公开(公告)号：US20170091628A1

公开(公告)日：2017-03-30

申请号：US14866889

申请日：2015-09-26

Applicant: Lama Nachman ,  Ashwini Asokan ,  Giuseppe Raffa ,  Rita H. Wouhaybi ,  Saurav Sahay ,  Omar U. Florez ,  Rahul C. Shah ,  Chieh-Yih Wan ,  Jonathan J. Huang ,  Hong Lu ,  Sangita Sharma ,  Junaith Ahemed Shahabdeen ,  Douglas P. Bogia ,  Lenitra Durham

Inventor： Lama Nachman ,  Ashwini Asokan ,  Giuseppe Raffa ,  Rita H. Wouhaybi ,  Saurav Sahay ,  Omar U. Florez ,  Rahul C. Shah ,  Chieh-Yih Wan ,  Jonathan J. Huang ,  Hong Lu ,  Sangita Sharma ,  Junaith Ahemed Shahabdeen ,  Douglas P. Bogia ,  Lenitra Durham

IPC: G06N5/04 ,  G06F17/27 ,  G06N99/00 ,  G06T11/20

CPC classification number: G06F17/2785 ,  G06F16/9535 ,  G06N5/022

Abstract: Technologies for automated context-aware media curation include a computing device that captures context data associated with media objects. The context data may include location data, proximity data, behavior data of the user, and social activity data. The computing device generates inferred context data using one or more cognitive or machine learning algorithms. The inferred context data may include semantic time or location data, activity data, or sentiment data. The computing device updates a user context model and an expanded media object graph based on the context data and the inferred context data. The computing device selects one or more target media objects using the user context model and the expanded media object graph. The computing device may present context-aware media experiences to the user with the target media objects. Context-aware media experiences may include contextual semantic search and contextual media browsing. Other embodiments are described and claimed.

公开(公告)号：US20150095678A1

公开(公告)日：2015-04-02

申请号：US14040339

申请日：2013-09-27

Applicant: Lama Nachman ,  Sangita Sharma ,  Giuseppe Raffa ,  Adam Jordan ,  Ashwini Asokan ,  Philip Corriveau

Inventor： Lama Nachman ,  Sangita Sharma ,  Giuseppe Raffa ,  Adam Jordan ,  Ashwini Asokan ,  Philip Corriveau

IPC: G06F1/32

CPC classification number: G06F1/3234 ,  G06F1/3206 ,  G06F3/017

Abstract: Techniques for modifying a power state of a device are described herein. The techniques include receiving data from a sensor indicating movement of the device, and determining whether the device movement is associated with a predetermined device movement. Based on the determination, the techniques include modifying a power state of the device from either a first power state to a second power state, or from the second power state to the first power state, wherein the device consumes more power in the first power state than in the second power state.

Abstract translation: 本文描述了用于修改设备的电源状态的技术。 这些技术包括从传感器接收指示设备移动的数据，以及确定设备移动是否与预定的设备移动相关联。 基于该确定，所述技术包括将设备的电力状态从第一电力状态改变到第二电力状态，或者从第二电力状态改变到第一电力状态，其中所述装置在所述第一电力状态下消耗更多的电力 比在第二电力状态。

公开(公告)号：US20140188920A1

公开(公告)日：2014-07-03

申请号：US13728548

申请日：2012-12-27

Applicant: Sangita Sharma ,  Giuseppe Raffa ,  Chieh-Yih Wan ,  David L. Graumann

Inventor： Sangita Sharma ,  Giuseppe Raffa ,  Chieh-Yih Wan ,  David L. Graumann

IPC: G06F17/30

CPC classification number: G06F16/635 ,  G06F16/64

Abstract: Systems and methods to receive content and generate a playlist of content based at least in part on content interests and/or preferences of occupants of a vehicle is disclosed. The playlist may further be generated based on user interests and/or preferences of multiple occupants of the vehicle. In addition, a drive context of the vehicle may be used in the selection of content for receiving and/or rendering.

