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-0724623 (2015-05-28) |
등록번호 | US-9966065 (2018-05-08) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 1 인용 특허 : 1875 |
Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription proces
Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each substring can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.
1. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to: receive speech input from a user, wherein the speech input compr
1. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to: receive speech input from a user, wherein the speech input comprises a single utterance having one or more actionable commands;in direct response to receiving the speech input comprising the single utterance: generate a text string based on the speech input using a speech transcription process;parse the text string into at least a first candidate substring and a second candidate substring;determine a first probability that the first candidate substring corresponds to a first actionable command and a second probability that the second candidate sub string corresponds to a second actionable command;in response to the first probability and the second probability exceeding a threshold, determine a first intent associated with the first candidate substring and a second intent associated with the second candidate substring;execute a first process identified by the first intent and a second process identified by the second intent; andprovide to the user an acknowledgment that the first process and the second process have at least begun execution. 2. The computer readable storage medium of claim 1, wherein parsing the text string into at least the first candidate substring and the second candidate substring comprises: identifying a first keyword in the text string that corresponds to a first domain to determine the first candidate substring; andidentifying a second keyword in the text string that corresponds to a second domain to determine the second candidate substring. 3. The computer readable storage medium of claim 1, wherein parsing the text string into at least the first candidate substring and the second candidate substring comprises: identifying a first imperative verb in the text string to determine the first candidate substring; andidentifying a second imperative verb in the text string to determine the second candidate substring. 4. The computer readable storage medium of claim 1, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: determining a first semantic coherence of the first candidate substring and a second semantic coherence of the second candidate substring; anddetermining the first probability and the second probability based on the first semantic coherence and the second semantic coherence. 5. The computer readable storage medium of claim 1, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: comparing the first candidate substring and the second candidate substring to one or more user request templates; anddetermining the first probability and the second probability based on the comparison. 6. The computer readable storage medium of claim 1, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: submitting the first candidate substring and the second candidate substring to at least a first service and a second service;receiving a first likelihood that the first service can resolve the first actionable command and a second likelihood that the second service can resolve the second actionable command; anddetermining the first probability and the second probability based on the first likelihood and the second likelihood. 7. The computer readable storage medium of claim 1, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the second intent based on at least one word in the first candidate substring. 8. The computer readable storage medium of claim 1, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the first intent or the second intent based on information displayed on a display associated with the electronic device. 9. The computer readable storage medium of claim 8, wherein the information comprises a list; and wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the first intent or the second intent based on an ordinal descriptor in the first candidate substring or the second candidate substring, wherein the ordinal descriptor is associated with one or more items in the list. 10. The computer readable storage medium of claim 8, wherein the information comprises one or more notifications. 11. The computer readable storage medium of claim 8, wherein the information comprises one or more emails. 12. The computer readable storage medium of claim 8, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining one or more potential user requests based on the information displayed on the display; anddetermining the first intent or the second intent based on the one or more potential user requests. 13. The computer readable storage medium of claim 1, wherein the acknowledgment comprises an audible confirmation. 14. The computer readable storage medium of claim 1, wherein the acknowledgment comprises haptic feedback. 15. The computer readable storage medium of claim 1, wherein providing to the user the acknowledgment associated with the first intent and the second intent comprises: providing a first task associated with the first intent and a second task associated with the second intent. 16. The computer readable storage medium of claim 15, wherein providing the first task associated with the first intent and the second task associated with the second intent comprises: displaying the first task and the second task. 17. The computer readable storage medium of claim 15, further comprising: in response to completing the first process, providing a first indicator associated with the first task; andin response to completing the second process, providing a second indicator associated with the second task. 18. The computer readable storage medium of claim 17, wherein providing the first indicator associated with the first task comprises displaying the first indicator; and wherein providing the second indicator associated with the second task comprises displaying the second indicator. 19. The computer readable storage medium of claim 17, further comprising: before completing the first process, providing a first processing status indicator associated with the first task; andbefore completing the second process, providing a second processing status indicator associated with the second task. 20. The computer readable storage medium of claim 19, wherein providing the first processing status indicator associated with the first task comprises displaying the first processing status indicator; and wherein providing the second processing status indicator associated with the second task comprises displaying the second processing status indicator. 21. The computer readable storage medium of claim 19, wherein the first indicator and the second indicator comprise a checkmark. 22. The computer readable storage medium of claim 19, wherein the first processing status indicator and the second processing status indicator comprise one or more of an hourglass, an animation, or a status bar. 23. The computer readable storage medium of claim 1, wherein providing to the user the acknowledgment associated with the first intent and the second intent comprises: displaying the first candidate substring using a first emphasis and displaying the second candidate substring using a second emphasis that is different than the first emphasis. 