JP6920398B2 - Continuous conversation function in artificial intelligence equipment - Google Patents

Description

The following description relates to an artificial intelligence conversation system.

In general, artificial intelligence conversation systems used in personal secretary systems, chatbot platforms, artificial intelligence (AI) speakers, etc. understand the intent of human commands and provide corresponding responses. The method of doing is adopted.

Primarily, artificial intelligence conversation systems are executed in such a way that when a human transmits a functional request, the machine provides a response to the human request, but the microphone receives the user's voice input and the received voice input is used. It is possible to control device operation and content provision based on this.

For example, Patent Document 1 provides a home network service using a second communication network such as Wi-Fi (registered trademark) in addition to a mobile communication network (first communication network). It is possible, and discloses a technology that enables multi-control of a plurality of multimedia devices in a home by voice commands without the user having to operate a button.

In general, artificial intelligence conversation systems use predefined keywords (ie, wake up words) (eg, device names, etc.) as conversation activation triggers to activate the device. doing.

The artificial intelligence device will execute the voice recognition function based on the keyword call. For example, when the user calls the device name, the device is activated and becomes a standby mode for collecting the user's voice command.

Without the keyword call, the device will not activate itself, and every time it tries to retry a voice instruction in a short period of time, the keyword call is required first, so each time it is used. I had to feel tired.

Korean Publication No. 10-2011-0139977

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

It provides an artificial intelligence continuous conversation method and system that can automatically switch to a voice command standby state without calling a keyword depending on the work corresponding to the previous voice command.

It is an artificial intelligence continuous conversation method realized by a computer, and when a conversation activation trigger is recognized while the conversation function is inactive, the stage of activating the conversation function and entering a voice command standby state, the voice When a voice command is received in the command waiting state, a step of executing the work corresponding to the voice command and a step of providing a continuous conversation function by immediately entering the next voice command waiting state based on the type of the work. Provides artificial intelligence continuous conversation methods, including.

According to one aspect, the keyword specified in the wakeup word is used as the conversation activation trigger, and the stage of providing the continuous conversation function does not require the call of the keyword depending on the work corresponding to the voice command. May also include maintaining the active state of the conversation function and automatically switching to the next voice command standby state.

According to another aspect, the stage of providing the continuous conversation function is to maintain the active state of the conversation function and to maintain the active state of the conversation function when the work corresponding to the voice command is not a work requiring continuous operation. It may include automatically switching to the voice command standby state.

According to another aspect, the stage of providing the continuous conversation function is a first work that is continued until the end command is input and a second work that ends at a predetermined time even if there is no end command. When the work corresponding to the voice command corresponds to the second work, it may include maintaining the active state of the conversation function and automatically switching to the next voice command standby state.

According to another aspect, the stage of providing the continuous conversation function maintains the active state of the conversation function when the work corresponding to the voice command includes a conversational operation requiring a user's response. It may include automatically switching to the next voice command standby state.

According to another aspect, the stage of providing the continuous conversation function is when the work corresponding to the voice command corresponds to the work in which an additional voice command is predicted based on the result of learning the execution pattern for each work. It may include maintaining the active state of the conversation function and automatically switching to the next voice command standby state.

According to another aspect, when the work corresponding to the voice command is a work that requires continuous operation, the step of switching the conversation function to the inactive state and ending the voice command standby state is performed. Further may be included.

According to still another aspect, the stage of ending the voice command standby state deactivates the conversation function when the work corresponding to the voice command is related to the work requiring the continuous operation. It may include switching to the above-mentioned state and ending the voice command waiting state.

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

Provided is a computer-readable recording medium on which the computer program is recorded.

A computer-implemented artificial intelligence continuous conversation system that includes at least one processor implemented to execute a computer-readable instruction, the at least one processor having conversation with the conversation function inactive. When the activation trigger is recognized, the process of activating the conversation function to enter the voice command standby state, and when the voice command is received in the voice command standby state, the process of executing the work corresponding to the voice command. , And an artificial intelligence continuous conversation system that processes the process of providing the continuous conversation function by immediately entering the next voice command standby state based on the type of work.

According to the embodiment of the present invention, after the previous voice command is given, depending on the work corresponding to the previous voice command, the device is maintained in the active state and automatically switched to the next voice command standby state. Even if the voice command is retried within a short period of time, it is not necessary to call the keyword for activating the device, and the operation can be performed immediately, so that the user convenience and the degree of fatigue in use can be improved.