Abstract translation: 公开了至少部分地基于车辆的乘客的内容兴趣和/或偏好来接收内容并生成内容的播放列表的系统和方法。 还可以基于车辆的多个乘客的用户兴趣和/或偏好来生成播放列表。 此外，车辆的驾驶环境可以用于选择用于接收和/或呈现的内容。

公开(公告)号：US20130293505A1

公开(公告)日：2013-11-07

申请号：US13996471

申请日：2011-09-30

Applicant: Lakshman Krishnamurthy ,  David L. Graumann ,  Sangita Sharma ,  Jameson H. Williams

Inventor： Lakshman Krishnamurthy ,  David L. Graumann ,  Sangita Sharma ,  Jameson H. Williams

IPC: G06F3/041

CPC classification number: G06F3/041 ,  G06F3/0488 ,  G06F9/451 ,  G06F2203/0339 ,  G06F2203/04808

Abstract: Method and apparatus for multi-dimensional interaction interface for mobile devices. An embodiment of a mobile device includes a touch screen to provide a display and to generate a touch screen signal upon contact to the touch screen, a touch sensor to generate a touch sensor signal upon contact to the touch sensor, and a module to provide for cooperative operation of the touch screen signal and the touch sensor signal in providing input to the mobile device upon determining that an input to the touch screen indicates a multipoint input.

Abstract translation: 用于移动设备的多维交互界面的方法和装置。 移动设备的实施例包括触摸屏以提供显示并且在与触摸屏接触时产生触摸屏信号，触摸传感器在与触摸传感器接触时产生触摸传感器信号，以及模块，用于提供 在确定对触摸屏的输入指示多点输入时，触摸屏信号和触摸传感器信号的协作操作向移动设备提供输入。

公开(公告)号：US20110254796A1

公开(公告)日：2011-10-20

申请号：US13169524

申请日：2011-06-27

Applicant: Peter S. Adamson ,  Mark D. Yarvis ,  David L. Graumann ,  Sangita Sharma

Inventor： Peter S. Adamson ,  Mark D. Yarvis ,  David L. Graumann ,  Sangita Sharma

IPC: G06F3/041

CPC classification number: G06F3/04883

Abstract: Briefly, a method and apparatus for recognizing temporal tapping patterns input to a touch panel interface is disclosed. The method may include receiving user input with a touch panel interface, recognizing a temporal tapping pattern in the user input, and performing an action associated with the temporal tapping pattern.

Abstract translation: 简而言之，公开了一种用于识别输入到触摸面板接口的时间点击图案的方法和装置。 该方法可以包括使用触摸面板接口接收用户输入，识别用户输入中的时间点击模式，以及执行与时间点击模式相关联的动作。

公开(公告)号：US20110246300A1

公开(公告)日：2011-10-06

申请号：US13162041

申请日：2011-06-16

Applicant: Mark D. Yarvis ,  Rita H. Wouhaybi ,  Philip Muse ,  Lenitra M. Durham ,  Sai P. Balasundaram ,  Sangita Sharma ,  Chieh-Yih Wan

Inventor： Mark D. Yarvis ,  Rita H. Wouhaybi ,  Philip Muse ,  Lenitra M. Durham ,  Sai P. Balasundaram ,  Sangita Sharma ,  Chieh-Yih Wan

IPC: G06Q30/00

CPC classification number: G06Q30/0255 ,  G06Q30/02

Abstract: An embodiment of the present invention provides a method of determining when a user is in-market for a specific product and knowing general shopping preferences and habits of users, comprising using web browsing behavior to determine the products the user is interested in purchasing and how the user typically likes to shop and wherein the web browsing behavior is determined by watching some or all web pages loaded and analyzing at least a URL, page text, and cookies associated with each loaded web page.

Abstract translation: 本发明的一个实施例提供了一种确定用户在特定产品何时进入市场并知道一般购物偏好和用户习惯的方法，包括使用网页浏览行为来确定用户感兴趣购买的商品以及如何 用户通常喜欢购物，并且其中通过观看加载的一些或所有网页并分析至少一个URL，页面文本和与每个加载的网页相关联的cookie来确定网络浏览行为。

公开(公告)号：US07254538B1

公开(公告)日：2007-08-07

申请号：US09714806

申请日：2000-11-16

Applicant: Hynek Hermansky ,  Sangita Sharma ,  Daniel Ellis

Inventor： Hynek Hermansky ,  Sangita Sharma ,  Daniel Ellis

IPC: G10L15/14

CPC classification number: G10L15/144

Abstract: The present invention successfully combines neural-net discriminative feature processing with Gaussian-mixture distribution modeling (GMM). By training one or more neural networks to generate subword probability posteriors, then using transformations of these estimates as the base features for a conventionally-trained Gaussian-mixture based system, substantial error rate reductions may be achieved. The present invention effectively has two acoustic models in tandem—first a neural net and then a GMM. By using a variety of combination schemes available for connectionist models, various systems based upon multiple features streams can be constructed with even greater error rate reductions.

