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-0500703 (2014-09-29) |
등록번호 | US-9633004 (2017-04-25) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 4 인용 특허 : 1662 |
Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In some examples, to process a textual representation of user speech using an active ontology having these concept nodes, a primary user intent can be determined fr
Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In some examples, to process a textual representation of user speech using an active ontology having these concept nodes, a primary user intent can be determined from the textual representation of user speech. Concepts referred to by the primary user intent can be identified, and substrings of the textual representation of user speech corresponding to the concepts can be identified. Secondary user intents for the substrings can be determined and a task flow based on the primary user intent and the secondary user intents can be generated and performed.
1. A method for operating a virtual assistant on an electronic device, the method comprising: receiving an audio input comprising user speech;converting the user speech of the audio input into a textual representation of the user speech;determining a primary user intent for the textual representatio
1. A method for operating a virtual assistant on an electronic device, the method comprising: receiving an audio input comprising user speech;converting the user speech of the audio input into a textual representation of the user speech;determining a primary user intent for the textual representation;identifying a first type of concept referred to by the primary user intent;identifying a first substring from the textual representation corresponding to the first type of concept;determining a secondary user intent for the first substring; andperforming a task flow comprising one or more tasks based at least in part on the primary user intent for the textual representation and the secondary user intent for the first substring. 2. The method of claim 1, wherein determining the primary user intent for the textual representation comprises: determining a confidence score for a plurality of interpretations of the textual representation; anddetermining the primary user intent for the textual representation based on an interpretation of the plurality of interpretations of the textual representation having the highest confidence score. 3. The method of claim 1, wherein the first type of concept comprises a place, a time, an event, or a person. 4. The method of claim 1, wherein identifying the first substring from the textual representation comprises: identifying one or more predetermined words corresponding to the first type of concept in the textual representation; andidentifying the first substring based on the one or more predetermined words corresponding to the first type of concept. 5. The method of claim 1, wherein determining the secondary user intent for the first substring comprises: determining a confidence score for a plurality of interpretations of the first substring; anddetermining the secondary user intent for the first substring based on an interpretation of the plurality of interpretations of the first substring having the highest confidence score. 6. The method of claim 5, wherein the plurality of interpretations of the first substring exclude interpretations from domains that do not output the first type of concept. 7. The method of claim 1, further comprising: identifying a second type of concept referred to by the primary user intent; identifying a second substring from the textual representation corresponding to the second type of concept; anddetermining a secondary user intent for the second substring, wherein performing the task flow is further based on the secondary user intent for the second substring. 8. The method of claim 7, wherein the second type of concept comprises a place, a time, an event, or a person. 9. The method of claim 7, wherein identifying the second substring from the textual representation comprises: identifying one or more predetermined words corresponding to the second type of concept in the textual representation; andidentifying the second substring based on the one or more predetermined words corresponding to the second type of concept. 10. The method of claim 7, wherein determining the secondary user intent for the second substring comprises: determining a confidence score for a plurality of interpretations of the second substring; anddetermining the secondary user intent for the second substring based on an interpretation of the plurality of interpretations of the second substring having the highest confidence score. 11. The method of claim 10, wherein the plurality of interpretations of the second substring exclude interpretations from domains that do not output the second type of concept. 12. The method of a claim 7, further comprising: identifying a third type of concept referred to by the secondary user intent for the first substring;identifying a third substring from the first substring corresponding to the third type of concept; anddetermining a tertiary user intent for the third substring, wherein performing the task flow is further based on the tertiary user intent for the third substring. 13. The method of claim 12, wherein the third type of concept comprises a place, a time, an event, or a person. 14. The method of claim 12, wherein identifying the third substring from the first substring comprises: identifying one or more predetermined words corresponding to the third type of concept in the first substring; andidentifying the third substring based on the one or more predetermined words corresponding to the third type of concept. 15. The method of claim 12, wherein determining the tertiary user intent for the third substring comprises: determining a confidence score for a plurality of interpretations of the third substring; anddetermining the tertiary user intent for the third substring based on an interpretation of the plurality of interpretations of the third substring having the highest confidence score. 16. The method of claim 15, wherein the plurality of interpretations of the third substring exclude interpretations from domains that do not output the third type of concept. 