公开(公告)号：WO2017146803A1

公开(公告)日：2017-08-31

申请号：PCT/US2016/066619

申请日：2016-12-14

Applicant: GOOGLE INC.

Inventor： GAO, Yuli ,  SUNG, Sangsoo ,  MENGIBAR, Pedro Jose Moreno

IPC: G06F17/30 ,  G10L15/22

CPC classification number: G06F17/30654 ,  G06F17/271 ,  G06F17/30684 ,  G10L15/265 ,  G10L2015/223 ,  G10L2015/225

Abstract: An offline semantic processor of a resource-constrained voice-enabled device such as a mobile device utilizes an offline grammar model with reduced resource requirements in order to facilitate offline semantic processing in the resource-constrained voice-enabled device. In various implementations, a query issued at a resource-constrained device may be semantically processed to identify candidate responsive actions that are performable by the resource-constrained device. Candidate responsive action performance statistics may be analyzed to select, from the one or more candidate responsive actions, a qualifying responsive action. In various implementations, the candidate responsive action performance statistics may relate to performance of the one or more candidate responsive actions by the resource-constrained device following issuance of the query. An offline grammar model stored in the resource-constrained device may be updated to include a mapping between the issued query and the qualifying responsive action, wherein the offline grammar model maps queries to actions that are performable by the resource-constrained device while offline.

Abstract translation: 资源受限的启用语音的设备（例如移动设备）的离线语义处理器利用具有减少的资源需求的离线语法模型，以促进资源受限的启用语音的语义处理 设备。 在各种实现中，可以对在资源受限设备处发出的查询进行语义处理，以识别可由资源受限设备执行的候选响应动作。 可以分析候选人响应行为表现统计，以从一个或多个候选人响应行为中选择合格的响应行为。 在各种实现中，候选人响应行为表现统计可以涉及资源受限设备在发出查询之后对一个或多个候选人响应行为的表现。 存储在资源受限设备中的离线语法模型可以被更新以包括发出的查询与合格的响应动作之间的映射，其中离线语法模型将查询映射到资源受限设备在离线时可执行的动作。 / p>