JP2020038709A - Continuous conversation function with artificial intelligence device - Google Patents

Abstract

To provide a technique for providing an artificial intelligence device with a continuous conversation function.SOLUTION: An artificial intelligence continuous conversation method comprises steps of; switching into a voice command stand-by mode by activating a conversation function upon recognition of a conversation activation trigger while the conversation function is inactive; upon receipt of a voice command while in the voice command stand-by mode, performing a task corresponding to the voice command; and enabling a continuous conversation function by switching to the next voice command stand-by mode straight away according to the type of the task.SELECTED DRAWING: Figure 5

Description

  The following description relates to an artificial intelligence conversation system.

  Generally, an artificial intelligence conversation system used in a personal secretary system, a chatbot platform, an artificial intelligence (AI) speaker, etc., understands a human intention to a command word and provides a corresponding response. It adopts the method of doing.

  Primarily, artificial intelligence conversation systems are executed in such a way that when a human conveys a functional request, a machine provides a response to the human request. Device operation and content provision can be controlled based on the device operation.

  For example, Patent Literature 1 discloses that in a home network service, a home network service is provided using a second communication network such as Wi-Fi (registered trademark) in addition to a mobile communication network (first communication network). It discloses a technique capable of multi-controlling a plurality of multimedia devices in a house by voice command without a user operating a button.

  In general, artificial intelligence conversation systems use a predetermined keyword (ie, wake up word) (eg, device name, etc.) as a conversation activation trigger to activate a device. are doing.

  The artificial intelligence device performs a voice recognition function based on a keyword call. For example, when a user calls a device name, the device is activated and enters a standby mode for collecting voice commands of the user.

  If there is no keyword call, the device does not activate itself, and if it tries to retry the voice command in a short time, it will be required to call the keyword each time, so each time it is used, I had to feel tired.

Korean Published Patent Application No. 10-2011-0139797

  Provided is an artificial intelligence continuous conversation method and system capable of re-requesting a voice command without invoking a keyword (wake-up word) for activating a device.

  Provided is an artificial intelligence continuous conversation method and system that can automatically switch to a voice command waiting state without calling a keyword depending on a task corresponding to a previous voice command.

  An artificial intelligence continuous conversation method implemented by a computer, wherein when a conversation activation trigger is recognized while the conversation function is inactive, the conversation function is activated to enter a voice command waiting state; Performing a task corresponding to the voice command when a voice command is received in the command waiting state; and providing a continuous conversation function by immediately entering a next voice command waiting state based on the type of the task. And an artificial intelligence continuous conversation method.

  According to one aspect, a keyword specified in a wake-up word is used as the conversation activation trigger, and the step of providing the continuous conversation function includes, depending on an operation corresponding to the voice command, without calling the keyword. May automatically switch to the next voice command waiting state while maintaining the active state of the conversation function.

  According to another aspect, the step of providing the continuous conversation function includes, if the operation corresponding to the voice command is not an operation requiring a continuous operation, maintaining the active state of the conversation function and performing the next operation. Automatically switching to a voice command waiting state may be included.

  According to another aspect, the step of providing the continuous conversation function includes a first task that is continued until an end command is input and a second task that ends at a predetermined time without an end command. When the work corresponding to the voice command corresponds to the second work, the method may include automatically switching to the next voice command waiting state while maintaining the active state of the conversation function.

  According to another aspect, the step of providing the continuous conversation function includes maintaining an active state of the conversation function when the work corresponding to the voice command includes a conversation-type operation requesting a response from a user. Automatically switching to the next voice command waiting state may be included.

  According to another aspect, the step of providing the continuous conversation function is based on a result of learning an execution pattern for each task, wherein a task corresponding to the voice command corresponds to a task in which an additional voice command is predicted. Automatically switching to the next voice command waiting state while maintaining the active state of the conversation function may be included.

  According to another aspect, when the task corresponding to the voice command is a task requiring continuous operation, the step of switching the conversation function to an inactive state and terminating the voice command waiting state is included. It may further include.

  According to yet another aspect, ending the voice command waiting state includes deactivating the conversation function when a task corresponding to the voice command is a task related to the task requiring the continuous operation. To end the voice command waiting state by switching to the normal state.

  A computer program for causing a computer to execute the artificial intelligence continuous conversation method is provided.