17. The method of claim 1, wherein performing the task flow comprises: identifying a primary task flow to accomplish the primary user intent;identifying one or more constraints associated with the primary task flow;identifying one or more queries, programs, methods, services, or APIs that satisfy the one or more constraints associated with the primary task flow; andgenerating the task flow from the primary task flow and the identified one or more queries, programs, methods, services, or APIs. 18. The method of claim 17, wherein the one or more constraints comprises a type of input required by the primary task flow, and wherein the identified one or more queries, programs, methods, services, or APIs are capable of providing the type of input required by the primary task flow. 19. The method of claim 1, further comprising: parsing the textual representation, wherein determining the primary user intent for the textual representation comprises determining the primary user intent for the parsed textual representation; andparsing the first substring, wherein determining the secondary user intent for the first substring comprises determining the secondary user intent for the parsed first substring. 20. The method of claim 1, wherein identifying the first type of concept referred to by the primary user intent is performed after determining the primary user intent. 21. An electronic device, comprising: one or more processors;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 an audio input comprising user speech;converting the user speech of the audio input into a textual representation of the user speech;determining a primary user intent for the textual representation;identifying a first type of concept referred to by the primary user intent;identifying a first substring from the textual representation corresponding to the first type of concept;determining a secondary user intent for the first substring; andperforming a task flow comprising one or more tasks based at least in part on the primary user intent for the textual representation and the secondary user intent for the first substring. 22. The device of claim 21, wherein determining the primary user intent for the textual representation comprises: determining a confidence score for a plurality of interpretations of the textual representation; anddetermining the primary user intent for the textual representation based on an interpretation of the plurality of interpretations of the textual representation having the highest confidence score. 23. The device of claim 21, wherein the first type of concept comprises a place, a time, an event, or a person. 24. The device of claim 21, wherein identifying the first substring from the textual representation comprises: identifying one or more predetermined words corresponding to the first type of concept in the textual representation; andidentifying the first substring based on the one or more predetermined words corresponding to the first type of concept. 25. The device of claim 21, wherein determining the secondary user intent for the first substring comprises: determining a confidence score for a plurality of interpretations of the first substring; anddetermining the secondary user intent for the first substring based on an interpretation of the plurality of interpretations of the first substring having the highest confidence score. 26. The device of claim 25, wherein the plurality of interpretations of the first substring exclude interpretations from domains that do not output the first type of concept. 27. The device of claim 21, wherein the one or more programs further include instructions for: identifying a second type of concept referred to by the primary user intent;identifying a second substring from the textual representation corresponding to the second type of concept; anddetermining a secondary user intent for the second substring, wherein performing the task flow is further based on the secondary user intent for the second substring. 28. The device of claim 27, wherein the second type of concept comprises a place, a time, an event, or a person. 29. The device of claim 27, wherein identifying the second substring from the textual representation comprises: identifying one or more predetermined words corresponding to the second type of concept in the textual representation; andidentifying the second substring based on the one or more predetermined words corresponding to the second type of concept. 30. The device of claim 27, wherein determining the secondary user intent for the second substring comprises: determining a confidence score for a plurality of interpretations of the second substring; anddetermining the secondary user intent for the second substring based on an interpretation of the plurality of interpretations of the second substring having the highest confidence score. 31. The device of claim 30, wherein the plurality of interpretations of the second substring exclude interpretations from domains that do not output the second type of concept. 32. The device of a claim 27, wherein the one or more programs further include instructions for: identifying a third type of concept referred to by the secondary user intent for the first substring;identifying a third substring from the first substring corresponding to the third type of concept; anddetermining a tertiary user intent for the third substring, wherein performing the task flow is further based on the tertiary user intent for the third substring. 33. The device of claim 32, wherein the third type of concept comprises a place, a time, an event, or a person. 34. The device of claim 32, wherein identifying the third substring from the first substring comprises: identifying one or more predetermined words corresponding to the third type of concept in the first substring; andidentifying the third substring based on the one or more predetermined words corresponding to the third type of concept. 35. The device of claim 32, wherein determining the tertiary user intent for the third substring comprises: determining a confidence score for a plurality of interpretations of the third substring; anddetermining the tertiary user intent for the third substring based on an interpretation of the plurality of interpretations of the third substring having the highest confidence score. 36. The device of claim 35, wherein the plurality of interpretations of the third substring exclude interpretations from domains that do not output the third type of concept. 