It is a figure which showed the example of the service environment which utilized the voice-based interface in one Embodiment of this invention. It is a figure which showed the other example of the service environment which utilized the voice-based interface in one Embodiment of this invention. It is a figure which showed the example of the cloud artificial intelligence platform in one Embodiment of this invention. It is a block diagram for demonstrating the internal structure of an electronic device and a server in one Embodiment of this invention. It is a flowchart which showed the artificial intelligence continuous conversation method in one Embodiment of this invention. It is explanatory drawing for demonstrating the work list which can immediately re-request a voice instruction without calling a keyword in one Embodiment of this invention. It is explanatory drawing for demonstrating the work list which can immediately re-request a voice instruction without calling a keyword in one Embodiment of this invention. It is explanatory drawing for demonstrating the work list which can immediately re-request a voice instruction without calling a keyword in one Embodiment of this 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.

The artificial intelligence continuous conversation method according to the embodiment of the present invention may be executed by the above-mentioned electronic device. At this time, the computer program according to the embodiment of the present invention may be installed and executed in the electronic device, and the electronic device may perform the artificial intelligence continuous conversation according to the embodiment of the present invention under the control of the executed computer program. You may carry out the method. The computer program described above may be recorded on a computer-readable recording medium in order for the electronic device realized by the computer to execute the artificial intelligence continuous conversation method.

FIG. 1 is a diagram showing 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 technique for connecting and controlling a device 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 a user 110. An example is shown in which the voice input "turn off the light" received by speech is recognized and analyzed, and the light power supply of the home lighting device 120 linked with the electronic device 100 is controlled in the home via an internal network.

For example, in-house devices include not only the above-mentioned in-house lighting device 120, but also home appliances such as TVs, PCs (Personal Computers), peripheral devices, air conditioners, refrigerators, robot cleaners, etc., as well as water, electricity, and cold. / It may include a variety of devices that can be connected and controlled online, such as energy consuming devices such as heating appliances, security appliances such as door locks and surveillance cameras. Also, as internal networks, wired network technologies such as Ethernet (registered trademark), HomePNA, IEEE 1394, Bluetooth (registered trademark), UWB (ultra Wide Band), Zigbee (registered trademark), Wireless 1394, Home RF, etc. Wireless network technology may be utilized.

The electronic device 100 may be one of the devices in the home. For example, the electronic device 100 may be one of devices such as an artificial intelligence speaker and a robot cleaner provided in the house. Further, 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 broadcasting 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 capable of connecting to the device in the house in order to receive the voice input of the user 110 and control the device in the house. Further, depending on the embodiment, the mobile device of the user 110 described above may be included as a device in the home.

FIG. 2 is a diagram showing another example of a service environment utilizing a voice-based interface according to an embodiment of the present invention. In FIG. 2, an 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 from an external server 210 today via an external network. It shows an example of acquiring information about the weather of the server and outputting the acquired information by voice such as "Today's weather is ...".

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

Also in the embodiment of FIG. 2, the electronic device 100 may be one of the devices in the home or one of the mobile devices of the user 110, and receives the voice input of the user 110. Any device that 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 is particularly limited. There is no.

As described above, the electronic device 100 according to the embodiment of the present invention is particularly limited as long as it is a device capable of processing a user instruction including at least a voice input received by the utterance of the user 110 by the voice platform interface. There is nothing. For example, the electronic device 100 may process the user command by directly recognizing and analyzing the user's voice input and executing an operation suitable for the voice input, but depending on the embodiment, the user's voice input may be performed. Processing such as recognition of the voice input, analysis of the recognized voice input, and synthesis of the voice provided to the user may be executed on an external platform linked with the electronic device 100.

FIG. 3 is a diagram showing 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 the home, and may include at least the electronic device 100 described above. Such an electronic device 310 or an application installed and executed in 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, Interface Connect 340 may provide the developer with an SDK (Software Development Kit) and / or a development document for developing an application installed and executed in the electronic device 310 or the electronic device 310. Further, the interface connect 340 may provide an API (Application Program Interface) that allows an application installed and executed on the electronic device 310 or the electronic device 310 to utilize the functions provided by the cloud artificial intelligence platform 320. As a specific example, devices and applications developed by developers using the SDK and / or development documents provided by Interface Connect 340 can use the API provided by Interface Connect 340 to create a cloud artificial intelligence platform 320. It is possible to utilize the functions provided by.