  A computer-readable recording medium recording the computer program is provided.

  A computer-implemented artificial intelligence continuous conversation system, comprising at least one processor implemented to execute computer-readable instructions, wherein the at least one processor has a conversation function inactive. Activating the conversation function and entering a voice command waiting state when an activation trigger is recognized, and performing a task corresponding to the voice command when a voice command is received in the voice command waiting state. And providing a continuous conversation function by immediately entering a next voice command waiting state based on the type of the task.

  According to the embodiment of the present invention, after the previous voice command is issued, depending on the operation corresponding to the previous voice command, by maintaining the active state of the device and automatically switching to the next voice command standby state, Even if the voice command is retried within a short time, it is not necessary to call out a keyword for activating the device, and the device can be operated immediately, thereby improving user convenience and use fatigue.

FIG. 2 is a diagram illustrating an example of a service environment utilizing a voice-based interface according to an embodiment of the present invention. FIG. 6 is a diagram illustrating another example of a service environment utilizing a voice-based interface according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of a cloud artificial intelligence platform according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an internal configuration of the electronic device and the server according to the embodiment of the present invention. 5 is a flowchart illustrating a method for continuous artificial intelligence conversation according to an embodiment of the present invention. FIG. 4 is an exemplary diagram illustrating a work list that can promptly re-request a voice command without calling a keyword according to an embodiment of the present invention. FIG. 4 is an exemplary diagram illustrating a work list that can promptly re-request a voice command without calling a keyword according to an embodiment of the present invention. FIG. 4 is an exemplary diagram illustrating a work list that can promptly re-request a voice command without calling a keyword according to an embodiment of the present invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

  The artificial intelligence continuous conversation system according to the embodiment of the present invention may be realized by an electronic device that provides an interface that operates based on a conversation with a user. At this time, the artificial intelligence continuous conversation system provides a continuous conversation function that can immediately re-request a voice command without having to call a keyword (wakeup word) for activating the device.

  An artificial intelligence continuous conversation method according to an embodiment of the present invention may be executed by the electronic device described above. At this time, the computer program according to one embodiment of the present invention may be installed and executed in the electronic device, and the electronic device performs the artificial intelligence continuous conversation according to one embodiment of the present invention according to the control of the executed computer program. The method may be performed. The above-described computer program may be recorded on a computer-readable recording medium in order to cause an electronic device implemented by a computer to execute the artificial intelligence continuous conversation method.

  FIG. 1 is a diagram illustrating an example of a service environment utilizing a voice-based interface according to an embodiment of the present invention. In the embodiment of FIG. 1, in a technology for connecting and controlling devices in a home, such as a smart home or a home network service, an electronic device 100 that provides an interface that operates based on voice is used by an electronic device 100 of a user 110. An example is shown in which the voice input “turn off the light” received by the utterance is recognized and analyzed, and the light power of the in-home lighting device 120 that is linked to the electronic device 100 in the home via the internal network is controlled.

  For example, home devices include not only the home lighting device 120 described above but also home appliances such as a television, a PC (Personal Computer), peripheral devices, an air conditioner, a refrigerator, and a robot cleaner. It may include various devices that can be connected and controlled online, such as energy consuming devices such as heating / heating devices and security devices such as door locks and surveillance cameras. As the internal network, a wired network technology such as Ethernet (registered trademark), HomePNA, or IEEE 1394, or Bluetooth (registered trademark), ultra wideband (UWB), ZigBee (registered trademark), Wireless 1394, or Home RF may be used. Various wireless network technologies may be used.

  Electronic device 100 may be one of the devices at home. For example, the electronic device 100 may be one of devices such as an artificial intelligence speaker and a robot cleaner provided in a house. The electronic device 100 may be a mobile device of the user 110 such as a smartphone, a mobile phone, a notebook PC, a digital broadcast terminal, a PDA (Personal Digital Assistant), a PMP (Portable Multimedia Player), a tablet, or the like. Good. As described above, the electronic device 100 is not particularly limited as long as it is a device including a function connectable to a device in the home to receive the voice input of the user 110 and control the device in the home. In some embodiments, the above-described mobile device of the user 110 may be included as a device in the house.

