Learning retrieval functions incorporating query differentiation for information retrieval
    1.
    发明授权
    Learning retrieval functions incorporating query differentiation for information retrieval 有权
    学习检索功能,包含信息检索的查询差异

    公开(公告)号:US08589371B2

    公开(公告)日:2013-11-19

    申请号:US13538237

    申请日:2012-06-29

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/3069

    摘要: The system and method of the present invention allows for the determination of the relevance of a content item to a query through the use of a machine learned relevance function that incorporate query differentiation. A method for selecting a relevance function to determine a relevance of a query-content item pair comprises generating a training set comprising one or more content item-query pairs. Content item-query pairs in the training set are collectively used to determine the relevance function by minimizing a loss function according to a relevance score adjustment function that accounts for query differentiation. The monotocity of relevance score adjustment function allows the trained relevance function to be directly applied to new queries.

    摘要翻译: 本发明的系统和方法允许通过使用结合查询区分的机器学习的相关性功能来确定内容项与查询的相关性。 用于选择相关函数以确定查询内容项对的相关性的方法包括生成包括一个或多个内容项查询对的训练集。 训练集中的内容项 - 查询对被统一用于根据考虑到查询区分的相关性分数调整功能来最小化损失函数来确定相关性函数。 相关性分数调整功能的一致性允许训练有素的相关函数直接应用于新查询。

    Learning retrieval functions incorporating query differentiation for information retrieval
    2.
    发明授权
    Learning retrieval functions incorporating query differentiation for information retrieval 有权
    学习检索功能,包含信息检索的查询差异

    公开(公告)号:US08250061B2

    公开(公告)日:2012-08-21

    申请号:US11343910

    申请日:2006-01-30

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/3069

    摘要: The system and method of the present invention allows for the determination of the relevance of a content item to a query through the use of a machine learned relevance function that incorporate query differentiation. A method for selecting a relevance function to determine a relevance of a query-content item pair comprises generating a training set comprising one or more content item-query pairs. Content item-query pairs in the training set are collectively used to determine the relevance function by minimizing a loss function according to a relevance score adjustment function that accounts for query differentiation. The monotocity of relevance score adjustment function allows the trained relevance function to be directly applied to new queries.

    摘要翻译: 本发明的系统和方法允许通过使用结合查询区分的机器学习的相关性功能来确定内容项与查询的相关性。 用于选择相关函数以确定查询内容项对的相关性的方法包括生成包括一个或多个内容项查询对的训练集。 训练集中的内容项 - 查询对被统一用于根据考虑到查询区分的相关性分数调整功能来最小化损失函数来确定相关性函数。 相关性分数调整功能的一致性允许训练有素的相关函数直接应用于新查询。

    Learning ranking functions incorporating boosted ranking in a regression framework for information retrieval and ranking
    3.
    发明授权
    Learning ranking functions incorporating boosted ranking in a regression framework for information retrieval and ranking 有权
    学习排名功能在信息检索和排名的回归框架中加入了排名

    公开(公告)号:US08051072B2

    公开(公告)日:2011-11-01

    申请号:US12060179

    申请日:2008-03-31

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30864 G06F17/30702

    摘要: Embodiments of the present invention provide for methods, systems and computer program products for learning ranking functions to determine the ranking of one or more content items that are responsive to a query. The present invention includes generating one or more training sets comprising one or more content item-query pairs, determining preference data for the one or more query-content item pairs of the one or more training sets and determining labeled data for the one or more query-content item pairs of the one or more training sets. A ranking function is determined based upon the preference data and the labeled data for the one or more content-item query pairs of the one or more training sets. The ranking function is then stored for application to query-content item pairs not contained in the one or more training sets.