37. The device of claim 21, wherein performing the task flow comprises: identifying a primary task flow to accomplish the primary user intent;identifying one or more constraints associated with the primary task flow;identifying one or more queries, programs, methods, services, or APIs that satisfy the one or more constraints associated with the primary task flow; andgenerating the task flow from the primary task flow and the identified one or more queries, programs, methods, services, or APIs. 38. The device of claim 37, wherein the one or more constraints comprises a type of input required by the primary task flow, and wherein the identified one or more queries, programs, methods, services, or APIs are capable of providing the type of input required by the primary task flow. 39. A non-transitory computer-readable storage medium comprising computer-executable instructions for: receiving an audio input comprising user speech;converting the user speech of the audio input into a textual representation of the user speech;determining a primary user intent for the textual representation;identifying a first type of concept referred to by the primary user intent;identifying a first substring from the textual representation corresponding to the first type of concept;determining a secondary user intent for the first substring; andperforming a task flow comprising one or more tasks based at least in part on the primary user intent for the textual representation and the secondary user intent for the first substring. 40. The computer-readable storage medium of claim 39, wherein determining the primary user intent for the textual representation comprises: determining a confidence score for a plurality of interpretations of the textual representation; anddetermining the primary user intent for the textual representation based on an interpretation of the plurality of interpretations of the textual representation having the highest confidence score. 41. The computer-readable storage medium of claim 39, wherein the first type of concept comprises a place, a time, an event, or a person. 42. The computer-readable storage medium of claim 39, wherein identifying the first substring from the textual representation comprises: identifying one or more predetermined words corresponding to the first type of concept in the textual representation; andidentifying the first substring based on the one or more predetermined words corresponding to the first type of concept. 43. The computer-readable storage medium of claim 39, wherein determining the secondary user intent for the first substring comprises: determining a confidence score for a plurality of interpretations of the first substring; anddetermining the secondary user intent for the first substring based on an interpretation of the plurality of interpretations of the first substring having the highest confidence score. 44. The computer-readable storage medium of claim 43, wherein the plurality of interpretations of the first substring exclude interpretations from domains that do not output the first type of concept. 45. The computer-readable storage medium of claim 39, further comprising instructions for: identifying a second type of concept referred to by the primary user intent;identifying a second substring from the textual representation corresponding to the second type of concept; anddetermining a secondary user intent for the second substring, wherein performing the task flow is further based on the secondary user intent for the second substring. 46. The computer-readable storage medium of claim 45, wherein the second type of concept comprises a place, a time, an event, or a person. 47. The computer-readable storage medium of claim 45, wherein identifying the second substring from the textual representation comprises: identifying one or more predetermined words corresponding to the second type of concept in the textual representation; andidentifying the second substring based on the one or more predetermined words corresponding to the second type of concept. 48. The computer-readable storage medium of claim 45, wherein determining the secondary user intent for the second substring comprises: determining a confidence score for a plurality of interpretations of the second substring; anddetermining the secondary user intent for the second substring based on an interpretation of the plurality of interpretations of the second substring having the highest confidence score. 49. The computer-readable storage medium of claim 48, wherein the plurality of interpretations of the second substring exclude interpretations from domains that do not output the second type of concept. 50. The computer-readable storage medium of a claim 45, further comprising instructions for: identifying a third type of concept referred to by the secondary user intent for the first substring;identifying a third substring from the first substring corresponding to the third type of concept; anddetermining a tertiary user intent for the third substring, wherein performing the task flow is further based on the tertiary user intent for the third substring. 51. The computer-readable storage medium of claim 50, wherein the third type of concept comprises a place, a time, an event, or a person. 52. The computer-readable storage medium of claim 50, wherein identifying the third substring from the first substring comprises: identifying one or more predetermined words corresponding to the third type of concept in the first substring; andidentifying the third substring based on the one or more predetermined words corresponding to the third type of concept. 53. The computer-readable storage medium of claim 50, wherein determining the tertiary user intent for the third substring comprises: determining a confidence score for a plurality of interpretations of the third substring; anddetermining the tertiary user intent for the third substring based on an interpretation of the plurality of interpretations of the third substring having the highest confidence score. 54. The computer-readable storage medium of claim 53, wherein the plurality of interpretations of the third substring exclude interpretations from domains that do not output the third type of concept. 55. The computer-readable storage medium of claim 39, wherein performing the task flow comprises: identifying a primary task flow to accomplish the primary user intent;identifying one or more constraints associated with the primary task flow;identifying one or more queries, programs, computer-readable storage mediums, services, or APIs that satisfy the one or more constraints associated with the primary task flow; andgenerating the task flow from the primary task flow and the identified one or more queries, programs, methods, services, or APIs. 56. The computer-readable storage medium of claim 55, wherein the one or more constraints comprises a type of input required by the primary task flow, and wherein the identified one or more queries, programs, methods, services, or APIs are capable of providing the type of input required by the primary task flow.
Copyright KISTI. All Rights Reserved.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.