  FIG. 2 is a diagram illustrating another example of a service environment utilizing a voice-based interface according to an embodiment of the present invention. FIG. 2 shows that the electronic device 100 that provides an interface that operates based on voice recognizes and analyzes the voice input “Today's weather” received by the utterance of the user 110, and transmits the voice input from the external server 210 via the external network. An example is shown in which information about the weather is acquired and the acquired information is output as a voice such as "Today's weather is ...".

  For example, an external network is a PAN (personal area network), a LAN (local area network), a CAN (campus area network), a MAN (metropolitan area network, a WAN (wide area network), a WAN (wide area network), and the like). It may include any one or more of the networks.

  In the embodiment of FIG. 2 as well, the electronic device 100 may be one of the devices at home or one of the mobile devices of the user 110, and may receive the voice input of the user 110. The device is not particularly limited as long as the device includes a function for processing and a function for connecting to the external server 210 via an external network and providing services and contents provided by the external server 210 to the user 110. There is no.

  As described above, the electronic device 100 according to the embodiment of the present invention is not particularly limited as long as it can process a user command including at least the voice input received by the utterance of the user 110 by the voice-based interface. Never. For example, the electronic device 100 may process the user command by directly recognizing and analyzing the user's voice input and performing an operation suitable for the voice input, but in some embodiments, the user's voice input may be performed. For example, processing such as recognition of the input, analysis of the recognized voice input, and synthesis of the voice provided to the user may be executed by an external platform linked to the electronic device 100.

  FIG. 3 is a diagram illustrating an example of a cloud artificial intelligence platform according to an embodiment of the present invention. FIG. 3 shows an electronic device 310, a cloud artificial intelligence platform 320, and a content service 330.

  As an example, the electronic device 310 may mean a device provided in a house, and may include at least the electronic device 100 described above. Such an electronic device 310 and an application installed and executed on the electronic device 310 (hereinafter, also referred to as an application) may be linked with the cloud artificial intelligence platform 320 via the interface connect 340. Here, the interface connect 340 may provide the developer with an electronic device 310 or a software development kit (SDK) and / or a development document for developing an application installed and executed on the electronic device 310. In addition, the interface connect 340 may provide an API (Application Program Interface) that allows the electronic device 310 or an application installed and executed on the electronic device 310 to utilize a function provided by the cloud artificial intelligence platform 320. As a specific example, a device or an application developed by the developer using the SDK and / or the development document provided by the interface connect 340 uses the API provided by the interface connect 340 to execute the cloud artificial intelligence platform 320. Can be utilized.

  Here, the cloud artificial intelligence platform 320 may provide a function for providing a voice-based service. For example, the cloud artificial intelligence platform 320 includes a voice processing module 321 for recognizing a received voice and synthesizing a voice to be output, a vision processing module 322 for analyzing and processing a received video or moving image, a received voice. A conversation processing module 323 for determining a suitable conversation for outputting a suitable voice according to the following, a recommendation module 324 for recommending a function suitable for the received voice, and a language for each sentence based on data learning based on artificial intelligence. For example, various modules for providing a voice-based service, such as a neural machine translation (NMT) 325 that assists in translating a document, may be included.

  For example, in the embodiments of FIGS. 1 and 2, it is assumed that the electronic device 100 transmits a voice input of the user 110 to the cloud artificial intelligence platform 320 using an API provided by the interface connect 340. In this case, the cloud artificial intelligence platform 320 may utilize the above-described modules 321 to 325 to recognize and analyze the received voice input, and synthesize and provide a suitable response voice according to the received voice input. Or an appropriate action may be recommended.

  In addition, the extension kit 350 may provide a development kit that enables a third-party content developer or company to implement a new voice-based function based on the cloud artificial intelligence platform 320. For example, in the embodiment of FIG. 2, the electronic device 100 transmits the voice input of the user 110 to the external server 210, and the external server 210 uses the API provided through the extension kit 350 to input the voice input to the cloud artificial intelligence platform 320. Is transmitted. In this case, as described above, the cloud artificial intelligence platform 320 recognizes and analyzes the received voice input and synthesizes and provides an appropriate response voice, or a function that must be processed according to the voice input. May be provided to the external server 210. As an example, in FIG. 2, the external server 210 transmits the voice input “today's weather” to the cloud artificial intelligence platform 320, and the keyword “today” extracted by the recognition of the voice input “today's weather” from the cloud artificial intelligence platform 320. "And" weather "are received. In this case, the external server 210 generates text information such as “Today's weather is ...” based on the keywords “today” and “weather”, and then generates the text information generated by the cloud artificial intelligence platform 320. May be sent. At this time, the cloud artificial intelligence platform 320 may provide the external server 210 by synthesizing the text information by voice. The external server 210 may transmit the synthesized voice to the electronic device 100, and the electronic device 100 receives the synthesized voice "Today's weather ..." from the user 110 by outputting the synthesized voice from the speaker. The voice input "Today's weather" is processed.

