-
公开(公告)号：US09519726B2
公开(公告)日：2016-12-13
申请号：US13161792
申请日：2011-06-16
Applicant: Amit Kumar , Milind Mahajan
Inventor： Amit Kumar , Milind Mahajan
CPC classification number: G06F17/3053 , G06F8/61 , G06F17/30554 , G06F17/30867 , G06F17/30876 , G06F17/30899 , G06Q30/0251 , G06Q30/0277
Abstract: Applications are surfaced to a user during browsing without requiring a specific search by the user. The applications can be selected for surfacing to the user based on the network address entered into the address bar of a browser, the content of the page corresponding to the network address, or a combination thereof. Applications may be selected for surfacing based on a partial address entered into the address bar and/or based on the web page content that is currently visible in the browser display.
Abstract translation: 应用程序在浏览时显示给用户，而不需要用户的特定搜索。 可以基于输入到浏览器的地址栏的网络地址，与网络地址相对应的页面的内容或其组合来选择用于表示用户的应用程序。 可以基于输入到地址栏的部分地址和/或基于当前在浏览器显示中可见的网页内容来选择应用程序来进行表面处理。
-
公开(公告)号：US08706491B2
公开(公告)日：2014-04-22
申请号：US12862001
申请日：2010-08-24
Applicant: Ciprian Chelba , Milind Mahajan
Inventor： Ciprian Chelba , Milind Mahajan
CPC classification number: G06F17/20 , G06F17/27 , G06F17/2705 , G06F17/271 , G06F17/2785 , G06F17/28 , G06F17/2881 , G10L15/00 , G10L15/04 , G10L15/05 , G10L15/18 , G10L15/1822 , G10L15/22
Abstract: One feature of the present invention uses the parsing capabilities of a structured language model in the information extraction process. During training, the structured language model is first initialized with syntactically annotated training data. The model is then trained by generating parses on semantically annotated training data enforcing annotated constituent boundaries. The syntactic labels in the parse trees generated by the parser are then replaced with joint syntactic and semantic labels. The model is then trained by generating parses on the semantically annotated training data enforcing the semantic tags or labels found in the training data. The trained model can then be used to extract information from test data using the parses generated by the model.
Abstract translation: 本发明的一个特征是在信息提取过程中使用结构化语言模型的解析能力。 在训练期间，结构化语言模型首先用语法注释的训练数据初始化。 然后通过在强制执行注释的组成边界的语义注释的训练数据上生成分析来训练该模型。 然后由解析器生成的解析树中的句法标签被替换为联合句法和语义标签。 然后通过在强制执行训练数据中发现的语义标签或标签的语义注释训练数据上生成分析来训练该模型。 然后可以使用经过训练的模型，使用由模型生成的分析来从测试数据中提取信息。
-
公开(公告)号：US08648914B1
公开(公告)日：2014-02-11
申请号：US12651115
申请日：2009-12-31
Applicant: Bruce K. Winker , Venkatarman Sundareswaran , Milind Mahajan , Steven L. Chen
Inventor： Bruce K. Winker , Venkatarman Sundareswaran , Milind Mahajan , Steven L. Chen
Abstract: A laser communication and spatial referencing system and related methods provides effective and secure non-line-of-sight communications. A laser communication and spatial referencing system includes a laser transmitter transmitting a pulsed laser beam encoded with binary communications data, and an imaging data receiver for receiving the pulsed laser beam reflecting off a reflective target. The imaging receiver decodes the binary communications data and determines the position of the laser beam. The laser communication and spatial referencing system may operate synchronously and/or asynchronously, and may include a display displaying a video image of area surrounding the target with the reflecting location superimposed on the image to provide visual identification of the target.
