remaining "sub devices (521)".

[0113] According to various embodiments, external electronic devices (e.g., a first external electronic device (902), a second external electronic device (903), and a third external electronic device (904)) can obtain information associated with a user utterance (e.g., first information, second information, and third information) in each of the 802 operation, the 803 operation, and the 804 operation. For example, referring to FIG. 9a, a user can utter a specific word (e.g., a starter word) within an environment (500) equipped with a plurality of electronic devices (e.g., an electronic device (901), a first external electronic device (902), a second external electronic device (903), and a third external electronic device (904)). The plurality of external electronic devices (902, 903, 904) can receive the user utterance containing the specific word (e.g., a starter word) using a microphone. The plurality of external electronic devices described above may convert the acquired user utterance into text and execute and / or drive a program (e.g., the intelligent service provision module (613) described above) for recognizing a specific word (e.g., a trigger word) and providing voice services. Alternatively, the plurality of external electronic devices (902, 903, 904) may receive the user utterance while continuing to execute the program for providing voice services, without being limited to those described above. The plurality of external electronic devices (902, 903, 904) may generate information associated with the acquired user utterance based on the acquisition of the user utterance containing the specific word. The information associated with the user utterance may include information indicating the intensity of the user utterance. For example, the information indicating the intensity of the user utterance may include information regarding the signal-to-noise ratio (SNR) of the user utterance and / or information regarding the quality of the user utterance, but there is no limitation on the type thereof. The quality of the user utterance may indicate the degree of clarity of the user utterance.

[0114] According to various embodiments, the electronic device may receive information associated with a user utterance (e.g., first information, second information, and third information) from each of a plurality of external electronic devices (e.g., a first external electronic device (902), a second external electronic device (903), and a third external electronic device (904)) in each of operations 805, 806, and 807. For example, the electronic device (901) may execute a program based on receiving information associated with a user utterance from one of the plurality of external electronic devices (902, 903, 904) (e.g., first receiving information associated with a user utterance from the first external electronic device (902)). Also, for example, the electronic device (901) may also execute a program to recognize a specific word included in the user utterance and provide a voice service based on receiving the user utterance using a microphone. Based on the execution of the above program, the state of the electronic device (901) may be set and / or switched to a state for processing information associated with user utterances received from other external electronic devices (902, 903, 904). For example, the electronic device (901) may set and / or start a session for processing information associated with the user utterances of the electronic device (901). That is, the electronic device (901) may set and / or start a session from the time it first receives information associated with user utterances from an external electronic device (the first external electronic device (902)) or from the time it receives user utterances using a microphone. The said session refers to a time for processing a user utterance, and information received after the said session may be identified as information associated with other user utterances other than the said user utterance.An electronic device (901) may receive information regarding a user utterance (e.g., first information, second information, and third information) during a session and may initiate an operation to identify a device to be woken up among external electronic devices (902, 903, 904) corresponding to the information regarding the user utterance (e.g., first information, second information, and third information). For example, the electronic device (901) may classify and / or manage the external electronic devices (902, 903, 904) corresponding to the information received during the session into groups for a user utterance and identify a device to be woken up by the user utterance among the external electronic devices classified into groups. In other words, if the electronic device receives information after the session, it may identify a device to be woken up based only on the information received during the session, excluding the information received after the session. The electronic device may identify a device to be woken up in another session based on information received after one session (e.g., information received during another session). The session includes a time-out and a guard time, and the time-out and the guard time may be changed based on information acquired and / or accumulated during the execution of the operation to identify a device to be woken up previously performed by the electronic device (901), as described later in FIGS. 13 to 15. Meanwhile, the electronic device (901) may receive information related to the user utterance as well as information related to the external electronic devices (902, 903, 904) from the external electronic devices (902, 903, 904) (e.g., identification information of the external electronic device, status information of the external electronic device), and identify a device to be woken up based on this, as described later in FIGS. 21 to 23.

[0115] According to various embodiments, the electronic device (901) can identify a device to be woken up based on a plurality of pieces of information (e.g., first information, second information, and third information) associated with a user utterance in an 808 operation. For example, the electronic device (901) can identify the respective SNR values ​​(e.g., first value, second value, third value) of a plurality of external electronic devices (e.g., first external electronic device (902), second external electronic device (903), and third external electronic device (904)) for a user utterance as shown in 910 of FIG. 9a, and can compare the magnitudes of the identified SNR values ​​as shown in 920 of FIG. 9a. The electronic device (901) can identify the device with the largest SNR value (e.g., first value) (e.g., first external electronic device (902)) as the device to be woken up. Meanwhile, the electronic device (901) can identify the device to be woken up based on information regarding the priority of multiple external electronic devices (902, 903, 904) as well as the relationship between the magnitudes of the SNR values, and the priority of the multiple external electronic devices (902, 903, 904) can be changed based on information obtained and / or accumulated from the operation of identifying the device to be woken up previously performed by the electronic device (901), which is described later in FIGS. 16 to 18.

[0116] According to various embodiments, the electronic device may transmit result information obtained as a result of performing an operation to identify a device to be woken up to a plurality of external electronic devices (e.g., a first external electronic device (902), a second external electronic device, and a third external electronic device (904)) in each of the 809, 810, and 811 operations. For example, the result information may include information for identifying a device to be woken up. Accordingly, the plurality of external electronic devices identify a device to be woken up based on the result information, and the external electronic device identified as a device to be woken up (e.g., the first external electronic device (902)) may be woken up to process user utterances for control. Additionally, the remaining devices not identified as devices to be woken up (e.g., 903, 904) may terminate the execution of a program to provide an executed voice service or transition to a state where they do not process user utterances. The above-mentioned woke-up external electronic device (902) may provide information to indicate that it has been "woke up." For example, the first external electronic device (902) may display a message on a display indicating that it has been "woke up" or output a sound through a speaker indicating that it has been "woke up".

[0117] According to various embodiments, a woke-up external electronic device (e.g., a first external electronic device (902)) may provide an intelligent service (e.g., an intelligent voice service) together with the intelligent server (530) in an 812 operation. For example, the woke-up electronic device (e.g., 902) may receive a user utterance (e.g., "Turn up the volume") for controlling the woke-up electronic device (902) using a microphone, as shown in FIG. 9b, and transmit information (931) about the received user utterance to the intelligent server (530). The above-mentioned woke-up electronic device (e.g., 902) receives information (932) for providing a specific service obtained as a result of processing the user utterance from the intelligent server (530), and can perform at least one operation (e.g., increasing the volume) (or perform the function of the woke-up electronic device (e.g., 901)) based on the received information (932). The information (932) for providing a specific service may include a plan that includes a plurality of operations for performing a task corresponding to the user's voice input as described above, and a plurality of concepts related to the plurality of operations. Also, for example, the above-mentioned woke-up electronic device (e.g., 902) may receive information (932) for providing a specific service obtained as a result of processing the user utterance from the intelligent server (530), and can display a screen containing specific information or output sound through a speaker based on the received information (932).

[0118] As described above, the problem of two or more external electronic devices being woken up by user speech can be resolved by the electronic device set as the "main device (520)" selecting the optimal device among multiple other external electronic devices set as the "sub device (521)" as the device to be woken up. Accordingly, the operational burden of external electronic devices that are unnecessarily consumed can be reduced by terminating the voice service provision operation of the external electronic devices that are unnecessary for voice services among the two or more woke-up external electronic devices.

[0120] Hereinafter, other examples of the operation of an electronic device included in an IoT system according to various embodiments will be described.

[0121] According to various embodiments, when an electronic device configured as a "main device" receives information associated with a user utterance from a plurality of external electronic devices, it can identify the optimal device to be woken up among the plurality of external electronic devices based not only on the information associated with the user utterance but also on values ​​(e.g., time-out, priority) used in the operation of identifying the device to be woken up. For example, the values ​​may include information regarding a time interval (e.g., time-out) for processing information associated with the user utterance received from the plurality of external electronic devices, or information regarding the priority of the plurality of external electronic devices to be selected as the device to be woken up. Additionally, the electronic device may set the values ​​based on information obtained from a previously performed operation of identifying the device to be woken up, so that the optimal electronic device is identified as the device to be woken up within an environment equipped with an IoT system.

[0122] FIG. 10 is a flowchart (1000) for illustrating an example of the operation of an electronic device according to various embodiments. According to various embodiments, the operations illustrated in FIG. 10 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 10, or at least one fewer operation may be performed. FIG. 10 will be described below with reference to FIG. 11 and FIG. 12.

[0123] FIG. 11 is a diagram illustrating an example of an operation to identify a device to be woken up of an electronic device set as a "main device" according to various embodiments. FIG. 12 is a diagram illustrating an example of an operation to process information associated with a user utterance of an electronic device set as a "main device" according to various embodiments.

[0124] According to various embodiments, an electronic device (e.g., 1101) may establish communication connections with a plurality of external electronic devices (e.g., 1102, 1103, 1104) to provide intelligent voice services in a 1001 operation. For example, an electronic device (1101) set as the "main device" may establish communication connections with other external electronic devices (1102, 1103, 1104) provided within a work environment (e.g., home) as illustrated in FIG. 11. Since the 1001 operation of the electronic device (1101) can be performed in the same way as the 801 operation of the electronic device (1101) described above, a redundant description is omitted.

[0125] According to various embodiments, an electronic device (e.g., 1101) may receive at least one piece of information associated with a user utterance including a specific word for wake-up (e.g., a wake-up word) from at least some of the plurality of external electronic devices (e.g., 1102, 1103, 1104) in operation 1002. For example, as illustrated in FIG. 11, when a user performs an utterance of a specific word (e.g., a wake-up utterance), the electronic device (1101) may receive information associated with the user utterance (e.g., information about the intensity of the user utterance) obtained by the other external electronic devices (1102, 1103, 1104) from the other external electronic devices (1102, 1103, 1104) based on the communication connection. The 1002 operation of the above electronic device (1101) can be performed in the same way as the 805 to 807 operations of the above electronic device (1101), so a redundant description is omitted.

