公开(公告)号：US10277479B2

公开(公告)日：2019-04-30

申请号：US13696930

申请日：2010-05-11

申请人： Jesper Olsen ,  Happia Cao ,  Jilei Tian

发明人： Jesper Olsen ,  Happia Cao ,  Jilei Tian

IPC分类号： G06F13/00 ,  H04L12/26 ,  H04W4/02 ,  H04L29/08

摘要： An approach is provided for training a device to associate user, object or device context information with a user defined context. The context information platform receives recorded context information from a device. The associated recorded context information is then associated with the context to enable training of a context model associated with the context.

公开(公告)号：US20130145024A1

公开(公告)日：2013-06-06

申请号：US13817065

申请日：2010-08-16

申请人： Happia Cao ,  Jilei Tian ,  Jesper Olsen ,  Pekka Ketola ,  Satu Kalliokulju

发明人： Happia Cao ,  Jilei Tian ,  Jesper Olsen ,  Pekka Ketola ,  Satu Kalliokulju

IPC分类号： H04L29/08

CPC分类号： H04L67/22 ,  G06F16/24575 ,  G06F16/903

摘要： An approach is provided for initiating a device action in response to determining context information associated with a device, a user of the device, or a combination thereof. Activity information on at least one of the device and one or more other devices is monitored by a context processing platform. The context processing platform defines a context based on the activity information. An action is then executed by the device or the one or more other devices based on the determined context.

摘要翻译： 提供了一种用于响应于确定与设备，设备的用户或其组合相关联的上下文信息而发起设备动作的方法。 至少一个设备和一个或多个其他设备的活动信息由上下文处理平台监视。 上下文处理平台基于活动信息来定义上下文。 然后，基于所确定的上下文，该设备或一个或多个其他设备执行动作。

公开(公告)号：US20130132566A1

公开(公告)日：2013-05-23

申请号：US13696930

申请日：2010-05-11

申请人： Jesper Olsen ,  Happia Cao ,  Jilei Tian

发明人： Jesper Olsen ,  Happia Cao ,  Jilei Tian

IPC分类号： H04L12/26

CPC分类号： H04L43/00 ,  H04L67/306 ,  H04W4/025

摘要： An approach is provided for training a device to associate user, object or device context information with a user defined context. The context information platform receives recorded context information from a device. The associated recorded context information is then associated with the context to enable training of a context model associated with the context.

摘要翻译： 提供了一种用于训练设备以将用户，对象或设备上下文信息与用户定义的上下文相关联的方法。 上下文信息平台从设备接收记录的上下文信息。 然后将相关联的记录的上下文信息与上下文相关联，以便能够对与上下文相关联的上下文模型进行训练。

公开(公告)号：US20120331137A1

公开(公告)日：2012-12-27

申请号：US13582232

申请日：2010-03-01

申请人： Jesper Olsen ,  Jilei Tian

发明人： Jesper Olsen ,  Jilei Tian

IPC分类号： G06F15/173

CPC分类号： H04L67/22 ,  G06Q10/10 ,  G06Q30/02 ,  H04L67/04 ,  H04L67/306

摘要： An approach is provided for estimating user characteristics based on user interaction data. A characteristics determination logic retrieves an interaction data from a device associated with a use. Next, the characteristics determination logic determines a usage vector from the interaction data. Then, the characteristics determination logic correlates the determined usage vector with one or more predefined characteristics. Then, the characteristics determination logic computes a user characteristics profile based, at least in part, on the one or more correlated characteristics.

摘要翻译： 提供了一种基于用户交互数据来估计用户特征的方法。 特征确定逻辑从与使用相关联的设备检索交互数据。 接下来，特征确定逻辑从交互数据确定使用向量。 然后，特征确定逻辑将所确定的使用向量与一个或多个预定特征相关联。 然后，特性确定逻辑至少部分地基于一个或多个相关特征来计算用户特征简档。