  At this time, the electronic device 100 may execute the artificial intelligence continuous conversation method according to the embodiment of the present invention in order to perform device operation and content provision based on conversation with the user.

  FIG. 4 is a block diagram illustrating an internal configuration of an electronic device and a server according to an embodiment of the present invention. The electronic device 410 in FIG. 4 may correspond to the electronic device 100 described above, and the server 420 may correspond to the external server 210 or one computer device that implements the cloud artificial intelligence platform 320 described above.

  The electronic device 410 and the server 420 may include memories 411 and 421, processors 412 and 422, communication modules 413 and 423, and input / output interfaces 414 and 424. The memories 411 and 421 are computer-readable recording media, and may include a permanent mass storage device such as a random access memory (RAM), a read only memory (ROM), and a disk drive. Here, a permanent large-capacity recording device such as a ROM or a disk drive may be included in the electronic device 410 or the server 420 as another permanent recording device distinguished from the memories 411 and 421. The memories 411 and 421 include an operating system and at least one program code (for example, a code for an application installed on the electronic device 410 and executed by the electronic device 410 to provide a specific service). ) May be recorded. Such a software component may be loaded from a computer-readable recording medium other than the memories 411 and 421. Such another computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, disk, tape, DVD / CD-ROM drive, memory card, and the like. In another embodiment, the software components may be loaded into the memories 411 and 421 through the communication modules 413 and 423 that are not computer-readable storage media. For example, the at least one program may be installed on the electronic device 410 based on a program (for example, the above-described application) installed by a file provided by a developer or a file distribution system that distributes an installation file of the application via the network 430. It may be loaded into the memory 411.

  Processors 412, 422 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processors 412, 422 by the memories 411, 421 or the communication modules 413, 423. For example, the processors 412, 422 may be configured to execute instructions received according to program codes recorded on a recording device such as the memories 411, 421.

  The communication modules 413 and 423 may provide a function for the electronic device 410 and the server 420 to communicate with each other via the network 430, or the electronic device 410 and / or the server 420 may connect to another electronic device or another server. A function for communicating with the server may be provided. As an example, a request generated by the processor 412 of the electronic device 410 according to a program code recorded in a recording device such as the memory 411 may be transmitted to the server 420 via the network 430 under the control of the communication module 413. Conversely, control signals, commands, contents, files, and the like provided under the control of the processor 422 of the server 420 are received by the electronic device 410 through the communication module 423 and the communication module 413 of the electronic device 410 via the network 430. May be done. For example, a control signal or a command of the server 420 received through the communication module 413 may be transmitted to the processor 412 or the memory 411, and the content or the file may be stored in a recording medium that the electronic device 410 can further include (the above-described persistent medium). Recording device).

  The input / output interface 414 may be a means for interfacing with the input / output device 415. For example, the input device may include a device such as a microphone, a keyboard, or a mouse, and the output device may include a device such as a display or a speaker. As another example, the input / output interface 414 may be a means for interfacing with a device in which input and output functions are integrated into one, such as a touch screen. The input / output device 415 may be composed of the electronic device 410 and one device. Also, the input / output interface 424 of the server 420 may be a means for connecting to the server 420 or interfacing with an input or output device (not shown) that the server 420 may include.

  Also, in other embodiments, electronic device 410 and server 420 may include fewer or more components than those of FIG. However, most prior art components need not be clearly shown in the figures. For example, the electronic device 410 may be realized to include at least a part of the input / output device 415 described above, or may be a transceiver, a GPS (Global Positioning System) module, a camera, various sensors, a database, and the like. Other components may be further included. As a more specific example, when the electronic device 410 is a smartphone, generally, an acceleration sensor, a gyro sensor, a motion sensor, a camera module, various physical buttons, buttons using a touch panel, input / Various components, such as an output port and a vibrator for vibration, may be implemented to be further included in the electronic device 410.

