公开(公告)号：US08055670B2

公开(公告)日：2011-11-08

申请号：US11837920

申请日：2007-08-13

申请人： Remi Kwan

发明人： Remi Kwan

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/2264

摘要： Systems, methods and computer program products for generating substitute titles for a content item in response to a user submitted title for the content item. A method receives a user generated title and generates a plurality of candidate substitute titles. A first quality score is calculated for the user generated title and a plurality of second quality scores are generated for the plurality of candidate substitute titles. The user generated title for the content item is replaced with at least one of the plurality of candidate substitute titles on the basis of the quality scores.

摘要翻译： 系统，方法和计算机程序产品，用于为内容项目生成替代标题，以响应用户提交的用于内容项目的标题。 一种方法接收用户生成的标题并产生多个候选替代标题。 对于用户生成的标题计算第一质量分数，并为多个候选替代标题生成多个第二质量分数。 基于质量得分，用多个候选替代标题中的至少一个代替内容项目的用户生成的标题。

公开(公告)号：US07865452B2

公开(公告)日：2011-01-04

申请号：US12491133

申请日：2009-06-24

申请人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

发明人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

IPC分类号： G06F15/18

CPC分类号： G06N5/022

摘要： Techniques for automatically scoring submissions to an online question-and-answer submission system are disclosed. According to one such technique, an initial set of user submissions are scored by human operators and/or automated algorithmic mechanisms. The submissions and their accompanying scores are provided as training data to an automated machine learning mechanism. The machine learning mechanism processes the training data and automatically detects patterns in the provided submissions. The machine learning mechanism automatically correlates these patterns with the scores assigned to the submissions that match those patterns. As a result, the machine learning mechanism is trained. Thereafter, the machine learning mechanism processes unscored submissions. The machine learning mechanism automatically identifies, from among the patterns that the machine learning mechanism has already detected, one or more patterns that these submissions match. The machine learning mechanism automatically scores these submissions based on the matching patterns and the scores that are associated with those patterns.

摘要翻译： 公开了自动评分提交给在线问答提交系统的技术。 根据一种这样的技术，人类操作者和/或自动算法机制对初始的用户提交集进行评分。 提交的材料及其附带的分数作为培训数据提供给自动化机器学习机制。 机器学习机制处理训练数据并自动检测提供的提交中的模式。 机器学习机制自动将这些模式与分配给与这些模式匹配的提交的分数相关联。 因此，机器学习机制得到了培训。 此后，机器学习机制处理未评分的提交。 机器学习机制自动识别机器学习机制已经检测到的模式之一，这些提交匹配的一个或多个模式。 机器学习机制根据与这些模式相关联的匹配模式和分数自动对这些提交进行评分。

公开(公告)号：US20080154819A1

公开(公告)日：2008-06-26

申请号：US11583464

申请日：2006-10-18

申请人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

发明人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

IPC分类号： G06F15/18

CPC分类号： G06N5/022

摘要： Techniques for automatically scoring submissions to an online question-and-answer submission system are disclosed. According to one such technique, an initial set of user submissions are scored by human operators and/or automated algorithmic mechanisms. The submissions and their accompanying scores are provided as training data to an automated machine learning mechanism. The machine learning mechanism processes the training data and automatically detects patterns in the provided submissions. The machine learning mechanism automatically correlates these patterns with the scores assigned to the submissions that match those patterns. As a result, the machine learning mechanism is trained. Thereafter, the machine learning mechanism processes unscored submissions. The machine learning mechanism automatically identifies, from among the patterns that the machine learning mechanism has already detected, one or more patterns that these submissions match. The machine learning mechanism automatically scores these submissions based on the matching patterns and the scores that are associated with those patterns.

摘要翻译： 公开了自动评分提交给在线问答提交系统的技术。 根据一种这样的技术，人类操作者和/或自动算法机制对初始的用户提交集进行评分。 提交的材料及其附带的分数作为培训数据提供给自动化机器学习机制。 机器学习机制处理训练数据并自动检测提供的提交中的模式。 机器学习机制自动将这些模式与分配给与这些模式匹配的提交的分数相关联。 因此，机器学习机制得到了培训。 此后，机器学习机制处理未评分的提交。 机器学习机制自动识别机器学习机制已经检测到的模式之一，这些提交匹配的一个或多个模式。 机器学习机制根据与这些模式相关联的匹配模式和分数自动对这些提交进行评分。

公开(公告)号：US20100198816A1

公开(公告)日：2010-08-05

申请号：US12362896

申请日：2009-01-30

申请人： Remi Kwan

发明人： Remi Kwan

IPC分类号： G06F7/06 ,  G06F17/30

CPC分类号： G06F16/338

摘要： A system and method for selecting content that is representative of one or more documents is provided. Aspects provide for a fully automated machine-learned system that does not require costly manual selection and supervision of content. The system enables search engines to leverage existing news feeds and content bases to generate a more compelling presentation of search engine results.

