专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US08626677B2 Training SVMs with parallelized stochastic gradient descent 有权
标题翻译：用并行随机梯度下降训练SVM
公开(公告)号：US08626677B2
公开(公告)日：2014-01-07
申请号：US12790532
申请日：2010-05-28
申请人： Weizhu Chen , Gang Wang , Zheng Chen
发明人： Weizhu Chen , Gang Wang , Zheng Chen
IPC分类号： G06F15/18
CPC分类号： G06K9/6269 , G06N99/005
摘要： Techniques for training a non-linear support vector machine utilizing a stochastic gradient descent algorithm are provided. The computations of the stochastic gradient descent algorithm are parallelized via a number of processors. Calculations of the stochastic gradient descent algorithm on a particular processor may be combined according to a packing strategy before communicating the results of the calculations with the other processors.
摘要翻译：提供了利用随机梯度下降算法训练非线性支持向量机的技术。随机梯度下降算法的计算通过多个处理器并行化。在将计算结果与其他处理器通信之前，可以根据打包策略来组合特定处理器上的随机梯度下降算法。

22. 发明申请

US20130173571A1 CLICK NOISE CHARACTERIZATION MODEL 有权
标题翻译：点击噪声特征模型
公开(公告)号：US20130173571A1
公开(公告)日：2013-07-04
申请号：US13341653
申请日：2011-12-30
申请人： Weizhu Chen , Zheng Chen , Adish Singla
发明人： Weizhu Chen , Zheng Chen , Adish Singla
IPC分类号： G06F17/30
CPC分类号： G06F17/30 , G06F17/30424 , G06F17/3053 , G06F17/30634 , G06F17/30657 , G06F17/30864
摘要： The techniques discussed herein consider a degree of noise associated with user clicks performed during search sessions. The techniques then generate a model that characterizes click noise so that search engines can more accurately infer document relevance.
摘要翻译：这里讨论的技术考虑了与在搜索会话期间执行的用户点击相关联的噪音程度。然后，该技术产生表征点击噪声的模型，使得搜索引擎可以更准确地推断文档相关性。

23. 发明申请

US20110213763A1 WEB CONTENT MINING OF PAIR-BASED DATA 审中-公开
标题翻译：基于对象数据的WEB内容采集
公开(公告)号：US20110213763A1
公开(公告)日：2011-09-01
申请号：US13101061
申请日：2011-05-04
申请人： Weizhu Chen , Long Jiang , Ming Zhou , Benyu Zhang , Zheng Chen , Jian Wang
发明人： Weizhu Chen , Long Jiang , Ming Zhou , Benyu Zhang , Zheng Chen , Jian Wang
IPC分类号： G06F17/30
CPC分类号： G06F16/951
摘要： Described herein is technology for, among other things, mining pair-based data on the web. The technology involves an online pair-based data mining system as well as an offline SVM training system. By subjecting a pair-based input data to the systems, one may grow a pool of pair-based data which share characteristics of the pair-based input data in more efficient manner.
摘要翻译：这里描述的是用于在网络上挖掘基于对的数据的技术。该技术涉及一个在线的基于对的数据挖掘系统以及离线SVM培训系统。通过对基于对的输入数据进行系统的处理，可以以更有效的方式增加基于成对的输入数据的特征的基于对的数据池。

