专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20110320767A1 Parallelization of Online Learning Algorithms 有权
标题翻译：在线学习算法的并行化
公开(公告)号：US20110320767A1
公开(公告)日：2011-12-29
申请号：US12822918
申请日：2010-06-24
申请人： Taha Bekir Eren , Oleg Isakov , Weizhu Chen , Jeffrey Scott Dunn , Thomas Ivan Borchert , Joaquin Quinonero Candela , Thore Kurt Hartwig Graepel , Ralf Herbrich
发明人： Taha Bekir Eren , Oleg Isakov , Weizhu Chen , Jeffrey Scott Dunn , Thomas Ivan Borchert , Joaquin Quinonero Candela , Thore Kurt Hartwig Graepel , Ralf Herbrich
IPC分类号： G06F15/76 , G06F9/02
CPC分类号： G06N99/005
摘要： Methods, systems, and media are provided for a dynamic batch strategy utilized in parallelization of online learning algorithms. The dynamic batch strategy provides a merge function on the basis of a threshold level difference between the original model state and an updated model state, rather than according to a constant or pre-determined batch size. The merging includes reading a batch of incoming streaming data, retrieving any missing model beliefs from partner processors, and training on the batch of incoming streaming data. The steps of reading, retrieving, and training are repeated until the measured difference in states exceeds a set threshold level. The measured differences which exceed the threshold level are merged for each of the plurality of processors according to attributes. The merged differences which exceed the threshold level are combined with the original partial model states to obtain an updated global model state.
摘要翻译：提供了方法，系统和媒体，用于在线学习算法并行化中使用的动态批处理策略。动态批量策略基于原始模型状态和更新的模型状态之间的阈值水平差，而不是根据常数或预定的批量大小来提供合并功能。合并包括读取一批传入的流式传输数据，从合作伙伴处理器中检索任何丢失的模型信念，以及对批量的传入流数据进行培训。重复读取，检索和训练的步骤，直到测量的状态差异超过设定的阈值水平。根据属性对多个处理器中的每一个合并超过阈值水平的测量差异。将超过阈值水平的合并差异与原始部分模型状态相结合以获得更新的全局模型状态。

2. 发明授权

US08904149B2 Parallelization of online learning algorithms 有权
标题翻译：在线学习算法的并行化
公开(公告)号：US08904149B2
公开(公告)日：2014-12-02
申请号：US12822918
申请日：2010-06-24
申请人： Taha Bekir Eren , Oleg Isakov , Weizhu Chen , Jeffrey Scott Dunn , Thomas Ivan Borchert , Joaquin Quinonero Candela , Thore Kurt Hartwig Graepel , Ralf Herbrich
发明人： Taha Bekir Eren , Oleg Isakov , Weizhu Chen , Jeffrey Scott Dunn , Thomas Ivan Borchert , Joaquin Quinonero Candela , Thore Kurt Hartwig Graepel , Ralf Herbrich
IPC分类号： G06F15/76 , G06F9/02 , G06N99/00
CPC分类号： G06N99/005
摘要： Methods, systems, and media are provided for a dynamic batch strategy utilized in parallelization of online learning algorithms. The dynamic batch strategy provides a merge function on the basis of a threshold level difference between the original model state and an updated model state, rather than according to a constant or pre-determined batch size. The merging includes reading a batch of incoming streaming data, retrieving any missing model beliefs from partner processors, and training on the batch of incoming streaming data. The steps of reading, retrieving, and training are repeated until the measured difference in states exceeds a set threshold level. The measured differences which exceed the threshold level are merged for each of the plurality of processors according to attributes. The merged differences which exceed the threshold level are combined with the original partial model states to obtain an updated global model state.
摘要翻译：提供了方法，系统和媒体，用于在线学习算法并行化中使用的动态批处理策略。动态批量策略基于原始模型状态和更新的模型状态之间的阈值水平差，而不是根据常数或预定的批量大小来提供合并功能。合并包括读取一批传入的流式传输数据，从合作伙伴处理器中检索任何丢失的模型信念，以及对批量的传入流数据进行培训。重复读取，检索和训练的步骤，直到测量的状态差异超过设定的阈值水平。根据属性对多个处理器中的每一个合并超过阈值水平的测量差异。将超过阈值水平的合并差异与原始部分模型状态相结合以获得更新的全局模型状态。

