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

US20160132602A1 GUIDED SEARCH 审中-公开
标题翻译：指导搜索
公开(公告)号：US20160132602A1
公开(公告)日：2016-05-12
申请号：US14582065
申请日：2014-12-23
申请人： Kumaresh Pattabiraman , Nihit Desai , Daniel Tunkelang
发明人： Kumaresh Pattabiraman , Nihit Desai , Daniel Tunkelang
IPC分类号： G06F17/30 , G06Q50/00
摘要： Techniques for assisting a user in conducting a search for online content are described. According to various embodiments, a set of search results is generated, in response to a user search query. A list of candidate facet-value pairs, for inclusion in a suggestion facet user interface element for display in-line with the set of search results, is then accessed. The suggestion facet user interface element may be configured, upon user selection, to filter the set of search results based on the corresponding facet-value pair. Thereafter, win rate information identifying win rates associated with each of the candidate facet-value pairs is accessed. A specific one of the candidate facet-value pairs having the highest win rate is then selected for inclusion in the suggestion facet user interface element.
摘要翻译：描述了用于辅助用户进行在线内容搜索的技术。根据各种实施例，响应于用户搜索查询而生成一组搜索结果。然后访问候选面值对的列表，以便包含在用于与搜索结果集合一起显示的建议面用户界面元素中。建议小平面用户界面元素可以在用户选择时根据相应的面值对来过滤搜索结果集。此后，访问识别与每个候选面值对相关联的胜利率的胜率信息。然后选择具有最高胜率的候选面值对中的特定一个以包含在建议小平面用户界面元素中。

2. 发明申请

US20200234244A1 PROVIDING LIMITED PERMISSION LEVEL FUNCTIONALITY FOR LISTINGS IN A NETWORK 审中-公开
公开(公告)号：US20200234244A1
公开(公告)日：2020-07-23
申请号：US16255195
申请日：2019-01-23
申请人： Li Zhou , Chong Zhang , Andrew Walter Chimka , Kevin Chuang , Kumaresh Pattabiraman , Yixiao Lu , Chen Qian , George Pearman
发明人： Li Zhou , Chong Zhang , Andrew Walter Chimka , Kevin Chuang , Kumaresh Pattabiraman , Yixiao Lu , Chen Qian , George Pearman
IPC分类号： G06Q10/10
摘要： Disclosed are systems, methods, and non-transitory computer-readable media for providing profiles with limited permission level functionality in the network. In response to receiving a request to post the new employment listing, a collaboration system updates a permission list of the employment listing to provide a first user account with an administrator permission level in relation to the employment listing. The administrator permission level provides a first function and a second function in relation to the employment listing. The collaboration system receives a request to tag a second user account to the employment listing and updates the permission list to provide the second user account with a limited permission level in relation to the employment listing. The limited permission level provides the second user account with permission to perform the first function in relation to the employment listing but does not provide permission to perform the second function.

3. 发明授权

US08370337B2 Ranking search results using click-based data 有权
标题翻译：使用点击数据排名搜索结果
公开(公告)号：US08370337B2
公开(公告)日：2013-02-05
申请号：US12762929
申请日：2010-04-19
申请人： Tapas Kanungo , Kumaresh Pattabiraman , Nitin Agrawal , Kieran Richard McDonald , Christopher Avery Meyers , Nipoon Malhotra
发明人： Tapas Kanungo , Kumaresh Pattabiraman , Nitin Agrawal , Kieran Richard McDonald , Christopher Avery Meyers , Nipoon Malhotra
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06N99/005 , G06F17/30882
摘要： Methods and computer-storage media having computer-executable instructions embodied thereon that facilitate generating a machine-learned model for ranking search results using click-based data are provided. Data is referenced from user queries, which may include search results generated by general search engines and vertical search engines. A training set is generated from the search results and click-based judgments are associated with the search results in the training set. Based on click-based judgments, identifiable features are determined from the search results in a training set. Based on determining identifiable features in a training set, a rule set is generated for ranking subsequent search results.
摘要翻译：提供了具有其上包含计算机可执行指令的方法和计算机存储介质，其利用基于点击的数据便于生成用于对搜索结果进行排名的机器学习模型。数据来自用户查询，可能包括由一般搜索引擎和垂直搜索引擎生成的搜索结果。从搜索结果生成训练集，并且基于点击的判断与训练集中的搜索结果相关联。基于点击判断，可以从训练集中的搜索结果确定可识别的特征。基于确定训练集中的可识别特征，生成用于对后续搜索结果进行排序的规则集。