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 has an audio processing module 321 for recognizing received audio and synthesizing output audio, a vision processing module 322 for analyzing and processing received video and video, and received audio. Conversation processing module 323 for determining suitable conversation to output appropriate voice according to, recommendation module 324 for recommending functions suitable for received voice, artificial intelligence language based on data learning in sentence units It may include various modules for providing voice-based services, such as Neural Machine Translation (325) 325, which assists in translating.

For example, in the embodiment of FIGS. 1 and 2, it is assumed that the electronic device 100 transmits the voice input of the user 110 to the cloud artificial intelligence platform 320 by using the API provided by the interface connect 340. In this case, the cloud artificial intelligence platform 320 may recognize and analyze the received voice input by utilizing the modules 321 to 325 described above, and synthesize and provide a suitable response voice according to the received voice input. , You may recommend suitable operation.

Further, the expansion kit 350 may provide a development kit that enables a third-party content developer or a company to realize 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 expansion kit 350 to input the voice to the cloud artificial intelligence platform 320. Is sent. In this case, as described above, the cloud artificial intelligence platform 320 must recognize and analyze the received voice input to synthesize and provide an appropriate response voice, or process it according to the voice input. The recommendation information for is 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 from the cloud artificial intelligence platform 320 by recognizing the voice input “today's weather”. ”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 the text information generated on the cloud artificial intelligence platform 320. May be sent. At this time, the cloud artificial intelligence platform 320 may synthesize text information by voice and provide it to the external server 210. The external server 210 may transmit the synthesized voice to the electronic device 100, and the electronic device 100 receives the synthesized voice from the user 110 by outputting the synthesized voice “Today's weather is ...” from the speaker. Voice input "Today's weather" will be 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 carry out device operation and content provision based on conversation with the user.

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

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

Processors 412 and 422 may be configured to process instructions in a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to processors 412, 422 by memory 411, 421 or communication modules 413, 423. For example, processors 412 and 422 may be configured to execute instructions received according to program code recorded in a recording device such as memory 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, and the electronic device 410 and / or the server 420 may provide other electronic devices or other electronic devices or other. It may provide a function for communicating with the server. As an example, a request generated by the processor 412 of the electronic device 410 according to the program code recorded in the 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. On the contrary, control signals, instructions, contents, files, etc. provided under the control of the processor 422 of the server 420 are received by the electronic device 410 through the communication module 413 of the electronic device 410 via the communication module 423 and the network 430. May be done. For example, the control signals and instructions of the server 420 received through the communication module 413 may be transmitted to the processor 412 and the memory 411, and the contents and files may be further included in the recording medium (permanent described above). It may be recorded in a target recording device).

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

Also, in other embodiments, the electronics 410 and the server 420 may include fewer or more components than the components of FIG. However, it is not necessary to clearly illustrate most of the prior art components. For example, the electronic device 410 may be realized to include at least a part of the above-mentioned input / output device 415, such as 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, the acceleration sensor, gyro sensor, motion sensor, camera module, various physical buttons, buttons using the touch panel, input / input, which are generally included in the smartphone. Various components, such as output ports, accelerometers for vibration, etc., may be implemented to be further included in the electronic device 410.

In the present embodiment, the electronic device 410 may basically include a microphone for receiving the user's voice input as the input / output device 415, and sounds such as a response voice or audio content corresponding to the user's voice input. A speaker for outputting the above may be further included as an 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 realized to execute a control instruction by the code of the operating system included in the memory 411 or the code of at least one program. Here, the processor 412 may control the electronic device 410 so that the electronic device 410 executes the steps included in the artificial intelligence continuous conversation method described later according to the control instruction provided by the code recorded in the electronic device 410. ..

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

At step 510, the electronic device 410 may activate the conversation function when a predetermined keyword (51) is recognized from the user's utterance through the conversation infrastructure interface in the inactive state (50) (keyword). Call function). For example, the electronic device 410 may receive the voice input uttered by the user through a voice input device such as a microphone included in the electronic device 410 or a microphone interlocking with the electronic device 410 as a conversation infrastructure interface. In other words, the electronic device 410 recognizes the keyword 51 when the user utters the keyword 51 specified in the wakeup word in an inactive state (50) such as an idle state in which no work is executed. You may activate the conversation function. At this time, the electronic device 410 causes the user to recognize the conversation active state through an output device (for example, a PUI (physical user interface)) included in the electronic device 410 or interlocking with the electronic device 410 when the conversation is activated. You may turn on the display or output a sound effect. The keyword calling function described above can be executed not only when the electronic device 410 is not working, but also when a work such as music playback is being executed.

