利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.023 秒)

    Spam filtration utilizing sender activity data
    1.
    发明授权
    Spam filtration utilizing sender activity data 有权
    垃圾邮件过滤利用发送者活动数据

    公开(公告)号：US08224905B2

    公开(公告)日：2012-07-17

    申请号：US11567632

    申请日：2006-12-06

    申请人： Alexei V. Bocharov ,  Joshua T. Goodman

    发明人： Alexei V. Bocharov ,  Joshua T. Goodman

    IPC分类号： G06F15/16

    CPC分类号： G06Q10/107

    摘要： Spam is identified by computing sender reputation derived from historical activity data across counts for various categories. A spam filter or machine learning system can be trained utilizing pre-categorized data in conjunction with activity data associated with a sender aggregated across at least one time period. This sender activity filter can be employed alone or in combination with other filters to facilitate classification of messages as spam or non-spam.

    摘要翻译： 通过计算来自各种类别的历史活动数据的发送者信誉来识别垃圾邮件。 可以使用预先分类的数据结合在至少一个时间段内聚集的发送者的活动数据来训练垃圾邮件过滤器或机器学习系统。 该发件人活动过滤器可以单独使用或与其他过滤器组合使用，以便于将邮件分类为垃圾邮件或非垃圾邮件。

    Automatically Displaying Keywords and Other Supplemental Information
    2.
    发明申请
    Automatically Displaying Keywords and Other Supplemental Information 有权
    自动显示关键字和其他补充信息

    公开(公告)号：US20070299815A1

    公开(公告)日：2007-12-27

    申请号：US11426509

    申请日：2006-06-26

    申请人： Bryan T. Starbuck ,  Ojiakonobi Udezue ,  Stephen Lardieri ,  Manish M. Anand ,  Joshua T. Goodman ,  Alexei V. Bocharov

    发明人： Bryan T. Starbuck ,  Ojiakonobi Udezue ,  Stephen Lardieri ,  Manish M. Anand ,  Joshua T. Goodman ,  Alexei V. Bocharov

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30648 ,  Y10S707/99933

    摘要： Various embodiments can utilize information that is displayed for a user to automatically generate a list of keywords and use that list as a means to display supplemental information that is relevant to the keywords. In at least some embodiments, the displayed information is analyzed using an extraction algorithm to identify words or, more generally, character strings of interest. If these words or character strings of interest are determined to constitute relevant search terms or “keywords”, then a special user interface portion can be used to display this supplemental information along with the information that is already displayed for the user. This supplemental information can include the search terms themselves, ads that pertain to the search terms, and/or search results that have been ascertained from a web search engine.

    摘要翻译： 各种实施例可以利用为用户显示的信息来自动生成关键字列表，并使用该列表作为显示与关键字相关的补充信息的手段。 在至少一些实施例中，使用提取算法来分析所显示的信息以识别字词，或者更一般地，识别感兴趣的字符串。 如果确定这些关键词或字符串构成相关搜索词或“关键字”，则可以使用特殊用户界面部分来显示该补充信息以及已经为用户显示的信息。 该补充信息可以包括搜索词本身，与搜索词相关的广告，和/或已从网页搜索引擎确定的搜索结果。

    SPAM FILTRATION UTILIZING SENDER ACTIVITY DATA
    3.
    发明申请
    SPAM FILTRATION UTILIZING SENDER ACTIVITY DATA 有权
    垃圾邮件过滤利用SENDER活动数据

    公开(公告)号：US20080140781A1

    公开(公告)日：2008-06-12

    申请号：US11567632

    申请日：2006-12-06

    申请人： Alexei V. Bocharov ,  Joshua T. Goodman

    发明人： Alexei V. Bocharov ,  Joshua T. Goodman

    IPC分类号： G06F15/16

    CPC分类号： G06Q10/107

    摘要： Spam is identified by computing sender reputation derived from historical activity data across counts for various categories. A spam filter or machine learning system can be trained utilizing pre-categorized data in conjunction with activity data associated with a sender aggregated across at least one time period. This sender activity filter can be employed alone or in combination with other filters to facilitate classification of messages as spam or non-spam.

    摘要翻译： 通过计算来自各种类别的历史活动数据的发送者信誉来识别垃圾邮件。 可以使用预先分类的数据结合在至少一个时间段内聚集的发送者的活动数据来训练垃圾邮件过滤器或机器学习系统。 该发件人活动过滤器可以单独使用或与其他过滤器组合使用，以便于将邮件分类为垃圾邮件或非垃圾邮件。

    Detecting instabilities in time series forecasting
    6.
    发明授权
    Detecting instabilities in time series forecasting 有权
    检测时间序列预测中的不稳定性

    公开(公告)号：US07617010B2

    公开(公告)日：2009-11-10

    申请号：US11319894

    申请日：2005-12-28

    申请人： Alexei V. Bocharov ,  David M. Chickering ,  David E. Heckerman

    发明人： Alexei V. Bocharov ,  David M. Chickering ,  David E. Heckerman

    IPC分类号： G05B13/02

    CPC分类号： G06F17/30539

    摘要： A predictive model analysis system comprises a receiver component that receives predictive samples created by way of forward sampling. An analysis component analyzes a plurality of the received predictive samples and automatically determines whether a predictive model is reliable at a time range associated with the plurality of predictive sample, wherein the determination is made based at least in part upon an estimated norm associated with a forward sampling operator.

    摘要翻译： 预测模型分析系统包括接收器组件，其接收通过前向采样创建的预测样本。 分析组件分析多个接收到的预测样本，并且在与所述多个预测样本相关联的时间范围内自动确定预测模型是否可靠，其中所述确定至少部分地基于与前向相关联的估计范数 抽样运算符。

    SIMILIARITY MEASURES FOR SHORT SEGMENTS OF TEXT
    7.
    发明申请
    SIMILIARITY MEASURES FOR SHORT SEGMENTS OF TEXT 审中-公开
    短篇短文的类似措施

    公开(公告)号：US20090240498A1

    公开(公告)日：2009-09-24

    申请号：US12051183

    申请日：2008-03-19

    申请人： Wen-tau Yih ,  Alexei V. Bocharov ,  Christopher A. Meek

    发明人： Wen-tau Yih ,  Alexei V. Bocharov ,  Christopher A. Meek

    IPC分类号： G10L15/08

    CPC分类号： G06F17/2211 ,  G06F16/35

    摘要： Systems and methods to perform short text segment similarity measures. Illustratively, a short text segment similarity environment comprises a short text engine operative to process data representative of short segments of text and an instruction set comprising at least one instruction to instruct the short text engine to process data representative of short text segment inputs according to a selected short text similarity identification paradigm. Illustratively, two or more short text segments can be received as input by the short text engine and a request to identify similarities among the two or more short text segments. Responsive to the request and data input, the short text engine executes a selected similarity identification technique in accordance with the sort text similarity identification paradigm to process the received data and to identify similarities between the short text segment inputs.

    摘要翻译： 执行短文本段相似性度量的系统和方法。 示例性地，短文本段相似性环境包括用于处理代表短段文本的数据的短文本引擎和包括至少一个指令的指令集，以指示短文本引擎根据以下内容来处理代表短文本段输入的数据 选择短文本相似性识别范式。 说明性地，可以接收短文本引擎的两个或多个短文本段作为输入，以及用于标识两个或更多个短文本段之间的相似性的请求。 响应于请求和数据输入，短文本引擎根据排序文本相似性识别范例来执行所选择的相似性识别技术，以处理接收到的数据并识别短文本段输入之间的相似性。