JP2019120935A - Method for providing service using plural wake word in artificial intelligence device and system thereof - Google Patents

Abstract

To provide a method for providing a service using a plurality of wake word in an artificial intelligence device, and to provide a system thereof.SOLUTION: A service-providing system includes: a step of defining a plurality of wake words to be used as a dialog-activating trigger for activating a dialog function of an electronic apparatus, and of setting desired reply information range to each of wake words; a step of activating the dialog function when one specified wake word is recognized among the plurality of wake words by an audio interface of the electronic apparatus; and a step of providing reply information based on the desired reply information range corresponding to the specific wake word, to an audio query inputted in a state where the dialog function is activated.SELECTED DRAWING: Figure 6

Description

  The following description relates to an artificial intelligence dialogue system.

  In general, artificial intelligence dialogue systems used in personal secretarial systems, artificial intelligence (AI) speakers, chatbot platforms, etc. understand the intentions of command words issued by humans and the corresponding responses Has adopted a scheme to provide

  In the artificial intelligence dialogue system, mainly, when a functional request is transmitted from a human, an apparatus provides an answer to such a human request, and a voice of a user is input by a microphone. Based on the received and received voice input, control of the operation of the device and the provision of content is performed.

  For example, Patent Document 1 (publication date: December 30, 2011) discloses a technique capable of multi-controlling a plurality of multimedia devices in a home according to a user's voice command in a home network service.

  A typical artificial intelligence dialogue system uses a pre-defined wake word (e.g. the name of the instrument etc) as an interaction activation trigger to activate the instrument. This causes the artificial intelligence device to perform the speech recognition function based on the wake word. For example, when the user gives a device name, the device is activated, and then enters a standby mode to receive the user's voice query.

Korean Published Patent No. 10-2011-0139797

  Provided are methods and systems that can partition two or more wakewords of an artificial intelligence device providing a voice-based interface, and partition service targets according to each wakeword.

  A method for providing voice-based services implemented in a computer-implemented electronic device, comprising: defining a plurality of wake words to be used as an interactive activity trigger for activating an interactive function of the electronic device; each wake word Setting a desired response information range in the step of activating the interactive function when a specific wake word of the plurality of wake words is recognized by the voice interface of the electronic device; A method of providing a voice-based service, comprising providing response information based on a desired response information range corresponding to the specific wakeword to a voice query input in a state where an interactive function is activated.

  According to one aspect, the plurality of wake words and the desired response information range of each wake word may be directly set by the user of the electronic device.

  According to another aspect, the providing step comprises, in response to the voice input received by the voice interface, constructing and transmitting a query including the desired response information range to the server, and as a response to the query. Receiving response information from the server based on a desired response information range corresponding to a specific wakeword may be output at the voice interface.

  According to yet another aspect, the providing step includes communicating voice input received at the voice interface as a query for a service request along with information regarding the particular wakeword, and responding to the query. The method may include the step of: receiving, from the server, response information based on a desired response information range corresponding to the particular wakeword and outputting the response information at the voice interface.

  According to another aspect, the response information may include a search result corresponding to the desired response information range at a higher priority than a search result not corresponding to the desired response information range.

  According to another aspect, the response information may be limited to search results corresponding to the desired response information range.

  Further, according to another aspect, the response information may be configured based on personalization information in consideration of past usage details of the user of the electronic device.

  According to another aspect, an age group may be set for each wake word for the plurality of wake words.

  According to still another aspect, the providing may provide search information corresponding to an age group of the particular wakeword as the response information, or in an output form corresponding to an age group of the particular wakeword. The response information may be provided.

  A method of providing a voice-based service executed by a computer implemented by a server, comprising: defining a plurality of wake words to be used as an interaction activation trigger for activating an interaction function of an electronic device; and requesting each wake word Setting a response information range, receiving from the electronic device a query including information on a particular wakeword used to activate the interactive function among the plurality of wakewords, for the particular wakeword A method of providing a voice-based service, comprising: configuring response information based on a corresponding desired response information range; and providing the configured response information to the electronic device as a response to the received query.

  According to another aspect of the present invention, there is provided a computer program stored in a computer-readable recording medium for causing a computer to execute the method for providing voice-based services in combination with a computer.

  According to another aspect of the present invention, there is provided a computer-readable recording medium having recorded thereon a program for causing a computer to execute the method for providing voice-based services.

  A system for providing voice-based services of an electronic device implemented by a computer, comprising at least one processor implemented to execute computer readable instructions, the at least one processor interacting with the electronic device A wake word setting unit that defines a plurality of wake words used as an interaction activation trigger for activating a function, and sets a desired response information range for each wake word, the plurality of wake words in the voice interface of the electronic device A voice processing unit that activates the dialog function when any one of the specific wake words is recognized, and the specific wake for a voice query input with the dialog function activated. Provide response information based on the desired response information range corresponding to the word It includes a response processing unit, to provide a voice-based service providing system.

