[미국특허]
Electronic device for processing multi-modal input, method for processing multi-modal input and server for processing multi-modal input
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-003/16
G10L-015/18
G10L-015/22
G06F-003/0481
G06F-003/0482
G06F-003/0488
G10L-015/26
G10L-015/30
H04R-001/02
출원번호
US-0824331
(2017-11-28)
등록번호
US-10191718
(2019-01-29)
우선권정보
KR-10-2016-0159704 (2016-11-28)
발명자
/ 주소
Rhee, In Jong
Lee, Ji Min
Kang, Sang Ki
Ku, Han Jun
Park, Sung Pa
Seo, Jang Seok
Song, In Wook
Ahn, Won Ick
Woo, Kyoung Gu
Yi, Ji Soo
Jeon, Chang Kyun
Jaygarl, Ho Jun
Choi, Il Hwan
Hong, Yoo Jin
Kim, Ji Hyun
Yeo, Jae Yung
출원인 / 주소
Samsung Electronics Co., Ltd.
대리인 / 주소
Jefferson IP Law, LLP
인용정보
피인용 횟수 :
0인용 특허 :
15
초록▼
An electronic device is provided. The electronic device includes a housing, a touchscreen display exposed through a first portion of the housing, a microphone disposed at a second portion of the housing, a speaker disposed at a third portion of the housing, a memory disposed inside the housing, a pr
An electronic device is provided. The electronic device includes a housing, a touchscreen display exposed through a first portion of the housing, a microphone disposed at a second portion of the housing, a speaker disposed at a third portion of the housing, a memory disposed inside the housing, a processor disposed inside the housing, and electrically connected to the display, the microphone, the speaker, and the memory. The memory is configured to store a plurality of application programs, each of which includes a graphic user interface (GUI).
대표청구항▼
1. An electronic device comprising: a housing;a touchscreen display exposed through a first portion of the housing;a microphone disposed at a second portion of the housing;a speaker disposed at a third portion of the housing;a memory disposed inside the housing; andat least one processor disposed in
1. An electronic device comprising: a housing;a touchscreen display exposed through a first portion of the housing;a microphone disposed at a second portion of the housing;a speaker disposed at a third portion of the housing;a memory disposed inside the housing; andat least one processor disposed inside the housing, and electrically connected to the display, the microphone, the speaker, and the memory,wherein the memory is configured to store a plurality of application programs, each of the application programs including a graphic user interface (GUI), andwherein the memory is further configured to store instructions that, when executed, cause the at least one processor to: control the microphone to receive an utterance from a user;generate or receive text data based on the utterance;generate or receive a sequence of states in which the electronic device performs a task based on the text data, wherein the sequence of states includes at least two states of at least one of the application programs;select one of the application programs, based at least partly on the sequence of states;launch the selected application program;control to display the GUI of the selected application program on the display;control to display at least part of a sequence of automatically providing an input into the GUI on the display, based at least partly on the sequence of states;cause the selected application program to perform an operation that utilizes at least one parameter, using the input as the at least one parameter, depending on the sequence of states; andcontrol to display a result of the operation on the display. 2. The electronic device of claim 1, wherein the instructions further cause the at least one processor to download at least one of the plurality of application programs from a server. 3. The electronic device of claim 1, wherein the instructions are part of a software framework that provides an application programming interface to the plurality of application programs. 4. The electronic device of claim 1, wherein the instructions further cause the at least one processor to: control to display, on the display, one or more identifiers, each of which represents a respective one of the plurality of application programs, based at least partly on the text data;receive a selection of one of the identifiers from the user via the display or the microphone; andselect the one of the application programs, based on the received selection. 5. The electronic device of claim 4, wherein the identifiers are in a form of at least one of an icon, a symbol, an image, or text. 6. The electronic device of claim 1, wherein, when the text data lacks a parameter for the selected application program to perform the operation, the instructions further cause the at least one processor to: control to display a cursor in an input area of the GUI for receiving the parameter;receive text input for the parameter via the display; andcause the application program to perform the operation, using the text input. 7. The electronic device of claim 1, wherein the instructions further cause the at least one processor to: generate or receive intent of the utterance and the parameter for performing the intent based on the text data; andgenerate or receive the sequence of the operation of the selected application program based on the intent and the parameter. 8. The electronic device of claim 7, wherein the one path rule includes the operation of the selected application program and the parameter utilized to perform the operation. 9. An electronic device comprising: a housing;a touchscreen display exposed through a first portion of the housing;a microphone disposed at a second portion of the housing;a speaker disposed at a third portion of the housing;a memory disposed inside the housing; andat least one processor disposed inside the housing, and electrically connected to the display, the microphone, the speaker, and the memory,wherein the memory is configured to store a first plurality of application programs and a second plurality of application programs, wherein each of the application programs includes a graphic user interface (GUI), andwherein the memory is further configured to store instructions that, when executed, cause the at least one processor to: control the microphone to receive an utterance from a user;generate or receive text data based on the utterance;generate or receive a sequence of states in which the electronic device performs a task based on the text data, wherein the sequence of states includes at least two states of at least one of the application programs;select a first application program from the first plurality of application programs, based at least partly on the sequence of states;launch the selected first application program;control to display the GUI of the selected first application program on the display;cause the selected first application program to perform a first operation that utilizes at least one first parameter, based at least partly on the sequence of states, while displaying at least part of a sequence of performing the first operation on the display;control to display a result of the first operation on the display;after displaying the result, control to display one or more identifiers on the display, based at least partly on the sequence of states, wherein each of the identifiers represents a respective one of the second plurality of application programs;receive a selection of one of the identifiers from the user via the display or the microphone;select a second application program from the second plurality of application programs, based on the received selection; andcause the selected second application program to perform a second operation that utilizes at least one second parameter, using at least part of the result of the first operation. 