[0126] According to various embodiments, an electronic device (e.g., 1101) can identify a device to be woken up among at least some of the plurality of external electronic devices (e.g., 1102, 1103, 1104) based on at least one piece of information in operation 1003 and a value set based on information obtained in each of the previously performed operations to identify the device to be woken up. For example, the value may include information about a designated time interval (e.g., time-out) for identifying the device to be woken up by processing information associated with user utterances received from the plurality of external electronic devices (1102, 1103, 1104), and information about the priority of the device to be woken up among the plurality of external electronic devices (1102, 1103, 1104). Below, an operation to identify the device to be woken up of the electronic device (1101) based on information about each time interval or information about priority is described.

[0127] First, an example of an operation to identify a device to be woken up based on a designated time interval for processing information associated with a user utterance received from a plurality of external electronic devices (1102, 1103, 1104) of an electronic device (1101) is described below.

[0128] According to various embodiments, the electronic device (1101) can identify a device to be woken up by processing at least one piece of information (e.g., 1201, 1202, 1203) received during a specified time-out period among information related to a user utterance received from external electronic devices (1102, 1103, 1104). For example, as illustrated in FIG. 12, the electronic device (1101) can receive information related to a user utterance from a plurality of external electronic devices (1102, 1103, 1104) during a session from the time it first receives information related to a user utterance (e.g., 1201) from one of the plurality of external electronic devices (1102, 1103, 1104) (e.g., the first external electronic device (1102)). For example, an electronic device (1101) receives a user utterance and, based on a program for providing voice services from the time the user utterance is received, can receive information associated with the user utterance from a plurality of external electronic devices (1102, 1103, 1104) during a session. The session refers to the time for processing a user utterance, and information received after the session may be identified as information associated with a user utterance other than the user utterance. Since the session is as described in detail in FIGS. 8 and 9, a redundant description is omitted.The above session may include a first time-out period in which, when information associated with a user utterance is received from an external electronic device (1101) as illustrated in FIG. 12, the electronic device (1101) is configured to process the information (e.g., identify SNR values ​​and compare the magnitudes of the SNR values) to identify the device to be woken up, and a second time-out period in which, when information associated with a user utterance is received from an external electronic device (1101), the electronic device (1101) is configured not to process the information. The electronic device (1101) can perform an operation to identify a device to be woken up based on information (1201, 1202, 1203) (e.g., SNR value) associated with user utterances from external electronic devices (1102, 1103, 1104) (e.g., first external electronic device (1102) and second external electronic device (1103)) received during a first time-out period as illustrated in FIG. 12. Here, the first information (1201) may be received from the first external electronic device (1102), the second information (1202) may be received from the second external electronic device (1103), and the third information (1203) may be received from the third external electronic device (1104). The electronic device (1101) identifies external electronic devices (1102, 1103, 1104) corresponding to information (1201, 1202, 1203) received during a first time-out as a candidate group of devices to be woken up by user speech, and can identify a device to be woken up among the external electronic devices (1102, 1103, 1104) included in the candidate group based on each piece of information. The electronic device (1101) can transmit information resulting from the operation of identifying the device to be woken up to the external electronic devices (1102, 1103, 1104).A plurality of external electronic devices (1102, 1103, 1104) execute a program to provide voice services from the time they receive a user utterance, and as shown in FIG. 12, the state of an external electronic device (1101) (e.g., device state) can be set to an idle state for receiving result information. When the plurality of external electronic devices (1102, 1103, 1104) receive result information, the external electronic device to be woken up (e.g., the first external electronic device (1102)) switches from the idle state to a listening state to receive a user utterance for control and to provide voice recognition services, and the remaining external electronic device (1101) can terminate the execution of the program.

[0129] According to various embodiments, the electronic device (1101) may pre-set and store information regarding a time interval and, based on the information regarding the time interval, initiate and / or set up the aforementioned session to perform an operation to identify a device to be woken up. The information regarding the time interval may include at least one of information indicating the length of a session, information indicating the length of a first time interval (time-out) included in the session, or information indicating the length of a second time interval (guard time). Without being limited to what is described, the information regarding the length of the time interval may also indicate information regarding the length of a session and the ratio of the first time interval (time-out) and the second time interval (guard time) during the session.

[0130] At this time, the electronic device (1101) set as the "main device" can dynamically change the length of the first time-out as shown in FIG. 12. The time at which information (1201, 1202, 1203) is received from a plurality of external electronic devices (1102, 1103, 1104) by the electronic device (1101) set as the main device may vary depending on the state of communication connection between the electronic device (1101) and the plurality of external electronic devices (1102, 1103, 1104) or the performance (e.g., communication performance) of the external electronic device (1101). For example, if the communication connection status is poor and / or congested, or if the performance of the external electronic devices (1102, 1103, 1104) is significant, information may be received from the external electronic devices (1102, 1103, 1104) to the electronic device (1101) after the first time-out. Accordingly, the electronic device (1101) may set and / or change and store information regarding the length of the first time-out based on the time when information regarding user utterance was received from the external electronic devices (1102, 1103, 1104) during a previous session (e.g., a session prior to the current session or a session prior to the current time). For example, the electronic device (1101) may extend or shorten the length of the existing first time-out based on the time when information regarding user utterance is received from external electronic devices (1102, 1103, 1104) during the previous session. In other words, the current first time-out for the electronic device (1101) to identify the device to be woken up may be set by changing the existing first time-out. Meanwhile, the first time-out when the electronic device (1101) first performs the operation of identifying the device to be woken up may be a value pre-set in the electronic device (1101).Specific examples of operations for changing the length of the first time-out of the electronic device (1101) are described later in FIGS. 13 to 15. At this time, if the length of the session is maintained, the second guard time may be automatically changed to the remaining time length other than the length of the first time-out set. Alternatively, if the length of the session is variable, the length of the second guard time may be maintained, and the length of the session may be changed by the amount by which the length of the first time-out has been changed.

[0131] Depending on the dynamic change of the above time-out, the number of candidate devices to identify the device to be woken up may be appropriately controlled, or the timing of switching the idle state of the external electronic device (1101) to a listening state may be appropriately controlled.

[0132] Below, an example of an operation to identify a device to be woken up based on a designated time interval for processing information associated with a user utterance received from a plurality of external electronic devices (1102, 1103, 1104) of an electronic device (1101) is described.

[0133] According to various embodiments, the electronic device (1101) can identify a device to be woken up among a plurality of external electronic devices (1102, 1103, 1104) based on information about user utterances received from external electronic devices (1102, 1103, 1104) as well as information about the priority of each of the external electronic devices (1102, 1103, 1104) (e.g., a fourth value, a fifth value, a sixth value). For example, the electronic device (1101) can receive a high-intensity user utterance among the plurality of external electronic devices (1102, 1103, 1104) and identify the external electronic device (1101) having a high priority as the device to be woken up. For example, an electronic device (1101) may identify information regarding SNR values ​​of a user utterance (e.g., a first value, a second value, and a third value) from external electronic devices (1102, 1103, 1104) (e.g., a first external electronic device (1102), a second external electronic device (1103), and a third external electronic device (1104)) as shown in 1111 of FIG. 11, and perform an operation to compare the magnitudes of the SNR values ​​as shown in 1112 of FIG. 11. At this time, the SNR values ​​of the user utterance (e.g., a first value, a second value, and a third value) may be values ​​received during the first time-out period described above. The electronic device (1101) can identify the highest SNR value (e.g., a first value) and an SNR value similar to the highest SNR value (e.g., a second value) based on the comparison result of the SNR values, as shown in 1113 of FIG. 11. The meaning that the one value and the other value are similar may mean that the one value is a value that falls within a specified range (e.g., within a specific ratio of the other value) from the other value.The electronic device (1101) can identify external electronic devices (1102, 1103, 1104) (e.g., first external electronic device (1102) and second external electronic device (1103)) corresponding to the identified similar SNR values ​​(e.g., first value, second value), and can identify priorities (e.g., fourth value, fifth value) corresponding to (or set) the identified external electronic devices. Based on the identification of the priorities, the electronic device (1101) can identify the external electronic device (e.g., first external electronic device (1102)) having the higher (or highest) priority (e.g., fourth value) among the identified external electronic devices (1102, 1103, 1104) as the device to be woken up, as illustrated in 1114 of FIG. 11. Meanwhile, if the electronic device (1101) does not have an SNR value similar to the highest SNR value, it can identify an external electronic device corresponding to the highest SNR value (e.g., a first external electronic device (1102)) as the device to be woken up.

[0134] According to various embodiments, an electronic device (1101) set as a "main device" may pre-set and store information regarding the priority of a plurality of external electronic devices (1102, 1103, 1104), and perform an operation to identify a device to be woken up based on the information regarding the priority.

[0135] First, the electronic device (1101) may initially receive information regarding the priority set for each of the multiple external electronic devices (1102, 1103, 1104) and store the received information regarding the priority. For example, the electronic device (1101) may receive information regarding the priority for the external electronic device (1101) from an external server (e.g., an intelligent server (530)). For another example, the electronic device (1101) may receive information regarding the priority set for the external electronic device (1101) from each of the external electronic devices (1102, 1103, 1104). For another example, the electronic device (1101) may already store the information regarding the priority for the external electronic devices (1102, 1103, 1104) without needing to receive it.

