최소 단어 이상 선택하여야 합니다.
최대 10 단어까지만 선택 가능합니다.
다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
NTIS 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
DataON 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Edison 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Kafe 바로가기국가/구분 | United States(US) Patent 등록 |
---|---|
국제특허분류(IPC7판) |
|
출원번호 | US-0784694 (2013-03-04) |
등록번호 | US-8930191 (2015-01-06) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 83 인용 특허 : 1623 |
Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A user request is received, the user request including at least a speech input received from a user. In response to the user request, (1) an echo of the speech input based on a
Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A user request is received, the user request including at least a speech input received from a user. In response to the user request, (1) an echo of the speech input based on a textual interpretation of the speech input, and (2) a paraphrase of the user request based at least in part on a respective semantic interpretation of the speech input are presented to the user.
1. A method for operating an intelligent automated assistant, comprising: at an electronic device comprising a processor and memory storing instructions for execution by the processor: receiving a user request, the user request including at least a speech input received from a user, wherein the spee
1. A method for operating an intelligent automated assistant, comprising: at an electronic device comprising a processor and memory storing instructions for execution by the processor: receiving a user request, the user request including at least a speech input received from a user, wherein the speech input includes at least one value of at least one parameter; andpresenting to the user an echo of the speech input based on a textual interpretation of the speech input;determining a task to be performed by the electronic device, from a plurality of tasks performable by the electronic device, wherein the task is determined by performing natural language processing on the speech input; andpresenting to the user a paraphrase of the task, including a natural language formulation of the task and the at least one value of the at least one parameter. 2. The method of claim 1, wherein a respective sentence used in the paraphrase is tailored to a respective modality used to present the paraphrase to the user, and wherein a more verbose sentence is used in the paraphrase when the paraphrase is to be presented in audible form than when the paraphrase is to be presented in written form. 3. The method of claim 1, wherein the echo includes one or more first words and the paraphrase includes one or more second words, and wherein the one or more second words represent a respective semantic interpretation of the one or more first words and associate the one or more first words with a concept of a respective domain among a plurality of predefined domains. 4. The method of claim 1, wherein the echo and the paraphrase are presented on a conversation screen, and wherein the paraphrase includes the at least one value of the at least one parameter presented in a highlighted format. 5. The method of claim 1, wherein the paraphrase indicates a real-time progress of the task. 6. The method of claim 1, wherein the paraphrase provides a summary of a result set, and wherein the paraphrase is presented in addition to the result set. 7. The method of claim 1, wherein the paraphrase specifies multiple selection criteria derived from the user request, and indicates that no result meeting all of the multiple selection criteria have been found, and wherein the paraphrase specifies a relaxed form of the multiple selection criteria and presents a summary of results obtained based on the relaxed form of the multiple selection criteria. 8. The method of claim 1, further comprising presenting to the user, concurrently with the paraphrase of the task, a result set generated as a result of performing the task. 9. The method of claim 1, wherein presenting the paraphrase of the task includes presenting a real-time progress of the task, the method further comprising: retrieving a result set;ceasing to present the paraphrase of the task; andafter ceasing to present the paraphrase of the task, presenting a summary of a result set, wherein the summary of the result set includes a natural language formulation of the task and the least one value of the at least one parameter. 10. The method of claim 1, wherein the echo of the speech input is presented visually, and the paraphrase is presented via speech output. 11. The method of claim 10, wherein the echo of the speech input is not presented via speech output, and the paraphrase is presented visually. 12. The method of claim 10, further comprising visually presenting a result set generated as a result of the performance of the task. 13. A system for operating an intelligent automated assistant, comprising: one or more processors; andmemory having instructions stored thereon, the instructions, when executed by the one or more processors, cause the processors to perform operations comprising: receiving a user request, the user request including at least a speech input received from a user, wherein the speech input includes at least one value of at least one parameter; andpresenting to the user an echo of the speech input based on a textual interpretation of the speech inputdetermining a task to be performed by the electronic device, from a plurality of tasks performable by the electronic device, wherein the task is determined by performing natural language processing on the speech input; andpresenting to the user a paraphrase of the task, including a natural language formulation of the task and the at least one value of the at least one parameter. 