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

US08266141B2 Efficient use of computational resources for interleaving 有权
标题翻译：有效利用计算资源进行交织
公开(公告)号：US08266141B2
公开(公告)日：2012-09-11
申请号：US12964346
申请日：2010-12-09
申请人： Filip Radlinski , Nick Craswell , Peter Bailey , Daniel Schwartz , Aidan Crook , Likhita Krishnamurthy
发明人： Filip Radlinski , Nick Craswell , Peter Bailey , Daniel Schwartz , Aidan Crook , Likhita Krishnamurthy
IPC分类号： G06F17/30
CPC分类号： G06F17/30867
摘要： Methods and computer-readable media are provided for improving the efficiency of the interleaving process. Once it is determined that a search query is to be used in an interleaving experiment, a primary ranking system and a secondary ranking system are analyzed to determine whether their respective search results for that search query would be identical. If the search results would be identical, the search query is routed only to the primary ranking system and not the secondary ranking system. If, however, it is determined that the search results would not be identical, both the primary ranking system and the secondary ranking system receive the search query for processing.
摘要翻译：提供了用于提高交错处理效率的方法和计算机可读介质。一旦确定在交织实验中使用搜索查询，则分析主要排名系统和次级排名系统以确定其针对该搜索查询的各自的搜索结果是否相同。如果搜索结果相同，则搜索查询仅被路由到主要排名系统而不是辅助排名系统。然而，如果确定搜索结果不相同，则主要排名系统和次级排名系统都接收用于处理的搜索查询。

2. 发明申请

US20120150837A1 OPTIMIZING BLENDING ALGORITHMS USING INTERLEAVING 有权
标题翻译：优化使用交互的混合算法
公开(公告)号：US20120150837A1
公开(公告)日：2012-06-14
申请号：US12964353
申请日：2010-12-09
申请人： FILIP RADLINSKI , NICK CRASWELL , PETER BAILEY
发明人： FILIP RADLINSKI , NICK CRASWELL , PETER BAILEY
IPC分类号： G06F17/30
CPC分类号： G06F17/30864
摘要： Methods and computer-readable media are provided for interleaving multiple sets of blended search results to identify a preferred set of blended search results for a search query or for a category of search queries. A search query is received and routed to multiple ranking systems, which return search results that are blended into sets of blended search results. Interleaving experiments are performed to determined, based on user preferences, which set of blended search results are preferred for that particular search query. Based on the outcome, a preferred blending algorithm is identified.
摘要翻译：提供方法和计算机可读介质用于交织多组混合搜索结果以识别用于搜索查询或搜索查询类别的混合搜索结果的优选集合。搜索查询被接收并被路由到多个排名系统，这些系统返回混合到混合搜索结果集合中的搜索结果。执行交织实验以基于用户偏好确定哪一组混合搜索结果对于该特定搜索查询是优选的。基于结果，确定了优选的混合算法。

3. 发明申请

US20080201315A1 CONTENT ITEM QUERY FORMULATION 有权
标题翻译：内容项查询配方
公开(公告)号：US20080201315A1
公开(公告)日：2008-08-21
申请号：US11677180
申请日：2007-02-21
申请人： Ariel Lazier , Hugh J. Williams , Nick Craswell , Charles Clarke , Julie H. Farago
发明人： Ariel Lazier , Hugh J. Williams , Nick Craswell , Charles Clarke , Julie H. Farago
IPC分类号： G06F7/00
CPC分类号： G06F17/30646 , G06F3/04812 , G06F3/04817 , G06F3/04855 , G06F17/30864 , Y10S707/99943
摘要： A system and method for formulating a related content query are provided. A search engine receives queries having terms for content items and stores the queries and user interaction data in a query log. Also, the search engine provides a collection of content items and related content item queries for each content item within the collection of content items, in response the queries. Each content item in the collection of content items includes terms that match the received queries. The related content item queries are generated by an advisor engine that processes the query log and each content item in the collection of content items to select query terms, different from the received query terms, which previously resulted in a specified content item being accessed or selected.
摘要翻译：提供了一种用于制定相关内容查询的系统和方法。搜索引擎接收具有内容项的术语的查询，并将查询和用户交互数据存储在查询日志中。此外，响应于查询，搜索引擎为内容项集合内的每个内容项目提供内容项集合和相关内容项查询。内容项集合中的每个内容项包括与接收的查询相匹配的条款。相关内容项查询由处理查询日志和内容项集合中的每个内容项的顾问引擎生成，以选择与接收的查询术语不同的查询词，其先前导致被访问或选择的指定内容项。