FIG. 1 illustrates an example of a service environment utilizing a voice based interface in accordance with one embodiment of the present invention. FIG. 7 is a diagram illustrating another example of a service environment utilizing a voice-based interface according to an embodiment of the present invention. FIG. 5 illustrates an example of a cloud artificial intelligence platform in one embodiment of the present invention. It is a block diagram for demonstrating the internal structure of an electronic device and a server in one Embodiment of this invention. FIG. 5 illustrates an example of a component that may be included in a processor of an electronic device in an embodiment of the present invention. 5 is a flowchart illustrating an example of a method that an electronic device may perform in an embodiment of the present invention. FIG. 6 is an exemplary view for explaining a wakeword for which a service target is identified according to an embodiment of the present invention. FIG. 6 illustrates an example of components that may be included in a processor of a server in an embodiment of the present invention. FIG. 5 is a flow chart illustrating an example of a method that the server may perform in an embodiment of the present invention.

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

  The voice-based service providing system according to an embodiment of the present invention may be implemented by an electronic device that provides an interface that operates based on interaction with a user. At this time, the voice-based service providing system may use two or more wake words to activate the device, and may divide the operation of the device according to each wake word.

  The voice-based service providing method according to an embodiment of the present invention may be performed by the electronic device described above. At this time, a computer program according to an embodiment of the present invention may be installed and driven in the electronic device, and the electronic device may provide voice-based service according to an embodiment of the present invention according to control of the computer program to be driven. You may carry out the method. The computer program described above may be stored in a computer readable recording medium in order to cause a computer to execute a voice based service providing method in combination with a computer-implemented electronic device.

  FIG. 1 is a diagram showing an example of a service environment utilizing a voice-based interface in an embodiment of the present invention. In the embodiment of FIG. 1, in the technology of connecting and controlling devices in the home such as a smart home (smart home) and home network service, the electronic device 100 which provides an interface operating based on voice is the user 110 An example of recognizing and analyzing the voice input “turn off the electricity” received by speech and controlling the power supply of the indoor lighting device 120 connected to the electronic device 100 via the internal network in the home is shown.

  For example, in addition to the in-home lighting device 120 described above, home-use devices include household appliances such as TVs, personal computers (PCs), peripheral devices, air conditioners, refrigerators, and robot cleaners, as well as water, electricity, and air conditioning. A variety of devices connected and controlled online may be included, such as energy consuming devices such as devices, security devices such as door locks and surveillance cameras, etc. Also, the internal network may be wired network technology such as Ethernet (registered trademark (Ethernet)), HomePNA, IEEE 1394, Bluetooth (registered trademark (Bluetooth)), UWB (ultra Wide Band), ZigBee, Wireless 1394 Wireless network technology such as Home RF may be utilized.

  The electronic device 100 may be one of in-home devices. For example, the electronic device 100 may be one of devices such as an artificial intelligence speaker or a robot cleaner provided in a house. In addition, the electronic device 100 includes a smart phone (smart phone), a mobile phone, navigation, a notebook pancon, a terminal for digital broadcasting, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet, a game console, a wearable device, IoT It may be a mobile device of the user 110 such as an (internet of things) device, a virtual reality (VR) device, an augmented reality (AR) device or the like. As described above, the electronic device 100 is not particularly limited as long as it is a device including a function that can be connected to the in-home device in order to receive the voice input of the user 110 and control the in-home device. Also, depending on the embodiment, the mobile device of the user 110 described above may be included as an in-home device.

  FIG. 2 is a diagram showing another example of a service environment utilizing a voice-based interface in an embodiment of the present invention. FIG. 2 shows that the electronic device 100 providing an interface operating based on speech recognizes and analyzes the speech input “today's weather” received by the speech of the user 110, and transmits it from the external server 210 through the external network. An example of acquiring information on the weather and outputting the acquired information by voice as "Today's weather is ..." is shown.

  For example, the external network may be a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), the Internet, etc. Any one or more of the networks may be included.

  Also in the embodiment of FIG. 2, the electronic device 100 may be one of the in-home devices or one of the mobile devices of the user 110, and receives and processes the voice input of the user 110. The device is not particularly limited as long as it is a device including a function to connect to the external server 210 via the external network and a function to provide the user 110 with a service or content provided by the external server 210.

