公开(公告)号：US20150023567A1

公开(公告)日：2015-01-22

申请号：US13943953

申请日：2013-07-17

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： DUSAN MACHO

IPC: G06K9/00 ,  G06F21/32 ,  G06F21/36 ,  G06F3/0484

CPC classification number: G06K9/00087 ,  G06F3/017 ,  G06F3/0304 ,  G06F3/0426 ,  G06F3/0482 ,  G06F3/0484 ,  G06F21/32 ,  G06F21/36 ,  G06K9/00 ,  G06K9/00013 ,  G06K9/03 ,  G06K2009/00953 ,  G06Q30/0271 ,  H04L63/0861 ,  H04L63/0892

Abstract: A user is identified and an in-place personalized interactive display provided by detecting, via a first imaging system, one or more unique characteristics of a user's palm, identifying the user via the one or more unique characteristics and a database containing mappings between detectable unique characteristics and user identities, retrieving user-specific interactive content as a function of the identity of the user, projecting, via a second imaging system, the user-specific interactive content onto the user's palm, and detecting, via a third imaging system, a user's interaction with the projected user-specific interactive content. The user may be identified by transmitting the one or more unique characteristics to a remote authentication server and receiving, in response, an identity of the user. User-specific content as a function of the identity of the user may be retrieved from a remote interactive content server.

Abstract translation: 通过经由第一成像系统检测用户手掌的一个或多个独特特征，经由一个或多个独特特征识别用户，以及包含可检测到的独特特征之间的映射的数据库来提供用户，并提供就地个性化交互式显示 特征和用户身份，根据用户的身份检索用户特定的交互内容，经由第二成像系统将用户特定的交互内容投射到用户的手掌上，以及经由第三成像系统检测 用户与预计的用户特定交互式内容的交互。 可以通过将一个或多个唯一特征发送到远程认证服务器并且作为响应来接收用户的身份来识别用户。 可以从远程交互式内容服务器检索作为用户身份的函数的用户特定内容。

公开(公告)号：US20140122087A1

公开(公告)日：2014-05-01

申请号：US13663850

申请日：2012-10-30

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： DUSAN MACHO

IPC: G10L15/22

CPC classification number: G10L15/22 ,  G06F1/3203 ,  G10L13/033 ,  G10L15/265 ,  G10L17/22 ,  G10L2015/088

Abstract: An apparatus, method, and computer program for initiating a word spotting algorithm (220) on one or more wireless communication devices in a first power mode to detect a keyword data sequence (224) embedded within a sampled audio signal (222). In response to detecting the keyword data sequence (226), the word spotting algorithm is terminated and a plurality of identification algorithms (230) are initiated on the one or more wireless communication devices operating in a second power mode to detect the presence of identification data (240). If identification data is detected on a particular wireless communication device it is activated to accept speech and/or voice commands (242). On the other hand, if identification data is not detected, the plurality of identification algorithms are terminated, and the word spotting algorithm is reinitiated on the one or more wireless communication devices that are then operating in the first power mode (244).

Abstract translation: 一种用于在第一功率模式下在一个或多个无线通信设备上发起字检测算法（220）的装置，方法和计算机程序，以检测嵌入在采样音频信号（222）内的关键字数据序列（224）。 响应于检测到关键字数据序列（226），终止单词识别算法，并且在以第二功率模式操作的一个或多个无线通信设备上启动多个识别算法（230），以检测识别数据的存在 （240）。 如果在特定无线通信设备上检测到识别数据，则其被激活以接受语音和/或语音命令（242）。 另一方面，如果未检测到识别数据，则终止多个识别算法，并且在随后以第一功率模式（244）操作的一个或多个无线通信设备上重新启动单词识别算法。

公开(公告)号：US20140181083A1

公开(公告)日：2014-06-26

申请号：US13723746

申请日：2012-12-21

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： DUSAN MACHO ,  KENNETH W. DOUROS ,  SAMEER B. TOTEY

IPC: G06F17/30 ,  G06F3/0481

CPC classification number: G06F16/252 ,  G06F3/04817 ,  G06F16/43 ,  G06F16/7335 ,  G06F16/90328 ,  G06F16/9038

Abstract: A method and user terminal are provided that graphically formulate a search query. The method and user terminal display, via a display screen, a multi-dimensional graphical representation of a search query space, receive a plurality of parameters from a user, wherein the parameters define the search query space, position a multi-dimensional icon in the multi-dimensional representation of the search query space, associate one or more of a keyword and multimedia content with the icon, and generate a search query based on the keyword and the position of the icon in the multi-dimensional representation of the search query space. The method and user terminal further may graphically display the results of the corresponding database search, wherein the retrieved content is displayed as one or more icons positioned in a multi-dimensional graph having a plurality of axes associated with the plurality of parameters defining a context of the search query.

Abstract translation: 提供了以图形方式制定搜索查询的方法和用户终端。 方法和用户终端通过显示屏显示搜索查询空间的多维图形表示，从用户接收多个参数，其中参数定义搜索查询空间，将多维图标定位在 搜索查询空间的多维表示，将关键字和多媒体内容中的一个或多个与图标相关联，并且基于搜索查询空间的多维表示中的图标的关键字和位置生成搜索查询 。 方法和用户终端还可以图形地显示相应的数据库搜索的结果，其中所检索的内容被显示为位于具有多个轴的多维图中的一个或多个图标，所述多个图与多个参数相关联，所述多个参数定义了 搜索查询。

公开(公告)号：US20140009682A1

公开(公告)日：2014-01-09

申请号：US13680502

申请日：2012-11-19

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： YANG M. CHENG ,  DUSAN MACHO

IPC: H04N5/14

CPC classification number: H04N5/14 ,  G06F17/30787 ,  G11B27/105 ,  G11B27/28

Abstract: A method for determining a relatedness between a query video and a database video is provided. A processor extracts an audio stream from the query video to produce a query audio stream, extracts an audio stream from the database video to produce a database audio stream, produces a first-sized snippet from the query audio stream, and produces a first-sized snippet from the database audio stream. An estimation is made of a first most probable sequence of latent evidence probability vectors generating the first-sized audio snippet of the query audio stream. An estimation is made of a second most probable sequence of latent evidence probability vectors generating the first-sized audio snippet of the database audio stream. A similarity is measured between the first sequence and the second sequence producing a score of relatedness between the two snippets. Finally a relatedness is determined between the query video and a database video.

Abstract translation: 提供了一种用于确定查询视频和数据库视频之间的相关性的方法。 处理器从查询视频中提取音频流以产生查询音频流，从数据库视频中提取音频流以产生数据库音频流，从查询音频流产生第一大小的片段，并产生第一大小 来自数据库音频流的片段。 估计生成查询音频流的第一大小音频片段的潜在证据概率向量的第一最可能序列。 估计产生数据库音频流的第一大音频片段的潜在证据概率向量的第二最可能序列。 在第一序列和第二序列之间测量相似性，产生两个片段之间的相关性得分。 最后，在查询视频和数据库视频之间确定相关性。