摘要翻译： 提供了一种用于选择表示一个或多个文档的内容的系统和方法。 方面提供了一个完全自动化的机器学习系统，不需要昂贵的手动选择和监督内容。 该系统使搜索引擎能够利用现有的新闻源和内容库来产生更引人注目的搜索引擎结果。

公开(公告)号：US07571145B2

公开(公告)日：2009-08-04

申请号：US11583464

申请日：2006-10-18

申请人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

发明人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

IPC分类号： G06F15/18

CPC分类号： G06N5/022

摘要： Techniques for automatically scoring submissions to an online question-and-answer submission system are disclosed. According to one such technique, an initial set of user submissions are scored by human operators and/or automated algorithmic mechanisms. The submissions and their accompanying scores are provided as training data to an automated machine learning mechanism. The machine learning mechanism processes the training data and automatically detects patterns in the provided submissions. The machine learning mechanism automatically correlates these patterns with the scores assigned to the submissions that match those patterns. As a result, the machine learning mechanism is trained. Thereafter, the machine learning mechanism processes unscored submissions. The machine learning mechanism automatically identifies, from among the patterns that the machine learning mechanism has already detected, one or more patterns that these submissions match. The machine learning mechanism automatically scores these submissions based on the matching patterns and the scores that are associated with those patterns.

摘要翻译： 公开了自动评分提交给在线问答提交系统的技术。 根据一种这样的技术，人类操作者和/或自动算法机制对初始的用户提交集进行评分。 提交的材料及其附带的分数作为培训数据提供给自动化机器学习机制。 机器学习机制处理训练数据并自动检测提供的提交中的模式。 机器学习机制自动将这些模式与分配给与这些模式匹配的提交的分数相关联。 因此，机器学习机制得到了培训。 此后，机器学习机制处理未评分的提交。 机器学习机制自动识别机器学习机制已经检测到的模式之一，这些提交匹配的一个或多个模式。 机器学习机制根据与这些模式相关联的匹配模式和分数自动对这些提交进行评分。

公开(公告)号：US20090049478A1

公开(公告)日：2009-02-19

申请号：US11837920

申请日：2007-08-13

申请人： Remi Kwan

发明人： Remi Kwan

IPC分类号： G06F3/00

CPC分类号： G06F17/2264

摘要： The present invention is directed towards systems, methods and computer program products for generating substitute titles for a content item in response to a user submitted title for the content item. The method of the present invention comprises receiving a user generated title and generating a plurality of candidate substitute titles. A first quality score is calculated for the user generated title and a plurality of second quality scores are generated for the plurality of candidate substitute titles. The user generated title for the content item is replaced with at least one of said plurality of candidate substitute titles on the basis of the quality scores.

摘要翻译： 本发明涉及系统，方法和计算机程序产品，用于响应于用户提交的内容项目的标题来产生用于内容项目的替换标题。 本发明的方法包括接收用户产生的标题并产生多个候选替代标题。 对于用户生成的标题计算第一质量分数，并为多个候选替代标题生成多个第二质量分数。 基于质量得分，用所述多个候选替代标题中的至少一个代替用于内容项目的用户生成的标题。

公开(公告)号：US20090276381A1

公开(公告)日：2009-11-05

申请号：US12491133

申请日：2009-06-24

申请人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

发明人： Daniel Boies ,  Benoit Dumoulin ,  Remi Kwan

IPC分类号： G06F15/18 ,  G06N5/02

CPC分类号： G06N5/022

摘要： Techniques for automatically scoring submissions to an online question-and-answer submission system are disclosed. According to one such technique, an initial set of user submissions are scored by human operators and/or automated algorithmic mechanisms. The submissions and their accompanying scores are provided as training data to an automated machine learning mechanism. The machine learning mechanism processes the training data and automatically detects patterns in the provided submissions. The machine learning mechanism automatically correlates these patterns with the scores assigned to the submissions that match those patterns. As a result, the machine learning mechanism is trained. Thereafter, the machine learning mechanism processes unscored submissions. The machine learning mechanism automatically identifies, from among the patterns that the machine learning mechanism has already detected, one or more patterns that these submissions match. The machine learning mechanism automatically scores these submissions based on the matching patterns and the scores that are associated with those patterns.

摘要翻译： 公开了自动评分提交给在线问答提交系统的技术。 根据一种这样的技术，人类操作者和/或自动算法机制对初始的用户提交集进行评分。 提交的材料及其附带的分数作为培训数据提供给自动化机器学习机制。 机器学习机制处理训练数据并自动检测提供的提交中的模式。 机器学习机制自动将这些模式与分配给与这些模式匹配的提交的分数相关联。 因此，机器学习机制得到了培训。 此后，机器学习机制处理未评分的提交。 机器学习机制自动识别机器学习机制已经检测到的模式之一，这些提交匹配的一个或多个模式。 机器学习机制根据与这些模式相关联的匹配模式和分数自动对这些提交进行评分。