  As described above, the electronic device 100 according to the embodiment of the present invention is not particularly limited as long as it is a device capable of processing user commands including voice input received by the speech of the user 110 at the voice-based interface. Good. For example, the electronic device 100 may process user instructions 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 is recognized Processing such as analysis of recognized speech input, synthesis of speech provided to the user, and the like may be performed on an external platform linked with the electronic device 100.

  FIG. 3 is a diagram showing an example of a cloud artificial intelligence platform in an embodiment of the present invention. FIG. 3 shows the electronics 310 and the cloud artificial intelligence platform 320 (Brain), and the content service 330.

  As an example, the electronic device 310 may mean a device provided in a home, and may include at least the electronic device 100 described above. Such an electronic device 310 or an application installed and driven on the electronic device 310 (hereinafter referred to as an application) may be linked to the cloud artificial intelligence platform 320 via the interface connect 340. Here, the interface connect 340 may provide a developer with a software development kit (SDK) and / or a development document for developing an application installed and driven in the electronic device 310 or the electronic device 310. In addition, the interface connect 340 may provide an application program interface (API) that allows an application installed and driven in the electronic device 310 or the electronic device 310 to utilize a function provided by the cloud artificial intelligence platform 320. As a specific example, a developer may use an SDK (Software Development Kit) provided by Interface Connect 340 and / or a device or application developed using a development document using a cloud provided by Interface Connect 340. The functions provided by the artificial intelligence platform 320 can be utilized.

  Here, the cloud artificial intelligence platform 320 may provide functionality to provide voice based services. For example, the cloud artificial intelligence platform 320 recognizes a received voice, and a voice processing module 321 for synthesizing an output voice, a vision processing module 322 for analyzing and processing a received video or video, and a received voice Dialog processing module 323 for determining the appropriate dialog to output a suitable voice, a recommendation module 324 for recommending a function suitable for the received voice, artificial intelligence uses language on a sentence basis based on data learning Various modules may be included to provide voice-based services, such as Neural Machine Translation (NMT) 325, which assists in translating.

  For example, in the embodiments of FIGS. 1 and 2, the electronic device 100 may transmit to the cloud artificial intelligence platform 320 using an API that provides the user 110 voice input at the interface connect 340. In this case, the cloud artificial intelligence platform 320 may recognize and analyze the received voice input using the above-described modules 321 to 325, and synthesize and provide an appropriate response voice according to the received voice input. , And may recommend appropriate action.

  In addition, the extension kit 350 may provide a development kit that allows a third party content developer or company to realize new voice infrastructure functions based on the cloud artificial intelligence platform 320. For example, in the embodiment of FIG. 2, the electronic device 100 may transmit the voice input of the user 110 to the external server 210, and the external server 210 utilizes the API provided by the expansion kit 350 to provide a cloud artificial intelligence platform. An audio input may be sent to 320. 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 provides recommendation information for functions to be processed by the voice input. May be provided to the external server 210. As an example, in FIG. 2, the external server 210 may send the speech input "today's weather" to the cloud artificial intelligence platform 320, which is extracted from the cloud artificial intelligence platform 320 by recognizing the speech input "today's weather" Suppose that the keywords "Today's" 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's" and "Weather", and the text information generated by the cloud artificial intelligence platform 320 is May be resent. At this time, the cloud artificial intelligence platform 320 may synthesize the text information by speech 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 is received from the user 110 by outputting the synthesized voice "Today's weather ..." from the speaker Voice input "today's weather" may be processed. At this time, the electronic device 100 is for implementing device operation and content provision based on the interaction with the user.

  FIG. 4 is a block diagram for explaining an internal configuration of the electronic device and the server in 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 one computer device that implements the external server 210 or the cloud artificial intelligence platform 320 described above.

  The electronic device 410 and the server 420 may include memories 411, 421, processors 412, 422, communication modules 413, 423, and input / output interfaces 414, 424. The memories 411 and 421 are computer readable recording media such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), flash memory, and the like. Permanent mass storage device. Here, a permanent mass storage device such as a ROM, an SSD, a flash memory, a disk drive, etc. may be included in the electronic device 410 or the server 420 as another permanent storage device divided from the memories 411 and 421. . In addition, the memory 411, 421 includes an operating system and at least one program code (for example, a code for an application installed on the electric device 410 and driven by the electronic device 410 for providing a specific service, etc.) May be stored. 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 the memory 411, 421 through the communication module 413, 423 which is not a computer readable recording medium. For example, at least one program may be an electronic device 410 based on a computer program (for example, the application described above) installed by a file provided by a file distribution system that distributes a developer or an application installation file via the network 430. May be loaded into the memory 411 of

  Processors 412, 422 may be configured to process computer program instructions by performing basic arithmetic operations, logical operations, and input / output operations. The instructions may be provided to the processor 412, 422 by the memory 411, 421 or the communication module 413, 423. For example, the processors 412, 422 may be configured to execute instructions received in accordance with program code stored in a recording device, such as the memories 411, 421.