24. 发明授权

US07962507B2 Web content mining of pair-based data 有权
标题翻译：基于对数据的Web内容挖掘
公开(公告)号：US07962507B2
公开(公告)日：2011-06-14
申请号：US11941968
申请日：2007-11-19
申请人： Weizhu Chen , Long Jiang , Ming Zhou , Benyu Zhang , Zheng Chen , Jian Wang
发明人： Weizhu Chen , Long Jiang , Ming Zhou , Benyu Zhang , Zheng Chen , Jian Wang
IPC分类号： G06F17/30 , G06F7/00
CPC分类号： G06F17/30864
摘要： Described herein is technology for, among other things, mining pair-based data on the web. The technology involves an online pair-based data mining system as well as an offline SVM training system. By subjecting a pair-based input data to the systems, one may grow a pool of pair-based data which share characteristics of the pair-based input data in more efficient manner.
摘要翻译：这里描述的是用于在网络上挖掘基于对的数据的技术。该技术涉及一个在线的基于对的数据挖掘系统以及离线SVM培训系统。通过对基于对的输入数据进行系统的处理，可以以更有效的方式增加基于成对的输入数据的特征的基于对的数据池。

25. 发明授权

US07873904B2 Internet visualization system and related user interfaces 有权
标题翻译：互联网可视化系统及相关用户界面
公开(公告)号：US07873904B2
公开(公告)日：2011-01-18
申请号：US11972073
申请日：2008-01-10
申请人： Min Wang , Weizhu Chen , Benyu Zhang , Zheng Chen , Jian Wang
发明人： Min Wang , Weizhu Chen , Benyu Zhang , Zheng Chen , Jian Wang
IPC分类号： G06F17/30
CPC分类号： G06F17/30864 , G06F2216/03
摘要： Systems and methods are described for an Internet visualization system and related user interfaces. In one implementation, the system analyzes Internet search logs to determine most popular search queries across the world at a current time. A user interface displays a keyword of each of the most popular queries in a single visual display that relates each query to a geographical location of greatest popularity. The system can also filter queries according to demographics. In one implementation the user interface provides a 3-dimensional Internet visualization that adopts an ocean or seascape theme. The ocean floor displays a map of the world, and query bubbles rise from geographical locations on the map. The size and duration of each query bubble denotes the relative popularity of a given query.
摘要翻译：为互联网可视化系统和相关的用户界面描述了系统和方法。在一个实现中，系统分析互联网搜索日志以确定当前世界上最流行的搜索查询。用户界面在单个视觉显示中显示每个最流行的查询的关键字，其将每个查询与最受欢迎的地理位置相关联。该系统还可以根据人口特征来过滤查询。在一个实现中，用户界面提供采用海洋或海景主题的三维互联网可视化。海底显示世界地图，查询气泡从地图上的地理位置上升。每个查询气泡的大小和持续时间表示给定查询的相对受欢迎程度。

26. 发明申请

US20090193047A1 CONTRUCTING WEB QUERY HIERARCHIES FROM CLICK-THROUGH DATA 有权
标题翻译：从点击数据中进行网页查询分层
公开(公告)号：US20090193047A1
公开(公告)日：2009-07-30
申请号：US12020574
申请日：2008-01-28
申请人： Weizhu Chen , Benyu Zhang , Zheng Chen , Jian Wang , Dou Shen
发明人： Weizhu Chen , Benyu Zhang , Zheng Chen , Jian Wang , Dou Shen
IPC分类号： G06F17/30
CPC分类号： G06F17/30864
摘要： The claimed subject matter is directed to constructing query hierarchies in response to a query request. To construct a query hierarchy, a list of related candidate queries is generated in response to the received query request. The list of related candidate queries is generated by determining the relative coverage of information shared by the candidate queries and the query request. Relationships between the submitted query request and the candidate queries in the list are determined based upon the extent of relative coverage of information shared by the candidate queries and the query request. A query hierarchy is then constructed to reflect the determined relationships between the query request and the candidate queries.
摘要翻译：所要求保护的主题涉及响应于查询请求构建查询层次结构。为了构建查询层次结构，响应于接收的查询请求生成相关候选查询的列表。通过确定候选查询和查询请求共享的信息的相对覆盖率来生成相关候选查询的列表。基于候选查询和查询请求共享的信息的相对覆盖范围确定列表中提交的查询请求与候选查询之间的关系。然后构建查询层次结构以反映所确定的查询请求和候选查询之间的关系。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式