[0136] At this time, the electronic device (1101) set as the "main device" can change the priorities for a plurality of external electronic devices (1102, 1103, 1104) to control the optimal device that meets the user's intention to wake up. For example, the electronic device (1101) can change the priorities for a plurality of external electronic devices (1102, 1103, 1104) based on information that the external electronic device (1101) was selected as the wake-up device during previous sessions (e.g., the current session or sessions prior to the current point in time). In other words, the priorities (e.g., the 4th value, the 5th value, the 6th value) of the current plurality of external electronic devices (1102, 1103, 1104) for the electronic device (1101) to identify the device to be woken up may be set by changing the existing priorities. Specific examples of operations for changing the priorities of external electronic devices (1102, 1103, 1104) of the electronic device (1101) are described later in FIGS. 16 to 18.

[0138] Hereinafter, another example of the operation of an electronic device included in an IoT system according to various embodiments is described.

[0139] According to various embodiments, an electronic device (e.g., 1410) set as the “main device” may change a time interval (e.g., time-out) for identifying the device to be woken up based on the time of receiving information (e.g., information associated with user utterance) received during a session.

[0140] FIG. 13 is a flowchart (1300) for illustrating an example of the operation of an electronic device according to various embodiments. According to various embodiments, the operations illustrated in FIG. 13 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 13, or at least one fewer operation may be performed. FIG. 13 will be described below with reference to FIG. 14 and FIG. 15.

[0141] FIG. 14 is a drawing for illustrating an example of an operation to extend a specified time interval of an electronic device according to various embodiments. FIG. 15 is a drawing for illustrating an example of an operation to shorten a specified time interval of an electronic device according to various embodiments.

[0142] According to various embodiments, an electronic device (e.g., 1410) may establish communication connections with a plurality of external electronic devices to provide intelligent voice services in operation 1301, and may receive information associated with a user utterance containing a specific word from at least some of the external electronic devices in operation 1302. For example, an electronic device (1410) set as a “main device” may establish communication connections with other external electronic devices provided within a work environment (e.g., home). When a user utters a specific word (e.g., a wake-up word) within the work environment (e.g., a wake-up utterance), the electronic device (1410) may receive information associated with the user utterance (e.g., information about the intensity of the user utterance) obtained by the other external electronic devices from the other external electronic devices based on the communication connections. Since the 1301 to 1302 operations of the electronic device (1410) described above can be performed in the same way as the 801 operation of the electronic device (1410) and the 805 to 807 operations of the electronic device (1410) described above, a redundant description is omitted.

[0143] According to various embodiments, an electronic device (e.g., 1410) may identify a device to be woken up among at least some of a plurality of external electronic devices based on at least one first piece of information received during a time interval for identifying a device to be woken up in operation 1303. For example, the electronic device (1410) may execute and / or run a program to provide an intelligent voice service when it receives a user utterance containing a specific word through a microphone, as illustrated in FIG. 14 and FIG. 15. Based on information regarding the time interval, the electronic device (1410) may establish and / or start a session from the time when information associated with the user utterance (e.g., 1401 in FIG. 14, or 1501 in FIG. 15) is first received from an external electronic device or from the time when said user utterance is received, and may receive information associated with the user utterance (e.g., information about SNR values) from other external electronic devices during the established session. The electronic device (1410) can identify the device to be woken up based on information associated with a user utterance received during a designated first time interval (e.g., time-out) of the session. For example, the electronic device (1410) can identify the device to be woken up based on the result of comparing the relative magnitudes of SNR values ​​(e.g., identifying the external electronic device corresponding to the highest SNR value (e.g., the one that transmitted the information) as the device to be woken up). Also, for example, the electronic device (1410) can identify the device to be woken up based on the priority of the external electronic devices when similar SNR values ​​are identified. Since the 1303 operation of the electronic device (1410) can be performed as described in the 808 operation of the electronic device (1410) and the 1003 operation of the electronic device (1410) described above, a redundant description is omitted.

[0144] According to various embodiments, an electronic device (e.g., 1410) can identify whether information (e.g., information associated with a user utterance) has been received after a time interval (e.g., time-out) in operation 1304. The electronic device (1410) can identify whether information associated with a user utterance has been received from at least some of a plurality of external electronic devices during the remaining time interval (e.g., guard time) after a designated time interval (e.g., time-out) of a session. For example, the electronic device (1410) can identify whether the identified time is included in the remaining time interval (guard time) after the designated time interval (time-out, guard time) by comparing the time when information (e.g., 1401, 1402, 1403, 1501, 1502, 1503) is received from a plurality of external electronic devices with the time intervals of the time intervals (time-out, guard time). The electronic device (1410) can calculate a first time period from the time when the session is initiated until a first time period after a designated time-out, and can identify a second time period from the first time period until a second time period after a remaining guard-time. The electronic device (1410) can identify a time when information (e.g., 1401, 1402, 1403, 1501, 1502, 1503) is received from a plurality of external electronic devices, and can identify whether the identified time is included in the first time period or the second time period. For example, the electronic device (1410) can identify in real time when information (e.g., 1401, 1402, 1403, 1501, 1502, 1503) is received from a plurality of external electronic devices, and can identify whether the identified time is included in the remaining time interval after a specified time interval. For example, the electronic device (1410) can identify the passage of time by setting a timer from the time when the session is initiated (e.g., the time when a user utterance is received).The electronic device (1410) can identify the time at which information is received when information is received from an external electronic device while identifying the passage of time, and can identify a time interval (e.g., time-out, or guard time) that includes the identified time. Meanwhile, not limited to what is described, the electronic device (1410) may identify the time at which information is transmitted from a plurality of external electronic devices instead of the time at which each piece of information is received by the electronic device (1410), and identify whether the identified transmission time is included in the time interval.

[0145] According to various embodiments, an electronic device (e.g., 1410) may identify a first modified time interval (e.g., a time interval longer than the time-out) based on the time of reception of the information received after the time interval in operation 1305 when information is received after the time interval (e.g., time-out). For example, the electronic device (1410) may identify a first length of the first time interval (time-out) such that the time of reception of the information (1403) received during a second time interval (guard-time) after the first time interval (time-out), as illustrated in FIG. 14, is included. For example, the electronic device (1410) may identify a point in time after a first time-out has elapsed from the point in time when the session is initiated (e.g., when a user utterance is received), calculate the difference from the identified point in time to the point in time when information (1403) is received during the second time-out (guard time), and identify a new first time-out by adding the calculated difference to the current first time-out (e.g., time-out). For another example, the electronic device (1410) may identify the length of time from the point in time when the session is initiated (e.g., when a user utterance is received) to the point in time when the information (1403) is received as the first time-out to be changed (e.g., time-out). At this time, the electronic device (1410) may identify the time length obtained by adding a predetermined time length to the identified time length as the first time out to be changed, thereby ensuring that the time of receiving the information (1403) is included in the first time out even if the reception of the information is delayed. If there are multiple pieces of information received during the second guard time after the first time out, the electronic device (1410) may identify the first time out to be changed based on the time of receiving the latest information among the information received during the second guard time.Alternatively, the electronic device (1410) may calculate a designated time based on the reception times of information received during the second guard time, and change the guard time based on the calculated time. The calculated time may include a time that is the average of the reception times, the latest received time among the remaining times of the reception times excluding the upper or lower times of the designated ratio, and a time that is the average of the remaining times.

[0146] According to various embodiments, the electronic device (1410) may perform an operation of identifying a first change time interval based on the time of reception of information (e.g., 1403) received after the time-out when a specified condition is satisfied. In other words, the electronic device (1410) may identify the times of reception of information identified as satisfying a specified condition among the information received after the time-out, and perform an operation of identifying a first change time interval based on the identified times of reception.

[0147] For example, the satisfaction of the specified condition may include identifying an external electronic device corresponding to information received after the time-out (e.g., 1403) as the device to be woken up. The electronic device (1410) may identify information received during the first time-out (e.g., time-out) as well as information received during the second time-out (e.g., guard-time), and identify the device to be woken up based on said information. Unlike the operation in which the electronic device (1410) controls the identified device to be woken up after identifying the device to be woken up in the 1303 operation, the electronic device (1410) may not control the identified device to be woken up after the operation in which the device to be woken up is identified based on said information (e.g., 1403). The electronic device (1410) can identify, based on the result of the operation of identifying the device to be woken up, that an external electronic device corresponding to the information received during the second guard time is identified as the device to be woken up (e.g., when the SNR value of the external electronic device is highest). Based on the identification result, the electronic device (1410) can perform an operation to change the length of the first guard time (e.g., time-out) described above based on the time of receiving the information. If the external electronic device corresponding to the information received during the second guard time is not identified as the device to be woken up, the electronic device (1410) may not perform an operation to change the length of the first guard time. If the number of pieces of information received during the second time interval is multiple, the electronic device (1410) may identify the information among the multiple pieces of information that is identified as the device to be woken up and perform an operation to change the length of the first time interval (e.g., time-out) based on the time of reception of the identified information.

[0148] For example, the satisfaction of the specified condition may include identifying a location (e.g., living room) associated with information received after the specified time interval (e.g., time-out) and a location (e.g., living room) associated with information received during the specified time interval. The control operation based on the location is described later in FIGS. 19 and 20.

[0149] According to various embodiments, if information is not received after a time interval (e.g., time-out), an electronic device (e.g., 1410) may identify a second modified time interval (e.g., a time interval shorter than the time-out) based on the time of receipt of information received within the time interval in the 1306 operation. For example, the electronic device (1410) may perform an operation to change the length of the first time interval (time-out) based on the latest time of receipt (e.g., the time of receipt of information (1503)) among the times of receipt of information (1501, 1502, 1503) received during the first time interval (time-out) as illustrated in FIG. 15. For example, the electronic device (1410) may change the length of the first time-out to the time length from when the session is initiated (e.g., when a user utterance is received) to the latest time of receipt (e.g., when information (1503) is received). At this time, the electronic device (1410) may change the length of the first time-out by adding a predetermined time length to the time length from when the session is initiated (e.g., when a user utterance is received) to the latest time of receipt (e.g., when information (1503) is received), so that even if the reception of information is delayed, the time of receipt of information is included in the first time-out.

