-
公开(公告)号：US08560293B2
公开(公告)日：2013-10-15
申请号：US13569728
申请日：2012-08-08
申请人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
发明人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
IPC分类号： G06F17/50
CPC分类号： G06F17/3089
摘要： Content items are selected to be displayed on a portal page in such a way as to maximize a performance metric such as click-through rate. Problems relating to content selection are addressed, such as changing content pool, variable performance metric, and delay in receiving feedback on an item once the item has been displayed to a user. An adaptation of priority-based schemes for the multi-armed bandit problem, are used to project future trends of data. The adaptation introduces experiments concerning a future time period into the calculation, which increases the set of data on which to solve the multi-armed bandit problem. Also, a Bayesian explore/exploit method is formulated as an optimization problem that addresses all of the issues of content item selection for a portal page. This optimization problem is modified by Lagrange relaxation and normal approximation, which allow computation of the optimization problem in real time.
摘要翻译： 内容项被选择以在门户页面上显示，以便最大化诸如点击率的性能度量。 解决与内容选择相关的问题，例如改变内容池，可变性能度量，以及一旦项目已被显示给用户，对项目的反馈的延迟。 用于多武装强盗问题的基于优先权的方案的适应性用于预测未来数据趋势。 适应性将关于未来时间段的实验引入计算，这增加了解决多武装强盗问题的数据集。 此外，贝叶斯探索/漏洞利用方法被制定为一个优化问题，解决门户页面的内容项目选择的所有问题。 该优化问题由拉格朗日弛豫和正态逼近法进行修正，可实时计算优化问题。
-
公开(公告)号：US08244517B2
公开(公告)日：2012-08-14
申请号：US12267534
申请日：2008-11-07
申请人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
发明人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
IPC分类号： G06F9/45
CPC分类号： G06F17/3089
摘要： Content items are selected to be displayed on a portal page in such a way as to maximize a performance metric such as click-through rate. Problems relating to content selection are addressed, such as changing content pool, variable performance metric, and delay in receiving feedback on an item once the item has been displayed to a user. An adaptation of priority-based schemes for the multi-armed bandit problem are used to project future trends of data. The adaptation introduces experiments concerning a future time period into the calculation, which increases the set of data on which to solve the multi-armed bandit problem. Also, a Bayesian explore/exploit method is formulated as an optimization problem that addresses all of the issues of content item selection for a portal page. This optimization problem is modified by Lagrange relaxation and normal approximation, which allow computation of the optimization problem in real time.
摘要翻译： 内容项被选择以在门户页面上显示，以便最大化诸如点击率的性能度量。 解决与内容选择相关的问题，例如改变内容池，可变性能度量，以及一旦项目已被显示给用户，对项目的反馈的延迟。 用于多武装强盗问题的基于优先权的方案的改编用于预测未来数据趋势。 适应性将关于未来时间段的实验引入计算，这增加了解决多武装强盗问题的数据集。 此外，贝叶斯探索/漏洞利用方法被制定为一个优化问题，解决门户页面的内容项目选择的所有问题。 该优化问题由拉格朗日弛豫和正态逼近法进行修正，可实时计算优化问题。
-
公开(公告)号：US20100121624A1
公开(公告)日：2010-05-13
申请号：US12267534
申请日：2008-11-07
申请人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
发明人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
IPC分类号： G06G7/48
CPC分类号： G06F17/3089
摘要： Content items are selected to be displayed on a portal page in such a way as to maximize a performance metric such as click-through rate. Problems relating to content selection are addressed, such as changing content pool, variable performance metric, and delay in receiving feedback on an item once the item has been displayed to a user. An adaptation of priority-based schemes for the multi-armed bandit problem are used to project future trends of data. The adaptation introduces experiments concerning a future time period into the calculation, which increases the set of data on which to solve the multi-armed bandit problem. Also, a Bayesian explore/exploit method is formulated as an optimization problem that addresses all of the issues of content item selection for a portal page. This optimization problem is modified by Lagrange relaxation and normal approximation, which allow computation of the optimization problem in real time.