14. The system of claim 13, wherein a respective sentence used in the paraphrase is tailored to a respective modality used to present the paraphrase to the user, and wherein a more verbose sentence is used in the paraphrase when the paraphrase is to be presented in audible form than when the paraphrase is to be presented in written form. 15. The system of claim 13, wherein the echo includes one or more first words and the paraphrase includes one or more second words, and wherein the one or more second words represent a respective semantic interpretation of the one or more first words and associate the one or more first words with a concept of a respective domain among a plurality of predefined domains. 16. The system of claim 13, wherein the echo and the paraphrase are presented on a conversation screen, and wherein the paraphrase includes the at least one value of the at least one parameter presented in a highlighted format. 17. The system of claim 13, wherein the paraphrase indicates a real-time progress of the task. 18. The system of claim 13, wherein the paraphrase provides a summary of a result set, and wherein the paraphrase is presented in addition to the result set. 19. The system of claim 13, wherein the paraphrase specifies multiple selection criteria derived from the user request, and indicates that no result meeting all of the multiple selection criteria have been found, and wherein the paraphrase specifies a relaxed form of the multiple selection criteria and presents a summary of results obtained based on the relaxed form of the multiple selection criteria. 20. The system of claim 13, the operations further comprising presenting to the user, concurrently with the paraphrase of the task, a result set generated as a result of performing the task. 21. The system of claim 13, wherein presenting the paraphrase of the task includes presenting a real-time progress of the task, the method further comprising: retrieving a result set;ceasing to present the paraphrase of the task; andafter ceasing to present the paraphrase of the task, presenting a summary of a result set, wherein the summary of the result set includes a natural language formulation of the task and the least one value of the at least one parameter. 22. A non-transitory computer readable storage medium having instructions stored thereon, the instructions, when executed by one or more processors, cause the processors to perform operations comprising: receiving a user request, the user request including at least a speech input received from a user, wherein the speech input includes at least one value of at least one parameter; andpresenting to the user an echo of the speech input based on a textual interpretation of the speech input;determining a task to be performed by the electronic device, from a plurality of tasks performable by the electronic device, wherein the task is determined by performing natural language processing on the speech input; andpresenting to the user a paraphrase of the task, including a natural language formulation of the task and the at least one value of the at least one parameter. 23. The computer readable storage medium of claim 22, wherein a respective sentence used in the paraphrase is tailored to a respective modality used to present the paraphrase to the user, and wherein a more verbose sentence is used in the paraphrase when the paraphrase is to be presented in audible form than when the paraphrase is to be presented in written form. 24. The computer readable storage medium of claim 22, wherein the echo includes one or more first words and the paraphrase includes one or more second words, and wherein the one or more second words represent a respective semantic interpretation of the one or more first words and associate the one or more first words with a concept of a respective domain among a plurality of predefined domains. 25. The computer readable storage medium of claim 22, wherein the echo and the paraphrase are presented on a conversation screen, and wherein the paraphrase includes the at least one value of the at least one parameter presented in a highlighted format. 26. The computer readable storage medium of claim 22, wherein the paraphrase indicates a real-time progress of the task. 27. The computer readable storage medium of claim 22, wherein the paraphrase provides a summary of a result set, and wherein the paraphrase is presented in addition to the result set. 28. The computer readable storage medium of claim 22, wherein the paraphrase specifies multiple selection criteria derived from the user request, and indicates that no result meeting all of the multiple selection criteria have been found, and wherein the paraphrase specifies a relaxed form of the multiple selection criteria and presents a summary of results obtained based on the relaxed form of the multiple selection criteria. 29. The computer readable storage medium of claim 22, the operations further comprising presenting to the user, concurrently with the paraphrase of the task, a result set generated as a result of performing the task. 30. The computer readable storage medium of claim 22, wherein presenting the paraphrase of the task includes presenting a real-time progress of the task, the method further comprising: retrieving a result set;ceasing to present the paraphrase of the task; andafter ceasing to present the paraphrase of the task, presenting a summary of a result set, wherein the summary of the result set includes a natural language formulation of the task and the least one value of the at least one parameter.
Copyright KISTI. All Rights Reserved.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.