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. 发明授权

US08521662B2 System and methods for finding hidden topics of documents and preference ranking documents 有权
公开(公告)号：US08521662B2
公开(公告)日：2013-08-27
申请号：US13078984
申请日：2011-04-03
申请人： Xi Chen , Yanjun Qi , Bing Bai
发明人： Xi Chen , Yanjun Qi , Bing Bai
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , G06F17/30705
摘要： Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

2. 发明申请

US20120323825A1 SYSTEM AND METHODS FOR FINDING HIDDEN TOPICS OF DOCUMENTS AND PREFERENCE RANKING DOCUMENTS 有权
公开(公告)号：US20120323825A1
公开(公告)日：2012-12-20
申请号：US13078984
申请日：2011-04-03
申请人： Xi Chen , Yanjun Qi , Bing Bai
发明人： Xi Chen , Yanjun Qi , Bing Bai
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , G06F17/30705
摘要： Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

3. 发明授权

US08738547B2 System and methods for finding hidden topics of documents and preference ranking documents 有权
标题翻译：查找文档隐藏主题和偏好排序文件的系统和方法
公开(公告)号：US08738547B2
公开(公告)日：2014-05-27
申请号：US13083391
申请日：2011-04-08
申请人： Xi Chen , Yanjun Qi , Bing Bai
发明人： Xi Chen , Yanjun Qi , Bing Bai
IPC分类号： G06N99/00
CPC分类号： G06N99/005 , G06F17/30705
摘要： Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.
摘要翻译：公开了系统和方法来对一组文件执行偏好学习，包括从存储在数据存储设备上的文档集接收原始输入特征; 从原始输入特征生成多项式组合; 产生一个或多个参数; 将参数应用于一个或多个分类器以产生输出; 确定损失函数和参数梯度以及更新确定一个或多个稀疏规则化条件并更新参数的参数; 并且在搜索查询中表达一个文档优于另一个文档，并且响应于搜索查询来检索一个或多个文档。

4. 发明申请

US20120191632A1 SYSTEM AND METHODS FOR FINDING HIDDEN TOPICS OF DOCUMENTS AND PREFERENCE RANKING DOCUMENTS 有权
公开(公告)号：US20120191632A1
公开(公告)日：2012-07-26
申请号：US13083391
申请日：2011-04-08
申请人： Xi Chen , Yanjun Qi , Bing Bai
发明人： Xi Chen , Yanjun Qi , Bing Bai
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , G06F17/30705
摘要： Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

5. 发明授权

US08612369B2 System and methods for finding hidden topics of documents and preference ranking documents 有权
标题翻译：查找文档隐藏主题和偏好排序文件的系统和方法
公开(公告)号：US08612369B2
公开(公告)日：2013-12-17
申请号：US13083402
申请日：2011-04-08
申请人： Xi Chen , Yanjun Qi , Bing Bai
发明人： Xi Chen , Yanjun Qi , Bing Bai
IPC分类号： G06N5/00
CPC分类号： G06N99/005 , G06F17/30705
摘要： Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.
摘要翻译：公开了系统和方法来对一组文件执行偏好学习，包括从存储在数据存储设备上的文档集接收原始输入特征; 从原始输入特征生成多项式组合; 产生一个或多个参数; 将参数应用于一个或多个分类器以产生输出; 确定损失函数和参数梯度以及更新确定一个或多个稀疏规则化条件并更新参数的参数; 并且在搜索查询中表达一个文档优于另一个文档，并且响应于搜索查询来检索一个或多个文档。

6. 发明申请

US20120179634A1 SYSTEM AND METHODS FOR FINDING HIDDEN TOPICS OF DOCUMENTS AND PREFERENCE RANKING DOCUMENTS 有权
标题翻译：发现隐藏文件主题和偏好排序文件的系统和方法
公开(公告)号：US20120179634A1
公开(公告)日：2012-07-12
申请号：US13083402
申请日：2011-04-08
申请人： Xi Chen , Yaonjun Qi , Bing Bai
发明人： Xi Chen , Yaonjun Qi , Bing Bai
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , G06F17/30705
摘要： Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.
摘要翻译：公开了系统和方法来对一组文件执行偏好学习，包括从存储在数据存储设备上的文档集接收原始输入特征; 从原始输入特征生成多项式组合; 产生一个或多个参数; 将参数应用于一个或多个分类器以产生输出; 确定损失函数和参数梯度以及更新确定一个或多个稀疏规则化条件并更新参数的参数; 并且在搜索查询中表达一个文档优于另一个文档，并且响应于搜索查询来检索一个或多个文档。

7. 发明授权

US09921665B2 Input method editor application platform 有权
公开(公告)号：US09921665B2
公开(公告)日：2018-03-20
申请号：US13586267
申请日：2012-08-15
申请人： Matthew Robert Scott , Huihua Hou , Xi Chen , Weipeng Liu , Rongfeng Lai , Xi Chen , Yonghong Shi
发明人： Matthew Robert Scott , Huihua Hou , Xi Chen , Weipeng Liu , Rongfeng Lai , Xi Chen , Yonghong Shi
IPC分类号： G06F15/177 , G06F3/023 , G06F17/27 , H04L12/58 , G06F17/24 , G06Q50/00 , G06F17/30 , G06Q10/10 , G06F3/0484
CPC分类号： G06F17/276 , G06F3/0237 , G06F3/04842 , G06F17/24 , G06F17/273 , G06F17/2735 , G06F17/30241 , G06F17/30477 , G06F17/30554 , G06F17/3056 , G06F17/3064 , G06F17/3087 , G06Q10/10 , G06Q50/01 , H04L51/10 , H04L51/32
摘要： An input method editor (IME) provides a distributed platform architecture that enables associating multiple applications with the IME to provide extended functionalities. The presentations of the applications, such as skins, may be different from each other and that of the IME. The applications may be represented in a manifest file that is human-readable and editable. The IME collects multiple parameters relating to a user input into a host application including a query input by the user and a scenario of the host application, and selects one or more applications to provide candidates based on a score or ranking of the applications under the collected multiple parameters. Machine-learning may be used to improve the score or ranking. The candidates may include text candidates, rich candidates, and informative candidates.