In the present embodiment, it is explained that a specific keyword is used as a conversation activation trigger, but the present invention is not limited to this, and various forms of conversation activity such as a specific action, sound, signal, etc. are used. The conversion trigger may be used.

At 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 standby state). The activated electronic device 410 automatically maintains a standby state of waiting for a user's voice command for a certain period of 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 step 530, the electronic device 410 may count the time specified for the voice command standby state and determine whether a certain time has elapsed after entering the voice command standby state. If the voice command from the user is not confirmed within the specified fixed time, the electronic device 410 performs a timeout process for the voice command waiting state and returns to the inactive state (50).

At step 540, when the electronic device 410 receives a voice command from the user within a certain period of time in the voice command standby state, the electronic device 410 may analyze the received voice command (voice analysis function). The electronic device 410 may receive the user's voice input through the conversation infrastructure interface in the voice command standby state. For example, the electronic device 410 may receive a voice input uttered by the user through a voice input device such as a microphone included in the electronic device 410 or a microphone interlocking with the electronic device 410 as a conversation infrastructure interface, and the received voice command may be received. You may perform a natural language understanding (NLU) task to analyze the meaning of.

In the present embodiment, it is described that the voice analysis function is executed by the electronic device 410, but the present embodiment is not limited to this. For example, the electronic device 410 can also perform a process of receiving a user's voice command in a voice command standby state, transmitting the received voice command to the server 420, and analyzing the user's voice command on the server 420.

At step 550, the electronic device 410 may perform work based on the result of semantic analysis by the voice analysis function (work execution function). The electronic device 410 outputs information corresponding to a user's voice command, and may perform work based on the semantic analysis result together with TTS (text to speech) for operation guidance, if necessary. The information corresponding to the user's voice command may include at least one of voice information, video information, and operation information as information that can be output by the conversation infrastructure interface. As an example, the electronic device 410 may output voice information corresponding to a user's voice command from a voice output device such as a speaker included in the electronic device 410 or a speaker linked with the electronic device 410. Further, the electronic device 410 may output video information corresponding to a user's voice command from a video output device such as a display included in the electronic device 410 or a display linked with the electronic device 410. Further, the electronic device 410 may output operation information corresponding to a voice command of the user from the motor control operation device included in the electronic device 410 or the motor control operation device linked with the electronic device 410. For example, when the electronic device 410 is a conversation robot, the related operation may be realized according to the information corresponding to the user's voice command.

In the present embodiment, it is 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 can also have a process of receiving information corresponding to a user's voice command from the server 420 and outputting the received information on the conversation infrastructure interface.

At step 560, the electronic device 410 may determine whether a continuous conversation function is required according to the work corresponding to the user's voice command. As an example, the electronic device 410 has a work that is continued until an end command is given by the user (hereinafter, referred to as "first work") and a work that ends at a predetermined time even if the end command is not given (hereinafter, referred to as "first work"). It may be classified from (referred to as "second work") (that is, work that does not require continuous movement), and the second work may be determined to be work that requires a continuous conversation function. At this time, the work related to the work that is continued until the end command is given by the user (for example, the operation of raising the volume of the music being played) may also be classified as the first work. As another example, the electronic device 410 is a work that requires a continuous conversation function when the work corresponding to the user's voice command includes a conversational operation such as asking the user a question and requesting a reply. May be determined. As another example, the electronic device 410 learns the execution pattern of the corresponding work for each work, and is predicted to lead to an additional voice command within a short time (for example, 7 seconds) based on the learning result. In this case, it may be determined that the work requires the continuous conversation function.

In particular, when it is determined that the work corresponding to the user's voice command is a work that requires a continuous conversation function, the electronic device 410 maintains the active state of the device and automatically enters the next voice command standby 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 maintaining the active state of the device as it is. Therefore, it is possible to immediately re-request the voice command from the user without calling the keyword to wake up the device. Even in the next voice command waiting state, a certain time is specified as the waiting time as in the previous voice command waiting state, so if the user rejects the additional command and the voice command is not input, Timeout processing is performed immediately after the waiting time has elapsed.

At step 570, the electronic device 410 switches the device to the inactive state (50) and ends the voice command waiting process when the work corresponding to the user's voice command does not correspond to the work requiring the continuous conversation function. Let me. In other words, in the case of work that does not require the continuous conversation function, the electronic device 410 maintains the inactive state (50) of the device until the keyword is called after ending the voice command standby process, and the keyword. May be reactivated when is called.

