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-0725616 (2012-12-21) |
등록번호 | US-8892446 (2014-11-18) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 52 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 the user. The user request is processed to obtain a representation of user intent,
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 the user. The user request is processed to obtain a representation of user intent, where the representation of user intent associates the user request with a task flow operationalizing a requested task, and the task flow is operable to invoke a plurality of services each supporting functions according to a respective plurality of service parameters. Based on the representation of user intent, one or more relevant task parameters are identified from a plurality of task parameters of the task flow. A subset of the plurality of services are selectively invoked during execution of the task flow, where the selectively invoked subset of the plurality of services support functions according to the identified one or more relevant task parameters.
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 the user;processing the
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 the user;processing the user request to obtain a representation of user intent, wherein the representation of user intent associates the user request with a task flow operationalizing a requested task, and the task flow is operable to invoke a plurality of services each supporting functions according to a respective plurality of service parameters;based on the representation of user intent, identifying a plurality of relevant task parameters for the task flow, wherein the plurality of relevant task parameters including at least one task parameter explicitly expressed in the speech input and at least one task parameter inferred from context information associated with the speech input; andexecuting the task flow by selectively invoking a subset of the plurality of services in accordance with the plurality of relevant task parameters, wherein the execution of the task flow further comprises: after an unsuccessful attempt to complete the task in accordance with all of the plurality of relevant task parameters: selecting one or more task parameters from the plurality of relevant task parameters to relax in an additional attempt to complete the task, wherein the selecting is based on whether the one or more task parameters were inferred from the context information or explicitly expressed in the speech input. 2. The method of claim 1, further comprising: transforming at least one task parameter according to respective APIs of multiple services of the selected subset of the plurality of services. 3. The method of claim 1, further comprising: gathering service results from the selected subset of the plurality of services; andmerging the service results into a unified result in a service-independent format to fulfill the user request. 4. The method of claim 1, further comprising: assessing relative ability of multiple subsets of services from the plurality of services to satisfy the user request, each of the multiple subsets operable to provide functions according to the identified plurality of relevant task parameters; andbased on the assessment, selecting one of the multiple subsets of services for invocation during the execution of the task flow. 5. The method of claim 1, wherein each service is associated with a respective service capability model comprising declarative descriptions of respective capabilities and properties of the service. 6. The method of claim 5, wherein selectively invoking the subset of the plurality of services further comprises: dynamically selecting the subset of the plurality of services for invocation based on the respective service capability models of the plurality of services. 7. The method of claim 1, further comprising: generating at least one merged result based on results received from the selectively invoked subset of services; andselectively invoking a second plurality of services to annotate the at least one merged result. 8. A system, comprising: one or more processors; andmemory having instructions stored thereon, the instructions, when executed by the one or more processors, cause the processors to perfoim operations comprising: receiving a user request, the user request including at least a speech input received from the user;processing the user request to obtain a representation of user intent, wherein the representation of user intent associates the user request with a task flow operationalizing a requested task, and the task flow is operable to invoke a plurality of services each supporting functions according to a respective plurality of service parameters;based on the representation of user intent, identifying a plurality of relevant task parameters for the task flow, wherein the plurality of relevant task parameters including at least one task parameter explicitly expressed in the speech input and at least one task parameter inferred from context information associated with the speech input; andexecuting the task flow by selectively invoking a subset of the plurality of services in accordance with the plurality of relevant task parameters, wherein the execution of the task flow further comprises: after an unsuccessful attempt to complete the task in accordance with all of the plurality of relevant task parameters: selecting one or more task parameters from the plurality of relevant task parameters to relax in an additional attempt to complete the task, wherein the selecting is based on whether the one or more task parameters were inferred from the context information or explicitly expressed in the speech input. 9. The system of claim 8, wherein the operations further comprise: transforming at least one task parameter according to respective APIs of multiple services of the selected subset of the plurality of services. 10. The system of claim 8, wherein the operations further comprise: gathering service results from the selected subset of the plurality of services; andmerging the service results into a unified result in a service-independent format to fulfill the user request. 11. The system of claim 8, wherein the operations further comprise: assessing relative ability of multiple subsets of services from the plurality of services to satisfy the user request, each of the multiple subsets operable to provide functions according to the identified plurality of relevant task parameters; andbased on the assessment, selecting one of the multiple subsets of services for invocation during the execution of the task flow. 12. The system of claim 8, wherein each service is associated with a respective service capability model comprising declarative descriptions of respective capabilities and properties of the service. 13. The system of claim 12, wherein selectively invoking the subset of the plurality of services further comprises: dynamically selecting the subset of the plurality of services for invocation based on the respective service capability models of the plurality of services. 14. The system of claim 8, wherein the operations further comprise: generating at least one merged result based on results received from the selectively invoked subset of services; andselectively invoking a second plurality of services to annotate the at least one merged result. 15. 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 the user;processing the user request to obtain a representation of user intent, wherein the representation of user intent associates the user request with a task flow operationalizing a requested task, and the task flow is operable to invoke a plurality of services each supporting functions according to a respective plurality of service parameters;based on the representation of user intent, identifying a plurality of relevant task parameters for the task flow, wherein the plurality of relevant task parameters including at least one task parameter explicitly expressed in the speech input and at least one task parameter inferred from context information associated with the speech input; andexecuting the task flow by selectively invoking a subset of the plurality of services in accordance with the plurality of relevant task parameters, wherein the execution of the task flow further comprises: after an unsuccessful attempt to complete the task in accordance with all of the plurality of relevant task parameters: selecting one or more task parameters from the plurality of relevant task parameters to relax in an additional attempt to complete the task, wherein the selecting is based on whether the one or more task parameters were inferred from the context information or explicitly expressed in the speech input. 16. The computer readable storage medium of claim 15, wherein the operations further comprise: transforming at least one task parameter according to respective APIs of multiple services of the selected subset of the plurality of services. 17. The computer readable storage medium of claim 15, wherein the operations further comprise: gathering service results from the selected subset of the plurality of services; andmerging the service results into a unified result in a service-independent format to fulfill the user request. 18. The computer readable storage medium of claim 15, wherein the operations further comprise: assessing relative ability of multiple subsets of services from the plurality of services to satisfy the user request, each of the multiple subsets operable to provide functions according to the identified plurality of relevant task parameters; andbased on the assessment, selecting one of the multiple subsets of services for invocation during the execution of the task flow. 19. The computer readable storage medium of claim 15, wherein each service is associated with a respective service capability model comprising declarative descriptions of respective capabilities and properties of the service. 20. The computer readable storage medium of claim 19, wherein selectively invoking the subset of the plurality of services further comprises: dynamically selecting the subset of the plurality of services for invocation based on the respective service capability models of the plurality of services. 21. The computer readable storage medium of claim 15, wherein the operations further comprise: generating at least one merged result based on results received from the selectively invoked subset of services; andselectively invoking a second plurality of services to annotate the at least one merged result.
Copyright KISTI. All Rights Reserved.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.