3. 发明申请

US20140052751A1 SMART USER-CENTRIC INFORMATION AGGREGATION 有权
标题翻译： SMART用户中心信息聚合
公开(公告)号：US20140052751A1
公开(公告)日：2014-02-20
申请号：US13586711
申请日：2012-08-15
申请人： Jianwen Zhang , Zhimin Zhang , Jian-Tao Sun , Jun Yan , Ning Liu , Lei Ji , Weizhu Chen , Zheng Chen
发明人： Jianwen Zhang , Zhimin Zhang , Jian-Tao Sun , Jun Yan , Ning Liu , Lei Ji , Weizhu Chen , Zheng Chen
IPC分类号： G06F17/30
CPC分类号： G06F17/30032 , G06F17/30905
摘要： A smart user-centric information aggregation system allows a user to define a region of content displayed in a display of a device and performs information aggregation on behalf of the user. The smart user-centric information aggregation system searches, aggregates and groups information related to content included in the region of content for the user while the user can continue to perform his/her original course of actions without interruption. After finding information related to the desired content, the smart user-centric information aggregation system may notify the user and present the found information to the user upon receiving confirmation from the user. The smart user-centric information aggregation system may continue to find new related information and update the presentation with the newly found information periodically, in some instances without user intervention or input.
摘要翻译：以智能用户为中心的信息聚合系统允许用户定义显示在设备显示器中的内容区域，并代表用户执行信息聚合。智能用户为中心的信息聚合系统在用户可以继续执行他/她的原始行为过程而不间断地搜索，聚合和分组与用户内容区域中包含的内容相关的信息。在找到与期望内容相关的信息之后，智能用户为中心的信息聚合系统可以在接收到来自用户的确认时通知用户并向用户呈现找到的信息。以智能用户为中心的信息聚合系统可以继续寻找新的相关信息，并且在某些情况下，不需要用户干预或输入，定期更新新发现的信息。

4. 发明授权

US08407236B2 Mining new words from a query log for input method editors 有权
标题翻译：从输入法编辑器的查询日志挖掘新单词
公开(公告)号：US08407236B2
公开(公告)日：2013-03-26
申请号：US12244774
申请日：2008-10-03
申请人： Weizhu Chen , Qian Xun Li , Li Ju , Zheng Chen , Dong Li , Zhikai Fan
发明人： Weizhu Chen , Qian Xun Li , Li Ju , Zheng Chen , Dong Li , Zhikai Fan
IPC分类号： G06F17/30
CPC分类号： G06F17/30731
摘要： Described is a technology in which new words (including a phrase or set of Chinese characters) are mined from a query log. The new words may be added to (or otherwise supplement) an IME dictionary. A set of candidate queries may be selected from the log based upon market (e.g., the Chinese market) and/or by language. From this set, various filtering steps are performed to locate only new words that are frequently in used. For example, only frequent queries are kept for further processing, which may include filtering out queries based on length (e.g., less than two or greater than eight Chinese characters), and/or filtering out queries based on too many stop-words in the query. Processing may also include filtering out a query that is a substring of a larger query, or vice-versa. Also described is Pinyin-based clustering and filtering, and filtering out queries already handled in the dictionary.
摘要翻译：描述了从查询日志中挖出新词（包括短语或一组汉字）的技术。新词可能会添加到（或以其他方式补充）IME词典。可以基于市场（例如，中国市场）和/或按语言从日志中选择一组候选查询。从该集合中，执行各种过滤步骤以仅定位经常使用的新词。例如，只有频繁的查询被保留用于进一步的处理，其可以包括基于长度（例如，少于两个或大于八个汉字）过滤掉查询，和/或基于过多的停止词过滤掉查询查询。处理还可以包括过滤掉作为较大查询的子串的查询，反之亦然。还描述了基于拼音的群集和过滤，并且过滤掉已经在字典中处理的查询。

5. 发明申请

US20120123993A1 Action Prediction and Identification Temporal User Behavior 有权
标题翻译：行动预测和识别时间用户行为
公开(公告)号：US20120123993A1
公开(公告)日：2012-05-17
申请号：US12947871
申请日：2010-11-17
申请人： Gang Wang , Weizhu Chen , Zheng Chen , Zhikai Fan
发明人： Gang Wang , Weizhu Chen , Zheng Chen , Zhikai Fan
IPC分类号： G06N7/02
CPC分类号： G06N5/02 , G06F17/30693 , G06N5/043 , G06Q30/00 , G06Q30/0202
摘要： User behavior modeling can include determining temporal- or time-based actions performed by various users. From the mined temporal-based user actions, future actions can be predicted. Certain implementations include providing information and/or services based on the predicted future actions. Some implementations, include providing relevant information, services, and/or goods regarding the predicted future action.
摘要翻译：用户行为建模可以包括确定由各种用户执行的时间或时间的动作。从开采的基于时间的用户操作，可以预测未来的行动。某些实施方式包括基于预测的未来行动来提供信息和/或服务。一些实施方式包括提供有关预测未来行动的相关信息，服务和/或商品。

6. 发明授权

US09355095B2 Click noise characterization model 有权
标题翻译：点击噪声表征模型
公开(公告)号：US09355095B2
公开(公告)日：2016-05-31
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。

