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-0458664 (2017-03-14) |
등록번호 | US-10083690 (2018-09-25) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 1 인용 특허 : 2043 |
Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determ
Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determine a primary domain representing a user intent for the textual representation. A first substring from the textual representation that corresponds to a first attribute of the primary domain is identified. The identified first substring is parsed to determine a secondary domain representing a user intent for the first substring. A task flow comprising one or more tasks is performed based on the primary domain and the secondary domain.
1. A method for operating a digital assistant, the method comprising: at an electronic device having one or more processors and memory: receiving user speech input;generating a textual representation of the user speech input;parsing the textual representation to determine a primary domain representi
1. A method for operating a digital assistant, the method comprising: at an electronic device having one or more processors and memory: receiving user speech input;generating a textual representation of the user speech input;parsing the textual representation to determine a primary domain representing a user intent for the textual representation;identifying a first substring from the textual representation that corresponds to a first attribute of the primary domain;parsing the identified first substring to determine a secondary domain representing a user intent for the first sub string;performing a task flow comprising one or more tasks based on the primary domain and the secondary domain; andoutputting a response in accordance with the performed task flow. 2. The method of claim 1, wherein parsing the textual representation comprises: determining a confidence score for a plurality of interpretations of the textual representation; anddetermining the primary domain representing the 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 attribute 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, in the textual representation, one or more predetermined words corresponding to the first attribute; andidentifying the first substring based on the one or more predetermined words corresponding to the first attribute. 5. The method of claim 1, wherein parsing the identified first substring comprises: determining a confidence score for a plurality of interpretations of the first substring; anddetermining the secondary domain representing the 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 include the first attribute. 7. The method of claim 1, further comprising: identifying a second substring from the textual representation that corresponds to a second attribute of the primary domain; andparsing the identified second substring to determine a second secondary domain representing a user intent for the second substring, wherein performing the task flow is further based on the second secondary domain. 8. The method of claim 7, wherein the second attribute comprises a place, a time, an event, or a person. 9. The method of claim 7, wherein identifying the second sub string from the textual representation comprises: identifying in the textual representation one or more predetermined words corresponding to the second attribute; andidentifying the second substring based on the one or more predetermined words corresponding to the second attribute. 10. The method of claim 7, wherein parsing the identified second substring comprises: determining a confidence score for a plurality of interpretations of the second substring; anddetermining the second secondary domain representing a 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 attribute. 12. The method of claim 1, wherein performing the task flow comprises: identifying a primary task flow to accomplish the user intent for the textual representation;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. 13. The method of claim 12, 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. 14. The method of claim 1, wherein the first attribute is represented by a first node of the primary domain, and wherein the first node of the primary domain stems from a root node of the primary domain. 15. The method of claim 14, wherein the secondary domain includes a first node representing the first attribute, and wherein the first node of the secondary domain stems from a root node of the secondary domain. 16. The method of claim 1, wherein the identified first substring is parsed to determine the secondary domain without parsing any portion of the text representation other than the identified first substring. 17. The method of claim 1, wherein the secondary domain representing the user intent for the first substring is determined based on the first attribute. 18. The method of claim 1, further comprising: determining a value for the first attribute based on the secondary domain, wherein the task flow is performed using the determined value for the first attribute. 19. The electronic device of claim 1, wherein performing the task flow comprises: identifying a primary task flow to accomplish the user intent for the textual representation;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. 20. An electronic device, comprising: one or more processors; andmemory storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for: receiving user speech input;generating a textual representation of the user speech input;parsing the textual representation to determine a primary domain representing a user intent for the textual representation;identifying a first substring from the textual representation that corresponds to a first attribute of the primary domain;parsing the identified first substring to determine a secondary domain representing a user intent for the first sub string;performing a task flow comprising one or more tasks based on the primary domain and the secondary domain; andoutputting a response in accordance with the performed task flow. 21. The electronic device of claim 20, wherein parsing the textual representation comprises: determining a confidence score for a plurality of interpretations of the textual representation; anddetermining the primary domain representing the user intent for the textual representation based on an interpretation of the plurality of interpretations of the textual representation having the highest confidence score. 22. The electronic device of claim 20, wherein identifying the first substring from the textual representation comprises: identifying, in the textual representation, one or more predetermined words corresponding to the first attribute; andidentifying the first substring based on the one or more predetermined words corresponding to the first attribute. 23. The electronic device of claim 20, wherein parsing the identified first substring comprises: determining a confidence score for a plurality of interpretations of the first substring; anddetermining the secondary domain representing the user intent for the first substring based on an interpretation of the plurality of interpretations of the first substring having the highest confidence score. 24. The electronic device of claim 20, wherein the one or more programs further include instructions for: identifying a second substring from the textual representation that corresponds to a second attribute of the primary domain; andparsing the identified second substring to determine a second secondary domain representing a user intent for the second substring, wherein performing the task flow is further based on the second secondary domain. 25. A non-transitory computer-readable storage medium comprising computer-executable instructions for: receiving user speech input;generating a textual representation of the user speech input;parsing the textual representation to determine a primary domain representing a user intent for the textual representation;identifying a first substring from the textual representation that corresponds to a first attribute of the primary domain;parsing the identified first substring to determine a secondary domain representing a user intent for the first sub string;performing a task flow comprising one or more tasks based on the primary domain and the secondary domain; andoutputting a response in accordance with the performed task flow. 26. The non-transitory computer-readable storage medium of claim 25, wherein parsing the textual representation comprises: determining a confidence score for a plurality of interpretations of the textual representation; anddetermining the primary domain representing the user intent for the textual representation based on an interpretation of the plurality of interpretations of the textual representation having the highest confidence score. 27. The non-transitory computer-readable storage medium of claim 25, wherein identifying the first substring from the textual representation comprises: identifying, in the textual representation, one or more predetermined words corresponding to the first attribute; andidentifying the first substring based on the one or more predetermined words corresponding to the first attribute. 28. The non-transitory computer-readable storage medium of claim 25, wherein parsing the identified first substring comprises: determining a confidence score for a plurality of interpretations of the first substring; anddetermining the secondary domain representing the user intent for the first substring based on an interpretation of the plurality of interpretations of the first substring having the highest confidence score. 29. The non-transitory computer-readable storage medium of claim 25, further comprising computer-executable instructions for: identifying a second substring from the textual representation that corresponds to a second attribute of the primary domain; andparsing the identified second substring to determine a second secondary domain representing a user intent for the second substring, wherein performing the task flow is further based on the second secondary domain. 30. The non-transitory computer-readable storage medium of claim 25, wherein performing the task flow comprises: identifying a primary task flow to accomplish the user intent for the textual representation;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.
Copyright KISTI. All Rights Reserved.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.