4. 发明申请

US20120143794A1 ANSWER MODEL COMPARISON 有权
标题翻译：解答模型比较
公开(公告)号：US20120143794A1
公开(公告)日：2012-06-07
申请号：US12959402
申请日：2010-12-03
申请人： Tapas Kanungo , Kuansan Wang , Ran Gilad-Bachrach , Kieran McDonald , Kumaresh Pattabiraman , Christopher Meyers , Ashok Ponnuswami , Luke Simon
发明人： Tapas Kanungo , Kuansan Wang , Ran Gilad-Bachrach , Kieran McDonald , Kumaresh Pattabiraman , Christopher Meyers , Ashok Ponnuswami , Luke Simon
IPC分类号： G06F15/18
CPC分类号： G06F17/30554
摘要： This patent application pertains to answer model comparison. One implementation can determine a first frequency at which an individual answer category appears in an individual slot on a query results page when utilizing a first model. The method can ascertain a second frequency at which the individual answer category appears in the individual slot on the query results page when utilizing a second model. The method can calibrate the second model so that the second frequency approaches the first frequency.
摘要翻译：该专利申请涉及回答模型比较。当使用第一模型时，一个实现可以确定在查询结果页面上的单个插槽中出现个人答案类别的第一频率。当使用第二模型时，该方法可以确定在查询结果页面上的个别插槽中出现个人答案类别的第二频率。该方法可以校准第二个模型，使得第二个频率接近第一个频率。

5. 发明申请

US20160132834A1 PERSONALIZED JOB SEARCH 审中-公开
标题翻译：个性化工作搜索
公开(公告)号：US20160132834A1
公开(公告)日：2016-05-12
申请号：US14863188
申请日：2015-09-23
申请人： Kumaresh Pattabiraman , Ganesh Venkataraman , Shakti Dhirendraji Sinha
发明人： Kumaresh Pattabiraman , Ganesh Venkataraman , Shakti Dhirendraji Sinha
IPC分类号： G06Q10/10 , G06F17/30
CPC分类号： G06Q10/1053 , G06F16/951
摘要： Techniques for assisting a user in conducting an online job search for online job listings are described. According to various embodiments, a user specification of a job search query including at least one user-specified job search query term is received. Values for one or more member profile attributes of the user are then accessed. Thereafter, the job search query is modified based on the accessed values for the member profile attributes of the user, the modifying comprising inserting job search query terms corresponding to the values for the member profile attributes into the job search query. Search results corresponding to job listings posted on the job search engine are then generated, based on the modified job search query. Further, one or more of the search results may be displayed, via a user interface.
摘要翻译：描述了用于协助用户进行在线工作搜索的在线工作清单的技术。根据各种实施例，接收包括至少一个用户指定的作业搜索查询项的作业搜索查询的用户指定。然后访问用户的一个或多个成员配置文件属性的值。此后，基于用户的成员简档属性的访问值修改作业搜索查询，修改包括将对应于成员简档属性的值的作业搜索查询术语插入到作业搜索查询中。然后根据修改的作业搜索查询生成与发布在作业搜索引擎上的作业列表相对应的搜索结果。此外，可以经由用户界面来显示搜索结果中的一个或多个。