[0150] According to various embodiments, the electronic device (1410) may perform a time-out change operation based on the time of reception of information received during the time-out (e.g., the time of reception of information (1503)) when a specified condition is satisfied. For example, the satisfaction of the specified condition may include identifying a location (e.g., a living room) associated with the latest information received among the information received during the specified time-out (e.g., time-out) as corresponding to a location (e.g., a living room) associated with other information. The adjustment operation based on the location is described later in FIGS. 19 and 20.

[0151] According to various embodiments, an electronic device (e.g., 1410) may change a time interval (e.g., time-out) based on a first change time interval or a second change time interval in operation 1307. For example, the electronic device (1410) may change and / or set and store the currently set time interval to the length of the time interval to be changed in response to identifying the length of the time interval to be changed in each of the 1305 operation and the 1306 operation. Also, for example, but not limited to as described, the electronic device (1410) may perform the operation to identify the time interval (1305 operation and 1306 operation) a specified number of times (e.g., 100 times) and change the time interval based on the time lengths identified based on the time interval identification operations performed a specified number of times. For example, the electronic device (1410) can calculate the average value of the time lengths and change the first time-out based on the calculated average value. At this time, the electronic device (1410) may identify the remaining time lengths excluding the upper or lower time lengths of a specified ratio among the time lengths and calculate the average value of the remaining time lengths.

[0153] Hereinafter, another example of the operation of an electronic device included in an IoT system according to various embodiments is described.

[0154] According to various embodiments, an electronic device set as a “main device” (e.g., 1711) may change the priority of at least some of a plurality of external electronic devices (e.g., 1712, 1713) based on information about the finally identified device to be woken up, as a result of performing an operation to identify the device to be woken up.

[0155] FIG. 16 is a flowchart (1600) for illustrating an example of the operation of an electronic device according to various embodiments. According to various embodiments, the operations illustrated in FIG. 16 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 16, or at least one fewer operation may be performed. FIG. 16 will be described below with reference to FIG. 17 and FIG. 18.

[0156] FIG. 17 is a diagram illustrating an example of an operation for identifying a device to be finally woken up of an electronic device according to various embodiments. FIG. 18 is a diagram illustrating an example of an operation for changing the priority of a plurality of external electronic devices of an electronic device according to various embodiments.

[0157] According to various embodiments, an electronic device (e.g., 1711) may establish communication connections with a plurality of external electronic devices (e.g., 1712, 1713) to provide intelligent voice services in operation 1601, and may receive information associated with a user utterance containing a specific word from at least some of the plurality of external electronic devices in operation 1602. For example, an electronic device (1711) set as the "main device" may establish communication connections with other external electronic devices (1712, 1713) provided within a work environment (e.g., home), as illustrated in 1701 of FIG. 17. When a user utters a specific word (e.g., a first user utterance) within a work environment, the electronic device (1711) may receive information associated with the user utterance (e.g., information about the intensity of the user utterance) obtained by other external electronic devices (1712, 1713) from other external electronic devices (1712, 1713) based on the communication connection. Since the 1601 and 1602 operations of the electronic device (1711) can be performed in the same way as the 801 operation of the electronic device (1711) and the 805 and 807 operations of the electronic device (1711) described above, a redundant description is omitted.

[0158] According to various embodiments, an electronic device (e.g., 1711) may identify a first external electronic device (e.g., 1712) among a plurality of external electronic devices as the device to be woken up based on at least one piece of information received in operation 1603 and information regarding the priority of a plurality of external electronic devices (e.g., 1712, 1713). For example, as illustrated in 1701 of FIG. 17, the electronic device (1711) may identify a device among a plurality of external electronic devices (1712, 1713) as the device to be woken up based on a plurality of SNR values ​​(e.g., 170 dB, 160 dB) received from a plurality of external electronic devices (1712, 1713) and the priority of the plurality of external electronic devices (e.g., 0.8, 0.7). At this time, the received SNR values ​​may be values ​​received during a specified time interval (e.g., time-out) of a session. For example, the electronic device (1711) may identify the highest SNR value (e.g., a first value) based on the result of comparing multiple SNR values ​​and identify the external electronic device (1711) (e.g., a first external electronic device (1712)) having the identified highest SNR value as the device to be woken up. For another example, the electronic device (1711) may identify an SNR value (e.g., 160 dB) similar to the highest SNR value (e.g., 170 dB) based on the result of comparing multiple SNR values ​​and identify external electronic devices (1712, 1713) (e.g., a first external electronic device (1712) and a second external electronic device (1713)) corresponding to the identified similar SNR values. The electronic device (1711) can identify priorities (e.g., 0.8, 0.7) corresponding to (or set) the identified external electronic devices (1712, 1713), and identify the external electronic device (1711) (e.g., the first external electronic device (1712)) having a higher priority (e.g., 0.8) as the device to be woken up.Since the 1603 operation of the electronic device (1711) can be performed as described in the 808 operation of the electronic device (1711) and the 1003 operation of the electronic device (1711) described above, a redundant description is omitted.

[0159] According to various embodiments, an electronic device (e.g., 1711) can identify whether the device to be woken up is re-selected in operation 1604. For example, after the electronic device (1711) controls a specific external electronic device (1711) to be woken up in operation 1603, it can re-identify another external electronic device (1711) as the device to be woken up. Examples of operations for re-identifying another external electronic device (1711) of the electronic device (1711) as the device to be woken up are described below.

[0160] For example, the electronic device (1711) may re-identify another external electronic device (e.g., 1713) as the device to be woken up based on receiving a second user utterance different from the first user utterance. As an example, as illustrated in 1702 of FIG. 17, the user may move from an existing location (e.g., a location far from the second external electronic device (1713)) to a location adjacent to the other external electronic device (1711) (e.g., the second external electronic device (1713)) and utter a specific word (e.g., a starter word) (e.g., the second user utterance). Based on receiving the second user utterance, the electronic device (1711) may perform the operation of re-identifying the device to be woken up by initiating a session different from the session initiated based on receiving the first user utterance. As illustrated in 1702 of FIG. 17, the electronic device (1711) can perform an operation of comparing SNR values ​​received during a specified time interval (e.g., time-out) of another session to re-identify the second external electronic device (1713) having the highest SNR value (e.g., 220 dB) as the device to be woken up. At this time, the electronic device (1711) can identify the time difference between the one session and the other session (or the time difference between the time when the device to be woken up was first identified and the time when the other external electronic device (1711) was re-identified, or the time difference between the time when the first user utterance was received and the time when the second user utterance was received), and if the identified time difference is less than or equal to a preset value, it can perform an operation (1721, e.g., changing 0.7 to 0.9) to change the priority of the external electronic devices (1712, 1713). Not limited to what is described, the electronic device (1711) can perform an operation to change the priority of external electronic devices (1712, 1713) without identifying the time difference between one session and another session.

[0161] For example, the electronic device (1711) may re-identify another external electronic device (e.g., 1713) as the device to be woken up based on the user's action of inputting another external electronic device (e.g., 1713) as the device to be woken up. For example, the other external electronic device (1713) may receive user input to wake up (e.g., receive input to select as the device to be woken up on an interface provided on the device's display), and the electronic device (1711) may receive a message or signal from the other external electronic device (1711) indicating that the other external electronic device (1713) is woken up. For another example, the electronic device (1711) may receive user input directly from the user to wake up the other external electronic device (1713) (e.g., receive input to select as the device to be woken up on an interface provided on the display of the electronic device (1711). As another example, the user wakes up another external electronic device (1713) through the user terminal, and the electronic device (1711) can receive a message or signal from the user terminal and / or intelligent server (530) indicating that the other external electronic device (1711) has been woken up.

[0162] According to various embodiments, the electronic device (1711) may change the priority of the second external electronic device (1713) re-identified as the device to be woken up in operation 1605 when the external electronic device (1711) is identified as being re-selected. For example, the electronic device (1711) may set the priority of the second external electronic device (1713) re-identified as the device to be woken up higher, as illustrated in 1702 of FIG. 17. For example, the electronic device (1711) may set the priority of the second external electronic device (1713) higher than the priority of the first external electronic device (1712) initially identified as the device to be woken up. Accordingly, as illustrated in FIG. 18, even if the electronic device (1711) is fired from the original location (e.g., a distance from the second external electronic device (1713)), the electronic device (1711) may identify the second external electronic device (1713) rather than the first external electronic device (1712) as the device to be woken up based on the fact that the priority of the second external electronic device (1713) (e.g., 0.9) is higher than the priority of the first external electronic device (1712) (e.g., 0.8).

[0164] Hereinafter, another example of the operation of an electronic device included in an IoT system according to various embodiments is described.

[0165] According to various embodiments, an electronic device set as a “main device” (e.g., 2010) can set values ​​(e.g., time-out, priority) used in an operation to identify a device to be woken up based on information about the location of other external electronic devices set as “sub devices” (e.g., 2013, 2014, 2015, 2016).

[0166] FIG. 19 is a flowchart (1900) for illustrating an example of the operation of an electronic device according to various embodiments. According to various embodiments, the operations illustrated in FIG. 19 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 19, or at least one fewer operation may be performed. FIG. 19 will be described below with reference to FIG. 20a and FIG. 20b.

[0167] FIG. 20a is a diagram illustrating an example of an operation to generate an artificial intelligence model based on various information accumulated when performing an operation to identify a device to be woken up of an electronic device according to various embodiments. FIG. 20b is a diagram illustrating an example of an operation to identify a device to be woken up based on a generated artificial intelligence model of an electronic device according to various embodiments.