Abstract translation: 激光通信和空间参考系统及相关方法提供有效和安全的非视距通信。 激光通信和空间参考系统包括传输用二进制通信数据编码的脉冲激光束的激光发射器和用于接收反射出反射目标的脉冲激光束的成像数据接收器。 成像接收机解码二进制通信数据并确定激光束的位置。 激光通信和空间参考系统可以同步和/或异步地操作，并且可以包括显示在目标周围的区域的视频图像的显示器，其中反射位置叠加在图像上以提供目标的视觉识别。
-
公开(公告)号：US07805302B2
公开(公告)日：2010-09-28
申请号：US10151979
申请日：2002-05-20
Applicant: Ciprian Chelba , Milind Mahajan
Inventor： Ciprian Chelba , Milind Mahajan
CPC classification number: G06F17/20 , G06F17/27 , G06F17/2705 , G06F17/271 , G06F17/2785 , G06F17/28 , G06F17/2881 , G10L15/00 , G10L15/04 , G10L15/05 , G10L15/18 , G10L15/1822 , G10L15/22
Abstract: One feature of the present invention uses the parsing capabilities of a structured language model in the information extraction process. During training, the structured language model is first initialized with syntactically annotated training data. The model is then trained by generating parses on semantically annotated training data enforcing annotated constituent boundaries. The syntactic labels in the parse trees generated by the parser are then replaced with joint syntactic and semantic labels. The model is then trained by generating parses on the semantically annotated training data enforcing the semantic tags or labels found in the training data. The trained model can then be used to extract information from test data using the parses generated by the model.
Abstract translation: 本发明的一个特征是在信息提取过程中使用结构化语言模型的解析能力。 在训练期间，结构化语言模型首先用语法注释的训练数据初始化。 然后通过在强制执行注释的组成边界的语义注释的训练数据上生成分析来训练该模型。 然后由解析器生成的解析树中的句法标签被替换为联合句法和语义标签。 然后通过在强制执行训练数据中发现的语义标签或标签的语义注释训练数据上生成分析来训练该模型。 然后可以使用经过训练的模型，使用由模型生成的分析来从测试数据中提取信息。
-
公开(公告)号：US20080177536A1
公开(公告)日：2008-07-24
申请号：US11626726
申请日：2007-01-24
Applicant: Adil Sherwani , Christopher Weare , Patrick Nguyen , Milind Mahajan , Alex Acero , Manuel Clement , Patrick Nelson
Inventor： Adil Sherwani , Christopher Weare , Patrick Nguyen , Milind Mahajan , Alex Acero , Manuel Clement , Patrick Nelson
IPC: G10L15/26
CPC classification number: G11B27/10 , G06F16/685 , G10L15/26 , G11B27/034
Abstract: A/V content creation, editing and publishing is disclosed. Speech recognition can be performed on the A/V content to identify words therein and form a transcript of the words. The transcript can be aligned with the associated A/V content and displayed to allow selective editing of the transcript and associated A/V content. Keywords and a summary for the transcript can also be identified for use in publishing the A/V content.
Abstract translation: 披露了A / V内容创作，编辑和出版。 可以对A / V内容执行语音识别，以识别其中的单词并形成单词的抄本。 誊本可以与相关的A / V内容对齐，并显示为允许选择性地编辑抄本和相关的A / V内容。 关键词和抄本的摘要也可以用于发布A / V内容。
-
Patent Agency Ranking
公开(公告)号：US07363224B2
公开(公告)日：2008-04-22
申请号：US10748404
申请日：2003-12-30
Applicant: Xuendong D. Huang , Alejandro Acero , Kuansan Wang , Milind Mahajan
Inventor： Xuendong D. Huang , Alejandro Acero , Kuansan Wang , Milind Mahajan
IPC: G10L15/04
CPC classification number: G06F3/0237 , G06F3/16 , G10L15/1815 , G10L15/22 , G10L2015/228
Abstract: In a method of entering text into a device a first character input is provided that is indicative of a first character of a text entry. Next, a vocalization of the text entry is captured. A probable word candidate is then identified for a first word of the vocalization based upon the first character input and an analysis of the vocalization. Finally, the probable word candidate is displayed for a user.
Abstract translation: 在将文本输入到设备中的方法中，提供指示文本输入的第一个字符的第一个字符输入。 接下来，捕获文本条目的发声。 然后基于第一个字符输入和发声分析，识别发音的第一个单词的可能的词候选。 最后，为用户显示可能的候选词。
-
公开(公告)号：US07117153B2
公开(公告)日：2006-10-03
申请号：US10365850
申请日：2003-02-13
Applicant: Milind Mahajan , Yonggang Deng , Alejandro Acero , Asela J. R. Gunawardana , Ciprian Chelba
Inventor： Milind Mahajan , Yonggang Deng , Alejandro Acero , Asela J. R. Gunawardana , Ciprian Chelba
CPC classification number: G10L15/197 , G10L15/183
Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.
