利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

339 条记录 (耗时 0.017 秒)

    VIDEO RECOMMENDATION METHOD, SERVER AND STORAGE MEDIUM
    2.
    发明公开
    VIDEO RECOMMENDATION METHOD, SERVER AND STORAGE MEDIUM 审中-公开
    视频推荐方法，服务器和存储介质

    公开(公告)号：EP3322194A1

    公开(公告)日：2018-05-16

    申请号：EP16820705.8

    申请日：2016-05-17

    申请人： Tencent Technology (Shenzhen) Company Limited

    发明人： XIE, Yiran ,  ZHANG, Wenyu ,  XU, Zhao ,  XIANG, Yu

    IPC分类号： H04N21/466 ,  G06F17/30

    CPC分类号： H04N21/251 ,  G06F17/3082 ,  G06F17/30828 ,  G06F17/30858 ,  H04N21/25891 ,  H04N21/44204 ,  H04N21/44222 ,  H04N21/4826 ,  H04N21/6582 ,  H04N21/8405

    摘要： A video recommending method, including: obtaining videos, the video including long videos and short videos; obtaining long videos, of which video attribute values are greater than corresponding attribute thresholds, in the long videos; obtaining a watching record of a user, and obtaining similarities between the short videos and videos in the watching record, to extract a preset quantity of short videos having highest similarities; and recommending the long videos, of which video attribute values are greater than corresponding attribute thresholds, in the long videos to the user, and/or recommending the preset quantity of short videos having highest similarities to the user.

    摘要翻译： 一种视频推荐方法，包括：获取视频，所述视频包括长视频和短视频; 获取长视频中视频属性值大于对应属性阈值的长视频; 获取用户的观看记录，获取观看记录中短视频与视频的相似度，提取预设个数的相似度最高的短视频; 并向用户推荐长视频中视频属性值大于对应属性阈值的长视频和/或推荐与用户具有最高相似度的预设数量的短视频。

    TRANSMISSION AND RECEPTION OF BROADCAST CONTENTS WITH ENCRYPTED METADATA
    3.
    发明授权
    TRANSMISSION AND RECEPTION OF BROADCAST CONTENTS WITH ENCRYPTED METADATA 有权
    使用加密的元数据传输和接收广播内容

    公开(公告)号：EP2323391B1

    公开(公告)日：2018-02-28

    申请号：EP10179411.3

    申请日：2010-09-24

    申请人： Saturn Licensing LLC

    发明人： Kitazato, Naohisa

    IPC分类号： H04N7/24

    CPC分类号： H04N21/435 ,  H04N21/235 ,  H04N21/2353 ,  H04N21/2362 ,  H04N21/25875 ,  H04N21/4331 ,  H04N21/4345 ,  H04N21/4532 ,  H04N21/6125 ,  H04N21/63345 ,  H04N21/8405

    摘要： A content broadcast device for broadcasting a content, using a broadcast wave, the content broadcast device including a first supply section configured to supply service information to a content reception device through a predetermined network in response to a request from the content reception device, the service information including at least a broadcast schedule of metadata and location information that indicates where the metadata is located in the broadcast wave, and a broadcast section configured to broadcast, using the broadcast wave, the metadata, which includes at least a broadcast schedule of the content and location information that indicates where the content is located in the broadcast wave, in accordance with the broadcast schedule of the metadata, included in the service information, and broadcast, using the broadcast wave, the content in accordance with the broadcast schedule of the content, included in the metadata.

    REAL-TIME NATURAL LANGUAGE PROCESSING OF DATASTREAMS
    8.
    发明公开
    REAL-TIME NATURAL LANGUAGE PROCESSING OF DATASTREAMS 有权
    埃及大选日内瓦特在NATRRICHER SPRACHE

    公开(公告)号：EP2798529A4

    公开(公告)日：2015-11-04

    申请号：EP11878980

    申请日：2011-12-28

    申请人： INTEL CORP

    发明人： SMITH ELLIOT ,  SZILAGYI VICTOR

    IPC分类号： G06F17/20 ,  G06F3/048 ,  G06F17/30

    CPC分类号： G06F17/28 ,  G06F3/048 ,  G06F17/27 ,  G06F17/30684 ,  G06F17/30796 ,  H04N21/4126 ,  H04N21/4355 ,  H04N21/4722 ,  H04N21/8405

    摘要： Systems and methods for identifying and locating related content using natural language processing are generally disclosed herein. One embodiment includes an HTML5/JavaScript user interface configured to execute scripting commands to perform natural language processing and related content searches, and to provide a dynamic interface that enables both user-interactive and automatic methods of obtaining and displaying related content. The natural language processing may extract one or more context-sensitive key terms of text associated with a set of content. Related content may be located and identified using keyword searches that include the context-sensitive key terms. For example, text associated with video of a first content, such as text originating from subtitles or closed captioning, may be used to perform searches and locate related content such as a video of a second content, or text of a third content.

    摘要翻译： 本文通常公开了使用自然语言处理来识别和定位相关内容的系统和方法。 一个实施例包括被配置为执行脚本命令以执行自然语言处理和相关内容搜索的HTML5 / JavaScript用户界面，并且提供能够实现用户交互和自动的获取和显示相关内容的方法的动态界面。 自然语言处理可以提取与一组内容相关联的文本的一个或多个上下文相关关键词。 可以使用包括上下文相关关键词的关键词搜索来定位和标识相关内容。 例如，可以使用与第一内容的视频（例如源自字幕的文本或隐藏字幕）相关联的文本来执行搜索并定位诸如第二内容的视频或第三内容的文本的相关内容。