  In this embodiment, the electronic device 410 may basically include a microphone for receiving the user's voice input as the input / output device 415, and may respond to the user's voice input such as a response voice or a sound such as audio content. May be further included as the input / output device 415.

  The artificial intelligence continuous conversation method according to the embodiment of the present invention may be executed by a computer device such as the electronic device 410 described above. At this time, the processor 412 of the electronic device 410 may be implemented to execute a control instruction based on an operating system code or at least one program code included in the memory 411. Here, the processor 412 may control the electronic device 410 such that the electronic device 410 performs a step included in an artificial intelligence continuous conversation method described below according to a control command provided by a code recorded in the electronic device 410. .

  FIG. 5 is a flowchart illustrating an example of an artificial intelligence continuous conversation method according to an embodiment of the present invention.

  In operation 510, the electronic device 410 may activate a conversation function when a predetermined keyword (51) is recognized from a user's utterance through the conversation-based interface in an inactive state (50) (keyword). Calling function). For example, the electronic device 410 may receive a voice input by a user's utterance through a voice input device such as a microphone included in the electronic device 410 or a microphone associated with the electronic device 410 as a conversation-based interface. In other words, when the user utters the keyword 51 specified in the wake-up word in an inactive state (50) such as an idle state in which no operation is performed, the electronic device 410 recognizes the corresponding keyword 51. To activate the conversation function. At this time, when the conversation is activated, the electronic device 410 may allow the user to recognize a conversation active state through an output device (for example, a physical user interface (PUI)) included in the electronic device 410 or capable of interlocking with the electronic device 410. For example, the display may be turned on or a sound effect may be output. The above-described keyword calling function can be executed not only in a state where the electronic device 410 is not working but also in a state where a work such as music playback is being performed.

  In the present embodiment, it is described that a specific keyword is used as a conversation activation trigger. However, the present invention is not limited to this, and various forms of conversation activation such as specific actions, sounds, signals, and the like are used. An activation trigger may be used.

  In step 520, the electronic device 410 may wait for a voice command of the user according to the activation of the conversation function by calling the keyword (51) (voice command waiting state). The activated electronic device 410 automatically maintains a standby state of waiting for a user's voice command for a predetermined time (for example, 7 seconds). After recognizing the conversation active state of the electronic device 410 by, for example, the PUI, the user may input a voice command within a certain period of time during which the electronic device 410 maintains the standby state.

  In operation 530, the electronic device 410 may determine whether a predetermined time has elapsed after entering the voice command waiting state by counting a time designated for the voice command waiting state. If the voice command from the user is not confirmed within the specified time, the electronic device 410 returns to the inactive state (50) by performing a time-out process on the voice command waiting state.

  In operation 540, when the voice command is received from the user within a predetermined time in the voice command waiting state, the electronic device 410 may analyze the received voice command (voice analysis function). The electronic device 410 may receive a user's voice input through the conversation-based interface in a voice command waiting state. For example, the electronic device 410 may receive a voice input by a user's utterance through a voice input device such as a microphone included in the electronic device 410 or a microphone associated with the electronic device 410 as a conversation-based interface. May perform a natural language understanding (NLU) task of analyzing the meaning of the language.

  In the present embodiment, it is described that the voice analysis function is executed by the electronic device 410, but the present invention is not limited to this. For example, the electronic device 410 may receive the voice command of the user in the voice command waiting state, transmit the received voice command to the server 420, and analyze the user's voice command in the server 420.

  In operation 550, the electronic device 410 may perform an operation based on a result of the semantic analysis performed by the voice analysis function (operation performing function). The electronic device 410 outputs information corresponding to a user's voice command, and may execute a task based on a semantic analysis result together with a text-to-speech (TTS) for operation guidance as needed. The information corresponding to the user's voice command may include at least one of voice information, video information, and motion information as information that can be output by the conversation-based interface. As an example, the electronic device 410 may output audio information corresponding to the user's voice command from an audio output device such as a speaker included in the electronic device 410 or a speaker that works with the electronic device 410. In addition, the electronic device 410 may output video information corresponding to the user's voice command from a video output device such as a display included in the electronic device 410 or a display linked to the electronic device 410. Further, the electronic device 410 may output operation information corresponding to a user's voice command from a motor control operation device included in the electronic device 410 or a motor control operation device linked to the electronic device 410. For example, when the electronic device 410 is a conversation robot, a related operation may be implemented according to information corresponding to a voice command of a user.

