公开(公告)号：US08924314B2

公开(公告)日：2014-12-30

申请号：US13198560

申请日：2011-08-04

申请人： Parashuram Kulkarni ,  Abdelhalim Abbas ,  Michael Mathieson ,  Jingzhou Hua ,  Jon Degenhardt ,  Ramakrishnan Natarajan

发明人： Parashuram Kulkarni ,  Abdelhalim Abbas ,  Michael Mathieson ,  Jingzhou Hua ,  Jon Degenhardt ,  Ramakrishnan Natarajan

IPC分类号： G06F15/18 ,  G06F17/30

CPC分类号： G06F17/3053 ,  G06F17/30864 ,  G06N99/005

摘要： Various embodiments include systems and methods for search result ranking using machine learning. A goal model can be created using machine learning. Responsive to a search query, a plurality of data factors can be inputted into the goal model to create a model output. Search results can be presented to a user based on the model output.

摘要翻译： 各种实施例包括使用机器学习的搜索结果排序的系统和方法。 可以使用机器学习创建目标模型。 响应于搜索查询，可以将多个数据因子输入到目标模型中以创建模型输出。 搜索结果可以根据模型输出呈现给用户。

公开(公告)号：US20120078825A1

公开(公告)日：2012-03-29

申请号：US13198560

申请日：2011-08-04

申请人： Parashuram Kulkarni ,  Abdelhalim Abbas ,  Michael Mathieson ,  Jingzhou Hua ,  Jon Degenhardt ,  Ramakrishnan Natarajan

发明人： Parashuram Kulkarni ,  Abdelhalim Abbas ,  Michael Mathieson ,  Jingzhou Hua ,  Jon Degenhardt ,  Ramakrishnan Natarajan

IPC分类号： G06F15/18

CPC分类号： G06F17/3053 ,  G06F17/30864 ,  G06N99/005

摘要： Various embodiments include systems and methods for search result ranking using machine learning. A goal model can be created using machine learning. Responsive to a search query, a plurality of data factors can be inputted into the goal model to create a model output. Search results can be presented to a user based on the model output.

摘要翻译： 各种实施例包括使用机器学习的搜索结果排序的系统和方法。 可以使用机器学习创建目标模型。 响应于搜索查询，可以将多个数据因子输入到目标模型中以创建模型输出。 搜索结果可以根据模型输出呈现给用户。

公开(公告)号：US20120197758A1

公开(公告)日：2012-08-02

申请号：US13015362

申请日：2011-01-27

申请人： Qian Zhong ,  Ramakrishnan Natarajan ,  Parashuram Kulkarni ,  Abdelhalim Abbas ,  Zhigang Hua

发明人： Qian Zhong ,  Ramakrishnan Natarajan ,  Parashuram Kulkarni ,  Abdelhalim Abbas ,  Zhigang Hua

IPC分类号： G06Q30/00

CPC分类号： G06Q30/02 ,  G06Q30/0609 ,  G06Q50/01

摘要： A method and a system generate a reputation value for a user in a network-based community. A processor-implemented transaction data collector module collects transaction data of users of a network-based community. A processor-implemented transaction graph generator module generates a transaction graph based on the collected transaction data. The transaction graph has a transaction relationship between two users, and a weight corresponding to the transaction relationship. The weight is representative of a mutually reinforcing relationship between two users. A processor-implemented reputation generator module generates a reputation value for a user from the transaction graph.

摘要翻译： 方法和系统为基于网络的社区中的用户生成信誉值。 处理器实现的交易数据收集器模块收集基于网络的社区的用户的交易数据。 处理器实现的事务图生成器模块基于收集的事务数据生成事务图。 事务图具有两个用户之间的事务关系，并且与事务关系对应的权重。 这个权重代表了两个用户之间相互加强的关系。 处理器实现的信誉发生器模块从事务图形生成用户的信誉值。

公开(公告)号：US20120259844A1

公开(公告)日：2012-10-11

申请号：US13082226

申请日：2011-04-07

申请人： Ted Tao Yuan ,  Michael Mathieson ,  Parashuram Kulkarni

发明人： Ted Tao Yuan ,  Michael Mathieson ,  Parashuram Kulkarni

IPC分类号： G06F17/30

CPC分类号： G06F17/30867 ,  G06F17/3053 ,  G06F17/30864

摘要： A system and method for assessing excessive accessory listings in search results includes a processor-implemented textual mining module that parses a data field of a document and generates at least one token from the data field. A processor-implemented scoring module calculates a score for the at least one token, with the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications. The processor-implemented scoring module also calculates a score for the document based on the at least one token score, with the document score representing a probability of the document being in one of the two binary classifications. A processor-implemented decision tree module inputs the document score and document attribute values into a decision tree and generates an output representing a refined score based on the document score and at least one of the document attribute values.