-
14.发明申请公开(公告)号：US20110087673A1
公开(公告)日：2011-04-14
申请号：US12577045
申请日：2009-10-09
申请人： Jiang Chen , Wei Chu , Zhenzhen Kou , Zhaohui Zheng
发明人： Jiang Chen , Wei Chu , Zhenzhen Kou , Zhaohui Zheng
IPC分类号： G06F17/30
CPC分类号： G06F17/30864
摘要： Methods and systems are disclosed that relate to ranking functions for multiple different domains. By way of example but not limitation, ranking functions for multiple different domains may be trained based on inter-domain loss, and such ranking functions may be used to rank search results from multiple different domains so that they may be blended without normalizing relevancy scores.
摘要翻译： 公开了与多个不同域的排序功能相关的方法和系统。 作为示例而非限制，可以基于域间丢失来训练针对多个不同域的排序功能，并且可以使用这样的排名功能来对来自多个不同域的搜索结果进行排名，使得它们可以在不规范相关性分数的情况下进行混合。
-
公开(公告)号：US20100241597A1
公开(公告)日：2010-09-23
申请号：US12407785
申请日：2009-03-19
申请人： Bee-Chung Chen , Pradheep Elango , Deepak K. Agarwal , Wei Chu
发明人： Bee-Chung Chen , Pradheep Elango , Deepak K. Agarwal , Wei Chu
CPC分类号： G06Q30/02 , G06F16/958
摘要： Techniques are presented for estimating the current popularity of web content. Click and view data for articles are used to estimate popularity of the articles by analyzing click-through rates. Click-though rates are estimated such that a current click-through rate reflects fluctuations in popularity of articles through time.
摘要翻译： 介绍了估计网页内容当前流行度的技术。 点击查看文章数据用于通过分析点击率来估算文章的受欢迎程度。 点击率估算，使得当前的点击率反映了文章随着时间的流行度的波动。
-
公开(公告)号：US20130111005A1
公开(公告)日：2013-05-02
申请号：US13282285
申请日：2011-10-26
申请人： Wei Chu , Martin Zinkevich , Lihong Li , Achint Oommen Thomas , Belle Tseng
发明人： Wei Chu , Martin Zinkevich , Lihong Li , Achint Oommen Thomas , Belle Tseng
摘要： Software for online active learning receives content posted to an online stream at a website. The software converts the content into an elemental representation and inputs the elemental representation into a probit model to obtain a predictive probability that the content is abusive. The software also calculates an importance weight based on the elemental representation. And the software updates the probit model using the content, the importance weight, and an acquired label if a condition is met. The condition depends on an instrumental distribution. The software removes the content from the online stream if a condition is met. The condition depends on the predictive probability, if an acquired label is unavailable.
摘要翻译： 用于在线主动学习的软件会收到发布到网站上的在线流的内容。 软件将内容转换为元素表示，并将元素表示输入到概率模型中，以获得内容滥用的预测概率。 该软件还基于元素表示计算重要性权重。 并且如果满足条件，则软件使用内容，重要性权重以及获取的标签来更新概率模型。 条件取决于工具分配。 如果满足条件，该软件将从在线流中删除内容。 如果获取的标签不可用，则条件取决于预测概率。
-
公开(公告)号：US20120303349A1
公开(公告)日：2012-11-29
申请号：US13569728
申请日：2012-08-08
申请人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
发明人： H. Scott Roy , Raghunath Ramakrishnan , Pradheep Elango , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
IPC分类号： G06G7/62
CPC分类号： G06F17/3089
摘要： Content items are selected to be displayed on a portal page in such a way as to maximize a performance metric such as click-through rate. Problems relating to content selection are addressed, such as changing content pool, variable performance metric, and delay in receiving feedback on an item once the item has been displayed to a user. An adaptation of priority-based schemes for the multi-armed bandit problem, are used to project future trends of data. The adaptation introduces experiments concerning a future time period into the calculation, which increases the set of data on which to solve the multi-armed bandit problem. Also, a Bayesian explore/exploit method is formulated as an optimization problem that addresses all of the issues of content item selection for a portal page. This optimization problem is modified by Lagrange relaxation and normal approximation, which allow computation of the optimization problem in real time.
