公开(公告)号：US20130041878A1

公开(公告)日：2013-02-14

申请号：US13207595

申请日：2011-08-11

申请人： ASHWIN SATYANARAYANA ,  TABREEZ GOVANI ,  SAMIR SHIRAZ PRADHAN ,  BODO VON BILLERBECK ,  NITIN AGRAWAL

发明人： ASHWIN SATYANARAYANA ,  TABREEZ GOVANI ,  SAMIR SHIRAZ PRADHAN ,  BODO VON BILLERBECK ,  NITIN AGRAWAL

IPC分类号： G06F17/30

CPC分类号： G06F16/3322 ,  G06F16/90324

摘要： Methods, systems, and computer-readable media for suggesting search queries to a user while the user is typing in characters of a search query. The suggested search queries are based in part on the characters entered and are presented before the user submits the query to the search engine. The suggested queries may be displayed in a dropdown box that allows the user to select one of the suggested queries. Embodiments of the present invention present search queries that do not begin with the characters entered by the user.

摘要翻译： 方法，系统和计算机可读介质，用于在用户输入搜索查询的字符时向用户建议搜索查询。 建议的搜索查询部分基于输入的字符，并在用户将查询提交给搜索引擎之前呈现。 建议的查询可能会显示在允许用户选择其中一个建议查询的下拉框中。 本发明的实施例提出了不以用户输入的字符开始的搜索查询。

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。

公开(公告)号：US20130086509A1

公开(公告)日：2013-04-04

申请号：US13248261

申请日：2011-09-29

申请人： ASHWIN SATYANARAYANA ,  TABREEZ GOVANI ,  SAMIR SHIRAZ PRADHAN ,  GIRIDHAR KUMARAN ,  XIN FU ,  FENG PAN ,  NITIN AGRAWAL

发明人： ASHWIN SATYANARAYANA ,  TABREEZ GOVANI ,  SAMIR SHIRAZ PRADHAN ,  GIRIDHAR KUMARAN ,  XIN FU ,  FENG PAN ,  NITIN AGRAWAL

IPC分类号： G06F17/30 ,  G06F3/048

CPC分类号： G06F16/3322

摘要： Computer-readable media, computer systems, and computing devices method of facilitating presentation of alternative query suggestions. The method includes referencing an initial query having a plurality of terms. A term(s) to remove from the initial query is identified, for example, based at least on a number of times the term(s) occur in previous queries. The initial query is modified by removing the term(s) from the initial query. Thereafter, the modified query is used to identify an alternative query suggestion(s) that includes at least one term that matches at least one term of the modified query.

摘要翻译： 计算机可读介质，计算机系统和计算设备方便的替代查询建议的呈现。 该方法包括引用具有多个项的初始查询。 识别从初始查询中移除的术语，例如至少基于先前查询中出现的术语的次数。 通过从初始查询中删除术语来修改初始查询。 此后，修改的查询用于标识包括与修改的查询的至少一个项匹配的至少一个项的替代查询建议。

公开(公告)号：US20100211561A1

公开(公告)日：2010-08-19

申请号：US12371242

申请日：2009-02-13

申请人： KEMP CROCKETT PETERSON ,  JAMES NICHOLS ,  ALFIAN TAN ,  JARED LEE REISINGER ,  TABREEZ GOVANI ,  ANTHONY TRAN ,  NITIN AGRAWAL

发明人： KEMP CROCKETT PETERSON ,  JAMES NICHOLS ,  ALFIAN TAN ,  JARED LEE REISINGER ,  TABREEZ GOVANI ,  ANTHONY TRAN ,  NITIN AGRAWAL

IPC分类号： G06F17/30

CPC分类号： G06F16/9038

摘要： Systems, methods, and computer storage media having computer-executable instructions embodied thereon that provide representative samples among search result sets are provided. Upon receiving a query, it is recognized whether to present a representative sample, or an indication thereof, along with a search result that relates to the query. Search results related to the query are presented to the user. A portion of the search results might include a representative sample, or an indication thereof. Such a representative sample might summarize a media object(s) associated with the search result presented.

