利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

212 条记录 (耗时 0.049 秒)

    Extracting classifying data in music from an audio bitstream
    1.
    发明授权
    Extracting classifying data in music from an audio bitstream 失效
    从音频比特流中提取音乐中的分类数据

    公开(公告)号：US07295977B2

    公开(公告)日：2007-11-13

    申请号：US09939954

    申请日：2001-08-27

    申请人： Brian Whitman ,  Gary W. Flake ,  Stephen R. Lawrence

    发明人： Brian Whitman ,  Gary W. Flake ,  Stephen R. Lawrence

    IPC分类号： G10L15/16 ,  G10H7/10

    CPC分类号： G10L17/02 ,  G10L17/26 ,  G10L25/30

    摘要： The method of the present invention utilizes machine-learning techniques, particularly Support Vector Machines in combination with a neural network, to process a unique machine-learning enabled representation of the audio bitstream. Using this method, a classifying machine is able to autonomously detect characteristics of a piece of music, such as the artist or genre, and classify it accordingly. The method includes transforming digital time-domain representation of music into a frequency-domain representation, then dividing that frequency data into time slices, and compressing it into frequency bands to form multiple learning representations of each song. The learning representations that result are processed by a group of Support Vector Machines, then by a neural network, both previously trained to distinguish among a given set of characteristics, to determine the classification.

    摘要翻译： 本发明的方法利用机器学习技术，特别是与神经网络相结合的支持向量机来处理独特的机器学习使能的音频比特流表示。 使用这种方法，分类机能够自主地检测诸如艺术家或流派之类的音乐的特征，并相应地对其进行分类。 该方法包括将音乐的数字时域表示变换为频域表示，然后将该频率数据划分为时间片，并将其压缩为频带，以形成每首歌曲的多个学习表示。 结果的学习表示由一组支持向量机处理，然后由神经网络处理，两者都被训练以区分给定的一组特征，以确定分类。

    Machine assisted query formulation
    4.
    发明授权
    Machine assisted query formulation 有权
    机器辅助查询配方

    公开(公告)号：US08812534B2

    公开(公告)日：2014-08-19

    申请号：US13481168

    申请日：2012-05-25

    申请人： John C. Platt ,  Oliver Hurst-Hiller ,  Trenholme J. Griffin ,  Anoop Gupta ,  Gary W. Flake ,  Ramez Naam ,  Joshua T. Goodman

    发明人： John C. Platt ,  Oliver Hurst-Hiller ,  Trenholme J. Griffin ,  Anoop Gupta ,  Gary W. Flake ,  Ramez Naam ,  Joshua T. Goodman

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30389

    摘要： Architecture for completing search queries by using artificial intelligence based schemes to infer search intentions of users. Partial queries are completed dynamically in real time. Additionally, search aliasing can also be employed. Custom tuning can be performed based on at least query inputs in the form of text, graffiti, images, handwriting, voice, audio, and video signals. Natural language processing occurs, along with handwriting recognition and slang recognition. The system includes a classifier that receives a partial query as input, accesses a query database based on contents of the query input, and infers an intended search goal from query information stored on the query database. A query formulation engine receives search information associated with the intended search goal and generates a completed formal query for execution.

    摘要翻译： 通过使用基于人工智能的方案来推断用户的搜索意图来完成搜索查询的架构。 部分查询是实时动态完成的。 此外，还可以使用搜索别名。 可以至少基于文本，涂鸦，图像，手写，语音，音频和视频信号的查询输入进行定制调整。 自然语言处理发生，手写识别和俚语识别。 该系统包括接收部分查询作为输入的分类器，基于查询输入的内容访问查询数据库，并从存储在查询数据库中的查询信息推断预期的搜索目标。 查询制定引擎接收与预期搜索目标相关联的搜索信息，并生成完成的正式查询以供执行。

    Serialization of run-time state
    9.
    发明授权
    Serialization of run-time state 有权
    运行时状态的序列化

    公开(公告)号：US08595356B2

    公开(公告)日：2013-11-26

    申请号：US11536562

    申请日：2006-09-28

    申请人： Debi P. Mishra ,  Amit Mital ,  Gary W. Flake ,  Matthew B. MacLaurin ,  Alexander G. Gounares ,  Ira L. Snyder, Jr. ,  Henricus Johannes Maria Meijer

    发明人： Debi P. Mishra ,  Amit Mital ,  Gary W. Flake ,  Matthew B. MacLaurin ,  Alexander G. Gounares ,  Ira L. Snyder, Jr. ,  Henricus Johannes Maria Meijer

    IPC分类号： G06F15/173

    CPC分类号： H04L41/50 ,  G06F9/4856

    摘要： The claimed subject matter provides a system and/or a method that facilitates re-locating a web application associated with a network service utilizing a portion of serialized data. The network service can be any collection of resources that are maintained by a party (e.g., third-party, off-site, etc.) and accessible by an identified user over a network (e.g., WAN, Internet, etc.). An interface component can receive a portion of serialized data with transparent structure related to an application specification. A hydrate component can create a web application independent of a network service based at least in part upon the serialized data, the web application has state within the network service.

    摘要翻译： 所要求保护的主题提供了利用序列化数据的一部分来促进与网络服务相关联的web应用重新定位的系统和/或方法。 网络服务可以是由一方维护的任何资源集合（例如，第三方，非现场等），并且可以由被识别的用户通过网络（例如，WAN，因特网等）访问。 接口组件可以接收与应用规范相关的透明结构的序列化数据的一部分。 至少部分地基于序列化数据，水合物组分可以创建独立于网络服务的web应用，web应用具有网络服务内的状态。

    EXTRACTING A PORTION OF A DOCUMENT, SUCH AS A WEB PAGE
    10.
    发明申请
    EXTRACTING A PORTION OF A DOCUMENT, SUCH AS A WEB PAGE 有权
    提取文档的一部分，如网页

    公开(公告)号：US20130290828A1

    公开(公告)日：2013-10-31

    申请号：US13460632

    申请日：2012-04-30

    申请人： Gary W. Flake ,  Thomas J. Montgomery ,  Gregory T. Pascale ,  Kenneth J. Perkins ,  Mark R. Dawson

    发明人： Gary W. Flake ,  Thomas J. Montgomery ,  Gregory T. Pascale ,  Kenneth J. Perkins ,  Mark R. Dawson

    IPC分类号： G06F17/00

    CPC分类号： G06F17/30047 ,  G06F17/30277 ,  G06F17/30864

    摘要： A facility for extracting visual contents of a page is described. The facility renders a page including visual contents, the rendered page including an extraction control. In response to user input activating the extraction control, the facility (1) selects a proper subset of the visual contents of the page that are specified by a publisher on the page for extraction using the extraction control, and (2) transmits a representation of the selected subset of visual contents for storage independent of the page.

    摘要翻译： 描述用于提取页面的视觉内容的设备。 该设施呈现包括视觉内容的页面，所渲染的页面包括提取控件。 响应于激活提取控制的用户输入，设施（1）使用提取控制来选择由页面上的发布者指定的页面的可视内容的适当子集，并且（2）发送表示 所选择的视觉内容子集独立于页面进行存储。