8. 发明授权

US09959340B2 Semantic lexicon-based input method editor 有权
公开(公告)号：US09959340B2
公开(公告)日：2018-05-01
申请号：US13635274
申请日：2012-06-29
申请人： Chi-Ho Li , Weijiang Xu , Matthew Robert Scott , Weipeng Liu , Xi Chen , Xi Chen
发明人： Chi-Ho Li , Weijiang Xu , Matthew Robert Scott , Weipeng Liu , Xi Chen , Xi Chen
IPC分类号： G06F17/21 , G06F17/30 , G06F17/27 , G06F3/0482
CPC分类号： G06F17/30675 , G06F3/0482 , G06F17/2785
摘要： Some implementations provide techniques and arrangements for semantic lexicon based processing, such as in an input method editor. In some instances, a semantic label may be received that is to be defined for a semantic lexicon and at least a first term may be identified as a positive or negative example of the semantic label. In response, some examples may label at least a second term in the semantic lexicon with the semantic label based at least in part on the identification of the first term as a positive or negative example of the semantic label.

9. 发明申请

US20130346872A1 INPUT METHOD EDITOR APPLICATION PLATFORM 有权
标题翻译：输入法编辑器应用平台
公开(公告)号：US20130346872A1
公开(公告)日：2013-12-26
申请号：US13586267
申请日：2012-08-15
申请人： Matthew Robert Scott , Huihua Hou , Xi Chen , Weipeng Liu , Rongfeng Lai , Xi Chen , Yonghong Shi
发明人： Matthew Robert Scott , Huihua Hou , Xi Chen , Weipeng Liu , Rongfeng Lai , Xi Chen , Yonghong Shi
IPC分类号： G06F3/048 , G06F15/16
CPC分类号： G06F17/276 , G06F3/0237 , G06F3/04842 , G06F17/24 , G06F17/273 , G06F17/2735 , G06F17/30241 , G06F17/30477 , G06F17/30554 , G06F17/3056 , G06F17/3064 , G06F17/3087 , G06Q10/10 , G06Q50/01 , H04L51/10 , H04L51/32
摘要： An input method editor (IME) provides a distributed platform architecture that enables associating multiple applications with the IME to provide extended functionalities. The presentations of the applications, such as skins, may be different from each other and that of the IME. The applications may be represented in a manifest file that is human-readable and editable. The IME collects multiple parameters relating to a user input into a host application including a query input by the user and a scenario of the host application, and selects one or more applications to provide candidates based on a score or ranking of the applications under the collected multiple parameters. Machine-learning may be used to improve the score or ranking. The candidates may include text candidates, rich candidates, and informative candidates.
摘要翻译：输入法编辑器（IME）提供了一种分布式平台架构，可将多个应用程序与IME相关联，以提供扩展功能。应用程序的介绍（如皮肤）可能会彼此不同，也可能与IME的不同。应用程序可以在人类可读和可编辑的清单文件中表示。 IME收集与主机应用中的用户输入有关的多个参数，包括用户输入的查询和主机应用的场景，并且根据所收集的应用程序的得分或排名选择一个或多个应用程序来提供候选者多个参数。机器学习可用于提高得分或排名。候选人可以包括文本候选人，丰富的候选人和资料丰富的候选人。

10. 发明申请

US20150121290A1 Semantic Lexicon-Based Input Method Editor 有权
标题翻译：基于语义词法的输入法编辑器
公开(公告)号：US20150121290A1
公开(公告)日：2015-04-30
申请号：US13635274
申请日：2012-06-29
申请人： Chi-Ho Li , Weijiang Xu , Matthew Robert Scott , Weipeng Liu , Xi Chen , Xi Chen
发明人： Chi-Ho Li , Weijiang Xu , Matthew Robert Scott , Weipeng Liu , Xi Chen , Xi Chen
IPC分类号： G06F17/30 , G06F3/0482
CPC分类号： G06F17/30675 , G06F3/0482 , G06F17/2785
摘要： Some implementations provide techniques and arrangements for semantic lexicon based processing, such as in an input method editor. In some instances, a semantic label may be received that is to be defined for a semantic lexicon and at least a first term may be identified as a positive or negative example of the semantic label. In response, some examples may label at least a second term in the semantic lexicon with the semantic label based at least in part on the identification of the first term as a positive or negative example of the semantic label.
摘要翻译：一些实现提供了基于语义词典的处理的技术和布置，例如在输入法编辑器中。在一些情况下，可以接收将为语义词典定义的语义标签，并且至少第一项可以被识别为语义标签的正或负例子。作为响应，一些示例可以至少部分地基于第一术语的标识作为语义标签的正或负例示，将具有语义标签的语义词典中的至少第二项标记为语义标签。

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