4. 发明授权

US08484202B2 Optimizing blending algorithms using interleaving 有权
标题翻译：使用交错优化混合算法
公开(公告)号：US08484202B2
公开(公告)日：2013-07-09
申请号：US12964353
申请日：2010-12-09
申请人： Filip Radlinski , Nick Craswell , Peter Bailey
发明人： Filip Radlinski , Nick Craswell , Peter Bailey
IPC分类号： G06F7/06
CPC分类号： G06F17/30864
摘要： Methods and computer-readable media are provided for interleaving multiple sets of blended search results to identify a preferred set of blended search results for a search query or for a category of search queries. A search query is received and routed to multiple ranking systems, which return search results that are blended into sets of blended search results. Interleaving experiments are performed to determined, based on user preferences, which set of blended search results are preferred for that particular search query. Based on the outcome, a preferred blending algorithm is identified.
摘要翻译：提供方法和计算机可读介质用于交织多组混合搜索结果以识别用于搜索查询或搜索查询类别的混合搜索结果的优选集合。搜索查询被接收并被路由到多个排名系统，这些系统返回混合到混合搜索结果集合中的搜索结果。执行交织实验以基于用户偏好确定哪一组混合搜索结果对于该特定搜索查询是优选的。基于结果，确定了优选的混合算法。

5. 发明申请

US20110307482A1 SEARCH RESULT DRIVEN QUERY INTENT IDENTIFICATION 审中-公开
标题翻译：搜索结果驱动查询功能标识
公开(公告)号：US20110307482A1
公开(公告)日：2011-12-15
申请号：US12813376
申请日：2010-06-10
申请人： FILIP RADLINSKI , NICK CRASWELL , BODO BILLERBECK , MILAD SHOKOUHI , SANAZ AHARI , NITIN AGRAWAL , TIMOTHY HOAD , SONG ZHOU , MUHAMMAD AATIF AWAN , YATHARTH SARAF
发明人： FILIP RADLINSKI , NICK CRASWELL , BODO BILLERBECK , MILAD SHOKOUHI , SANAZ AHARI , NITIN AGRAWAL , TIMOTHY HOAD , SONG ZHOU , MUHAMMAD AATIF AWAN , YATHARTH SARAF
IPC分类号： G06F17/30 , G06F3/048
CPC分类号： G06F16/9535
摘要： A system and method are provided for detecting entity information contained within search results. The detected entity information can be used to determine a category of entity as well as a specific entity within the search results. The entity information can be used to alter the style and/or format of the presented results based the detected entity category.
摘要翻译：提供了一种用于检测搜索结果中包含的实体信息的系统和方法。检测到的实体信息可用于确定搜索结果内的实体类别以及特定实体。实体信息可以用于基于检测到的实体类别来改变呈现结果的风格和/或格式。

6. 发明申请

US20110289063A1 Query Intent in Information Retrieval 有权
标题翻译：信息检索中的查询意图
公开(公告)号：US20110289063A1
公开(公告)日：2011-11-24
申请号：US12784869
申请日：2010-05-21
申请人： Filip Radlinski , Martin Szummer , Nick Craswell
发明人： Filip Radlinski , Martin Szummer , Nick Craswell
IPC分类号： G06F17/30 , G06F17/21
CPC分类号： G06F17/30864 , G06Q30/00
摘要： Inferring query intent in information retrieval is described. In an example reformulations of an initial query by a user are used to create a query neighborhood. In the example, the query neighborhood is used to identify a set of possibly related queries. First and higher order reformulations of the initial query may be used to expand the query neighborhood. In an example precision can be improved by reducing the query neighborhood to more closely related queries for example, two queries can be connected if they are often clicked for the same document. In an example two queries can be connected using a random walk and all pairs of queries that are not connected by a random walk of less than a fixed threshold are removed. The connected queries can be used to form clusters and weights can be applied in order to determine the most likely related queries.
摘要翻译：描述信息检索中的查询意图。在一个示例中，用户初始查询的重新组合用于创建查询邻域。在该示例中，查询邻域用于标识一组可能相关的查询。可以使用初始查询的第一和更高阶重新格式来扩展查询邻域。在一个示例中，可以通过将查询邻域减少到更密切相关的查询来提高精度，例如，如果经常为同一文档点击，则可以连接两个查询。在一个示例中，可以使用随机游走连接两个查询，并且去除不通过小于固定阈值的随机游走连接的所有查询对。连接的查询可以用于形成群集，并且可以应用权重以便确定最可能的相关查询。

7. 发明授权

US07647338B2 Content item query formulation 有权
标题翻译：内容项查询制定
公开(公告)号：US07647338B2
公开(公告)日：2010-01-12
申请号：US11677180
申请日：2007-02-21
申请人： Ariel Lazier , Hugh J. Williams , Nick Craswell , Charles Clarke , Julia H. Farago
发明人： Ariel Lazier , Hugh J. Williams , Nick Craswell , Charles Clarke , Julia H. Farago
IPC分类号： G06F17/00
CPC分类号： G06F17/30646 , G06F3/04812 , G06F3/04817 , G06F3/04855 , G06F17/30864 , Y10S707/99943
摘要： A system and method for formulating a related content query are provided. A search engine receives queries having terms for content items and stores the queries and user interaction data in a query log. Also, the search engine provides a collection of content items and related content item queries for each content item within the collection of content items, in response the queries. Each content item in the collection of content items includes terms that match the received queries. The related content item queries are generated by an advisor engine that processes the query log and each content item in the collection of content items to select query terms, different from the received query terms, which previously resulted in a specified content item being accessed or selected.
摘要翻译：提供了一种用于制定相关内容查询的系统和方法。搜索引擎接收具有内容项的术语的查询，并将查询和用户交互数据存储在查询日志中。此外，响应于查询，搜索引擎为内容项集合内的每个内容项目提供内容项集合和相关内容项查询。内容项集合中的每个内容项包括与接收的查询相匹配的条款。相关内容项查询由处理查询日志和内容项集合中的每个内容项的顾问引擎生成，以选择与接收的查询术语不同的查询词，其先前导致被访问或选择的指定内容项。