摘要翻译： 用于评估搜索结果中的过多附件列表的系统和方法包括处理器实现的文本挖掘模块，其解析文档的数据字段并从数据字段生成至少一个令牌。 处理器实现的评分模块计算所述至少一个令牌的分数，所述至少一个令牌分数表示所述至少一个令牌属于两个二进制分类中的一个的可能性。 处理器实现的评分模块还基于至少一个令牌分数来计算文档的分数，文档分数表示文档处于两个二进制分类之一的概率。 处理器实施的决策树模块将文档分数和文档属性值输入到决策树中，并且基于文档分数和文档属性值中的至少一个生成表示精确分数的输出。

公开(公告)号：US09384278B2

公开(公告)日：2016-07-05

申请号：US13082226

申请日：2011-04-07

申请人： Ted Tao Yuan ,  Michael Mathieson ,  Parashuram Kulkarni

发明人： Ted Tao Yuan ,  Michael Mathieson ,  Parashuram Kulkarni

IPC分类号： G06F17/30

CPC分类号： G06F17/30867 ,  G06F17/3053 ,  G06F17/30864

摘要： A system and method for assessing excessive accessory listings in search results includes a processor-implemented textual mining module that parses a data field of a document and generates at least one token from the data field. A processor-implemented scoring module calculates a score for the at least one token, with the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications. The processor-implemented scoring module also calculates a score for the document based on the at least one token score, with the document score representing a probability of the document being in one of the two binary classifications. A processor-implemented decision tree module inputs the document score and document attribute values into a decision tree and generates an output representing a refined score based on the document score and at least one of the document attribute values.

摘要翻译： 用于评估搜索结果中的过多附件列表的系统和方法包括处理器实现的文本挖掘模块，其解析文档的数据字段并从数据字段生成至少一个令牌。 处理器实现的评分模块计算所述至少一个令牌的分数，所述至少一个令牌分数表示所述至少一个令牌属于两个二进制分类中的一个的可能性。 处理器实现的评分模块还基于至少一个令牌分数来计算文档的分数，文档分数表示文档处于两个二进制分类之一的概率。 处理器实施的决策树模块将文档分数和文档属性值输入到决策树中，并且基于文档分数和文档属性值中的至少一个生成表示精确分数的输出。

公开(公告)号：US20070027882A1

公开(公告)日：2007-02-01

申请号：US11192620

申请日：2005-07-28

申请人： Parashuram Kulkarni

发明人： Parashuram Kulkarni

IPC分类号： G06F7/00

CPC分类号： G06F17/2229 ,  G06F17/30911 ,  G06F17/30938 ,  Y10S707/99931 ,  Y10S707/99936 ,  Y10S707/99942 ,  Y10S707/99943 ,  Y10S707/99945

摘要： Techniques for identifying discrete records within a multi-record document are provided. According to one technique, a document is encoded based on some combination of visual tag encoding, text category encoding, and text content encoding that produces hash values based on the contents of portions of the document. According to one technique, repeating candidate patterns are identified in a document so encoded. The candidate patterns may be identified in a “fuzzy” manner that allows for some inconsistencies in the individual pattern instances. According to one technique, the identified candidate patterns are validated based on specified factors to determine a “best” pattern. According to one technique, the boundaries of discrete records in a multi-record document are marked based on the portions of the document that correspond to an identified repeating pattern.

摘要翻译： 提供了用于识别多记录文档内的离散记录的技术。 根据一种技术，基于视觉标签编码，文本类别编码和文本内容编码的组合来编码文档，该文本内容编码基于文档的部分内容产生散列值。 根据一种技术，在如此编码的文档中识别重复的候选模式。 可以以“模糊”的方式识别候选图案，其允许各个图案实例中的一些不一致。 根据一种技术，基于指定因素来确定所识别的候选模式以确定“最佳”模式。 根据一种技术，多记录文档中离散记录的边界基于对应于所识别的重复图案的文档部分进行标记。

公开(公告)号：US07483903B2

公开(公告)日：2009-01-27

申请号：US11253023

申请日：2005-10-17

申请人： Parashuram Kulkarni ,  Binu Raj

发明人： Parashuram Kulkarni ,  Binu Raj

IPC分类号： G06F7/00 ,  G06F12/00 ,  G06F17/00 ,  G06F17/30

CPC分类号： G06F17/30861

摘要： Techniques for correcting miscategorized features excerpted from web pages are provided. For each of several categories and several pages on a particular web site, a separate feature may be excerpted from that page and associated with that page in relation to that category. Often, many of the “high confidence” features that have been associated with the same category are found to be associated with similar characteristics regardless of the pages from which those features were excerpted. Thus, a set of category characteristics, which are often found associated with the “high confidence” features in a particular category, may be determined. For each page, a candidate feature that is associated with the set of category characteristics may be identified in that page. If, in relation to the particular category, a feature other than the candidate feature is associated with that page, then that other feature may be replaced by the candidate feature.

