-
公开(公告)号：US20180114108A1
公开(公告)日：2018-04-26
申请号：US15787615
申请日：2017-10-18
Applicant: Google Inc.
Inventor： Ni Lao , Lukasz Mieczyslaw Kaiser , Nitin Gupta , Afroz Mohiuddin , Preyas Popat
CPC classification number: G06N3/006 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06N5/04
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying answers to questions using neural networks. One of the methods includes receiving an input text passage and an input question string; processing the input text passage using an encoder neural network to generate a respective encoded representation for each passage token in the input text passage; at each time step: processing a decoder input using a decoder neural network to update the internal state of the decoder neural network; and processing the respective encoded representations and a preceding output of the decoder neural network using a matching vector neural network to generate a matching vector for the time step; and generating an answer score that indicates how well the input text passage answers a question posed by the input question string.
-
公开(公告)号：US20170011116A1
公开(公告)日：2017-01-12
申请号：US15195364
申请日：2016-06-28
Applicant: Google Inc.
Inventor： Yi Liu , Preyas Popat , Nitin Gupta , Afroz Mohiuddin
IPC: G06F17/30
CPC classification number: G06F16/3334 , G06F16/3329 , G06F16/35
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to answer-seeking queries. One of the methods includes receiving a query having multiple terms. The query is classified as an answer-seeking query of a particular question type, and one or more answer types associated with the particular question type are obtained. Search results satisfying the query are obtained, and a respective score is computed for each of one or more passages of text occurring in each document identified by the search results, wherein the score for each passage of text is based on how many of the one or more answer types match the passage of text. A presentation that includes information from one or more of the passages of text selected based on the respective score is provided in response to the query.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于产生答案查询的答案。 其中一种方法包括接收具有多个术语的查询。 查询被分类为特定问题类型的答案寻求查询，并且获得与特定问题类型相关联的一个或多个答案类型。 获得满足查询的搜索结果，并且针对由搜索结果识别的每个文档中出现的每个文本中的每一个文本的每一个计算相应的分数，其中每次文本通过的分数基于一个或多个 更多的答案类型与文本的通过相符。 响应于该查询，提供包括基于相应分数所选择的一个或多个文本段落的信息的演示文稿。
-
3.发明授权公开(公告)号：US09405834B1
公开(公告)日：2016-08-02
申请号：US13666930
申请日：2012-11-01
Applicant: GOOGLE INC.
Inventor： Abhinandan Sujit Das , Anwis Das , Nitin Gupta
IPC: G06F17/30
CPC classification number: G06F17/30864
Abstract: A computer-implemented method for identifying related search queries is performed on a server. The method includes receiving a search query from a user, identifying a set of ranked search results satisfying the search query, and identifying, using historical search query data, at least one last related search query in at least one chain of related search queries that is related to the search query and that includes at least one search result that was selected by users who issued the search query, each respective related search query in the at least one chain of related search queries except for the at least one last related search query in the at least one chain of related search queries violating a search result selection criterion. The method further includes returning the set of ranked search results and the at least one last related search query to the user.
Abstract translation: 在服务器上执行用于识别相关搜索查询的计算机实现的方法。 该方法包括从用户接收搜索查询，识别满足搜索查询的一组排名的搜索结果，以及使用历史搜索查询数据在至少一个相关搜索查询链中识别至少一个最后相关的搜索查询，该搜索查询是 与所述搜索查询相关并且包括由发布所述搜索查询的用户选择的至少一个搜索结果，所述至少一个相关搜索查询链中的每个相关搜索查询除了所述至少一个最后相关搜索查询之外 所述至少一个相关搜索查询链违反搜索结果选择标准。 该方法还包括将一组排名的搜索结果和至少一个最后相关的搜索查询返回给用户。
-
4.发明授权公开(公告)号：US09342626B1
公开(公告)日：2016-05-17
申请号：US14038392
申请日：2013-09-26
Applicant: Google Inc.
Inventor： Anwis Das , Abhinandan Sujit Das , Nitin Gupta , Renshen Wang
IPC: G06F17/30
CPC classification number: G06F17/3097
Abstract: Methods and apparatus for providing query suggestions to a user based on one or more past queries submitted by the user. Candidate query suggestions responsive to a current query may be identified. A candidate query similarity measure may be determined for a given candidate query suggestion based on matching entities related to the given candidate query suggestion and the one or more past queries. In some implementations, the similarity measure of the given candidate query suggestion may be based on a comparison of current entities of the given candidate query suggestion that match entities of one or more past queries, to a group of the current entities that includes entities that do not match the entities of one or more past queries. In some implementations a ranking of the candidate query suggestions may be determined based on the similarity measure.
Abstract translation: 基于用户提交的一个或多个过去查询向用户提供查询建议的方法和装置。 可以识别响应于当前查询的候选查询建议。 可以基于与给定候选查询建议相关联的匹配实体和一个或多个过去查询来确定给定候选查询建议的候选查询相似性度量。 在一些实现中，给定候选查询建议的相似性度量可以基于将与一个或多个过去查询的实体相匹配的给定候选查询建议的当前实体与包括实体的当前实体的组的比较 不符合一个或多个过去查询的实体。 在一些实现中，可以基于相似性度量来确定候选查询建议的排名。
-
公开(公告)号：US09898554B2
公开(公告)日：2018-02-20
申请号：US14083057
申请日：2013-11-18
Applicant: Google Inc.