    摘要翻译: 本发明的实施例提供了用于学习排名功能以确定响应于查询的一个或多个内容项目的排名的方法,系统和计算机程序产品。 本发明包括生成包括一个或多个内容项查询对的一个或多个训练集合,确定所述一个或多个训练集合的一个或多个查询内容项目对的偏好数据,并确定所述一个或多个查询对象的标记数据 - 一个或多个训练集的内容项对。 基于偏好数据和一个或多个训练集合的一个或多个内容项查询对的标记数据来确定排序功能。 然后将排序函数存储以用于不包含在一个或多个训练集中的查询内容项对。

    SYSTEM AND METHOD FOR BLENDING USER RANKINGS FOR AN OUTPUT DISPLAY
    4.
    发明申请
    SYSTEM AND METHOD FOR BLENDING USER RANKINGS FOR AN OUTPUT DISPLAY 审中-公开
    用于混合输出显示器的用户排名的系统和方法

    公开(公告)号:US20100082609A1

    公开(公告)日:2010-04-01

    申请号:US12242301

    申请日:2008-09-30

    IPC分类号: G06F17/30

    CPC分类号: G06Q30/02 G06F16/951

    摘要: A method and system for blending ranking for an output display includes receiving a first list of content items having a first ranking determined by first ranking parameters, the first ranking providing for a sequential ordering of the content items of the first list. A second list of content items having a second ranking determined by second ranking parameters are received, the first ranking is incompatible with the second ranking because ranking parameters are different. The first list of content items is transformed to a modified first list that maintains the order of the content items and makes the first ranking of the modified first list compatible with the second ranking of the second list. The second list and the modified first list are merged to generate a blended list for an output display utilizing the blended list.

    摘要翻译: 一种用于混合输出显示的排名的方法和系统包括:接收具有由第一排名参数确定的第一排名的内容项目的第一列表,第一排名提供第一列表的内容项目的顺序排序。 接收具有由第二排名参数确定的第二排名的内容项目的第二列表,因为排名参数不同,所以第一排名与第二排名不兼容。 内容项目的第一列表被转换为维护内容项目的顺序的修改的第一列表,并且使修改的第一列表的第一排名与第二列表的第二排名兼容。 第二列表和修改的第一列表被合并以利用混合列表生成用于输出显示的混合列表。

    Method and appartus for using B measures to learn balanced relevance functions from expert and user judgments
    6.
    发明授权
    Method and appartus for using B measures to learn balanced relevance functions from expert and user judgments 有权
    使用B措施从专家和用户判断中学习平衡相关功能的方法和应用

    公开(公告)号:US07685078B2

    公开(公告)日:2010-03-23

    申请号:US11755134

    申请日:2007-05-30

    IPC分类号: G06N5/00

    CPC分类号: G06F17/30864

    摘要: The present invention relates to systems and methods for determining a content item relevance function. The method comprises collecting user preference data at a search provider for storage in a user preference data store and collecting expert-judgment data at the search provider for storage in an expert sample data store. A modeling module trains a base model through the use of the expert-judgment data and tunes the base model through the use of the user preference data to learn a set of one or more tuned models. A measure (B measure) is designed to evaluate the balanced performance of tuned model over expert judgment and user preference. The modeling module generates or selects the content item relevance function from the tuned models with B measure as the selection criterion.

    摘要翻译: 本发明涉及用于确定内容项相关性功能的系统和方法。 该方法包括在搜索提供者处收集用户偏好数据以存储在用户偏好数据存储中,并在搜索提供商处收集专家判断数据以存储在专家样本数据存储中。 建模模块通过使用专家判断数据来训练基本模型,并通过使用用户偏好数据来调整基本模型,以学习一组或多个调谐模型。 测量(B测量)旨在评估调谐模型与专家判断和用户偏好的平衡性能。 建模模块从具有B测量的调谐模型生成或选择内容项相关性函数作为选择标准。

    ASSOCIATING DOCUMENTS WITH CLASSIFICATIONS AND RANKING DOCUMENTS BASED ON CLASSIFICATION WEIGHTS
    7.
    发明申请
    ASSOCIATING DOCUMENTS WITH CLASSIFICATIONS AND RANKING DOCUMENTS BASED ON CLASSIFICATION WEIGHTS 有权
    基于分类权重的分类文件和排序文件相关文件

    公开(公告)号:US20090187566A1

    公开(公告)日:2009-07-23

    申请号:US12416896

    申请日:2009-04-01

    IPC分类号: G06F17/30

    摘要: A method and apparatus for associating documents with classification values and ranking documents based on classification weights is provided. It is determined if a document is associated a classification. If the document is associated with a classification, then it is determined if a classification value, which is associated with the document, is associated with a weight. If the classification value is associated with a weight, then a rank of the document is adjusted based on the weight that is associated with the classification value.