[0168] According to various embodiments, an electronic device (e.g., 2010) may establish a communication connection with a plurality of external electronic devices (e.g., 2013, 2014, 2015, 2016) for providing intelligent voice services in operation 1901, and may receive at least one piece of information associated with a user utterance including a specific word for wake-up from at least some of the plurality of external electronic devices (2013, 2014, 2015, 2016) in operation 1902. For example, an electronic device (2010) set as a "main device" may establish a communication connection with other external electronic devices (2013, 2014, 2015, 2016) provided within an environment (e.g., a home) illustrated in FIGS. 20a and 20b. When a user (e.g., 2011) utters a specific word (e.g., a trigger word) (e.g., a first user utterance) within a work environment, the electronic device (2010) may receive information related to the user utterance (e.g., information about the intensity of the user utterance) obtained by other external electronic devices (2013, 2014, 2015, 2016) from other external electronic devices (2013, 2014, 2015, 2016) based on the communication connection. Since the 1901 and 1902 operations of the electronic device (2010) can be performed in the same way as the 801 operation of the electronic device (2010) and the 805 and 807 operations of the electronic device (2010) described above, a redundant description is omitted.

[0169] According to various embodiments, an electronic device (e.g., 2010) may identify information regarding the location of at least some of the plurality of external electronic devices (e.g., 2013, 2014, 2015, 2016) in operation 1903, and in operation 1904, set at least one of information regarding time intervals or information regarding priorities based on the information regarding the identified location. For example, as described above in FIG. 5b, the external electronic devices (2013, 2014, 2015, 2016) may be registered by location within the environment (e.g., room (2012), kitchen (2021), living room (2022)). When the electronic device (2010) receives information associated with a user utterance from at least some of the external electronic devices (2013, 2014, 2015, 2016), it can identify the locations of at least some of the external electronic devices (2013, 2014, 2015, 2016) based on the locations where the external electronic devices (2013, 2014, 2015, 2016) are registered. Below, examples of operations for setting values ​​(e.g., timeout, priority) based on information regarding the locations of the electronic device (2010) are described.

[0170] According to various embodiments, the electronic device (2010) can set and manage values ​​(e.g., time-out, priority) for each location within the environment (e.g., room (2012), kitchen (2021), living room (2022)). For example, the electronic device (2010) can set information regarding time-out and priority for each specific location. For example, as illustrated in 2001 of FIG. 20a, when a user (2011) performs a wake-up utterance at a specific location within the environment (e.g., room (2012)), the electronic device (2010) can receive information associated with the user utterance (e.g., wake-up utterance) from at least one external electronic device (2013) located at the specific location (e.g., room (2012)). External electronic devices (2014, 2015, 2016) located in other locations within the environment (e.g., kitchen (2021), living room (2022)) may not receive user utterances or may receive user utterances of a strength below a threshold, and thus may not transmit information associated with user utterances to the electronic device (2010) set as the “main device.” The electronic device (2010) may perform an operation to identify the device to be woken up based on receiving information associated with the utterance of the user (2011) from at least one external electronic device (2012) located in a specific location (e.g., room (2012)). While performing the operation of identifying a device to be woken up, the electronic device (2010) acquires at least one of information regarding the timing of reception of information received during a session as described in FIGS. 13 to 15 or information regarding a device re-identified as a device to be woken up as described in FIGS. 16 to 18, and can set and / or change at least one of a time-out or priority based on the acquired information. Since the operation of setting and / or changing at least one of the time-out or priority of the electronic device (2010) can be performed as described in FIGS. 13 to 18, a redundant description is omitted.The electronic device (2010) can store and manage information regarding a set time-out or a set priority associated with the specific location (e.g., room (2012)). Subsequently, when the electronic device (2010) receives information associated with a user utterance from at least one external electronic device (2010) registered with the specific location (e.g., room (2012)), it can perform an operation to identify a device to be woken up based on the information regarding the time-out and priority stored associated with the specific location (e.g., room (2012)). Also, for example, as shown in 2002 of FIG. 20a, when an electronic device (2010) receives information associated with a user utterance from external electronic devices (2014, 2015, 2016) located in at least two locations (e.g., kitchen (2021) and living room (2022)), it may set and / or change at least one of a time-out or priority and store it associated with said at least two locations (e.g., kitchen (2021) and living room (2022)).

[0171] As described above, since the electronic device (2010) manages priorities and timeouts for each location within the environment, when a user (2011) triggers a wake-up at different locations within the environment, an action can be performed to identify the optimal device to be woken up based on the timeout and priority suitable for the situation at each different location (e.g., external electronic devices (2013, 2014, 2015, 2016) provided at each location) (e.g., the timeout is not kept unnecessarily long).

[0172] Also, according to various embodiments, when an electronic device (2010) receives information from more than a preset number of external electronic devices (2014, 2015, 2016) as shown in 2051 to 2502 of FIG. 20b, it may perform an operation to set and / or change values ​​(e.g., time-out, priority). The preset number may be a certain proportion of the number of registered external electronic devices (2014, 2015, 2016).

[0174] Hereinafter, another example of the operation of an electronic device included in an IoT system according to various embodiments is described.

[0175] According to various embodiments, an electronic device (e.g., 2301) set as a "main device" accumulates various information while performing each of the operations to identify the device to be woken up, and can generate an artificial intelligence model based on the accumulated various information (e.g., status information of external electronic devices (e.g., 2302, 2303, 2304), information on the SNR of the external electronic devices, information on the initially selected device). The electronic device can input the various information obtained when performing the operation to identify the device to be woken up into the generated artificial intelligence model and identify the output external electronic device as the device to be woken up.

[0176] FIG. 21 is a flowchart (2100) for illustrating an example of the operation of an electronic device configured according to various embodiments. According to various embodiments, the operations illustrated in FIG. 21 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 21, or at least one fewer operation may be performed. FIG. 21 will be described below with reference to FIG. 22 and FIG. 23.

[0177] FIG. 22 is a diagram illustrating an example of an operation to generate an artificial intelligence model based on various information accumulated when performing an operation to identify a device to be woken up of an electronic device according to various embodiments. FIG. 23 is a diagram illustrating an example of an operation to identify a device to be woken up based on a generated artificial intelligence model of an electronic device according to various embodiments.

[0178] According to various embodiments, an electronic device (e.g., 2301 in FIG. 23) performs operations to identify a device to be woken up in operation 2101, and may store various information when performing each operation to identify a device to be woken up. For example, an electronic device set as a “main device” (e.g., 2301 in FIG. 23) may perform multiple operations to identify a device to be woken up based on receiving a user utterance containing a specific word, or receiving information associated with the user utterance from external electronic devices set as “sub devices” (e.g., 2032, 2303, 2304 in FIG. 23). The electronic device (e.g., 2301 in FIG. 23) may set up and / or initiate sessions to identify the device to be woken up and accumulate various information obtained during said sessions. For example, the various information may include information on the status of external electronic devices (e.g., 2032, 2303, 2304 of FIG. 23) as shown in 2201 of FIG. 22 (device-specific status information), information on the SNR value of external electronic devices (device-specific SNR information), information on the priority of external electronic devices (e.g., 2032, 2303, 2304 of FIG. 23) (not shown), information on an external electronic device identified as the device to be woken up initially (e.g., initial selection information), and information on an external electronic device identified as the device to be woken up finally after the device to be woken up initially has been identified (e.g., final selection information). For example, when performing an operation to identify a device to be woken up, an electronic device (e.g., 2301 of FIG. 23) may further receive information about the status of the external electronic devices, along with information associated with user utterance (e.g., information about SNR values) from each of the multiple external electronic devices (e.g., 2032, 2303, 2304 of FIG. 23).When an external electronic device receives a user utterance, it may identify information regarding the state of the external electronic device along with information associated with the user utterance based on the reception of the user utterance, and transmit the identified information to an electronic device (e.g., 2301 in FIG. 23). The information regarding the state may include information regarding the state of the external electronic device that is sensed and / or identifiable by type (e.g., TV, mobile phone, air conditioner, wearable watch, refrigerator, robot vacuum cleaner, speaker) of each external electronic device (e.g., 2032, 2303, 2304 in FIG. 23). For example, the information regarding the state may include information regarding the charging status, information regarding the application execution status (e.g., information indicating an application running in foreground mode), information regarding the current temperature, and information regarding the currently set mode, as illustrated in 2201 in FIG. 22. The information regarding the state is not limited to what is described and may include various types of information that are senseable by type of device.

[0179] According to various embodiments, an electronic device (e.g., 2301 in FIG. 23) can generate an artificial intelligence model by performing learning based on information accumulated in operation 2102. For example, the electronic device (e.g., 2301 in FIG. 23) can perform learning (e.g., machine learning, or deep learning) using the various information described above as training data based on an artificial intelligence learning algorithm (e.g., machine learning algorithm, deep learning algorithm) as shown in 2202 in FIG. 22. Since various types of machine learning or deep learning algorithms may be used as the artificial intelligence learning algorithm, in addition to artificial intelligence learning algorithms such as general ensemble algorithms, a description thereof is omitted. An electronic device (e.g., 2301 in FIG. 23) can perform learning by setting the final selection information (i.e., information about the external electronic device finally identified as the wake-up device) among the various information described above as the output data of the artificial intelligence model to be created, and the remaining information (e.g., information about the state of the external electronic devices (e.g., 2032, 2303, 2304 in FIG. 23) (state information), information about the SNR value of the external electronic device (SNR information), information about the priority of the external electronic devices (e.g., 2032, 2303, 2304 in FIG. 23) (priority information), and initial selection information) as the input data of the artificial intelligence model to be created.For example, an electronic device (e.g., 2301 in FIG. 23) can generate an artificial intelligence model (2231) (e.g., machine learning model, deep learning model) by performing an operation of assigning weights to external electronic devices (e.g., 2032, 2303, 2304 in FIG. 23) finally identified as wake-up devices set as output data, for each of the information set as input data (e.g., state information, SNR information, priority information, and initial selection information as shown in 2202 in FIG. 22). The generated artificial intelligence model (2231) can be configured to output the finally identified external electronic devices in response to receiving state information, SNR information, priority information, and initial selection information, as shown in 2203 in FIG. 22. The above-mentioned final identified external electronic device can be identified as a device to be woken up in the current session.