  The communication module 413, 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 be other electronic devices or other It may provide functionality to communicate with the server. As an example, a request generated by the processor 412 of the electronic device 410 according to the program code stored in the recording device such as the memory 411 may be transmitted to the server 420 via the network 430 according to the control of the communication module 413. Conversely, 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 423 and the network 430 and the communication module 413 of the electronic device 410. It may be done. For example, control signals, commands, contents, files and the like 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 electronic device 410. (It may be stored in the above-mentioned permanent storage device).

  Input / output interface 414 may be a means for interfacing with input / output device 415. For example, the input device may include devices such as a keyboard, a mouse, a microphone, a camera and the like, and the output device may include devices such as a display, a speaker, a haptic feedback device and the like. As another example, the input / output interface 414 may be a means for interfacing with a device such as a touch screen in which functions for input and output are integrated. The input / output device 415 may be configured of the electronic device 410 and one device. Also, the input / output interface 424 of the server 420 may be a means for interfacing with the server 420 or with an input or output device (not shown) that the server 420 can include. As a more specific example, when the processor 412 of the electronic device 410 processes the instructions of the computer program loaded in the memory 411, a service screen or the like configured using data provided by the server 420 or another electronic device Content may be displayed on a display via input / output interface 414.

  Also, in other embodiments, the electronic device 410 and the server 420 may include fewer or more components than those shown in FIG. Most prior art components are not described in detail herein. The electronic device 410 may be realized to include, for example, at least a part of the input / output device 415 described above, and may be a transceiver, a GPS (Global Positioning System) module, a camera, various sensors, a database, etc. May also include other components. As a more specific example, when the electronic device 410 is a smartphone, an acceleration sensor or a gyro sensor generally included in the smartphone, an operation sensor, a camera module, physical various buttons, a button using a touch panel, an input / input It may be realized to be further included in various components 3 such as an output port, a vibrator for vibration, etc., and an electronic device 410.

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

  The electronic device 410 providing such an audio interface is activated by the wakeword and receives an audio input uttered by the user in the activated state as a query. Activation may be referred to as activation or enable, etc., and deactivation may be referred to as deactivate or disable, etc. The voice query input in the activated state of the electronic device 410 is transmitted to the server 420, and the server 420 searches data to construct response information so as to conform to the voice query, and finally the response information is the electronic device. It is output at 410.

  In the case of the voice interface, since the result corresponding to the voice query is provided by voice output, the information that can be output is extremely limited, and it is necessary to provide more sorted information. Since the usual sorting process is, for example, in the form of providing only a small portion of the high-order results of the retrieved data, the burden of determining the information conforming to the user's query is heavy, and the result is also an individual's It depends on your preference.

  In order to solve this, a method of digitizing voice authentication (voice ID) based on machine learning, a method of setting in advance the user's interest, and based on a past record (for example, usage record or usage history) Personalization (i.e., individual customization) may be achieved, such as by a method of capturing user preferences. However, such personalization methods have the problem that a learning process and a setting process are separately required, and long-term usage records are required, and furthermore, privacy is related by the outflow of personalized information. Problems may be of concern.

  In the present invention, the wakeword for activating the device can be used as an application for limiting the service to the user's area of interest, without going through a separate personalization process. The electronic device 410 according to the present invention, in a state in which a plurality of wake words capable of specifying a category to be serviced is set, determines the corresponding wake word based on the wake word spoken by the user for device activation. A corresponding category of service can be provided.

  FIG. 5 is a block diagram illustrating an example of components that may be included in a processor of an electronic device according to an embodiment of the present invention, and FIG. 6 is executed by the electronic device according to an embodiment of the present invention. FIG. 6 is a flow chart illustrating an example of a possible method.

  A voice-based service providing system may be configured in the electronic device 410 according to the present embodiment. The voice based service providing system may be configured as a PC based program or an application dedicated to a mobile terminal. The voice-based service providing system according to the present embodiment may be realized in the form of an independently operating program, or may be configured in an in-app form of a specific application and operable on the specific application. May be realized.

  For example, based on instructions provided by an application installed in the electronic device 410, the voice-based service providing system implemented in the electronic device 410 may execute the voice-based service providing method. In order to execute the voice-based service providing method according to FIG. 6, the processor 412 of the electronic device 410 includes the wakeword setting unit 510, the voice processing unit 520, the query transfer unit, and the components as shown in FIG. A response processor may be provided. In some embodiments, components of processor 412 may optionally be included or excluded from processor 412. Also, in some embodiments, the components of processor 412 may be separate or merged to represent the functionality of processor 412.