6. 发明申请

US20160092571A1 SEARCH RELEVANCE 审中-公开
标题翻译：搜索相关
公开(公告)号：US20160092571A1
公开(公告)日：2016-03-31
申请号：US14581849
申请日：2014-12-23
申请人： Kumaresh Pattabiraman , Sachit Kamat , Eduardo Vivas
发明人： Kumaresh Pattabiraman , Sachit Kamat , Eduardo Vivas
IPC分类号： G06F17/30
CPC分类号： G06Q50/01 , G06F16/972 , G06Q30/0282
摘要： Systems, methods and a machine-readable media are described herein for a relevance booster module to calculate a relevance, with respect to at least one characteristic of a query, of each piece of content in a set of collected content and a set of premium content. The relevance booster module increases a calculated relevance of at least one piece of content in the set of premium content. The relevance booster module generates a list in which each piece of content in the set of collected content and the set of premium content is ranked according to a respective calculated relevance.
摘要翻译：本文描述了系统，方法和机器可读介质，用于相关性增强模块，以针对一组收集的内容和一组优质内容中的每条内容来计算关于查询的至少一个特征的相关性。相关性增强模块增加了该组优质内容中至少一片内容的计算的相关性。相关性增强模块生成列表，其中收集的内容集合中的每条内容和优质内容集合根据各自计算的相关性进行排名。

7. 发明授权

US08554700B2 Answer model comparison 有权
标题翻译：答案模式比较
公开(公告)号：US08554700B2
公开(公告)日：2013-10-08
申请号：US12959402
申请日：2010-12-03
申请人： Tapas Kanungo , Kuansan Wang , Ran Gilad-Bachrach , Kieran McDonald , Kumaresh Pattabiraman , Christopher Meyers , Ashok Ponnuswami , Luke Simon
发明人： Tapas Kanungo , Kuansan Wang , Ran Gilad-Bachrach , Kieran McDonald , Kumaresh Pattabiraman , Christopher Meyers , Ashok Ponnuswami , Luke Simon
IPC分类号： G06F15/18
CPC分类号： G06F17/30554
摘要： This patent application pertains to answer model comparison. One implementation can determine a first frequency at which an individual answer category appears in an individual slot on a query results page when utilizing a first model. The method can ascertain a second frequency at which the individual answer category appears in the individual slot on the query results page when utilizing a second model. The method can calibrate the second model so that the second frequency approaches the first frequency.
摘要翻译：该专利申请涉及回答模型比较。当使用第一模型时，一个实现可以确定在查询结果页面上的单个插槽中出现个人答案类别的第一频率。当使用第二模型时，该方法可以确定在查询结果页面上的个别插槽中出现个人答案类别的第二频率。该方法可以校准第二个模型，使得第二个频率接近第一个频率。

8. 发明申请

US20110258149A1 RANKING SEARCH RESULTS USING CLICK-BASED DATA 有权
标题翻译：使用基于点的数据排列搜索结果
公开(公告)号：US20110258149A1
公开(公告)日：2011-10-20
申请号：US12762929
申请日：2010-04-19
申请人： TAPAS KANUNGO , KUMARESH PATTABIRAMAN , NITIN AGRAWAL , KIERAN RICHARD McDONALD , CHRISTOPHER AVERY MEYERS , NIPOON MALHOTRA
发明人： TAPAS KANUNGO , KUMARESH PATTABIRAMAN , NITIN AGRAWAL , KIERAN RICHARD McDONALD , CHRISTOPHER AVERY MEYERS , NIPOON MALHOTRA
IPC分类号： G06F15/18 , G06F17/30
CPC分类号： G06N99/005 , G06F17/30882
摘要： Methods and computer-storage media having computer-executable instructions embodied thereon that facilitate generating a machine-learned model for ranking search results using click-based data are provided. Data is referenced from user queries, which may include search results generated by general search engines and vertical search engines. A training set is generated from the search results and click-based judgments are associated with the search results in the training set. Based on click-based judgments, identifiable features are determined from the search results in a training set. Based on determining identifiable features in a training set, a rule set is generated for ranking subsequent search results.
摘要翻译：提供了具有其上包含计算机可执行指令的方法和计算机存储介质，其利用基于点击的数据便于生成用于对搜索结果进行排名的机器学习模型。数据来自用户查询，可能包括由一般搜索引擎和垂直搜索引擎生成的搜索结果。从搜索结果生成训练集，并且基于点击的判断与训练集中的搜索结果相关联。基于点击判断，可以从训练集中的搜索结果确定可识别的特征。基于确定训练集中的可识别特征，生成用于对后续搜索结果进行排序的规则集。

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