会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 3. 发明申请
    • GENERATING A LIVE CHAT SESSION IN RESPONSE TO SELECTION OF A CONTEXTUAL SHORTCUT
    • 产生一个响亮的选择一个上下文的短片
    • US20100205544A1
    • 2010-08-12
    • US12368937
    • 2009-02-10
    • Vadim Von BrzeskiReiner Kraft
    • Vadim Von BrzeskiReiner Kraft
    • G06F3/00
    • H04L12/66
    • Embodiments are directed to identifying entities in content, highlighting the identified entities, and displaying an interactive chat session based on a selected entity. The interactive chat session and the content may be displayed in the same browser window. The interactive chat session may be overlaid on top of the content, inserted inline into the content, or otherwise embedded within the content. The content and the interactive chat session may both remain active in the browser window, enabling a user to conveniently read and chat about the content. The topic of the interactive chat session may be automatically selected from a hierarchical taxonomy of chat session topics, or the user may select the topic from one or more provided taxonomies.
    • 实施例旨在识别内容中的实体,突出显示所识别的实体,以及基于所选择的实体来显示交互式聊天会话。 交互式聊天会话和内容可以显示在同一浏览器窗口中。 交互式聊天会话可以覆盖在内容之上,插入到内容中或嵌入在内容中。 内容和交互式聊天会话可以在浏览器窗口中保持活动状态,使用户能够方便地阅读和聊天内容。 可以从聊天会话主题的分层分类中自动选择交互式聊天会话的主题,或者用户可以从一个或多个所提供的分类中选择主题。
    • 5. 发明申请
    • CONTEXTUAL RANKING OF KEYWORDS USING CLICK DATA
    • 使用点击数据的关键词的上下文排名
    • US20090265338A1
    • 2009-10-22
    • US12132071
    • 2008-06-03
    • Reiner KraftUtku IrmakVadim Von Brzeski
    • Reiner KraftUtku IrmakVadim Von Brzeski
    • G06F7/06
    • G06F17/30864
    • Techniques are provided for ranking the entities that are identified in a document based on an estimated likelihood that a user will actually make use of the annotations. According to one disclosed approach, usage data that indicates how users interact with annotations contained in documents presented to the users is collected. Based on the usage data, weights are generated for features of a feature vector. The weights are then used to modify feature scores of entities, and the modified feature scores are used to determine how to annotate documents. Specifically, a set of entities are identified within a document. A ranking for the identified entities is determined based, at least in part, on (a) feature vector scores for each of the identified entities, and (b) the weights generated for the features of the feature vector. The document is then annotated based, at least in part, on the ranking.
    • 提供技术用于基于用户实际使用注释的估计可能性来对文档中标识的实体进行排名。 根据一种公开的方法,收集指示用户如何与包含在呈现给用户的文档中的注释交互的使用数据。 基于使用数据,生成特征向量的特征权重。 然后使用权重来修改实体的特征分数,并且修改的特征得分用于确定如何注释文档。 具体来说,在文档内识别一组实体。 至少部分地基于(a)每个识别的实体的特征向量得分确定所识别的实体的排名,以及(b)为特征向量的特征生成的权重。 该文档至少部分地基于排名而进行注释。
    • 8. 发明授权
    • Contextual ranking of keywords using click data
    • 使用点击数据的关键字的上下文排名
    • US08051080B2
    • 2011-11-01
    • US12132071
    • 2008-06-03
    • Reiner KraftUtku IrmakVadim Von Brzeski
    • Reiner KraftUtku IrmakVadim Von Brzeski
    • G06F7/00G06F17/30
    • G06F17/30864
    • Techniques are provided for ranking the entities that are identified in a document based on an estimated likelihood that a user will actually make use of the annotations. According to one disclosed approach, usage data that indicates how users interact with annotations contained in documents presented to the users is collected. Based on the usage data, weights are generated for features of a feature vector. The weights are then used to modify feature scores of entities, and the modified feature scores are used to determine how to annotate documents. Specifically, a set of entities are identified within a document. A ranking for the identified entities is determined based, at least in part, on (a) feature vector scores for each of the identified entities, and (b) the weights generated for the features of the feature vector. The document is then annotated based, at least in part, on the ranking.
    • 提供技术用于基于用户实际使用注释的估计可能性来对文档中标识的实体进行排名。 根据一种公开的方法,收集指示用户如何与包含在呈现给用户的文档中的注释交互的使用数据。 基于使用数据,生成特征向量的特征权重。 然后使用权重来修改实体的特征分数,并且修改的特征得分用于确定如何注释文档。 具体来说,在文档内识别一组实体。 至少部分地基于(a)每个识别的实体的特征向量得分确定所识别的实体的排名,以及(b)为特征向量的特征生成的权重。 该文档至少部分地基于排名而进行注释。