摘要翻译： 提供了具有在其上实现的具有在搜索结果集中提供代表性样本的计算机可执行指令的系统，方法和计算机存储介质。 在接收到查询时，识别是否呈现代表性样本或其指示，以及与查询相关的搜索结果。 与查询相关的搜索结果呈现给用户。 搜索结果的一部分可能包括代表性样本或其指示。 这样的代表性样本可以概括与所呈现的搜索结果相关联的媒体对象。

公开(公告)号：US20090299964A1

公开(公告)日：2009-12-03

申请号：US12130212

申请日：2008-05-30

申请人： MICHAEL MAXWELL CAMERON ,  HUGH EVAN WILLIAMS ,  SRINATH REDDY AALETI ,  NITIN AGRAWAL ,  TABREEZ GOVANI

发明人： MICHAEL MAXWELL CAMERON ,  HUGH EVAN WILLIAMS ,  SRINATH REDDY AALETI ,  NITIN AGRAWAL ,  TABREEZ GOVANI

IPC分类号： G06F17/30

CPC分类号： G06F16/951

摘要： A method and medium are provided for determining whether search queries issued to a search engine are navigational search queries and displaying related search queries and corresponding URLs in association with a URL corresponding to a target of the navigational search query. One embodiment of the method includes receiving a query log and determining whether search queries are navigational search queries based on a comparison of URLs selected in response to the search queries. A set of related navigational queries and corresponding URLs is then compiled by analyzing the query log. The set can comprise search queries issued within a predetermined period of time from the receipt of a navigational search query. Search queries are filtered from the set if they are not navigational search queries. The set of related search queries and corresponding URLs is presented in association with the URL corresponding to the navigational search query.

摘要翻译： 提供了一种方法和介质，用于确定发出到搜索引擎的搜索查询是否是导航搜索查询，并且与对应于导航搜索查询的目标的URL相关联地显示相关搜索查询和对应的URL。 该方法的一个实施例包括：基于响应于搜索查询而选择的URL的比较，接收查询日志并确定搜索查询是否是导航搜索查询。 然后通过分析查询日志来编译一组相关的导航查询和相应的URL。 该集合可以包括从接收导航搜索查询的预定时间段内发出的搜索查询。 如果搜索查询不是导航搜索查询，则会从集合中过滤搜索查询。 该相关搜索查询和相应的URL与对应于导航搜索查询的URL相关联地呈现。

公开(公告)号：US20090182725A1

公开(公告)日：2009-07-16

申请号：US12013275

申请日：2008-01-11

申请人： TABREEZ GOVANI ,  HUGH WILLIAMS ,  JAMIE BUCKLEY ,  NITIN AGRAWAL ,  ANDY LAM ,  KENNETH A. MOSS

发明人： TABREEZ GOVANI ,  HUGH WILLIAMS ,  JAMIE BUCKLEY ,  NITIN AGRAWAL ,  ANDY LAM ,  KENNETH A. MOSS

IPC分类号： G06F17/30

CPC分类号： G06F17/3053 ,  G06F17/30864

摘要： Systems, methods, and computer-readable media for determining the Internet search popularity of an entity are provided. Embodiments of the present invention include receiving a group of Internet search records and assigning a popularity ranking based on the number of times an entity descriptor associated with an entity occurs within the group of Internet search records created over a designated time period. An entity descriptor is one or more terms commonly used to identify an entity. The trend in an entity's popularity rank may also be calculated. An entity's popularity rank and trend in popularity rank may be presented in a graph or in a list.

摘要翻译： 提供了用于确定实体的因特网搜索流行度的系统，方法和计算机可读介质。 本发明的实施例包括接收一组因特网搜索记录，并且基于在指定时间段内创建的因特网搜索记录组内发生与实体相关联的实体描述符的次数来分配流行度排序。 实体描述符是通常用于标识实体的一个或多个术语。 实体流行度的趋势也可能被计算出来。 实体的人气排名和流行度排名趋势可以以图表或列表形式呈现。