  The processor 412 and the components of the processor 412 may control the electronic device 410 to execute the steps 610 to 650 included in the voice-based service providing method of FIG. 6. For example, processor 412 and components of processor 412 may be implemented to execute instructions in code of the operating system that memory 411 includes and code of at least one program.

  Here, the components of the processor 412 are executed by the processor 412 in accordance with instructions provided by program code stored in the electronic device 410 (for example, instructions provided by an application driven by the electronic device 410). It may be a representation of different functions of For example, voice processor 520 may be utilized as a functional representation of processor 412 that controls electronic device 410 according to the instructions described above such that electronic device 410 processes voice input by user speech.

  At step 610, the processor 412 may read the necessary instructions from the memory 411 into which the instructions associated with the control of the electronic device 410 have been loaded. In this case, the read instruction may include an instruction to control the processor 412 to execute steps 620 to 650 described below.

  In operation 620, the wakeword setting unit 510 may define a wakeword to be used as an interaction activation trigger for activating the interaction function of the electronic device 410, and set a desired response information range for each wakeword. In the present invention, the wake word is used as an interaction activation trigger for activating the interaction function of the electronic device 410, and at the same time as an application for specifying a desired response information range which is a service object desired by the user. Be done. The wake words may be defined and set for each category for the service targets that can be provided to the user, and may be set arbitrarily by the user. The desired response information range specifies a service target, that is, a range for searching information, and in this specification, a category for dividing the service target will be described as a representative example.

  Referring to FIG. 7, a plurality of wake words 701 are defined, and in each wake word 701, a category 702 to be served, a language 703, and an additional search word 704 are specified. The wake word setting unit 510 (FIG. 5) may set the wake word 701, the category 702, the language 703, and the additional search word 704 as shown in FIG. May provide an editable function. For example, as shown in FIG. 7, the basic wakeword targeting the entire service without specifying the category is set as "Siri" (in this case, the category is set as "All"), and "baseball" is called. The wake word for the category is set as "Dr. Baseball", and the wake word for adding an additional search term ("Cooking method" or "Recipe") to the search word for the category "Cooking" as "Chef" The wake word set and limited to only English content may be set as "Connie." Thus, various wake words 701 identify a category 702 indicating the field of information service, a language 703 indicating the language of information to be provided, and an additional search term 704 indicating a search term additionally used at the time of information search. You may The wake word 701 may be an official language that applies equally to all users who use the service, but as another example, it may be any service target that the user frequently uses or is interested in It is also possible that the term is directly specified. Even if an optional wake word 701 is set for the category of information that the user wants to receive service (for example, child care information is "Jane mom") or a language (for example, "ne Hao" if Chinese content is desired) Good. Although not shown in the figure, the type of content desired (image, video, map, etc.), content source (group, blog, specific website, etc.), search date (within the last week, June 2002) Etc. can also be limited. Furthermore, it is also possible to divide service users and age groups by dividing wake words into two or more. For example, "James" may be for adult users and "Brown" may be for children users. That is, each wake word can specify not only the service target but also the user layer of the service. A common, predefined or user-defined wakeword 701 and service target category 702 of each wakeword 701 are stored on the electronic device 410 and the server 420 and are used to distinguish service targets by interworking. May be used. The wake word 701 may be mounted on the electronic device 410 and the server 420 in an audio form, a character value, or the like.

  Referring back to FIG. 6, in operation 630, the voice processing unit 520 detects the wake of one of the plurality of wake words that can identify the category of the service target. The interactive function may be activated. The audio processing unit 520 is configured such that the audio input received by the audio interface (for example, a speaker) corresponds to any one wake word among the plurality of wake words when the interactive function of the electronic device 410 is inactivated. If so, the interactive function may be activated automatically. At this time, the voice activation unit 520 may identify whether the preprocessed voice corresponds to a wakeword after performing a preprocessing process such as noise removal on the voice input received by the voice interface. .