  In the present embodiment, it has been described that the work execution function is executed by the electronic device 410, but the present invention is not limited to this. For example, the electronic device 410 may receive information corresponding to a user's voice command from the server 420 and output the received information through a conversation-based interface.

  At step 560, the electronic device 410 may determine whether a continuous conversation function is required according to the task corresponding to the voice command of the user. As an example, the electronic device 410 includes a task that is continued until a termination command is issued from the user (hereinafter, referred to as a “first task”) and a task that terminates at a predetermined point in time without the termination command (hereinafter, referred to as “first task”). (A task that does not require a continuous operation) may be classified, and the second task may be determined to be a task that requires a continuous conversation function. At this time, a task related to a task that is continued until a user issues an end command (for example, an operation to increase the volume of the music being reproduced) may be classified as the first task. As another example, the electronic device 410 is a task that requires a continuous conversation function when the task corresponding to the user's voice command includes a conversational operation such as asking the user for a response. May be determined. As another example, the electronic device 410 learns an execution pattern of a corresponding task for each task, and based on a result of the learning, performs a task that is predicted to lead to an additional voice command in a short time (for example, 7 seconds). In this case, it may be determined that the work requires the continuous conversation function.

  In particular, when it is determined that the task corresponding to the user's voice command is a task requiring the continuous conversation function, the electronic device 410 maintains the active state of the device and automatically enters the next voice command waiting state. You may switch. At this time, the electronic device 410 does not switch the device to the inactive state after the user's voice command is input, but automatically switches to the next voice command standby state while keeping the device active. Thus, it is possible to immediately re-request the voice command from the user without calling a keyword for waking up the device. In the next voice command waiting state, the fixed time is specified as the waiting time as in the previous voice command waiting state, so if the user rejects the additional command and no voice command is input, Timeout processing is performed immediately after the elapse of the waiting time.

  In operation 570, if the operation corresponding to the voice command of the user does not correspond to the operation requiring the continuous conversation function, the electronic device 410 switches the device to an inactive state (50) and ends the voice command waiting process. Let it. In other words, if the operation does not require the continuous conversation function, the electronic device 410 ends the voice command waiting process, and then maintains the device inactive state (50) until the keyword is called up. May be reactivated when is called.

  If the voice command analysis fails in the first voice command waiting process immediately after the call of the keyword, the voice command waiting process is performed after providing a TTS response of a predetermined content (for example, "I do not understand."). If the voice command analysis fails in the voice command waiting process provided as a continuous conversation function without calling a keyword, the voice command waiting process may be terminated without replying to the TTS.

  The electronic device 410 may output audio if the device requires continuous operation until an end command is issued by the user, such as a process of playing back content such as music, news, a fairy tale, or a radio. The command waiting process may be terminated, and the work requested to be executed may be continued. On the other hand, the work based on the voice command recognized in the previous voice command standby process may be a task that ends after information transmission without a termination command, such as a simple information request or a chat with a device, or a communication with the user. In this case, the active state of the device may be maintained without calling the keyword, and the apparatus may immediately enter the standby state for the next voice command.

  FIG. 6 shows an example of a work list belonging to the media content.

  The electronic device 410 may provide the media content as an example of a task corresponding to the voice command of the user. At this time, an example of the media content may include an audio content 600 including audio information. Referring to FIG. 6, the audio content 600 may be classified into music, news, fairy tales, radio, and the like.

  The electronic device 410 analyzes the meaning of the voice command received from the user, and performs an operation based on the result of the semantic analysis. Content classified as news out of 600 may be reproduced.

  As described above, since the audio content 600 corresponds to a task that is continuously executed until a termination command is issued by the user, the audio command waiting process is immediately terminated for such a task. Deactivate.

  FIG. 7 shows an example of a work list belonging to the TTS reply.