公开(公告)号：US08851277B2

公开(公告)日：2014-10-07

申请号：US13824257

申请日：2011-10-26

申请人： Jesper Olsen ,  Steffen Olsen

发明人： Jesper Olsen ,  Steffen Olsen

IPC分类号： B65G21/02 ,  B65G15/62

CPC分类号： B65G15/62 ,  B65G21/02 ,  B65G2207/26

摘要： The present invention relates to a conveyor system (2) comprising a support frame (4) and an endless carrier chain (6) arranged horizontally thereon and defining an upper part (6a) and a lower part (6b); the carrier chain thereby having an inner side (12) and an outer side (14);wherein the support frame comprises a shielding element (24) in an area (A) defined between the inner side (12a) of the upper part of the carrier chain (6) and the inner side (12b) of the lower part of the carrier chain (6); wherein the shielding element (24) itself, or in combination with the first main support element (16) and/or the second main support element (18) having an extension that blocks a direct access between any point P1 located on the inner side (12a) of the upper part of the carrier chain (6) and a corresponding point P2 located on the inner side (12b) of the lower part of the carrier chain.

摘要翻译： 本发明涉及一种输送机系统（2），其包括支撑框架（4）和水平地布置在其上并限定上部（6a）和下部（6b）的环形承载链（6）; 所述承载链由此具有内侧（12）和外侧（14）; 其中所述支撑框架包括在所述承载链（6）的上部的内侧（12a）和所述承载件的下部的内侧（12b）之间限定的区域（A）中的屏蔽元件（24） 链（6）; 其中所述屏蔽元件（24）本身或与所述第一主支撑元件（16）和/或所述第二主支撑元件（18）组合具有延伸部，所述延伸部阻挡位于所述内侧上的任何点P1 （6）的上部的12a）和位于载体链的下部的内侧（12b）上的对应点P2。

公开(公告)号：US09418662B2

公开(公告)日：2016-08-16

申请号：US12356814

申请日：2009-01-21

申请人： Jesper Olsen

发明人： Jesper Olsen

IPC分类号： G10L15/14 ,  G10L17/20 ,  G10L15/07

CPC分类号： G10L17/20 ,  G10L15/07

摘要： An apparatus for providing compound models for speech recognition adaptation. The apparatus may include processor and memory including computer program code with the memory, the computer program code being configured, with the processor, to cause the apparatus to at least receive a speech signal corresponding to a particular speaker. The apparatus may further be configured to select a cluster model including both a speaker independent portion and a speaker dependent portion based at least in part on a characteristic of speech of the particular speaker. The apparatus may be further configured to process the speech using the selected cluster model. The apparatus may be further configured to cause at least a speaker dependent portion of one or more non-selected cluster models to be stored remotely. A corresponding method and computer program product are also provided.

摘要翻译： 一种用于提供用于语音识别适配的复合模型的装置。 该装置可以包括处理器和存储器，其包括具有存储器的计算机程序代码，计算机程序代码与处理器一起配置，以使得该装置至少接收对应于特定说话者的语音信号。 该装置还可以被配置为至少部分地基于特定说话者的语音特征来选择包括与扬声器独立部分和扬声器相关部分两者的集群模型。 该装置还可以被配置为使用所选择的集群模型来处理语音。 该装置还可以被配置为使远程存储一个或多个未选择的群集模型的至少一个说话者相关部分。 还提供了相应的方法和计算机程序产品。

公开(公告)号：US20100185444A1

公开(公告)日：2010-07-22

申请号：US12356814

申请日：2009-01-21

申请人： Jesper Olsen

发明人： Jesper Olsen

IPC分类号： G10L15/00 ,  G10L11/00

CPC分类号： G10L17/20 ,  G10L15/07

摘要： An apparatus for providing compound models for speech recognition adaptation includes a processor. The processor may be configured to receive a speech signal corresponding to a particular speaker, select a cluster model including both a speaker independent portion and a speaker dependent portion based at least in part on a characteristic of speech of the particular speaker, and process the speech signal using the selected cluster model. A corresponding method and computer program product are also provided.