Inventor： Nitin Gupta , Preyas Popat , Steven D. Baker , Srinivasan Venkatachary
CPC classification number: G06F17/30967
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying implicit question queries. In one aspect, a method includes receiving a query in unstructured form, comparing terms of the query to query templates, determining, based on the comparison, a match of the query terms to a first query template, wherein the first query template is not determined to be indicative of a question query, determining, based on the first query template, a second query template, and determining that the query is an implicit question query in response to the second query template being indicative of a question queries.
-
Patent Agency Ranking
公开(公告)号：US09436747B1
公开(公告)日：2016-09-06
申请号：US14750483
申请日：2015-06-25
Applicant: Google Inc.
Inventor： Steven D. Baker , Michael E. Flaster , Nitin Gupta , Paul Haahr , Srinivasan Venkatachary , Yonghui Wu
CPC classification number: G06F17/30563 , G06F17/248 , G06F17/30389 , G06F17/3064 , G06F17/30864
Abstract: Methods, systems, and apparatus, including computer program products, for generating synthetic queries using seed queries and structural similarity between documents are described. In one aspect, a method includes identifying embedded coding fragments (e.g., HTML tag) from a structured document and a seed query; generating one or more query templates, each query template corresponding to at least one coding fragment, the query template including a generative rule to be used in generating candidate synthetic queries; generating the candidate synthetic queries by applying the query templates to other documents that are hosted on the same web site as the document; identifying terms that match structure of the query templates as candidate synthetic queries; measuring a performance for each of the candidate synthetic queries; and designating as synthetic queries the candidate synthetic queries that have performance measurements exceeding a performance threshold.
-
公开(公告)号：US09298852B2
公开(公告)日：2016-03-29
申请号：US13928868
申请日：2013-06-27
Applicant: GOOGLE INC.
Inventor： Emanuel Taropa , Jeffrey A. Dean , Simon Tong , Nitin Gupta , Noam M. Shazeer , Anwis Das , Murtaza A. Basrai
CPC classification number: G06F17/3097 , G06F17/3064 , G06F17/30646 , G06F17/30672
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reranking query completions based on activity session data. One of the methods includes receiving a query prefix from a user. Query completions are obtained for the query prefix. One or more likely queries that are likely to co-occur with a reference query in user activity sessions are obtained. If one of the likely queries matches one of the query completions, a modified ranking of the query completions is determined, including boosting a ranking of matching query completions. The modified ranking of the query completions is provided in response to receiving the query prefix.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于基于活动会话数据重新排列查询完成。 其中一种方法包括从用户接收查询前缀。 获取查询前缀的查询完成。 获得在用户活动会话中可能与参考查询共存的一个或多个可能的查询。 如果一个可能的查询与其中一个查询完成相匹配，则确定查询完成的修改排名，包括提升匹配查询完成的排名。 响应于接收查询前缀而提供查询完成的修改排名。
-
公开(公告)号：US20150169578A1
公开(公告)日：2015-06-18
申请号：US13928868
申请日：2013-06-27
Applicant: GOOGLE INC.
Inventor： Emanuel Taropa , Jeffrey A. Dean , Simon Tong , Nitin Gupta , Noam M. Shazeer , Anwis Das , Murtaza A. Basrai
IPC: G06F17/30
CPC classification number: G06F17/3097 , G06F17/3064 , G06F17/30646 , G06F17/30672
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reranking query completions based on activity session data. One of the methods includes receiving a query prefix from a user. Query completions are obtained for the query prefix. One or more likely queries that are likely to co-occur with a reference query in user activity sessions are obtained. If one of the likely queries matches one of the query completions, a modified ranking of the query completions is determined, including boosting a ranking of matching query completions. The modified ranking of the query completions is provided in response to receiving the query prefix.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于基于活动会话数据重新排列查询完成。 其中一种方法包括从用户接收查询前缀。 获取查询前缀的查询完成。 获得在用户活动会话中可能与参考查询共存的一个或多个可能的查询。 如果一个可能的查询与其中一个查询完成相匹配，则确定查询完成的修改排名，包括提升匹配查询完成的排名。 响应于接收查询前缀而提供查询完成的修改排名。
-
公开(公告)号：US11093813B2
公开(公告)日：2021-08-17
申请号：US15787615
申请日：2017-10-18
Applicant: Google Inc.
Inventor： Ni Lao , Lukasz Mieczyslaw Kaiser , Nitin Gupta , Afroz Mohiuddin , Preyas Popat
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying answers to questions using neural networks. One of the methods includes receiving an input text passage and an input question string; processing the input text passage using an encoder neural network to generate a respective encoded representation for each passage token in the input text passage; at each time step: processing a decoder input using a decoder neural network to update the internal state of the decoder neural network; and processing the respective encoded representations and a preceding output of the decoder neural network using a matching vector neural network to generate a matching vector for the time step; and generating an answer score that indicates how well the input text passage answers a question posed by the input question string.
-
公开(公告)号：US10360225B1
公开(公告)日：2019-07-23
申请号：US15155421
申请日：2016-05-16
Applicant: Google Inc.
Inventor： Anwis Das , Abhinandan Sujit Das , Nitin Gupta , Renshen Wang
IPC: G06F16/2457 , G06F16/9535
Abstract: Methods and apparatus for providing query suggestions to a user based on one or more past queries submitted by the user. Candidate query suggestions responsive to a current query may be identified. A candidate query similarity measure may be determined for a given candidate query suggestion based on matching entities related to the given candidate query suggestion and the one or more past queries. In some implementations, the similarity measure of the given candidate query suggestion may be based on a comparison of current entities of the given candidate query suggestion that match entities of one or more past queries, to a group of the current entities that includes entities that do not match the entities of one or more past queries. In some implementations a ranking of the candidate query suggestions may be determined based on the similarity measure.
-
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.027 seconds)