  The electronic device 410 may provide the response information 700 in a TTS format as an example of a task corresponding to the user's voice command. For example, when "tell me today's schedule" is received as a user's voice command, schedule information corresponding to today's date from among the user's schedule information may be output as a TTS.

  The TTS reply 700 such as information search is completed after information transmission even if no end command is given, and such work is likely to require additional information from the user in a short time. Considering the points, a continuous conversation function is provided by maintaining the active state of the device and immediately entering the next voice command waiting state.

  As described with reference to FIGS. 6 and 7, whether or not to switch to the next voice command standby state may be determined according to the type of command, that is, according to the work type corresponding to the voice command of the user.

  Referring to FIG. 8, in the operation of reproducing audio content such as music, and in the control operation related to the reproduction of audio content (for example, adjusting the volume, changing the reproduction content, etc.), the voice command waiting process is immediately terminated. Do not switch to the next voice command waiting state. On the other hand, in a task of providing a short answer type TTS reply or a simple chat task of exchanging a conversation with a user, the device is maintained in an active state and is immediately switched to a next voice command waiting state.

  Therefore, the electronic device 410 basically needs to call a keyword, and the preceding operation leads to a voice command waiting state. However, in the case of some types of work, that is, the voice If the command is a task that is likely to be retried, it is possible to immediately enter the voice command waiting state without calling the keyword.

  As described above, according to the embodiment of the present invention, after the previous voice command is issued, depending on the operation corresponding to the previous voice command, the device is kept in the active state and automatically enters the next voice command standby state. By switching, even if the voice command is retried within a short time, it is not necessary to call a keyword for activating the device, and the device can be operated immediately, so that user convenience and use fatigue can be improved.

  The apparatus described above may be realized by hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments include a processor, a controller, an ALU (arithmetic logic unit), a digital signal processor, a microcomputer, an FPGA (field programmable gate array), a PLU (programmable logic unit), a microprocessor, Or, it may be implemented utilizing one or more general purpose or special purpose computers, such as various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the OS. The processing device may also respond to the execution of the software, access the data, and record, manipulate, process, and generate the data. For convenience of understanding, one processing device may be described as being used, but those skilled in the art will appreciate that a processing device may include multiple processing elements and / or multiple types of processing elements. You can understand. For example, the processing device may include multiple processors or one processor and one controller. Other processing configurations, such as a parallel processor, are also possible.

  The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing device to operate at will, or instructing the processing device independently or collectively. Or you can. The software and / or data may be embodied in any type of machine, component, physical device, computer storage medium or device to interpret or provide instructions or data to a processing device. Good. The software may be distributed on computer systems connected by a network and recorded or executed in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.

  The method according to the embodiments may be implemented in the form of program instructions executable by various computer means and recorded on a computer-readable medium. At this time, the medium may continuously record a computer-executable program, or may temporarily record the program for execution or download. Further, the medium may be a variety of recording means or storage means in a form in which one or a plurality of hardware are combined, but is not limited to a medium directly connected to a certain computer system, and may be distributed on a network. May exist. Examples of media include hard disks, floppy disks, and magnetic media, such as magnetic tape, optical media, such as CD-ROMs and DVDs, magneto-optical media, such as floppy disks, And a ROM, a RAM, a flash memory, and the like, and may be configured to record program instructions. Further, examples of other media include an application store for distributing an application, and a recording medium or storage medium managed by a site or server that supplies or distributes various other software.

  As described above, the embodiments have been described based on the limited embodiments and the drawings. However, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in a different order than the described methods, and / or components, such as the described systems, structures, devices, circuits, etc., in different forms than the described methods. Appropriate results can be achieved even when combined or combined, and opposed or replaced by other components or equivalents.

  Therefore, even different embodiments belong to the appended claims as long as they are equivalent to the claims.