  In operation 640, the query transfer unit 530 may respond to a specific wake word used to activate the interactive function for voice input received by the voice interface with the interactive function of the electronic device 410 activated. The query including the reply information range may be configured and communicated to server 420. In other words, the query transfer unit 530 configures the query specified in the category corresponding to the specific wake word for which the service target is used for activating the interactive function, in response to the voice input received by the voice interface, It may be communicated to 420. As an example, the query transfer unit 530 may transfer voice input received with the interactive function activated as a query for a service request along with information on a specific wakeword. At this time, the query transfer unit 530 may configure the particular wakeword received by the voice interface and the voice input received following the particular wakeword as the query of the voice signal form as it is, or Character values obtained by converting speech signals received by the interface into text by speech recognition technology may be configured as queries. The query transfer unit 530 may simultaneously transmit the wake word and the voice input after the wake word to the server 420 or may transmit them in order. The query for the service request may be limited to the service target that the user intends to request, and this may be specified in the category corresponding to the wakeword used by the user. The query transmitted from the electronic device 410 to the server 420 may include the wakeword itself or the identification code used by the user, or may include category information corresponding to the wakeword used by the user. For example, in the case of the wake word example of FIG. 7, when the user utters as "Siri, what is the result of today's professional baseball?" While using the wake word "Siri", the service target is limited If there is no query transmitted to the server 420, but uttered like "Dr. baseball, what is the result of professional baseball today?", The query in which the category of service target is specified as "baseball" is sent to the server 420. It may be transmitted.

  In step 650, the response processing unit 540, as a response to the query from the server 420, response information based on the desired response information range corresponding to the wakeword used by the user, that is, the specific information used for activating the interactive function. The reply information including the service information of the category corresponding to the wake word may be received and output. The server 420 may provide the service information encoded with the feature of the wake word used by the user of the electronic device 410 for activation of the device, as a response, the result of the search with higher priority than other services. The response processing unit 540 may output the response information provided from the server 420 by using a voice interface. In other words, according to the present invention, it is possible to identify the service target only by the wake word used for activating the device without the complicated personalization process for identifying the service, and the wake word is specified by the wake word. It is possible to provide the retrieved response information with higher priority to the service. At this time, when the user layer of the service is specified by the wake word, the server 420 may provide the response information corresponding to the user layer, or the response processing unit 540 may output the information suitable for the user layer. The response information may be output depending on the form. For example, the child user may output the response information in a voice different from that of the adult user, and the form of the response sentence uttered from the voice interface may be generated to meet the child's level. . Therefore, by specifying the service target by the wake word used to activate the electronic device 410, the provided information will wake even if the same query (that is, the query content after the wake word is the same). Each word is different, which allows the user to obtain information suitable for personal interests and age groups without having to go through a separate setting process. Further, the response processing unit 540 can also output the received response information as a response to the query in the form of video and other forms in addition to voice output from the voice interface, and such response information can be Different information may be included, such as visual, auditory, tactile output etc.

  FIG. 8 is a diagram showing an example of components that can be included in a processor of a server in an embodiment of the present invention, and FIG. 9 is a server that can be executed in an embodiment of the present invention 3 is a flow chart illustrating an example of a method.

  A voice-based service providing system may be configured in the server 420 according to the present embodiment. The server 420 provides voice-based services to the client electronic device 410, and may provide response information to the service request received from the electronic device 410.

  In order to execute the voice-based service providing method according to FIG. 9, the processor 422 of the server 420 may include an information configuration unit 810 and an information providing unit 820 as components as shown in FIG. In some embodiments, components of processor 422 may optionally be included or excluded from processor 422. Also, in some embodiments, the components of processor 422 may be separate or merged to represent the functionality of processor 422.

  The processor 422 and the components of the processor 422 may control the electronic device 410 to execute steps 910 to 930 included in the voice-based service providing method of FIG. 9. For example, the processor 422 and the components of the processor 422 may be implemented to execute instructions according to the code of the operating system that the memory 421 includes and the code of the at least one program.

  Here, the components of the processor 422 may be representations of different functions of the processor 422 that are executed by the processor 422 in accordance with instructions provided by program code stored in the server 420. For example, the information configuration unit 810 may be used as a functional representation of the processor 422 that controls the server 420 according to the instructions described above so that the server 420 configures reply information.

  At stage 910, the processor 422 may read the necessary instructions from the memory 421 into which the instructions associated with the control of the server 420 have been loaded. In this case, the read instructions may include instructions for controlling the processor 422 to perform steps 920 and 930 described below.

  In operation 920, the information configuration unit 810 may configure, in response to the query received from the electronic device 410, response information including service information of a category corresponding to a specific wake word in the query. First, the information configuration unit 810 may perform natural language processing on the query received from the electronic device 410 to extract the intention and target of the corresponding query. The query received from the electronic device 410 may include information on the particular wakeword that the user has used to activate the device. The server 420 includes (or stores) user definitions for the wake word (including the wake word 701, the category 702, the language 703, and the additional search word 704 described above with reference to FIG. 7) for the user of the electronic device 410. It is done. Based on this user definition, the information configuration unit 810 may grasp a service target desired by the user from a specific wakeword included in the query. As an example, the information configuration unit 810 returns a result of searching for service information of a category corresponding to a wake word used by the user of the electronic device 410 for activation of the device with higher priority than other services. It may be configured as information. As another example, the information configuration unit 810 limits the service target for the query to the category corresponding to the wake word used by the user of the electronic device 410 to activate the device, and configures the response information by the information of the limited service. You may Therefore, the information configuration unit 810 can use the wake word used by the user to activate the device as the information selection criterion for forming the response information.