Abstract translation: 对语音识别系统进行建模的方法包括对从训练文本产生的语音信号进行解码以产生预测语音单元的序列。 训练文本包括与预测语音单元的序列一起使用以形成混淆模型的实际语音单元的序列。 在另外的实施例中，混淆模型用于对文本进行解码以识别如果语音识别系统基于文本解码的语音将会预期的错误率。
-
公开(公告)号：US09369562B2
公开(公告)日：2016-06-14
申请号：US13398351
申请日：2012-02-16
Applicant: Milind Mahajan , Amit Kumar
Inventor： Milind Mahajan , Amit Kumar
CPC classification number: H04M1/72525 , H04M1/56 , H04M1/57 , H04M1/72569 , H04M2250/60
Abstract: Computer-readable media, computer systems, and computing methods are provided for discovering applications using phone-number information. Initially, an application uploaded to an application marketplace is targeted. Phone numbers associated with the targeted application are discovered by identifying attributes of the targeted application from metadata associated therewith in the application marketplace, and identifying the phone numbers that reach at least one business affiliated with the targeted application or are relevant to the identified attributes of the targeted application. The associated phone numbers are mapped to the targeted application and maintained within an application manifest. Upon detecting user-initiated call-based operation(s) at a client device, the phone number(s) involved in the call-based operation(s) are compared against the application manifest to determine relevant applications. The relevant applications are distributed to the client device for presentation within a phone-number context, such as placing an outgoing call, receiving an incoming call, or reviewing a call-history log.
Abstract translation: 提供计算机可读介质，计算机系统和计算方法，用于使用电话号码信息来发现应用。 最初，上传到应用程序市场的应用程序是针对性的。 与目标应用相关联的电话号码通过从应用市场中与其相关的元数据识别目标应用的属性来发现，并且识别到达至少一个与目标应用有关的业务的电话号码，或者与所标识的属性相关 有针对性的应用。 相关联的电话号码映射到目标应用程序并保存在应用程序清单中。 在客户端设备检测用户发起的基于呼叫的操作时，将基于呼叫的操作中涉及的电话号码与应用程序清单进行比较以确定相关的应用程序。 将相关应用程序分发到客户端设备，以便在电话号码上下文中进行呈现，例如放置呼出呼叫，接收来电或查看呼叫历史日志。
-
公开(公告)号：US20130342841A1
公开(公告)日：2013-12-26
申请号：US13531918
申请日：2012-06-25
Applicant: MILIND MAHAJAN , Bruce K. Winker
Inventor： MILIND MAHAJAN , Bruce K. Winker
IPC: G01J4/00
Abstract: An orientation tracking system for a moving platform includes a transmitter which generates an beam having a known polarization with respect to a predefined coordinate system. The moving platform includes an ellipsometric detector capable of detecting the polarized beam when within the line-of-sight of the transmitter, and measuring its polarization state. The polarization state indicates the rotational orientation of the moving platform with respect to the predefined coordinate system. The beam could also be used to convey guidance commands to the platform.
Abstract translation: 用于移动平台的定向跟踪系统包括发射器，其产生相对于预定坐标系具有已知极化的光束。 移动平台包括能够在发射机的视线范围内检测偏振光束并测量其偏振状态的椭圆检测器。 偏振状态表示移动平台相对于预定坐标系的旋转取向。 梁还可用于将指导命令传达到平台。
-
公开(公告)号：US20120323898A1
公开(公告)日：2012-12-20
申请号：US13161792
申请日：2011-06-16
Applicant: AMIT KUMAR , MILIND MAHAJAN
Inventor： AMIT KUMAR , MILIND MAHAJAN
IPC: G06F17/30
CPC classification number: G06F17/3053 , G06F8/61 , G06F17/30554 , G06F17/30867 , G06F17/30876 , G06F17/30899 , G06Q30/0251 , G06Q30/0277
Abstract: Applications are surfaced to a user during browsing without requiring a specific search by the user. The applications can be selected for surfacing to the user based on the network address entered into the address bar of a browser, the content of the page corresponding to the network address, or a combination thereof. Applications may be selected for surfacing based on a partial address entered into the address bar and/or based on the web page content that is currently visible in the browser display.
Abstract translation: 应用程序在浏览时显示给用户，而不需要用户的特定搜索。 可以基于输入到浏览器的地址栏的网络地址，与网络地址相对应的页面的内容或其组合来选择用于表示用户的应用程序。 可以基于输入到地址栏的部分地址和/或基于当前在浏览器显示中可见的网页内容来选择应用程序来进行表面处理。
-
-
-
-
-
-
-
-
-
Search Results
50
records
(took 0.018 seconds)