100: Electronic device 110: User 210: External server

Claims (16)

An artificial intelligence continuous conversation method realized by a computer,
When a conversation activation trigger is recognized while the conversation function is inactive, activating the conversation function and entering a voice command waiting state;
When a voice command is received in the voice command standby state, performing a task corresponding to the voice command;
After performing the task, based on the type of task, provide a continuous conversation function by immediately entering a next voice command waiting state, or provide a conversation function by not entering the next voice command waiting state. And deactivating the conversation function so as not to enter the next voice command waiting state when the type of the task is a task requiring a continuous operation. Including, artificial intelligence continuous conversation method. The keyword specified in the wake-up word is used as the conversation activation trigger,
The step of providing the continuous conversation function includes:
2. The method according to claim 1, wherein, depending on a task corresponding to the voice command, automatically switching to the next voice command standby state while maintaining an active state of the conversation function without calling the keyword. 3. Artificial intelligence continuous conversation method. The step of providing the continuous conversation function includes:
The method according to claim 1, further comprising automatically switching to the next voice command waiting state while maintaining the active state of the conversation function, when the task corresponding to the voice command is not a task requiring continuous operation. The described artificial intelligence continuous conversation method. The step of providing the continuous conversation function includes:
When the work corresponding to the voice command corresponds to the second work, of the first work that is continued until the end command is input and the second work that ends at a predetermined time without the end command, The artificial intelligence continuous conversation method according to claim 1, further comprising: automatically switching to the next voice command waiting state while maintaining an active state of the conversation function. The step of providing the continuous conversation function includes:
If the operation corresponding to the voice command includes a conversation-type operation requesting a user's response, automatically switching to the next voice command waiting state while maintaining the active state of the conversation function. 2. The method for continuous conversation of artificial intelligence according to 1. The step of providing the continuous conversation function includes:
Based on the result of learning the execution pattern for each task, if the task corresponding to the voice command corresponds to a task in which an additional voice command is predicted, the active state of the conversation function is maintained and the next voice command waits. The artificial intelligence continuous conversation method according to claim 1, further comprising: automatically switching to a state. The step of deactivating the conversation function includes:
If the task corresponding to the voice command is a task related to the task requiring the continuous operation, switching the conversation function to an inactive state to end the voice command waiting state. The continuous method for continuous artificial intelligence according to claim 1.   A computer program for causing a computer to execute the artificial intelligence continuous conversation method according to any one of claims 1 to 7.   A computer-readable recording medium recording the computer program according to claim 8. An artificial intelligence continuous conversation system realized by a computer,
At least one processor implemented to execute computer readable instructions,
The at least one processor comprises:
When a conversation activation trigger is recognized while the conversation function is inactive, a step of activating the conversation function and entering a voice command waiting state;
Performing a task corresponding to the voice command when the voice command is received in the voice command standby state;
After performing the task, based on the type of task, provide a continuous conversation function by immediately entering a next voice command waiting state, or provide a conversation function by not entering the next voice command waiting state. In the deactivating step, when the type of the task is a task that requires a continuous operation, a step of deactivating a conversation function so as not to enter the next voice command waiting state. Processing, artificial intelligence continuous conversation system. The keyword specified in the wake-up word is used as the conversation activation trigger,
The step of providing the continuous conversation function,
The method according to claim 10, further comprising: maintaining an active state of the conversation function even without calling the keyword and automatically switching to the next voice command waiting state, depending on a task corresponding to the voice command. Artificial intelligence continuous conversation system. The step of providing the continuous conversation function,
The method according to claim 10, further comprising: if the operation corresponding to the voice command is not a task requiring continuous operation, automatically switching to the next voice command standby state while maintaining the active state of the conversation function. The described artificial intelligence continuous conversation system. The step of providing the continuous conversation function,
When the work corresponding to the voice command corresponds to the second work, of the first work that is continued until the end command is input and the second work that ends at a predetermined time without the end command, The artificial intelligence continuous conversation system according to claim 10, further comprising: automatically switching to the next voice command waiting state while maintaining the active state of the conversation function. The step of providing the continuous conversation function,
If the operation corresponding to the voice command includes a conversation-type operation requesting a user's response, automatically switching to the next voice command waiting state while maintaining the active state of the conversation function. 10. The artificial intelligence continuous conversation system according to item 10. The step of providing the continuous conversation function,
Based on the result of learning the execution pattern for each task, if the task corresponding to the voice command corresponds to a task in which an additional voice command is predicted, the active state of the conversation function is maintained and the next voice command waits. The artificial intelligence continuous conversation system according to claim 10, comprising automatically switching to a state. The step of deactivating the conversation function includes:
If the task corresponding to the voice command is a task related to the task requiring the continuous operation, switching the conversation function to an inactive state to end the voice command waiting state. Item 11. An artificial intelligence continuous conversation system according to Item 10.

Images