  The information configuration unit 810 may adjust the amount and quality of information to respond by grasping the service that the user desires from the specific wakewords included in the query. In addition, the information configuration unit 810 may configure response information by adding personalization information in consideration of the past usage details associated with the user of the electronic device 410 to the query received from the electronic device 410. The past usage breakdown may be stored on the server 420 for each user and may include records for query and reply information. For example, from the query “Dr. Baseball, how was the game of today's professional baseball team X?”, It can be understood that the user is interested in “professional baseball team X”, and the user's interests are recorded in the database, for example Ru. Thereafter, when the query “Dr. baseball, how was the game today?” Is uttered, the baseball information of “professional baseball team X” is used as the reply information based on the personalization information by the user's previous query. It may be configured. This eliminates the need for the user to ask the same type of query each time the user speaks a query, and allows the user to obtain the desired information with a simpler query. Since the voice response is a time consuming communication method in which the user must listen to everything until the end, it is important in the user experience to compose the important information with the simplest possible reply. Ultimately, it is possible to say that the role of personalization is to configure responses by focusing on the core contents as short as possible based on the breakdown of past usage. Also, as another example, when the short answer “Professional baseball team X lost 3: 5 to professional baseball team Y” is made in response to the same question in comparison with the past usage breakdown “What is the cause of loss? If you are a user who continued to ask additional questions, such as “?” Or “S, did you pitch a board,” it is also possible to construct more rich response information if asked the same thing next time. . For example, against the same later question such as “Dr. Baseball, how was the game of today's professional baseball team X”, while comparing with recent responses based on the past usage breakdown, “Today Unlike the previous day's game, the professional baseball team X lost 3: 5 to the professional baseball team Y. The S player, who is the MVP player, did not get on the board today. May be Or, based on the list of recent questions, “Pro baseball team X won 8: 1 in a match with today's pro baseball team Y. The decisive factor for the victory is the S-player's eight back 2 run home runs. The highlight is 4 times the front and 8 times the back. ”It is possible to compose the response information by rich and rich information of high quality.

  In operation 930, the information provider 820 may provide the electronic device 410 with the response information configured in operation 920 as a response to the query received from the electronic device 410. The response information may preferentially include service information that conforms to the characteristics of the wakeword used by the user to activate the device, and may include audio output, as well as information capable of video and other forms of output. It is good.

  Therefore, since the server 420 can immediately grasp the user's interest by the wake word used by the user to activate the device, the server 420 can effectively sort and configure the response information to the user query. When the user tries to search for a field of interest, the user can receive a desired result by using the wake word specified for the field. In other words, for multiple wakewords, the information provided may be different for each wakeword, so that the user does not go through a personalization process, for a particular consumer or personal interest, or You can receive information that matches your knowledge level.

  The above-described apparatus 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 arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), and a microprocessor. Or may be implemented using one or more general purpose or special purpose computers, 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 software execution, access data, and store, manipulate, process, and generate data. Although one processor may be described as being used for the convenience of understanding, it is understood by those skilled in the art that the processor may include a plurality of processing elements and / or a plurality of types of processing elements. You will understand. For example, the processing device may include multiple processors or one processor and one controller. Other processing arrangements are also possible, such as parallel processors.

  The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to operate as desired, instructing the processing unit to operate independently or collectively. You may The software and / or data may be embodied in any type of machine, component, physical device, computer storage medium or device to be interpreted based on the processing device or to provide instructions or data to the processing device. Good. The software may be distributed on computer systems connected by a network, and may be stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

  The method according to the embodiments may be realized 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 store the computer executable program or may temporarily store it for execution or download. Also, the medium may be various recording means or storage means in the form of combination of one or more hardware, and should not be limited to the medium directly connected to a certain computer system, and distributed on the network It may be present. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, magneto-optical media such as floppy disks, And ROM, RAM, flash memory, etc., and may be configured to store program instructions. In addition, as another example of the medium, an application store that distributes an application, a site that supplies or distributes various other software, a recording medium managed by a server, or a storage medium may be mentioned.

  Although the embodiments have been described based on the limited embodiments and the drawings as described above, various modifications and variations can be made by those skilled in the art from the above description. For example, components described in the systems, structures, devices, circuits, and the like may be performed in a different order from that of the methods described and / or different from those described in the methods described. Appropriate results can also be achieved if combined or combined, or counter-located or replaced by other components or equivalents.