摘要翻译： 用于提供用于语音识别适配的复合模型的装置包括处理器。 处理器可以被配置为接收对应于特定扬声器的语音信号，至少部分地基于特定说话者的语音特征来选择包括与扬声器无关部分和说话者相关部分两者的集群模型，并且处理语音 信号使用所选择的集群模型。 还提供了相应的方法和计算机程序产品。

公开(公告)号：US20070088552A1

公开(公告)日：2007-04-19

申请号：US11252475

申请日：2005-10-17

申请人： Jesper Olsen

发明人： Jesper Olsen

IPC分类号： G10L15/14

CPC分类号： G10L15/08 ,  G10L15/02 ,  G10L15/142

摘要： Method for speech recognition comprising inputting frames comprising samples of an audio signal; forming a feature vector comprising a first number of vector components for each frame; projecting the feature vector onto at least two subspaces so that the number of components of each projected feature vector is less than the first number and the total number of components of the projected feature vectors is the same as the first number; defining a set of mixture models for each projected vector which provides the highest observation probability; analysing the set of mixture models to determine the recognition result. When the recognition result is found, the method comprises determining a confidence measure for the recognition result, the determining comprising determining a probability that the recognition result is correct; determining a normalizing term; and dividing the probability by the normalizing term.

摘要翻译： 用于语音识别的方法，包括输入包括音频信号的采样的帧; 形成包括每帧的第一数量的向量分量的特征向量; 将特征向量投影到至少两个子空间，使得每个投影特征向量的分量的数量小于第一数量，并且投影特征向量的分量的总数与第一数目相同; 为每个提供最高观察概率的投影向量定义一组混合模型; 分析混合模型集合以确定识别结果。 当识别结果被发现时，该方法包括确定识别结果的置信度量度，该确定包括确定识别结果是正确的概率; 确定正常化术语; 并将概率除以归一化项。

公开(公告)号：US20130180833A1

公开(公告)日：2013-07-18

申请号：US13824257

申请日：2011-10-20

申请人： Jesper Olsen ,  Steffen Olsen

发明人： Jesper Olsen ,  Steffen Olsen

IPC分类号： B65G15/62

CPC分类号： B65G15/62 ,  B65G21/02 ,  B65G2207/26

摘要： The present invention relates to a conveyor system (2) comprising a support frame (4) and an endless carrier chain (6) arranged horizontally thereon and defining an upper part (6a) and a lower part (6b); the carrier chain thereby having an inner side (12) and an outer side (14);wherein said support frame comprises a shielding element (24) in an area (A) defined between the inner side (12a) of the upper part of the carrier chain (6) and the inner side (12b) of the lower part of the carrier chain (6); wherein said shielding element (24) itself, or in combination with the first main support element (16) and/or the second main support element (18) having an extension that blocks a direct access between any point P1 located on the inner side (12a) of the upper part of the carrier chain (6) and a corresponding point P2 located on the inner side (12b) of the lower part of the carrier chain.

摘要翻译： 本发明涉及一种输送机系统（2），其包括支撑框架（4）和水平地布置在其上并限定上部（6a）和下部（6b）的环形承载链（6）; 所述承载链由此具有内侧（12）和外侧（14）; 其中所述支撑框架包括在所述承载链（6）的上部的内侧（12a）和所述承载件的下部的内侧（12b）之间限定的区域（A）中的屏蔽元件（24） 链（6）; 其中所述屏蔽元件（24）本身或与第一主支撑元件（16）和/或第二主支撑元件（18）组合具有延伸部，该延伸部分阻止位于内侧的任何点P1 （6）的上部的12a）和位于载体链的下部的内侧（12b）上的对应点P2。

公开(公告)号：US07974993B2

公开(公告)日：2011-07-05

申请号：US11633250

申请日：2006-12-04

申请人： Robert Blanch ,  Srinivasan Parthasarathy ,  Jesper Olsen

发明人： Robert Blanch ,  Srinivasan Parthasarathy ,  Jesper Olsen

IPC分类号： G06F7/00

CPC分类号： G06F9/44536

摘要： A system for supporting version management is provided. The system includes a first application having a plurality of versions. Each of the plurality of versions is associated with a separate a version-specific assembly. A loader is configured to load one of the version-specific assemblies, the assembly then being utilized as a basis for deriving an object from a database associated with the first application. The object is provided to a second application, typically in response to a corresponding request.

摘要翻译： 提供了支持版本管理的系统。 该系统包括具有多个版本的第一应用。 多个版本中的每一个与单独的版本特定的组件相关联。 加载器被配置为加载特定于版本的程序集中的一个，组件然后被用作从与第一应用程序相关联的数据库中导出对象的基础。 该对象通常响应于相应的请求被提供给第二应用。