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

US09812123B1 Background audio identification for speech disambiguation 有权
公开(公告)号：US09812123B1
公开(公告)日：2017-11-07
申请号：US14825648
申请日：2015-08-13
申请人： Google Inc.
发明人： Jason Sanders , Gabriel Taubman , John J. Lee
IPC分类号： G10L15/20 , G10L15/08 , G06F17/30 , H04M3/493 , G10L15/26 , G10L21/0208
CPC分类号： G10L15/08 , G06F17/30746 , G10L15/1815 , G10L15/22 , G10L15/265 , G10L21/0208 , G10L21/0272 , G10L25/48 , G10L2015/225 , H04M3/4936 , H04M2201/40 , H04M2203/352
摘要： Implementations relate to techniques for providing context-dependent search results. A computer-implemented method includes receiving an audio stream at a computing device during a time interval, the audio stream comprising user speech data and background audio, separating the audio stream into a first substream that includes the user speech data and a second substream that includes the background audio, identifying concepts related to the background audio, generating a set of terms related to the identified concepts, influencing a speech recognizer based on at least one of the terms related to the background audio, and obtaining a recognized version of the user speech data using the speech recognizer.

2. 发明授权

US09229974B1 Classifying queries 有权
标题翻译：分类查询
公开(公告)号：US09229974B1
公开(公告)日：2016-01-05
申请号：US13656959
申请日：2012-10-22
申请人： Google Inc.
发明人： John J. Lee , Melissa K. Carroll
IPC分类号： G06F17/30
CPC分类号： G06F17/30424 , G06F17/30705
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying queries. A query that includes one or more query terms is received. One or more entity identifiers are extracted from one or more search results that are responsive to the query. One or more of the query terms are compared with the extracted entity identifiers. Based on comparing the query terms with the extracted entity identifiers, the query is classified as an entity-triggering query or as a description-triggering query.
摘要翻译：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，用于对查询进行分类。收到包含一个或多个查询词语的查询。从响应于查询的一个或多个搜索结果中提取一个或多个实体标识符。将一个或多个查询项与提取的实体标识符进行比较。通过将查询项与提取的实体标识符进行比较，将查询分类为实体触发查询或描述触发查询。

3. 发明授权

US09123338B1 Background audio identification for speech disambiguation 有权
标题翻译：用于语音消歧的背景音频识别
公开(公告)号：US09123338B1
公开(公告)日：2015-09-01
申请号：US13804986
申请日：2013-03-14
申请人： Google Inc.
发明人： Jason Sanders , Gabriel Taubman , John J. Lee
IPC分类号： G10L15/20 , H04M3/493 , G10L15/26 , G10L21/0208
CPC分类号： G10L15/08 , G06F17/30746 , G10L15/1815 , G10L15/22 , G10L15/265 , G10L21/0208 , G10L21/0272 , G10L25/48 , G10L2015/225 , H04M3/4936 , H04M2201/40 , H04M2203/352
摘要： Implementations relate to techniques for providing context-dependent search results. A computer-implemented method includes receiving an audio stream at a computing device during a time interval, the audio stream comprising user speech data and background audio, separating the audio stream into a first substream that includes the user speech data and a second substream that includes the background audio, identifying concepts related to the background audio, generating a set of terms related to the identified concepts, influencing a speech recognizer based on at least one of the terms related to the background audio, and obtaining a recognized version of the user speech data using the speech recognizer.
摘要翻译：实现涉及用于提供上下文相关搜索结果的技术。计算机实现的方法包括在时间间隔期间在计算设备处接收音频流，所述音频流包括用户语音数据和背景音频，将音频流分离成包括用户语音数据的第一子流和包括用户语音数据的第二子流背景音频，识别与背景音频相关的概念，产生与所识别的概念相关的一组术语，基于与背景音频相关的术语中的至少一个影响语音识别器，以及获得用户语音的识别版本使用语音识别器的数据。

4. 发明授权

US09594806B1 Detecting name-triggering queries 有权
标题翻译：检测名称触发查询
公开(公告)号：US09594806B1
公开(公告)日：2017-03-14
申请号：US14718285
申请日：2015-05-21
申请人： Google Inc.
发明人： John J. Lee
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06F17/3051 , G06F17/3053 , G06F17/30654 , G06F17/30864
摘要： A system may be configured to receive a query; identify an object and a verb associated with the query; obtain information indicating a quantity of occurrences, in one or more documents, of the object in a sentence that may include the verb, or a quantity of occurrences, in one or more documents, of one or more terms, which are related to the object, in a sentence that may include the verb; generate a confidence score that may indicate a probability that the query seeks a result relating to a name of a person; identify a set of documents that are responsive to the query; determine that the confidence score satisfies a threshold; identify one or more documents, of the set of documents, that are associated with one or more names of people; select a particular document, of the set of documents; and output information regarding the selected particular document.
摘要翻译：系统可以被配置为接收查询; 识别与查询相关联的对象和动词; 在一个或多个文档中的一个或多个文档中，在一个或多个文档中的一个或多个文档中的一个或多个文档中的一个或多个文档中的一个或多个文档中的一个或多个文档中的可能包括动词或出现的数量的事件的数量，在一个可能包含动词的句子中; 产生一个可信度分数，该分数可以指示该查询寻求与一个人的姓名有关的结果的概率; 识别响应于查询的一组文档; 确定置信分数满足阈值; 识别与一个或多个人的姓名相关联的一组文档中的一个或多个文档; 选择一组文件的特定文件; 并输出关于所选择的特定文档的信息。