  Therefore, even different embodiments, which are equivalent to the scope of the claims, belong to the appended claims.

412: processor 510: wake word setting unit 520: voice processing unit 530: query transfer unit 540: response processing unit

Claims (20)

A voice-based service providing method implemented by an electronic device realized by a computer, comprising:
Defining a plurality of wake words used as a dialog activation trigger for activating the dialog function of the electronic device, and setting a desired response information range for each wake word;
Activating the interactivity function when the specific wakeword of the plurality of wakewords is recognized in the audio interface of the electronic device, and the interactivity function is input in an activated state; Providing a response information based on a desired response information range corresponding to the specific wakeword to the voice query.   The method of claim 1, wherein the plurality of wake words and the desired response information range of each wake word are directly set by a user of the electronic device. The providing step may
In response to the voice input received by the voice interface, constructing a query including the desired response information range and transmitting it to the server, and as a response to the query, the desired response information range corresponding to the specific wakeword The method according to claim 1, further comprising the step of: receiving the response information from the server and outputting the response information on the voice interface. The providing step may
Conveying to the server a voice input received at the voice interface as a query for a service request along with information on the particular wakeword, and as a response to the query, desired reply information corresponding to the particular wakeword The voice based service providing method according to claim 1, further comprising the step of receiving from the server response information based on a range and outputting the information on the voice interface.   The method according to claim 1, wherein the response information includes a search result corresponding to the desired response information range in a higher priority than a search result not corresponding to the desired response information range.   The method according to claim 1, wherein the response information is limited to a search result corresponding to the desired response information range.   The method according to claim 1, wherein the response information is configured based on personalization information in consideration of past usage details of the user of the electronic device.   The method of claim 1, wherein an age range is set for each wake word for the plurality of wake words. The providing step may
The search information corresponding to the age group of the particular wakeword may be provided as the response information, or the response information may be provided in an output form corresponding to the age group of the particular wakeword. Voice based service delivery method. A method of providing a voice-based service executed by a server realized by a computer, comprising:
Defining a plurality of wake words to be used as a dialog activation trigger for activating the interaction function of the electronic device, and setting a desired response information range for each wake word;
Receiving from the electronic device a query including information on a specific wakeword used to activate the interactive function among the plurality of wakewords;
Configuring voice response information based on a desired response information range corresponding to the particular wakeword, and providing the configured response information to the electronic device as a response to the received query. Basic service provision method.   A computer program that causes a computer to execute the method for providing voice-based service according to any one of claims 1 to 10.   A computer-readable recording medium having a program recorded thereon for causing a computer to execute the method for providing voice-based service according to any one of claims 1 to 10. A voice-based service providing system for electronic devices realized by a computer, comprising:
At least one processor implemented to execute computer readable instructions;
The at least one processor is
A wake word setting unit that defines a plurality of wake words used as a dialog activation trigger for activating a dialog function of the electronic device, and sets a desired response information range for each wake word;
A voice processing unit that activates the dialog function when the wake interface of the electronic device recognizes a specific wake word of the plurality of wake words, and the dialog function is activated A voice-based service providing system, comprising: a response processing unit that provides response information based on a desired response information range corresponding to the specific wakeword in response to an input voice query.   The system of claim 13, wherein the plurality of wake words and the desired response information range of each wake word are directly set by a user of the electronic device. The at least one processor is
The system further comprises: a query transfer unit configured to transmit a query including a desired response information range to the service target in response to voice input received by the voice interface;
The response processing unit
The voice-based service providing system according to claim 13, wherein response information based on a desired response information range corresponding to the specific wakeword is received from the server and output through the voice interface as a response to the query. The at least one processor is
The system further comprises a query transfer unit for transferring the voice input received by the voice interface to the server as a query for a service request together with information on the particular wakeword,
The response processing unit
The voice-based service providing system according to claim 13, wherein response information based on a desired response information range corresponding to the specific wakeword is received from the server and output through the voice interface as a response to the query.   The voice base service providing system according to claim 13, wherein the response information includes a search result corresponding to the desired response information range in a higher priority than a search result not corresponding to the desired response information range.   The system according to claim 13, wherein the response information is limited to a search result corresponding to the desired response information range.   The voice-based service providing system according to claim 13, wherein the response information is configured based on personalization information in consideration of a past usage breakdown of the user of the electronic device. For each of the plurality of wake words, an age group is set for each wake word,
The response processing unit
The search information corresponding to the age group of the particular wakeword may be provided as the response information, or the response information may be provided in an output form corresponding to the age group of the particular wakeword. Voice based service delivery system.

Images