公开(公告)号：US09798719B2

公开(公告)日：2017-10-24

申请号：US15332084

申请日：2016-10-24

Applicant: Intel Corporation

Inventor： Yael Karov ,  Micha Breakstone ,  Reshef Shilon ,  Orgad Keller ,  Eric Shellef

IPC: G06F17/27 ,  G06F17/20 ,  G06F17/30

CPC classification number: G06F17/2785 ,  G06F17/271 ,  G06F17/277 ,  G06F17/279 ,  G06F17/30731 ,  G06F17/30976

Abstract: Technologies for natural language request processing include a computing device having a semantic compiler to generate a semantic model based on a corpus of sample requests. The semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies. The computing device generates a semantic representation of a natural language request by generating a lattice of candidate alternative representations, assigning a composite weight to each candidate, and finding the best route through the lattice. The composite weight may include semantic weights, phonetic weights, and/or linguistic weights. The semantic representation identifies a user intent and slots associated with the natural language request. The computing device may perform one or more dialog interactions based on the semantic request, including generating a request for additional information or suggesting additional user intents. The computing device may support automated analysis and tuning to improve request processing. Other embodiments are described and claimed.

公开(公告)号：US10346540B2

公开(公告)日：2019-07-09

申请号：US15695502

申请日：2017-09-05

Applicant: Intel Corporation

Inventor： Yael Karov ,  Micha Breakstone ,  Reshef Shilon ,  Orgad Keller ,  Eric Shellef

IPC: G06F17/27 ,  G06F16/36 ,  G06F16/9032

Abstract: Technologies for natural language request processing include a computing device having a semantic compiler to generate a semantic model based on a corpus of sample requests. The semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies. The computing device generates a semantic representation of a natural language request by generating a lattice of candidate alternative representations, assigning a composite weight to each candidate, and finding the best route through the lattice. The composite weight may include semantic weights, phonetic weights, and/or linguistic weights. The semantic representation identifies a user intent and slots associated with the natural language request. The computing device may perform one or more dialog interactions based on the semantic request, including generating a request for additional information or suggesting additional user intents. The computing device may support automated analysis and tuning to improve request processing. Other embodiments are described and claimed.

公开(公告)号：US20180107652A1

公开(公告)日：2018-04-19

申请号：US15695502

申请日：2017-09-05

Applicant: Intel Corporation

Inventor： Yael Karov ,  Micha Breakstone ,  Reshef Shilon ,  Orgad Keller ,  Eric Shellef

IPC: G06F17/27 ,  G06F17/30

CPC classification number: G06F17/2785 ,  G06F16/36 ,  G06F16/90332 ,  G06F17/271 ,  G06F17/277 ,  G06F17/279

Abstract: Technologies for natural language request processing include a computing device having a semantic compiler to generate a semantic model based on a corpus of sample requests. The semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies. The computing device generates a semantic representation of a natural language request by generating a lattice of candidate alternative representations, assigning a composite weight to each candidate, and finding the best route through the lattice. The composite weight may include semantic weights, phonetic weights, and/or linguistic weights. The semantic representation identifies a user intent and slots associated with the natural language request. The computing device may perform one or more dialog interactions based on the semantic request, including generating a request for additional information or suggesting additional user intents. The computing device may support automated analysis and tuning to improve request processing. Other embodiments are described and claimed.

公开(公告)号：US20170039181A1

公开(公告)日：2017-02-09

申请号：US15332084

申请日：2016-10-24

Applicant: Intel Corporation

Inventor： Yael Karov ,  Micha Breakstone ,  Reshef Shilon ,  Orgad Keller ,  Eric Shellef

IPC: G06F17/27 ,  G06F17/30

CPC classification number: G06F17/2785 ,  G06F17/271 ,  G06F17/277 ,  G06F17/279 ,  G06F17/30731 ,  G06F17/30976

Abstract: Technologies for natural language request processing include a computing device having a semantic compiler to generate a semantic model based on a corpus of sample requests. The semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies. The computing device generates a semantic representation of a natural language request by generating a lattice of candidate alternative representations, assigning a composite weight to each candidate, and finding the best route through the lattice. The composite weight may include semantic weights, phonetic weights, and/or linguistic weights. The semantic representation identifies a user intent and slots associated with the natural language request. The computing device may perform one or more dialog interactions based on the semantic request, including generating a request for additional information or suggesting additional user intents. The computing device may support automated analysis and tuning to improve request processing. Other embodiments are described and claimed.

Abstract translation: 用于自然语言请求处理的技术包括具有语义编译器的计算设备，用于基于样本请求的语料库生成语义模型。 语义编译器可以通过提取上下文语义特征或处理本体来生成语义模型。 计算设备通过生成候选替代表示的格子，为每个候选者分配复合权重，以及找到通过网格的最佳路线来生成自然语言请求的语义表示。 复合权重可以包括语义权重，语音权重和/或语言权重。 语义表示识别与自然语言请求相关联的用户意图和时隙。 计算设备可以基于语义请求来执行一个或多个对话交互，包括生成对附加信息的请求或建议额外的用户意图。 计算设备可以支持自动分析和调整以改善请求处理。 描述和要求保护其他实施例。

公开(公告)号：US20170364516A1

公开(公告)日：2017-12-21

申请号：US15129590

申请日：2015-12-24

Applicant: Intel Corporation

Inventor： Eric Ariel Shellef ,  Reshef Shilon ,  Peter Graff ,  Jonathan Eng ,  Guillermo Perez ,  Juan Manuel Lucas ,  Martin Henk Van Den Berg

IPC: G06F17/30 ,  G10L15/183 ,  G10L15/07 ,  G10L17/22 ,  G10L17/02 ,  G06K9/00

CPC classification number: G06F16/436 ,  G06K2009/00939 ,  G10L15/075 ,  G10L15/183 ,  G10L15/24 ,  G10L17/02 ,  G10L17/22

Abstract: The present disclosure describes dynamically adjusting linguistic models for automatic speech recognition based on biometric information to produce a more reliable speech recognition experience. Embodiments include receiving a speech signal, receiving a biometric signal from a biometric sensor implemented at least partially in hardware, determining a linguistic model based on the biometric signal, and processing the speech signal for speech recognition using the linguistic model based on the biometric signal.

公开(公告)号：US09772994B2

公开(公告)日：2017-09-26

申请号：US14341013

申请日：2014-07-25

Applicant: Intel Corporation

Inventor： Yael Karov ,  Micha Breakstone ,  Reshef Shilon ,  Orgad Keller ,  Eric Shellef

IPC: G06F17/27 ,  G06F17/20 ,  G06F17/30

CPC classification number: G06F17/2785 ,  G06F17/271 ,  G06F17/277 ,  G06F17/279 ,  G06F17/30731 ,  G06F17/30976

Abstract: Technologies for natural language request processing include a computing device having a semantic compiler to generate a semantic model based on a corpus of sample requests. The semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies. The computing device generates a semantic representation of a natural language request by generating a lattice of candidate alternative representations, assigning a composite weight to each candidate, and finding the best route through the lattice. The composite weight may include semantic weights, phonetic weights, and/or linguistic weights. The semantic representation identifies a user intent and slots associated with the natural language request. The computing device may perform one or more dialog interactions based on the semantic request, including generating a request for additional information or suggesting additional user intents. The computing device may support automated analysis and tuning to improve request processing. Other embodiments are described and claimed.