[0180] According to various embodiments, an electronic device (e.g., 2301 in FIG. 23) may perform an operation to identify a device to be woken up based on an artificial intelligence model generated in operation 2103. For example, when the electronic device (2301) receives a user utterance containing a specific word to initiate the provision of an intelligent voice service as illustrated in FIG. 23, it may establish and / or initiate a session and obtain status information (2311, 2312, 2313) along with information regarding the intensity (e.g., SNR value) of the user utterance from external electronic devices (2032, 2303, 2304) during the session. Additionally, the electronic device (2301 in FIG. 23) may identify information regarding the priority of the external electronic devices (2032, 2303, 2304) that transmitted information during the session. Additionally, an electronic device (e.g., 2301 in FIG. 23) can identify a device to be woken up (i.e., obtain initial selection information) based on SNR information or information regarding priority. The electronic device (e.g., 2301 in FIG. 23) can input the obtained state information, SNR information, information regarding priority, and initial selection information into a generated artificial intelligence model (2231), and obtain information regarding a final selected device (2304) output from the artificial intelligence model (2231). The electronic device (e.g., 2301 in FIG. 23) can identify the final selected device (2304) as a device to be woken up and control the device (2304) to be woken up (e.g., transmit result information indicating that the device (2304) is identified as a device to be woken up to the device (2304)).

[0181] Meanwhile, the artificial intelligence model (2231) may be generated to output information regarding priority or information regarding time-out, not limited to what is described. For example, an electronic device (e.g., 2301 in FIG. 23) may set information regarding priority or information regarding time-out among the accumulated information as output data, and perform learning by setting at least one of the remaining information excluding information regarding priority or information regarding time-out (e.g., at least one of status information, SNR information, initial selection information, or final selection information) as input data. The artificial intelligence model (2231) generated according to the performance of the learning may output information regarding priority or information regarding time-out in response to receiving at least one of status information, SNR information, initial selection information, or final selection information. An electronic device (e.g., 2301 in FIG. 23) can perform the operation of identifying a device to be woken up by setting a priority for each device with information about the priority that is output by an artificial intelligence model (2231) inputting information received during a session, or setting a time-out with information about the time-out that is output.

[0183] Hereinafter, another example of the operation of an electronic device included in an IoT system according to various embodiments is described.

[0184] According to various embodiments, an electronic device set as a “main device” (e.g., 2510) may update values ​​(e.g., time-out, and priority) used in an operation to identify the device to be woken up when a new device (e.g., 2521) is provided in the environment.

[0185] FIG. 24 is a flowchart (2400) for illustrating an example of the operation of an electronic device configured according to various embodiments. According to various embodiments, the operations illustrated in FIG. 24 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 24, or at least one fewer operation may be performed. FIG. 24 will be described below with reference to FIG. 25.

[0186] FIG. 25 is a diagram illustrating an example of an operation to generate an artificial intelligence model based on various information accumulated when performing an operation to identify a device to be woken up of an electronic device according to various embodiments.

[0187] According to various embodiments, an electronic device (e.g., 2510) may establish communication connections with a plurality of external electronic devices (e.g., 2511, 2512, 2513, 2514, 2515) to provide intelligent voice services in a 2401 operation. For example, the electronic device (2510), for example, the electronic device (2510) set as the "main device," may establish communication connections (e.g., establishing communication connections via a relay) with other external electronic devices (2511, 2512, 2513, 2514, 2515) provided within the work environment (e.g., home) shown in 2501 of FIG. 25. Since the 2401 operation of the electronic device (2510) can be performed in the same way as the 801 operation of the electronic device (2510), a redundant description is omitted.

[0188] According to various embodiments, an electronic device (e.g., 2510) may accumulate first information while performing an operation to wake up some of the plurality of external electronic devices (e.g., 2511, 2512, 2513, 2514, 2515) that have established the communication connection in the 2402 operation. For example, the electronic device (2510) may accumulate information obtained while performing an operation to identify the device to be woken up based on a user's wake-up utterance occurring in the environment. The above information may include the time of reception of information received from a plurality of external electronic devices (2511, 2512, 2513, 2514, 2515) during a session described in FIGS. 13 to 15, information about the external electronic device (2511, 2512, 2513, 2514, 2515) re-identified as the device to be woken up described in FIGS. 16 to 18, or various information described in FIGS. 21 to 23 (e.g., status information of the external electronic device (2511, 2512, 2513, 2514, 2515), SNR information, initial selection information, final selection information).

[0189] According to various embodiments, an electronic device (e.g., 2510) may set at least one of a time interval or a priority based on the accumulated first information in operation 2403. For example, the electronic device (2510) may set a time-out (e.g., extend or shorten) based on the time of receiving information received from a plurality of external electronic devices (2511, 2512, 2513, 2514, 2515) received during one session, as described in detail in FIGS. 13 to 15. Also, for example, the electronic device (2510) may change the priority of the re-identified external electronic devices (2511, 2512, 2513, 2514, 2515) based on information regarding the external electronic device re-identified as the device to be woken up, as described in detail in FIGS. 16 to 18. Also, for example, the electronic device (2510) may generate an artificial intelligence model as described in FIGS. 21 to 23 and set a time-out or priority based on the generated artificial intelligence model. Since the operation of the electronic device (2510) 2403 can be performed as described in FIGS. 13 to 15, FIGS. 16 to 18, and FIGS. 21 to 23, a redundant description is omitted.

[0190] According to various embodiments, an electronic device (e.g., 2510) may establish a communication connection with a first external electronic device (e.g., 2521) different from the plurality of external electronic devices (e.g., 2511, 2512, 2513, 2514, 2515) in operation 2404. For example, as illustrated in 2502 of FIG. 25, a new device (e.g., a first external electronic device (2521)) is provided within the environment, and the newly provided device may establish a communication connection (e.g., a communication connection via AP (540)) with other external electronic devices (2511, 2512, 2513, 2514, 2515) and be registered with an intelligent server (530). Based on the above registration, the electronic device (2510) set as the “main device” can identify information (e.g., identification information, and information about priority) regarding the registered first external electronic device (2521).

[0191] According to various embodiments, an electronic device (e.g., 2510) may store second information while performing an operation to wake up some of the plurality of external electronic devices (e.g., 2511, 2512, 2513, 2514, 2515) and the first external electronic device (e.g., 2521) in operation 2405. For example, when a user performs a wake-up utterance while the newly equipped device (e.g., the first external electronic device (2521)) is equipped, the electronic device (2510) may receive information associated with the user utterance (e.g., information about the intensity of the user utterance) from the newly equipped device (2521) and the existing external electronic devices (2511, 2512, 2513, 2514, 2515) and perform an operation to identify the device to be woken up. While performing the operation of identifying the device to be woken up, the electronic device (2510) can acquire the information described above (e.g., information about the time of reception described in FIGS. 13 to 15, information about the external electronic device re-identified as the device to be woken up described in FIGS. 15 to 18, and various accumulated information described in FIGS. 21 to 23).

[0192] According to various embodiments, the electronic device (2510) may reset at least one of the time interval or priority based on the stored second information in operation 2406. For example, the electronic device (2510) may shorten or extend a preset time-out based on the time of reception of information received from the newly equipped device (2321) as described in FIGS. 13 through 15. Also, for example, the electronic device (2510) may change the priority of the external electronic device (2511, 2512, 2513, 2514, 2515) if there is an external electronic device re-identified as a device to be woken up, as described in FIGS. 15 through 18. Also, for example, the electronic device (2510) may update information such as the state information and SNR information of the newly equipped device as described in FIGS. 21 to 23 with various information accumulated in advance, create a new artificial intelligence model based on the updated various information, and reset the time-out or priority based on the created model.

[0194] FIG. 26 is a block diagram of an electronic device (2601) in a network environment (2600) according to various embodiments. The description of the electronic device (2601) in the network environment (2600) described below may be applied to the description of electronic devices provided in the IOT system described above, so redundant descriptions are omitted.

[0195] Referring to FIG. 26, in a network environment (2600), an electronic device (2601) may communicate with an electronic device (2602) through a first network (2698) (e.g., a short-range wireless communication network) or with an electronic device (2604) or a server (2608) through a second network (2699) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (2601) may communicate with the electronic device (2604) through a server (2608). According to one embodiment, the electronic device (2601) may include a processor (2620), memory (2630), input device (2650), sound output device (2655), display device (2660), audio module (2670), sensor module (2676), interface (2677), haptic module (2679), camera module (2680), power management module (2688), battery (2689), communication module (2690), subscriber identification module (2696), or antenna module (2697). In some embodiments, at least one of these components (e.g., display device (2660) or camera module (2680)) may be omitted from the electronic device (2601), or one or more other components may be added. In some embodiments, some of these components may be implemented as a single integrated circuit. For example, a sensor module (2676) (e.g., fingerprint sensor, iris sensor, or light sensor) can be implemented embedded in a display device (2660) (e.g., display).