摘要翻译： 提供了从网页上摘录的分类功能的技巧。 对于特定网站上的几个类别和多个页面中的每一个，可以从该页面摘录单独的特征并且与该页面相关联地与该页面相关联。 通常，与相同类别相关联的许多“高信度”特征被发现与相似的特征相关，而不管这些特征被摘录的页面。 因此，可以确定通常发现与特定类别中的“高置信度”特征相关联的一组类别特征。 对于每个页面，可以在该页面中识别与该组类别特征相关联的候选特征。 如果关于特定类别，除了候选特征之外的特征与该页面相关联，则该另一特征可以被候选特征替换。

公开(公告)号：US08255391B2

公开(公告)日：2012-08-28

申请号：US12367646

申请日：2009-02-09

申请人： Parashuram Kulkarni

发明人： Parashuram Kulkarni

IPC分类号： G06F17/30

CPC分类号： G06F17/30864

摘要： A system and method for determining a ranking function for a search engine. A training data processor receives training data, the training data including at least a first page, a first label, a second page and a second label. A feature extraction processor receives the first page, identifies first features in the first page and calculates first values relating to the first features. The feature extraction processor receives the second page and identifies second features and calculates second values relating to the second features. A machine learning processor receives the first features, the first values, the first label, the second features, the second values, and the second label. The machine learning processor generates a ranking function based on first features, the first values, the first label, the second features, the second values, and the second label.

摘要翻译： 一种用于确定搜索引擎的排名功能的系统和方法。 训练数据处理器接收训练数据，训练数据至少包括第一页面，第一标签，第二页面和第二标签。 特征提取处理器接收第一页面，识别第一页面中的第一特征并计算与第一特征相关的第一值。 特征提取处理器接收第二页面并识别第二特征并计算与第二特征相关的第二值。 机器学习处理器接收第一特征，第一值，第一标签，第二特征，第二值和第二标签。 机器学习处理器基于第一特征，第一值，第一标签，第二特征，第二值和第二标签来生成排序函数。

公开(公告)号：US07606816B2

公开(公告)日：2009-10-20

申请号：US11192620

申请日：2005-07-28

申请人： Parashuram Kulkarni

发明人： Parashuram Kulkarni

IPC分类号： G06F7/00 ,  G06F17/00

CPC分类号： G06F17/2229 ,  G06F17/30911 ,  G06F17/30938 ,  Y10S707/99931 ,  Y10S707/99936 ,  Y10S707/99942 ,  Y10S707/99943 ,  Y10S707/99945

摘要： Techniques for identifying discrete records within a multi-record document are provided. According to one technique, a document is encoded based on some combination of visual tag encoding, text category encoding, and text content encoding that produces hash values based on the contents of portions of the document. According to one technique, repeating candidate patterns are identified in a document so encoded. The candidate patterns may be identified in a “fuzzy” manner that allows for some inconsistencies in the individual pattern instances. According to one technique, the identified candidate patterns are validated based on specified factors to determine a “best” pattern. According to one technique, the boundaries of discrete records in a multi-record document are marked based on the portions of the document that correspond to an identified repeating pattern.

摘要翻译： 提供了用于识别多记录文档内的离散记录的技术。 根据一种技术，基于视觉标签编码，文本类别编码和文本内容编码的组合来编码文档，该文本内容编码基于文档的部分内容产生散列值。 根据一种技术，在如此编码的文档中识别重复的候选模式。 可以以“模糊”的方式识别候选图案，其允许各个图案实例中的一些不一致。 根据一种技术，基于指定因素来确定所识别的候选模式以确定“最佳”模式。 根据一种技术，多记录文档中离散记录的边界基于对应于所识别的重复图案的文档部分进行标记。

公开(公告)号：US20070022085A1

公开(公告)日：2007-01-25

申请号：US11224887

申请日：2005-09-12

申请人： Parashuram Kulkarni

发明人： Parashuram Kulkarni

IPC分类号： G06F17/30

CPC分类号： G06F16/9566

摘要： Unsupervised crawling of the hidden Web utilizes a query engine, coupled to a crawler system, that automatically and intelligently inserts keywords into text input controls in Web page forms so that the filled form can be submitted to a server to retrieve dynamically generated Web content for indexing. The keywords used to fill form controls are based on the content of corresponding Web pages, which is automatically discovered to generate a set of keywords for filling the controls. The set of keywords can be expanded to include related keywords from other Web pages and Web sites and, therefore, to provide more effective coverage for crawling the Web content. The expanded set of keywords can be continuously expanded by recursively performing similarity analyses based on results from crawling the same and other Web sites.

摘要翻译： 隐藏Web的无监督抓取使用查询引擎，与爬网系统相结合，自动智能地将关键字插入网页表单中的文本输入控件中，以便将填写的表单提交到服务器以检索动态生成的Web内容进行索引 。 用于填写表单控件的关键字是基于相应网页的内容，自动发现该网页生成一组用于填充控件的关键字。 可以将这组关键字扩展为包括来自其他网页和网站的相关关键字，因此，为抓取Web内容提供更有效的覆盖。 通过根据爬行相同和其他网站的结果递归地执行相似性分析，可以不断扩展扩展的关键字集合。