10. The electronic device of claim 9, wherein the instructions further cause the at least one processor to download at least one of the first plurality of application programs or the second plurality of application programs from a server. 11. The electronic device of claim 9, wherein the instructions are part of a software framework that provides an application programming interface to the first plurality of application programs and the second plurality of application programs. 12. The electronic device of claim 9, wherein the instructions further cause the at least one processor to: after selecting the second application program, control to display the GUI of the selected second application program on the display;cause the selected second application program to perform the second operation, while displaying at least part of a sequence of performing the second operation on the display; andcontrol to display a result of the second operation on the display. 13. The electronic device of claim 9, wherein the identifiers are in a form of at least one of an icon, a symbol, an image, or text. 14. The electronic device of claim 9, wherein, when the text data lacks a first parameter for the first application program to perform the first operation, the instructions further cause the at least one processor to: control to display an input area of the GUI of the first application program on the display for receiving the first parameter;receive a first input for the first parameter via the display or the microphone; andcause the first application program to perform the operation, using the first input. 15. The electronic device of claim 9, wherein, when the text data lacks a second parameter for the second application program to perform the second operation, the instructions further cause the at least one processor to: control to display an input area of the GUI of the second application program on the display for receiving the second parameter;receive a second input for the second parameter via the display or the microphone; andcause the second application program to perform the operation, using the second input. 16. An electronic device comprising: a housing;a touchscreen display exposed through a first portion of the housing;a microphone disposed at a second portion of the housing;a speaker disposed at a third portion of the housing;a memory disposed inside the housing; andat least one processor disposed inside the housing, and electrically connected to the display, the microphone, the speaker, and the memory,wherein the memory is configured to store a plurality of application programs, each of the application programs including a graphic user interface (GUI), andwherein the memory is further configured to store instructions that, when executed, cause the at least one processor to: control the microphone to receive a verbal request from a user;generate or receive text data based on the request;generate or receive a sequence of states in which the electronic device performs a task based on the text data, wherein the sequence of states includes at least two states of at least one of the application programs;select one of the applications programs, based at least partly on the sequence of states;determine a portion of an operation that can be performed automatically on the selected application program, using the text data;launch the selected application program;control to display the GUI of the selected application program on the display;control to display at least part of a sequence of automatically performing the portion of the operation, based at least partly on the sequence of states, without completing the operation;receive a user input via the display or microphone; andcause the application program to complete the operation, using the received user input. 17. The electronic device of claim 16, wherein the instructions are part of a software framework that provides an application programming interface to the plurality of application programs. 18. The electronic device of claim 16, wherein the instructions further cause the at least one processor to: control to store user information in the memory; andwhen the text data lacks a parameter for the selected application program to perform the operation, propose the parameter to be added to the operation based on the stored user information. 19. A voice input processing method, the method comprising: receiving an utterance from a user via a microphone;generating or receiving text data based on the utterance;generate or receive a sequence of states in which the electronic device performs a task based on the text data, wherein the sequence of states includes at least two states of at least one of the application programs;selecting the application program based at least partly on the sequence of states;launching the selected application program;displaying a graphic user interface (GUI) of the selected application program on a display;displaying at least part of a sequence of automatically providing an input into the GUI of the selected application program on the display, based at least partly on the sequence of states, wherein the input is provided from outside the selected application program;causing the selected application program to perform an operation that utilizes at least one parameter, using the input as the at least one parameter, depending on the sequence of states; anddisplaying a result of the operation on the display. 20. The electronic device of claim 1, wherein the sequence of states is generated or received according to one of selecting the sequence of states from a set of predefined sequences of states or generating the sequence of states in real time in response to a user request.
Gruber, Thomas Robert; Cheyer, Adam John; Guzzoni, Didier Rene; Brigham, Christopher Dean; Giuli, Richard Donald; Bastea-Forte, Marcello; Saddler, Harry Joseph, Active input elicitation by intelligent automated assistant.
Guzzoni, Didier Rene; Cheyer, Adam John; Gruber, Thomas Robert; Brigham, Christopher Dean; Saddler, Harry Joseph, Disambiguation based on active input elicitation by intelligent automated assistant.
Gruber, Thomas Robert; Cheyer, Adam John; Kittlaus, Dag; Guzzoni, Didier Rene; Brigham, Christopher Dean; Giuli, Richard Donald; Bastea-Forte, Marcello; Saddler, Harry Joseph, Intelligent automated assistant.
Gruber, Thomas Robert; Cheyer, Adam John; Kittlaus, Dag; Guzzoni, Didier Rene; Brigham, Christopher Dean; Giuli, Richard Donald; Bastea-Forte, Marcello; Saddler, Harry Joseph, Intelligent automated assistant.
Cheyer, Adam John; Guzzoni, Didier Rene; Gruber, Thomas Robert; Brigham, Christopher Dean, Intent deduction based on previous user interactions with voice assistant.
Cheyer, Adam John; Guzzoni, Didier Rene; Gruber, Thomas Robert; Brigham, Christopher Dean; Kittlaus, Dag, Maintaining context information between user interactions with a voice assistant.
Gruber, Thomas Robert; Saddler, Harry Joseph; Cheyer, Adam John; Kittlaus, Dag; Brigham, Christopher Dean; Giuli, Richard Donald; Guzzoni, Didier Rene; Bastea-Forte, Marcello, Paraphrasing of user requests and results by automated digital assistant.
Gruber, Thomas Robert; Cheyer, Adam John; Guzzoni, Didier Rene; Brigham, Christopher Dean; Saddler, Harry Joseph, Prioritizing selection criteria by automated assistant.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.