8. 发明授权

US08380723B2 Query intent in information retrieval 有权
标题翻译：查询信息检索意图
公开(公告)号：US08380723B2
公开(公告)日：2013-02-19
申请号：US12784869
申请日：2010-05-21
申请人： Filip Radlinski , Martin Szummer , Nick Craswell
发明人： Filip Radlinski , Martin Szummer , Nick Craswell
IPC分类号： G06F17/30
CPC分类号： G06F17/30864 , G06Q30/00
摘要： Inferring query intent in information retrieval is described. In an example reformulations of an initial query by a user are used to create a query neighborhood. In the example, the query neighborhood is used to identify a set of possibly related queries. First and higher order reformulations of the initial query may be used to expand the query neighborhood. In an example precision can be improved by reducing the query neighborhood to more closely related queries for example, two queries can be connected if they are often clicked for the same document. In an example two queries can be connected using a random walk and all pairs of queries that are not connected by a random walk of less than a fixed threshold are removed. The connected queries can be used to form clusters and weights can be applied in order to determine the most likely related queries.
摘要翻译：描述信息检索中的查询意图。在一个示例中，用户初始查询的重新组合用于创建查询邻域。在该示例中，查询邻域用于标识一组可能相关的查询。可以使用初始查询的第一和更高阶重新格式来扩展查询邻域。在一个示例中，可以通过将查询邻域减少到更密切相关的查询来提高精度，例如，如果经常为同一文档点击，则可以连接两个查询。在一个示例中，可以使用随机游走连接两个查询，并且去除不通过小于固定阈值的随机游走连接的所有查询对。连接的查询可以用于形成群集，并且可以应用权重以便确定最可能的相关查询。

9. 发明授权

US09158846B2 Entity detection and extraction for entity cards 有权
标题翻译：实体卡的实体检测和提取
公开(公告)号：US09158846B2
公开(公告)日：2015-10-13
申请号：US12813390
申请日：2010-06-10
申请人： Filip Radlinski , Nick Craswell , Bodo Billerbeck , Milad Shokouhi , Sanaz Ahari , Nitin Agrawal , Timothy Hoad , Song Zhou , Muhammad Aatif Awan
发明人： Filip Radlinski , Nick Craswell , Bodo Billerbeck , Milad Shokouhi , Sanaz Ahari , Nitin Agrawal , Timothy Hoad , Song Zhou , Muhammad Aatif Awan
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06F17/3053 , G06F17/30477 , G06F17/30554 , G06F17/30864 , G06F17/30867
摘要： A system and method are provided for detecting entity information contained within search results. The detected entity information can be used to determine a category of entity as well as a specific entity within the search results. Entity information can be extracted from the documents associated with the search results. This information can be used as part of the information for an entity card, which can be displayed to a user in conjunction with and/or in place of the search results.
摘要翻译：提供了一种用于检测搜索结果中包含的实体信息的系统和方法。检测到的实体信息可用于确定搜索结果内的实体类别以及特定实体。可以从与搜索结果相关联的文档中提取实体信息。该信息可以用作实体卡的信息的一部分，其可以结合使用和/或代替搜索结果显示给用户。

10. 发明授权

US08706725B2 Ranking contextual signals for search personalization 有权
标题翻译：排名搜索个性化的上下文信号
公开(公告)号：US08706725B2
公开(公告)日：2014-04-22
申请号：US13047466
申请日：2011-03-14
申请人： Peter R. Bailey , Sebastian De La Chica , Aidan Crook , Nikhil B. Dandekar , Daniel R. Schwartz , William D. Ramsey , Nick Craswell
发明人： Peter R. Bailey , Sebastian De La Chica , Aidan Crook , Nikhil B. Dandekar , Daniel R. Schwartz , William D. Ramsey , Nick Craswell
IPC分类号： G06F17/30
CPC分类号： G06F17/30675
摘要： Methods are provided for re-ranking documents based on user-specific features. Search results are received from a non-contextual ranking system such that the search results are not specific toward a particular user, such as the user who submitted the search query. Contextual signals are received and provide user-specific features that are used to re-rank documents so that the most important and relevant documents are listed at the top of the list of search results. Each of the user-specific features are evaluated and compared to determine a new position of each document. A set of contextual search results is then generated based on the new positions.
摘要翻译：提供了基于用户特定功能重新排列文档的方法。从非上下文排序系统接收搜索结果，使得搜索结果不是特定于特定用户，例如提交搜索查询的用户。接收到上下文信号，并提供用于对文档进行重新排序的用户特定功能，以便最重要和相关的文档列在搜索结果列表的顶部。每个用户特定的特征被评估和比较以确定每个文档的新位置。然后基于新的位置生成一组上下文搜索结果。

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