[0196] The processor (2620) can, for example, execute software (e.g., program (2640)) to control at least one other component (e.g., hardware or software component) of the electronic device (2601) connected to the processor (2620) and perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (2620) can load commands or data received from other components (e.g., sensor module (2676) or communication module (2690)) into volatile memory (2632), process the commands or data stored in volatile memory (2632), and store the resulting data in non-volatile memory (2634). According to one embodiment, the processor (2620) may include a main processor (2621) (e.g., central processing unit or application processor) and an auxiliary processor (2623) (e.g., graphics processing unit, image signal processor, sensor hub processor, or communication processor) that can operate independently or together with it. Additionally or generally, the auxiliary processor (2623) may be configured to use less power than the main processor (2621) or to be specialized for a designated function. The auxiliary processor (2623) may be implemented separately from the main processor (2621) or as part thereof.

[0197] The auxiliary processor (2623) may control at least some of the functions or states associated with at least one component of the electronic device (2601) (e.g., display device (2660), sensor module (2676), or communication module (2690)) on behalf of the main processor (2621) while the main processor (2621) is in an inactive (e.g., sleep) state, or together with the main processor (2621) while the main processor (2621) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (2623) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (2680) or communication module (2690)).

[0198] The memory (2630) can store various data used by at least one component of the electronic device (2601) (e.g., processor (2620) or sensor module (2676)). The data may include, for example, input data or output data for software (e.g., program (2640)) and related commands. The memory (2630) may include volatile memory (2632) or non-volatile memory (2634).

[0199] The program (2640) may be stored as software in memory (2630) and may include, for example, an operating system (2642), middleware (2644), or an application (2646).

[0200] The input device (2650) may receive commands or data to be used for a component of the electronic device (2601) (e.g., processor (2620)) from outside the electronic device (2601) (e.g., user). The input device (2650) may include, for example, a microphone, a mouse, a keyboard, or a digital pen (e.g., a stylus pen).

[0201] The sound output device (2655) can output a sound signal to the outside of the electronic device (2601). The sound output device (2655) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback, and the receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0202] The display device (2660) can visually provide information to an external (e.g., user) of the electronic device (2601). The display device (2660) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display device (2660) may include a touch circuitry configured to detect a touch, or a sensor circuitry configured to measure the intensity of the force generated by said touch (e.g., a pressure sensor).

[0203] The audio module (2670) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (2670) can acquire sound through an input device (2650) or output sound through an audio output device (2655) or an external electronic device (e.g., electronic device (2602)) (e.g., speaker or headphones) that is directly or wirelessly connected to the electronic device (2601).

[0204] The sensor module (2676) can detect the operating state of the electronic device (2601) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (2676) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0205] The interface (2677) may support one or more specified protocols that can be used for the electronic device (2601) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (2602)). According to one embodiment, the interface (2677) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0206] The connection terminal (2678) may include a connector through which the electronic device (2601) can be physically connected to an external electronic device (e.g., electronic device (2602)). According to one embodiment, the connection terminal (2678) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0207] The haptic module (2679) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (2679) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0208] The camera module (2680) can capture still images and video. According to one embodiment, the camera module (2680) may include one or more lenses, image sensors, image signal processors, or flashes.

[0209] The power management module (2688) can manage the power supplied to the electronic device (2601). According to one embodiment, the power management module (2688) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0210] The battery (2689) can supply power to at least one component of the electronic device (2601). According to one embodiment, the battery (2689) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0211] The communication module (2690) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (2601) and an external electronic device (e.g., electronic device (2602), electronic device (2604), or server (2608)), and the performance of communication through the established communication channel. The communication module (2690) may include one or more communication processors that operate independently of the processor (2620) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (2690) may include a wireless communication module (2692) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (2694) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device through a first network (2698) (e.g., a short-range communication network such as Bluetooth, WiFi Direct, or IrDA (infrared data association)) or a second network (2699) (e.g., a cellular network, the Internet, or a long-range communication network such as a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (2692) can identify and authenticate the electronic device (2601) within a communication network such as the first network (2698) or the second network (2699) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (2696).

[0212] An antenna module (2697) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module may include a single antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (2697) may include a plurality of antennas. In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (2698) or a second network (2699), may be selected from the plurality of antennas, for example, by a communication module (2690). A signal or power may be transmitted or received between the communication module (2690) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., an RFIC) may be additionally formed as part of the antenna module (2697).

[0213] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0214] According to one embodiment, commands or data may be transmitted or received between the electronic device (2601) and an external electronic device (2604) through a server (2608) connected to a second network (2699). Each of the electronic devices (2602, 2604) may be the same or different type of device as the electronic device (2601). According to one embodiment, all or part of the operations performed on the electronic device (2601) may be performed on one or more of the external electronic devices (2602, 2604, or 2608). For example, if the electronic device (2601) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (2601) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (2601). The electronic device (2601) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, or client-server computing technology may be used.

[0215] The electronic device according to the various embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0216] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B, or C” may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as “first,” “second,” or “first” or “second” may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0217] As used in this document, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed as a whole, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0218] Various embodiments of the present document may be implemented as software (e.g., program (2640)) comprising one or more instructions stored in a storage medium (e.g., internal memory (2636) or external memory (2638)) readable by a machine (e.g., electronic device (2601)). For example, a processor (e.g., processor (2620)) of the machine (e.g., electronic device (2601)) may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' merely means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0219] According to one embodiment, 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 distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0220] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the components of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to the integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0221] According to various embodiments, in an electronic device (e.g., 503 in FIG. 5a), a communication circuit; a memory; and at least one processor; comprising, when instructions stored in the memory are executed, the instructions are such that the at least one processor: establishes a communication connection with a plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) for providing an intelligent voice service, receives at least one piece of information associated with a user utterance including a specific word from at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), identifies a device to be woken up among at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) based on at least one piece of first information received during a time interval (e.g., time-out) for identifying the device to be woken up, and when at least one piece of second information is received after the time interval (e.g., time-out), the at least one An electronic device (e.g., 503 in FIG. 5a) may be provided to change the time interval (e.g., time-out) to a first time interval (e.g., time-out) longer than the time interval (e.g., time-out) based on the time of receiving the second information.

[0222] According to various embodiments, the electronic device (e.g., 503 in FIG. 5a) may be set as a main device, the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5a) may be set as sub-devices, and the main device may be set to identify the device to be woken up among the sub-devices, and an electronic device (e.g., 503 in FIG. 5a) may be provided.

[0223] According to various embodiments, the device to be woken up is a first external electronic device, and the instructions cause the at least one processor to control the first external electronic device to be woken up, and the woke-up first external electronic device is capable of receiving and processing a first user utterance for controlling the first external electronic device, an electronic device (e.g., 503 in FIG. 5a) may be provided.

[0224] According to various embodiments, the device to be woken up is a first external electronic device, and the instructions may be provided with an electronic device (e.g., 503 in FIG. 5a) such that when the at least one processor re-identifies the device to be woken up based on the at least one first information and the received at least one second information, the processor identifies at least one second external electronic device corresponding to the at least one second information different from the first external electronic device as the device to be woken up, and changes the time interval (e.g., time-out) to the first time interval (e.g., time-out) based on the identification of the at least one second external electronic device as the device to be woken up.

[0225] According to various embodiments, the instructions may be provided with an electronic device (e.g., 503 in FIG. 5a) which causes the at least one processor to change the time interval (e.g., time-out) to the first time interval (e.g., time-out) based on the latest reception time among at least one reception time of the at least one second information when the number of the at least one second information is multiple.

[0226] According to various embodiments, the instructions may provide an electronic device (e.g., 503 in FIG. 5a) such that, if at least one second piece of information is not received after the time interval (e.g., time-out), the processor identifies the third piece of information received latest among at least one first piece of information received during the time interval (e.g., time-out), and based on the time of reception of the identified third piece of information, the time interval (e.g., time-out) is changed to a second time interval (e.g., time-out) shorter than the time interval (e.g., time-out).

[0227] According to various embodiments, the instructions may be provided with an electronic device (e.g., 503 in FIG. 5a) that causes the at least one processor to: calculate the average value of the first time interval (e.g., time-out) and the second time interval (e.g., time-out), and change the time interval (e.g., time-out) to the calculated average value.

[0228] According to various embodiments, the at least one first information includes information regarding the intensity associated with the user utterance identified in at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), and the instructions may be provided such that the at least one processor identifies the first external electronic device that transmitted information regarding the highest intensity associated with the user utterance among at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) based on the at least one first information, and an electronic device (e.g., 503 of FIG. 5A) may be provided.

[0229] According to various embodiments, the memory stores information regarding a priority for identifying the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) as the device to be woken up, and the instructions enable the at least one processor: to identify the first external electronic device and the second external electronic device as the device to be woken up among at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) based on the at least one first information, and to identify the first external electronic device having a higher priority among the first external electronic device and the second external electronic device as the device to be woken up based on the information regarding the priority of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A). Device (e.g., 503 in FIG. 5a).

[0230] According to various embodiments, the instructions may provide an electronic device (e.g., 503 in FIG. 5a) such that the at least one processor identifies the first external electronic device as the device to be woken up, identifies that the second external electronic device is re-identified as the device to be woken up, and, based on the re-identification of the second external electronic device as the device to be woken up, changes the priority of the second external electronic device to a higher priority than the priority of the first external electronic device.

[0231] According to various embodiments, the instructions cause the at least one processor to accumulate information obtained in at least one operation identifying a device to be woken up performed prior to receiving the at least one information, and the accumulated information comprises at least one of: information regarding the SNR of each of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) obtained in each of the operations for wake-up performed prior to receiving the at least one information; information regarding the time at which information is received from each of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A); information associated with the state of each of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A); information regarding a device identified as being initially woken up; and information regarding a device finally woken up. 503) of 5a may be provided.