24. The computer readable storage medium of claim 23, wherein each of the first emphasis and the second emphasis comprise one or more of bold text, italic text, underlined text, circled text, outlined text, colored text, and clustered text. 25. An electronic device, comprising: one or more processors;a memory; andone or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for: receiving speech input from a user, wherein the speech input comprises a single utterance having one or more actionable commands;in direct response to receiving the speech input comprising the single utterance: generating a text string based on the speech input using a speech transcription process;parsing the text string into at least a first candidate substring and a second candidate substring;determining a first probability that the first candidate substring corresponds to a first actionable command and a second probability that the second candidate substring corresponds to a second actionable command;in response to the first probability and the second probability exceeding a threshold, determining a first intent associated with the first candidate substring and a second intent associated with the second candidate substring;executing a first process identified by the first intent and a second process identified by the second intent; andproviding to the user an acknowledgment that the first process and the second process have at least begun execution. 26. A method for processing a multi-part voice command, the method comprising: at an electronic device: receiving speech input from a user, wherein the speech input comprises a single utterance having one or more actionable commands;in direct response to receiving the speech input comprising the single utterance: generating a text string based on the speech input using a speech transcription process;parsing the text string into at least a first candidate substring and a second candidate substring;determining a first probability that the first candidate substring corresponds to a first actionable command and a second probability that the second candidate substring corresponds to a second actionable command;in response to the first probability and the second probability exceeding a threshold, determining a first intent associated with the first candidate substring and a second intent associated with the second candidate substring;executing a first process identified by the first intent and a second process identified by the second intent; andproviding to the user an acknowledgment that the first process and the second process have at least begun execution. 27. The electronic device of claim 25, wherein parsing the text string into at least the first candidate substring and the second candidate substring comprises: identifying a first keyword in the text string that corresponds to a first domain to determine the first candidate substring; andidentifying a second keyword in the text string that corresponds to a second domain to determine the second candidate substring. 28. The electronic device of claim 25, wherein parsing the text string into at least the first candidate substring and the second candidate substring comprises: identifying a first imperative verb in the text string to determine the first candidate substring; andidentifying a second imperative verb in the text string to determine the second candidate substring. 29. The electronic device of claim 25, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: determining a first semantic coherence of the first candidate substring and a second semantic coherence of the second candidate substring; anddetermining the first probability and the second probability based on the first semantic coherence and the second semantic coherence. 30. The electronic device of claim 25, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: comparing the first candidate substring and the second candidate substring to one or more user request templates; anddetermining the first probability and the second probability based on the comparison. 31. The electronic device of claim 25, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: submitting the first candidate substring and the second candidate substring to at least a first service and a second service;receiving a first likelihood that the first service can resolve the first actionable command and a second likelihood that the second service can resolve the second actionable command; anddetermining the first probability and the second probability based on the first likelihood and the second likelihood. 32. The electronic device of claim 25, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the second intent based on at least one word in the first candidate substring. 33. The electronic device of claim 25, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the first intent or the second intent based on information displayed on a display associated with the electronic device. 34. The electronic device of claim 33, wherein the information comprises a list; and wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the first intent or the second intent based on an ordinal descriptor in the first candidate substring or the second candidate substring, wherein the ordinal descriptor is associated with one or more items in the list. 35. The electronic device of claim 33, wherein the information comprises one or more notifications. 36. The electronic device of claim 33, wherein the information comprises one or more emails. 37. The electronic device of claim 33, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining one or more potential user requests based on the information displayed on the display; anddetermining the first intent or the second intent based on the one or more potential user requests. 38. The electronic device of claim 25, wherein the acknowledgment comprises an audible confirmation. 39. The electronic device of claim 25, wherein the acknowledgment comprises haptic feedback. 40. The electronic device of claim 25, wherein providing to the user the acknowledgment associated with the first intent and the second intent comprises: providing a first task associated with the first intent and a second task associated with the second intent. 41. The electronic device of claim 40, wherein providing the first task associated with the first intent and the second task associated with the second intent comprises: displaying the first task and the second task. 42. The electronic device of claim 40, wherein the one or more programs further include instructions for: in response to completing the first process, providing a first indicator associated with the first task; andin response to completing the second process, providing a second indicator associated with the second task. 43. The electronic device of claim 42, wherein providing the first indicator associated with the first task comprises displaying the first indicator; and wherein providing the second indicator associated with the second task comprises displaying the second indicator. 