摘要翻译： 内容项被选择以在门户页面上显示，以便最大化诸如点击率的性能度量。 解决与内容选择相关的问题，例如改变内容池，可变性能度量，以及一旦项目已被显示给用户，对项目的反馈的延迟。 用于多武装强盗问题的基于优先权的方案的适应性用于预测未来数据趋势。 适应性将关于未来时间段的实验引入计算，这增加了解决多武装强盗问题的数据集。 此外，贝叶斯探索/漏洞利用方法被制定为一个优化问题，解决门户页面的内容项目选择的所有问题。 该优化问题由拉格朗日弛豫和正态逼近法进行修正，可实时计算优化问题。
-
公开(公告)号：US20100121801A1
公开(公告)日：2010-05-13
申请号：US12267538
申请日：2008-11-07
申请人： H. Scott Roy , Raghunath Ramakirshnan , Pardheep Elgano , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
发明人： H. Scott Roy , Raghunath Ramakirshnan , Pardheep Elgano , Nitin Motgi , Deepak K. Agarwal , Wei Chu , Bee-Chung Chen
摘要： Content items are selected to be displayed on a portal page in such a way as to maximize a performance metric such as click-through rate. Problems relating to content selection are addressed, such as changing content pool, variable performance metric, and delay in receiving feedback on an item once the item has been displayed to a user. An adaptation of priority-based schemes for the multi-armed bandit problem are used to project future trends of data. The adaptation introduces experiments concerning a future time period into the calculation, which increases the set of data on which to solve the multi-armed bandit problem. Also, a Bayesian explore/exploit method is formulated as an optimization problem that addresses all of the issues of content item selection for a portal page. This optimization problem is modified by Lagrange relaxation and normal approximation, which allow computation of the optimization problem in real time.
摘要翻译： 内容项被选择以在门户页面上显示，以便最大化诸如点击率的性能度量。 解决与内容选择相关的问题，例如改变内容池，可变性能度量，以及一旦项目已被显示给用户，对项目的反馈的延迟。 用于多武装强盗问题的基于优先权的方案的改编用于预测未来数据趋势。 适应性将关于未来时间段的实验引入计算，这增加了解决多武装强盗问题的数据集。 此外，贝叶斯探索/漏洞利用方法被制定为一个优化问题，解决门户页面的内容项目选择的所有问题。 该优化问题由拉格朗日弛豫和正态逼近法进行修正，可实时计算优化问题。
-
公开(公告)号：US10019518B2
公开(公告)日：2018-07-10
申请号：US12577045
申请日：2009-10-09
申请人： Jiang Chen , Wei Chu , Zhenzhen Kou , Zhaohui Zheng
发明人： Jiang Chen , Wei Chu , Zhenzhen Kou , Zhaohui Zheng
CPC分类号： G06F16/951
摘要： Methods and systems are disclosed that relate to ranking functions for multiple different domains. By way of example but not limitation, ranking functions for multiple different domains may be trained based on inter-domain loss, and such ranking functions may be used to rank search results from multiple different domains so that they may be blended without normalizing relevancy scores.
-
公开(公告)号：US09967218B2
公开(公告)日：2018-05-08
申请号：US13282285
申请日：2011-10-26
申请人： Wei Chu , Martin Zinkevich , Lihong Li , Achint Oommen Thomas , Belle Tseng
发明人： Wei Chu , Martin Zinkevich , Lihong Li , Achint Oommen Thomas , Belle Tseng
摘要： Software for online active learning receives content posted to an online stream at a website. The software converts the content into an elemental representation and inputs the elemental representation into a probit model to obtain a predictive probability that the content is abusive. The software also calculates an importance weight based on the elemental representation. And the software updates the probit model using the content, the importance weight, and an acquired label if a condition is met. The condition depends on an instrumental distribution. The software removes the content from the online stream if a condition is met. The condition depends on the predictive probability, if an acquired label is unavailable.
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.023 秒)