[0232] According to various embodiments, the instructions may be provided with an electronic device (e.g., 503 in FIG. 5a) wherein the at least one processor sets a value used in an operation to identify the device to be woken up based on information associated with the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5a), the value comprising at least one of the time interval (e.g., time-out) for obtaining information associated with the user voice to be processed for the wake-up, or a priority for identifying each of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5a) as the device to be woken up.

[0233] According to various embodiments, the instructions cause the at least one processor to perform learning based on an algorithm for generating an artificial intelligence model using at least some of the information associated with the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) as training data, and the artificial intelligence model provides information regarding the SNR of each of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), information associated with the state of each of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), and information regarding the device to be finally woken up in response to input information regarding the device identified as being initially woken up. An electronic device (e.g., 503 in FIG. 5a) configured to output information may be provided.

[0234] According to various embodiments, the instructions enable the at least one processor to: identify, from at least one piece of information received from at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), first information regarding the respective SNR of at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), second information associated with the respective state of at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), identify third information regarding a device identified as being woken up, determined based on the at least one piece of information, and input the first information, the second information, and the third information into the artificial intelligence model to identify the device to be woken up, which is output from the artificial intelligence model, electronic A device (e.g., 503 in FIG. 5a) may be provided.

[0235] According to various embodiments, a method of operating an electronic device (e.g., 503 in FIG. 5A) comprises: establishing a communication connection with a plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5A) for providing an intelligent voice service; receiving at least one piece of information associated with a user utterance including a specific word from at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5A); and identifying a device to be woken up among at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5A) based on at least one piece of first information received during a time interval (e.g., time-out) for identifying the device to be woken up. A method of operation may be provided, comprising the step of changing the time interval (e.g., time-out) to a first time interval (e.g., time-out) longer than the time interval (e.g., time-out) based on the time of receiving at least one second piece of information after the time interval (e.g., time-out).

[0236] According to various embodiments, an operation method may be provided in which the electronic device (e.g., 503 in FIG. 5a) is set as a main device, the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5a) are set as sub-devices, and the main device is set to identify the device to be woken up among the sub-devices.

[0237] According to various embodiments, the device to be woken up is a first external electronic device, and a method of operation may be provided further comprising the step of controlling the first external electronic device to be woken up, wherein the woke-up first external electronic device is capable of receiving and processing a first user utterance for controlling the first external electronic device.

[0238] According to various embodiments, a method of operation may be provided, further comprising: a step of identifying, when the device to be woken up is a first external electronic device, the device to be woken up is re-identified based on at least one first information and at least one received second information, at least one second external electronic device corresponding to the at least one second information different from the first external electronic device as the device to be woken up; and a step of changing the time interval (e.g., time-out) to the first time interval (e.g., time-out) based on the identification of the at least one second external electronic device as the device to be woken up.

[0239] According to various embodiments, a method of operation may be provided, further comprising the step of changing the time interval (e.g., time-out) to the first time interval (e.g., time-out) based on the latest reception time among at least one reception time of the at least one second information when the number of at least one second information is multiple.

[0240] According to various embodiments, in an electronic device (e.g., 503 in FIG. 5a), a communication circuit; a memory; and at least one processor; comprising, when instructions stored in the memory are executed, the instructions include: a network formed with a plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) for providing an intelligent voice service, and while performing an operation to wake up some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A) that formed the network, information associated with the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A), a time interval (e.g., time-out) for acquiring information associated with the user voice based on the accumulated information, and of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 of FIG. 5A). An electronic device (e.g., 503 in FIG. 5a) may be provided, which sets a priority for each and receives at least one piece of information associated with a user utterance containing a specific word for wake-up from at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5a), and identifies a device to be woken up among at least some of the plurality of external electronic devices (e.g., 501, 502, 404, 505, 506 in FIG. 5a) based on the at least one piece of information and at least one of the set time interval (e.g., time-out) or the priority.

Claims

Claim 1 An electronic device comprising: a communication circuit; a memory; and at least one processor, wherein instructions stored in the memory are executed by the at least one processor, the instructions are such that the electronic device: establishes a communication connection with a plurality of external electronic devices for providing an intelligent voice service; receives at least one piece of information associated with a user utterance including a specific word for wake-up from at least some of the plurality of external electronic devices; identifies a device to be woken up among at least some of the plurality of external electronic devices based on at least one piece of first information received during a time interval for identifying a device to be woken up among the at least one piece of the received information; identifies a first time interval longer than the time interval based on the time of receiving at least one piece of second information received during a guard time after the time interval among the at least one piece of the received information; and changes the time interval based on the first time interval. Claim 2 delete Claim 3 In claim 1, the identified device to be woken up is a first external electronic device, and the instructions are an electronic device that controls the electronic device to: cause the first external electronic device to be woken up. Claim 4 An electronic device according to claim 1, wherein the instructions enable the electronic device to: identify a first external electronic device as the device to be woken up based on at least one first information, and to re-identify the device to be woken up as the at least one second external electronic device based on receiving at least one second information corresponding to at least one second external electronic device different from the first external electronic device. Claim 5 In claim 4, the instructions enable the electronic device to identify the first time interval based on the latest reception time among at least one reception time of the at least one second information, where the number of the at least one second information is multiple. Claim 6 In claim 1, the instructions are an electronic device that: identifies the time of reception of the latest received first information among at least one first information received during the time interval based on the fact that at least one information is not received during the guard time; identifies a second time interval shorter than the time interval based on the time of reception of the latest received first information; and changes the time interval based on the second time interval. Claim 7 In claim 1, the instructions are an electronic device that: performs identification of the first time interval multiple times, and changes the time interval based on the plurality of first time intervals identified in each of the multiple performances. Claim 8 An electronic device according to claim 1, wherein the at least one first information comprises information regarding the intensity associated with the user utterance identified in at least some of the plurality of external electronic devices, and the instructions enable the electronic device to identify, based on the at least one first information, the external electronic device that transmits information corresponding to the highest intensity associated with the user utterance among at least some of the plurality of external electronic devices as the device to be woken up. Claim 9 An electronic device according to claim 1, wherein the memory stores information regarding priorities associated with the plurality of external electronic devices, and the instructions enable the electronic device to: identify a first external electronic device and a second external electronic device among at least some of the plurality of external electronic devices based on the at least one first information, and identify the first external electronic device having a higher priority among the first external electronic device and the second external electronic device as the device to be woken up based on the information regarding priorities of the plurality of external electronic devices. Claim 10 In claim 9, the instructions are an electronic device that: identifies the second external electronic device as the device to be woken up after identifying the first external electronic device as the device to be woken up, and, based on the second external electronic device being identified as the device to be woken up, changes the priority of the second external electronic device to a higher priority than the priority of the first external electronic device. Claim 11 An electronic device according to claim 1, wherein the instructions cause the electronic device to accumulate information obtained in at least one operation for identifying the device to be woken up performed prior to receiving the at least one information, and the accumulated information comprises at least one of: information regarding the SNR of each of the plurality of external electronic devices obtained in each of the wake-up operations performed prior to receiving the at least one information; information regarding the time at which information is received from each of the plurality of external electronic devices; information associated with the state of each of the plurality of external electronic devices; information regarding the device identified as being initially woken up; and information regarding the device finally woke up. Claim 12 In claim 11, the instructions enable the electronic device to identify a value used in an operation to identify the device to be woken up based on the accumulated information, wherein the value includes at least one of the time interval for identifying the device to be woken up, or a priority associated with the plurality of external electronic devices. Claim 13 In claim 11, the instructions are an electronic device that inputs at least one of the following to an artificial intelligence model learned using at least a portion of the accumulated information as training data: information regarding the SNR of at least one of the plurality of external electronic devices, information associated with the state of at least one of the plurality of external electronic devices, and information regarding the device identified as being initially woken up, thereby obtaining information regarding the device to be finally woken up. Claim 14 delete Claim 15 A method of operation of an electronic device comprising: establishing a communication connection with a plurality of external electronic devices for providing an intelligent voice service; receiving at least one piece of information associated with a user utterance including a specific word for wake-up from at least some of the plurality of external electronic devices; identifying a device to be woken up among at least some of the plurality of external electronic devices based on at least one piece of first information received during a time interval for identifying a device to be woken up among the at least one piece of information received; identifying a first time interval longer than the time interval based on the time of receiving at least one piece of second information received during a guard time after the time interval among the at least one piece of information received; and changing the time interval based on the first time interval. Claim 16 delete Claim 17 In claim 15, the identified device to be woken up is a first external electronic device, and the method of operation further comprises the step of controlling the first external electronic device to be woken up. Claim 18 A method of operation according to claim 15, wherein the identified device to be woken up is a first external electronic device, and further comprising the step of re-identifying the device to be woken up as the at least one second external electronic device based on receiving at least one second information corresponding to at least one second external electronic device different from the first external electronic device. Claim 19 A method of operation according to claim 18, further comprising the step of identifying the first time interval based on the latest reception time among at least one reception time of the at least one second information when the number of at least one second information is multiple. Claim 20 delete Claim 21 In claim 7, the instructions are an electronic device that causes the electronic device to change the time interval based on the average of the plurality of first time intervals. Claim 22 A method of operation according to claim 15, further comprising: a step of identifying the time of reception of the latest received first information among at least one first information received during the time interval based on the fact that at least one information is not received during the guard time; a step of identifying a second time interval shorter than the time interval based on the time of reception of the latest received first information; and a step of changing the time interval based on the second time interval. Claim 23 A method of operation according to claim 15, further comprising: a step of performing the identification of the first time interval multiple times; and a step of changing the time interval based on the plurality of first time intervals identified in each of the multiple performances. Claim 24 A computer-readable storage medium storing instructions, wherein the instructions, when executed by at least one processor, cause an electronic device to perform the method of any one of claims 15, 17, 18, 19, 22, or 23.

Images