If the voice command analysis fails in the first voice command waiting process immediately after the keyword is called, the voice command waiting process after providing a TTS response with the specified content (for example, "I don't understand"). If the voice command analysis fails in the voice command waiting process provided as the continuous conversation function without calling the keyword, the voice command waiting process may be terminated without replying to the TTS.

When the electronic device 410 requires continuous work of the device until the user gives a termination command, for example, the work of playing content such as music, news, fairy tales, radio, etc., the electronic device 410 is voiced. The instruction waiting process may be terminated and the work requested to be executed may be continued. On the other hand, the work by the voice command recognized in the previous voice command waiting process is the work to be finished after the information is transmitted even if there is no end command such as a simple information request or chat with the device, or with the user. In the case of continuous conversational work, the device may be kept active and immediately enter the next voice command standby state even if the keyword is not called.

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

The electronic device 410 may provide media content as an example of work corresponding to a user's voice command. At this time, as an example of the media content, the audio content 600 composed of audio information may be included, and 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 executes the work based on the meaning analysis result. However, when "with news" is received as the user's voice command, the audio content Content classified as news from among 600 may be played.

As described above, the audio content 600 corresponds to the work that is continuously executed until the end command is given by the user. Therefore, for such a work, the voice command standby process is immediately ended and the device is used. To deactivate.

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

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

In the TTS response 700 such as information retrieval, the work is completed after the information is transmitted even if the end command is not given, and it is highly likely that such work is requested by the user for additional information within a short period of time. Taking this into consideration, the continuous conversation function is provided by maintaining the active state of the device and immediately entering the next voice command standby state.

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

With reference to FIG. 8, in the work of playing audio content such as music, the control work related to the playback of audio content (for example, adjusting the volume, changing the playback content, etc.), the voice command waiting process is immediately terminated. Do not switch to the next voice command standby state. On the other hand, in the work of providing a short-answer type TTS response or a simple chat work of exchanging a conversation with a user, the active state of the device is maintained and the state is immediately switched to the next voice command standby state.

Therefore, the electronic device 410 is basically required to call a keyword, and when this is preceded, the electronic device 410 enters a voice command standby state, but in the case of some types of work, that is, voice within a short time. If the operation is likely to be retried, the voice instruction standby state can be immediately entered without calling the keyword.

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

The devices described above may be implemented by hardware components, software components, and / or combinations of hardware components and software components. For example, the apparatus 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 program gate array), a PLU (programmable log unit), a microprocessor, and the like. Alternatively, it may be implemented using one or more general purpose computers 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 processor may be described as being used, but one of ordinary skill in the art may appreciate that the processor 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 parallel processors, are also possible.

The software may include computer programs, code, instructions, or a combination of one or more of these, configuring the processing equipment to operate at will, or instructing the processing equipment independently or collectively. You may do it. The software and / or data is embodied in any type of machine, component, physical device, computer recording medium or device to be interpreted based on the processing device or to provide instructions or data to the processing device. good. The software is distributed on a networked computer system and may be recorded or executed in a distributed state. The software and data may be recorded on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed by various computer means and recorded on a computer-readable medium. At this time, the medium may be a continuous recording of a program that can be executed by a computer, or may be a temporary recording for execution or download. Further, the medium may be various recording means or storage means in the form of a combination of a single piece of hardware or a plurality of pieces of hardware, but the medium is not limited to a medium directly connected to a certain computer system, and is distributed on a network. It may exist. Examples of media include hard disks, floppy (registered trademark) disks, magnetic media such as magnetic tapes, optical media such as CD-ROMs and DVDs, optical magnetic media such as floptic discs, and the like. And ROM, RAM, flash memory, etc., and may be configured to record program instructions. Examples of other media also include recording media or storage media managed by application stores that distribute applications, sites that supply or distribute various other software, servers, and the like.

As described above, the embodiments have been described based on the limited embodiments and drawings, but those skilled in the art will be able to make various modifications and modifications from the above description. For example, the techniques described may be performed in a different order than the methods described, and / or components such as the systems, structures, devices, circuits described may be in a form different from the methods described. Appropriate results can be achieved even if they are combined or combined, or confronted or replaced by other components or equivalents.

Therefore, even if the embodiments are different, they belong to the attached claims as long as they are equal to the claims.