7. 发明申请

US20120143789A1 CLICK MODEL THAT ACCOUNTS FOR A USER'S INTENT WHEN PLACING A QUIERY IN A SEARCH ENGINE 审中-公开
标题翻译：在搜索引擎中放置校园时，用户的信息的点击模式
公开(公告)号：US20120143789A1
公开(公告)日：2012-06-07
申请号：US12957521
申请日：2010-12-01
申请人： Gang Wang , Weizhu Chen , Zheng Chen
发明人： Gang Wang , Weizhu Chen , Zheng Chen
IPC分类号： G06F17/30 , G06F15/18 , G06N5/02
CPC分类号： G06F16/951
摘要： A method of generating training data for a search engine begins by retrieving log data pertaining to user click behavior. The log data is analyzed based on a click model that includes a parameter pertaining to a user intent bias representing the intent of a user in performing a search in order to determine a relevance of each of a plurality of pages to a query. The relevance of the pages is then converted into training data.
摘要翻译：生成搜索引擎的训练数据的方法从检索与用户点击行为有关的日志数据开始。基于点击模型分析日志数据，所述点击模型包括与用户意图偏差相关的参数，所述参数表示用户执行搜索的意图，以便确定多个页面中的每一个与查询的相关性。然后将页面的相关性转换为训练数据。

8. 发明授权

US08589228B2 Click modeling for URL placements in query response pages 有权
标题翻译：点击查询响应页面中的网址展示位置的建模
公开(公告)号：US08589228B2
公开(公告)日：2013-11-19
申请号：US12795631
申请日：2010-06-07
申请人： Weizhu Chen , Gang Wang , Zheng Chen , Zhikai Fan , Thomas Minka
发明人： Weizhu Chen , Gang Wang , Zheng Chen , Zhikai Fan , Thomas Minka
IPC分类号： G06F15/18 , G06F17/60 , G06Q30/00 , G06N5/02
CPC分类号： G06Q30/02 , G06Q30/0255
摘要： A “General Click Model” (GCM) is constructed using a Bayesian network that is inherently capable of modeling “tail queries” by building the model on multiple attribute values that are shared across queries. More specifically, the GCM learns and predicts user click behavior towards URLs displayed on a query results page returned by a search engine. Unlike conventional click modeling approaches that learn models based on individual queries, the GCM learns click models from multiple attributes, with the influence of different attribute values being measured by Bayesian inference. This provides an advantage in learning that enables the GCM to achieve improved generalization and results, especially for tail queries, than conventional click models. In addition, most conventional click models consider only position and the identity of URLs when learning the model. In contrast, the GCM considers more session-specific attributes in making a final prediction for anticipated or expected user click behaviors.
摘要翻译：使用贝叶斯网络构建“通用点击模型”（GCM），该贝叶斯网络本质上能够通过在查询之间共享的多个属性值上建立模型来建模“尾部查询”。更具体地说，GCM学习并预测用户对搜索引擎返回的查询结果页面上显示的URL的点击行为。不同于传统的点击建模方法，基于个别查询的模型，GCM从多个属性学习点击模型，不同属性值的影响是通过贝叶斯推理来衡量的。这提供了学习的优势，使得GCM能够实现改进的泛化和结果，特别是尾部查询，而不是传统的点击模型。此外，大多数传统的点击模型只在学习模型时考虑URL的位置和身份。相比之下，GCM考虑更多的会话特定属性来对预期或预期的用户点击行为进行最终预测。

9. 发明授权

US08543580B2 Mining translations of web queries from web click-through data 有权
标题翻译：从网络点击数据挖掘网络查询的翻译
公开(公告)号：US08543580B2
公开(公告)日：2013-09-24
申请号：US12342098
申请日：2008-12-23
申请人： Weizhu Chen , Zheng Chen
发明人： Weizhu Chen , Zheng Chen
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30864 , G06F2216/03
摘要： Methods and technologies providing translations of web queries based on an analysis of user behavior in click-through data. These methods and technologies generates large-scale and timely query translation pairs guided by a small set of seed word pairs from a dictionary, without relying on additional knowledge or complex models.
摘要翻译：基于点击数据中的用户行为分析，提供Web查询翻译的方法和技术。这些方法和技术不但依赖于额外的知识或复杂的模型，而是从词典中产生由小型种子字对引导的大规模和及时的查询翻译对。

10. 发明授权

US08412665B2 Action prediction and identification temporal user behavior 有权
标题翻译：行动预测和识别临时用户行为
公开(公告)号：US08412665B2
公开(公告)日：2013-04-02
申请号：US12947871
申请日：2010-11-17
申请人： Gang Wang , Weizhu Chen , Zheng Chen , Zhikai Fan
发明人： Gang Wang , Weizhu Chen , Zheng Chen , Zhikai Fan
IPC分类号： G06F9/44 , G06N7/02 , G06N7/06
CPC分类号： G06N5/02 , G06F17/30693 , G06N5/043 , G06Q30/00 , G06Q30/0202
摘要： User behavior modeling can include determining temporal- or time-based actions performed by various users. From the mined temporal-based user actions, future actions can be predicted. Certain implementations include providing information and/or services based on the predicted future actions. Some implementations, include providing relevant information, services, and/or goods regarding the predicted future action.
摘要翻译：用户行为建模可以包括确定由各种用户执行的时间或时间的动作。从开采的基于时间的用户操作，可以预测未来的行动。某些实施方式包括基于预测的未来行动来提供信息和/或服务。一些实施方式包括提供有关预测未来行动的相关信息，服务和/或商品。

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