Abstract translation: 本发明成功地将神经网识别特征处理与高斯混合分布建模（GMM）相结合。 通过训练一个或多个神经网络以产生子词概率后代，然后使用这些估计的变换作为常规训练的基于高斯混合的系统的基本特征，可以实现显着的误码率降低。 本发明有效地将两个声学模型串联在神经网络中，然后是GMM。 通过使用可用于连接器型号的各种组合方案，可以以更大的错误率降低构建基于多个特征流的各种系统。

公开(公告)号：US09147057B2

公开(公告)日：2015-09-29

申请号：US13535795

申请日：2012-06-28

Applicant: Giuseppe Raffa ,  Sangita Sharma ,  Chieh-Yih Wan

Inventor： Giuseppe Raffa ,  Sangita Sharma ,  Chieh-Yih Wan

IPC: G06F3/01 ,  G06F21/32 ,  G06F3/0488

CPC classification number: G06F3/04883 ,  G06F3/0412 ,  G06F3/1423 ,  G06F21/32 ,  G06F21/36 ,  G06K9/00335 ,  G09G5/12 ,  G09G2354/00 ,  G09G2370/16

Abstract: Techniques for device connections using touch gestures are described. A method may comprise receiving a first gesture input at a first electronic device, receiving, at the first electronic device, a second gesture input from a second computing device in proximity to the first computing device, comparing the first gesture input and the second gesture input, and establishing a wireless connection between the first computing device and the second computing device if a similarity of the first gesture input and the second gesture input meets or exceeds a similarity threshold based on the comparing. Other embodiments are described and claimed.

Abstract translation: 描述使用触摸手势进行设备连接的技术。 一种方法可以包括在第一电子设备处接收第一手势输入，在第一电子设备处接收距离第一计算设备附近的第二计算设备的第二手势输入，比较第一手势输入和第二手势输入 以及如果所述第一手势输入和所述第二手势输入的相似度基于所述比较满足或超过相似性阈值，则在所述第一计算设备和所述第二计算设备之间建立无线连接。 描述和要求保护其他实施例。

公开(公告)号：US20140172990A1

公开(公告)日：2014-06-19

申请号：US13714908

申请日：2012-12-14

Applicant: CHIEH-YIH WAN ,  SANGITA SHARMA ,  GIUSEPPE RAFFA

Inventor： CHIEH-YIH WAN ,  SANGITA SHARMA ,  GIUSEPPE RAFFA

IPC: H04L12/58

CPC classification number: H04L51/14 ,  H04L51/046 ,  H04W4/025 ,  H04W4/046 ,  H04W4/14

Abstract: Systems and methods for receiving a communication on one or more user devices within a vehicle and redirecting the communications based at least in part on one or more user profiles associated with occupants of the vehicle is disclosed. The redirection of the communication may further be based at least in part on one or more sensor signals or a drive characteristic associated with the vehicle.

Abstract translation: 公开了用于在车辆内的一个或多个用户设备上接收通信并且至少部分地基于与车辆乘客相关联的一个或多个用户简档重定向通信的系统和方法。 通信的重定向还可以至少部分地基于与车辆相关联的一个或多个传感器信号或驱动特性。

公开(公告)号：US20140006954A1

公开(公告)日：2014-01-02

申请号：US13535795

申请日：2012-06-28

Applicant: GIUSEPPE RAFFA ,  SANGITA SHARMA ,  CHIEH-YIH WAN

Inventor： GIUSEPPE RAFFA ,  SANGITA SHARMA ,  CHIEH-YIH WAN

IPC: G06F3/01 ,  H04W8/00 ,  G06F15/16

CPC classification number: G06F3/04883 ,  G06F3/0412 ,  G06F3/1423 ,  G06F21/32 ,  G06F21/36 ,  G06K9/00335 ,  G09G5/12 ,  G09G2354/00 ,  G09G2370/16

Abstract: Techniques for device connections using touch gestures are described. A method may comprise receiving a first gesture input at a first electronic device, receiving, at the first electronic device, a second gesture input from a second computing device in proximity to the first computing device, comparing the first gesture input and the second gesture input, and establishing a wireless connection between the first computing device and the second computing device if a similarity of the first gesture input and the second gesture input meets or exceeds a similarity threshold based on the comparing. Other embodiments are described and claimed.

Abstract translation: 描述使用触摸手势进行设备连接的技术。 一种方法可以包括在第一电子设备处接收第一手势输入，在第一电子设备处接收距离第一计算设备附近的第二计算设备的第二手势输入，比较第一手势输入和第二手势输入 以及如果所述第一手势输入和所述第二手势输入的相似度基于所述比较满足或超过相似性阈值，则在所述第一计算设备和所述第二计算设备之间建立无线连接。 描述和要求保护其他实施例。