100: Electronic device 110: User 210: External server

Claims (16)

It is an artificial intelligence continuous conversation method realized by a computer.
When the conversation activation trigger is recognized while the conversation function is inactive, the stage of activating the conversation function and entering the voice command standby state,
When a voice command is received in the voice command waiting state, the stage of executing the work corresponding to the voice command, and after executing the work, immediately shifts to the next voice command waiting state based on the type of the work. or providing a continuous conversation function by entering, or the next voice command or as entering the standby state to deactivate the conversation function, stage of determining,
Including
Wherein the step of determining includes the type of the work when the work requiring a sustained operation determines that to deactivate the conversation function and do not enter into the next voice command standby state including,
Artificial intelligence continuous conversation method. The keyword specified in the wakeup word is used as the conversation activation trigger,
The artificial intelligence continuous conversation method further
The first aspect of the present invention includes a step of maintaining an active state of the conversation function and automatically switching to the next voice command standby state even if the keyword is not called when it is determined to provide the continuous conversation function. The described artificial intelligence continuous conversation method. The decision stage is
The artificial intelligence continuous conversation method according to claim 1 or 2 , wherein when the work corresponding to the voice command is not a work that requires continuous operation, it is determined to provide the continuous conversation function. The decision stage is
When the work corresponding to the voice command corresponds to the second work among the first work that is continued until the end command is input and the second work that ends at a predetermined time even if there is no end command. The artificial intelligence continuous conversation method according to claim 1 or 2 , which comprises determining to provide the continuous conversation function. The work that requires continuous operation is work that requires continuous operation until an end command is input.
The decision stage is
The artificial intelligence continuous conversation method according to claim 1 or 2 , wherein when the work corresponding to the voice command includes a conversational operation requiring a user's response, it is determined to provide the continuous conversation function. The decision stage is
Based on a result of learning the execution pattern by working, when the operator corresponding to the voice command corresponds to work additional voice instruction is predicted, and determining to provide the continuous conversation function, according to claim 1 or artificial intelligence continuous conversation method described in 2. The decision stage is
The artificial intelligence according to claim 1, wherein when the work corresponding to the voice command is a work related to the work requiring the continuous operation, it is determined to deactivate the conversation function. Continuous conversation method. 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 on which the computer program according to claim 8 is recorded. It is an artificial intelligence continuous conversation system realized by a computer.
Includes at least one processor implemented to execute computer-readable instructions
The at least one processor
When the conversation activation trigger is recognized while the conversation function is inactive, the process of activating the conversation function and entering the voice command standby state,
When a voice command is received in the voice command waiting state, the process of executing the work corresponding to the voice command, and after executing the work, immediately shifts to the next voice command waiting state based on the type of the work. or providing a continuous conversation function by entering, or the next or to deactivate the conversation function as entering the voice command standby state, excessive extent of determining,
Process and
The process of the determination, that the type of the work when the work requiring a sustained operation determines that to deactivate the conversation function and do not enter into the next voice command standby state include,
Artificial intelligence continuous conversation system. The keyword specified in the wakeup word is used as the conversation activation trigger,
The at least one processor further
A process of maintaining the active state of the conversation function and automatically switching to the next voice command standby state even if the keyword is not called when it is determined to provide the continuous conversation function.
Processing the artificial intelligence continuous conversation system according to claim 10. The decision process is
The artificial intelligence continuous conversation system according to claim 10 or 11 , wherein if the work corresponding to the voice command is not a work that requires continuous operation, it is determined to provide the continuous conversation function. The decision process is
When the work corresponding to the voice command corresponds to the second work among the first work that is continued until the end command is input and the second work that ends at a predetermined time even if there is no end command. The artificial intelligence continuous conversation system according to claim 10 or 11 , which comprises determining to provide the continuous conversation function. The work that requires continuous operation is work that requires continuous operation until an end command is input.
The decision process is
The artificial intelligence continuous conversation system according to claim 10 or 11 , wherein when the work corresponding to the voice command includes a conversational operation requiring a user's response, it is determined to provide the continuous conversation function. The decision process is
Based on a result of learning the execution pattern by working, when the operator corresponding to the voice command corresponds to work additional voice instruction is predicted, and determining to provide the continuous conversation function, claim 10 or 11. The artificial intelligence continuous conversation system according to 11. The decision process is
The artificial intelligence continuation according to claim 10, wherein when the work corresponding to the voice command is a work related to the work requiring the continuous operation, it is determined to deactivate the conversation function. Conversation system.

Images