44. The electronic device of claim 42, wherein the one or more programs further include instructions for: before completing the first process, providing a first processing status indicator associated with the first task; andbefore completing the second process, providing a second processing status indicator associated with the second task. 45. The electronic device of claim 44, wherein providing the first processing status indicator associated with the first task comprises displaying the first processing status indicator; and wherein providing the second processing status indicator associated with the second task comprises displaying the second processing status indicator. 46. The electronic device of claim 44, wherein the first indicator and the second indicator comprise a checkmark. 47. The electronic device of claim 44, wherein the first processing status indicator and the second processing status indicator comprise one or more of an hourglass, an animation, or a status bar. 48. The electronic device of claim 25, wherein providing to the user the acknowledgment associated with the first intent and the second intent comprises: displaying the first candidate substring using a first emphasis and displaying the second candidate substring using a second emphasis that is different than the first emphasis. 49. The electronic device of claim 48, wherein each of the first emphasis and the second emphasis comprise one or more of bold text, italic text, underlined text, circled text, outlined text, colored text, and clustered text. 50. The method of claim 26, wherein parsing the text string into at least the first candidate substring and the second candidate substring comprises: identifying a first keyword in the text string that corresponds to a first domain to determine the first candidate substring; andidentifying a second keyword in the text string that corresponds to a second domain to determine the second candidate substring. 51. The method of claim 26, wherein parsing the text string into at least the first candidate substring and the second candidate substring comprises: identifying a first imperative verb in the text string to determine the first candidate substring; andidentifying a second imperative verb in the text string to determine the second candidate substring. 52. The method of claim 26, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: determining a first semantic coherence of the first candidate substring and a second semantic coherence of the second candidate substring; anddetermining the first probability and the second probability based on the first semantic coherence and the second semantic coherence. 53. The method of claim 26, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: comparing the first candidate substring and the second candidate substring to one or more user request templates; anddetermining the first probability and the second probability based on the comparison. 54. The method of claim 26, wherein determining the first probability that the first candidate substring corresponds to the first actionable command and the second probability that the second candidate substring corresponds to the second actionable command comprises: submitting the first candidate substring and the second candidate substring to at least a first service and a second service;receiving a first likelihood that the first service can resolve the first actionable command and a second likelihood that the second service can resolve the second actionable command; anddetermining the first probability and the second probability based on the first likelihood and the second likelihood. 55. The method of claim 26, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the second intent based on at least one word in the first candidate substring. 56. The method of claim 26, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the first intent or the second intent based on information displayed on a display associated with the electronic device. 57. The method of claim 56, wherein the information comprises a list; and wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining the first intent or the second intent based on an ordinal descriptor in the first candidate substring or the second candidate substring, wherein the ordinal descriptor is associated with one or more items in the list. 58. The method of claim 56, wherein the information comprises one or more notifications. 59. The method of claim 56, wherein the information comprises one or more emails. 60. The method of claim 56, wherein determining the first intent associated with the first candidate substring and the second intent associated with the second candidate substring comprises: determining one or more potential user requests based on the information displayed on the display; anddetermining the first intent or the second intent based on the one or more potential user requests. 61. The method of claim 26, wherein the acknowledgment comprises an audible confirmation. 62. The method of claim 26, wherein the acknowledgment comprises haptic feedback. 63. The method of claim 26, wherein providing to the user the acknowledgment associated with the first intent and the second intent comprises: providing a first task associated with the first intent and a second task associated with the second intent. 64. The method of claim 63, wherein providing the first task associated with the first intent and the second task associated with the second intent comprises: displaying the first task and the second task. 65. The method of claim 63, further comprising: in response to completing the first process, providing a first indicator associated with the first task; andin response to completing the second process, providing a second indicator associated with the second task. 66. The method of claim 65, wherein providing the first indicator associated with the first task comprises displaying the first indicator; and wherein providing the second indicator associated with the second task comprises displaying the second indicator. 67. The method of claim 65, further comprising: before completing the first process, providing a first processing status indicator associated with the first task; andbefore completing the second process, providing a second processing status indicator associated with the second task. 68. The method of claim 67, wherein providing the first processing status indicator associated with the first task comprises displaying the first processing status indicator; and wherein providing the second processing status indicator associated with the second task comprises displaying the second processing status indicator. 69. The method of claim 67, wherein the first indicator and the second indicator comprise a checkmark. 70. The method of claim 67, wherein the first processing status indicator and the second processing status indicator comprise one or more of an hourglass, an animation, or a status bar. 71. The method of claim 26, wherein providing to the user the acknowledgment associated with the first intent and the second intent comprises: displaying the first candidate substring using a first emphasis and displaying the second candidate substring using a second emphasis that is different than the first emphasis. 72. The method of claim 71, wherein each of the first emphasis and the second emphasis comprise one or more of bold text, italic text, underlined text, circled text, outlined text, colored text, and clustered text.
Copyright KISTI. All Rights Reserved.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.