    摘要翻译: 提供了一种基于分类权重将文档与分类值和排序文档相关联的方法和装置。 确定文档是否与分类相关联。 如果文档与分类相关联,则确定与文档相关联的分类值是否与权重相关联。 如果分类值与权重相关联,则基于与分类值相关联的权重来调整文档的等级。

    Learning retrieval functions incorporating query differentiation for information retrieval
    8.
    发明申请
    Learning retrieval functions incorporating query differentiation for information retrieval 有权
    学习检索功能,包含信息检索的查询差异

    公开(公告)号:US20070179949A1

    公开(公告)日:2007-08-02

    申请号:US11343910

    申请日:2006-01-30

    IPC分类号: G06F17/30

    CPC分类号: G06F17/3069

    摘要: The system and method of the present invention allows for the determination of the relevance of a content item to a query through the use of a machine learned relevance function that incorporate query differentiation. A method for selecting a relevance function to determine a relevance of a query-content item pair comprises generating a training set comprising one or more content item-query pairs. Content item-query pairs in the training set are collectively used to determine the relevance function by minimizing a loss function according to a relevance score adjustment function that accounts for query differentiation. The monotocity of relevance score adjustment function allows the trained relevance function to be directly applied to new queries.

    摘要翻译: 本发明的系统和方法允许通过使用结合查询区分的机器学习的相关性功能来确定内容项与查询的相关性。 用于选择相关函数以确定查询内容项对的相关性的方法包括生成包括一个或多个内容项查询对的训练集。 训练集中的内容项 - 查询对被统一用于根据考虑到查询区分的相关性分数调整功能来最小化损失函数来确定相关性函数。 相关性分数调整功能的一致性允许训练有素的相关函数直接应用于新查询。

    Learning ranking functions incorporating isotonic regression for information retrieval and ranking
    10.
    发明授权
    Learning ranking functions incorporating isotonic regression for information retrieval and ranking 有权
    学习排名功能包括等渗回归信息检索和排名

    公开(公告)号:US07849076B2

    公开(公告)日:2010-12-07

    申请号:US12060195

    申请日:2008-03-31

    IPC分类号: G06F17/30 G06F7/00

    CPC分类号: G06F17/30675

    摘要: Embodiments of the present invention provide for methods, systems and computer program products for learning ranking functions to determine the ranking of one or more content items that are responsive to a query. The present invention includes generating one or more training sets comprising one or more content item-query pairs and determining one or more contradicting pairs in a given training sets. An optimization function to minimize the number of contradicting pairs in the training set is formulated, and modified by incorporating a grade difference between one or more content items corresponding to the query in the training set and applied to each query in the training set. A ranking function is determined based on the application of regression trees on the queries of the training set minimized by the optimization function and stored for application to content item-query pairs not contained in the one or more training sets.

    摘要翻译: 本发明的实施例提供了用于学习排名功能以确定响应于查询的一个或多个内容项目的排名的方法,系统和计算机程序产品。 本发明包括生成包括一个或多个内容项查询对并且确定给定训练集中的一个或多个矛盾对的一个或多个训练集。 制定了最小化训练集中的矛盾对数量的优化函数,并通过在训练集合中对应于查询的一个或多个内容项之间并入应用于训练集中的每个查询的等级差来进行修改。 基于对优化函数最小化的训练集的查询的回归树的应用来确定排序函数,并将其存储用于不包含在一个或多个训练集中的内容项查询对。