5. 发明授权

US09569487B1 Using an entity database to answer entity-triggering questions 有权
标题翻译：使用实体数据库来回答实体触发问题
公开(公告)号：US09569487B1
公开(公告)日：2017-02-14
申请号：US14740655
申请日：2015-06-16
申请人： Google Inc.
发明人： Melissa K. Carroll , John J. Lee
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06F17/30424 , G06F17/278 , G06F17/30554 , G06F17/30663
摘要： An embodiment may receive a question at a computing device; obtain a search result set in response to the question; identify, using the computing device, one or more entities that are associated with at least one document referenced by the search result set; select, using the computing device, one or more relevant entities identified as being associated with (i) documents referenced by the search result set and (ii) the question; and output, using the computing device, an answer to the question based at least on the selected one or more entities.
摘要翻译：实施例可以在计算设备处接收问题; 获取响应该问题的搜索结果集; 使用所述计算设备识别与所述搜索结果集所引用的至少一个文档相关联的一个或多个实体; 使用所述计算设备选择被识别为与所述搜索结果集所引用的文档相关联的一个或多个相关实体，以及（ii）所述问题; 并且使用所述计算设备至少基于所选择的一个或多个实体来输出对所述问题的答案。

6. 发明授权

US09529793B1 Resolving pronoun ambiguity in voice queries 有权
标题翻译：解决语音查询中的代词模糊
公开(公告)号：US09529793B1
公开(公告)日：2016-12-27
申请号：US13774082
申请日：2013-02-22
申请人： Google Inc.
发明人： Gabriel Taubman , John J. Lee
IPC分类号： G06F17/27
CPC分类号： G06F17/274 , G06F17/30761 , G06F17/30864 , G10L15/187 , G10L25/87
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for resolving ambiguity in received voice queries. An original voice query is received following one or more earlier voice queries, wherein the original voice query includes a pronoun or phrase. In one implementation, a plurality of acoustic parameters is identified for one or more words in the original voice query. A concept represented by the pronoun is identified based on the plurality of acoustic parameters, wherein the concept is associated with a particular query of the one or more earlier queries. The concept is associated with the pronoun. Alternatively, a concept may be associated with a phrase by using grammatical analysis of the query to relate the phrase to a concept derived from a prior query.
摘要翻译：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，用于解决接收的语音查询中的歧义。在一个或多个较早的语音查询之后接收原始语音查询，其中原始语音查询包括代词或短语。在一个实现中，为原始语音查询中的一个或多个单词识别多个声学参数。基于所述多个声学参数来识别由所述代词表示的概念，其中所述概念与所述一个或多个较早查询的特定查询相关联。这个概念与代词相关联。或者，概念可以通过使用查询的语法分析来将短语与从先前查询导出的概念相关联而与短语相关联。

7. 发明授权

US09081814B1 Using an entity database to answer entity-triggering questions 有权
标题翻译：使用实体数据库来回答实体触发问题
公开(公告)号：US09081814B1
公开(公告)日：2015-07-14
申请号：US13795652
申请日：2013-03-12
申请人： Google Inc.
发明人： Melissa K. Carroll , John J. Lee
IPC分类号： G06F7/00 , G06F17/30 , G06F17/27
CPC分类号： G06F17/30424 , G06F17/278 , G06F17/30554 , G06F17/30663
摘要： An embodiment may receive a question at a computing device; obtain a search result set in response to the question; identify, using the computing device, one or more entities that are associated with at least one document referenced by the search result set; select, using the computing device, one or more relevant entities identified as being associated with (i) documents referenced by the search result set and (ii) the question; and output, using the computing device, an answer to the question based at least on the selected one or more entities.
摘要翻译：实施例可以在计算设备处接收问题; 获取响应该问题的搜索结果集; 使用所述计算设备识别与所述搜索结果集所引用的至少一个文档相关联的一个或多个实体; 使用所述计算设备选择被识别为与所述搜索结果集所引用的文档相关联的一个或多个相关实体，以及（ii）所述问题; 并且使用所述计算设备至少基于所选择的一个或多个实体来输出对所述问题的答案。

8. 发明授权

US09063983B1 Detecting name-triggering queries 有权
标题翻译：检测名称触发查询
公开(公告)号：US09063983B1
公开(公告)日：2015-06-23
申请号：US13795650
申请日：2013-03-12
申请人： Google Inc.
发明人： John J. Lee
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06F17/3051 , G06F17/3053 , G06F17/30654 , G06F17/30864
摘要： A system may be configured to receive a query; identify an object and a verb associated with the query; obtain information indicating a quantity of occurrences, in one or more documents, of the object in a sentence that may include the verb, or a quantity of occurrences, in one or more documents, of one or more terms, which are related to the object, in a sentence that may include the verb; generate a confidence score that may indicate a probability that the query seeks a result relating to a name of a person; identify a set of documents that are responsive to the query; determine that the confidence score satisfies a threshold; identify one or more documents, of the set of documents, that are associated with one or more names of people; select a particular document, of the set of documents; and output information regarding the selected particular document.
摘要翻译：系统可以被配置为接收查询; 识别与查询相关联的对象和动词; 在一个或多个文档中的一个或多个文档中，在一个或多个文档中的一个或多个文档中的一个或多个文档中的一个或多个文档中的一个或多个文档中的一个或多个文档中的可能包括动词或出现的数量的事件的数量，在一个可能包含动词的句子中; 产生一个可信度分数，该分数可以指示该查询寻求与一个人的姓名有关的结果的概率; 识别响应于查询的一组文档; 确定置信分数满足阈值; 识别与一个或多个人的姓名相关联的一组文档中的一个或多个文档; 选择一组文件的特定文件; 并输出关于所选择的特定文档的信息。

9. 发明授权

US09679568B1 Training a dialog system using user feedback 有权
公开(公告)号：US09679568B1
公开(公告)日：2017-06-13
申请号：US13668603
申请日：2012-11-05
申请人： Google Inc.
发明人： Gabriel Taubman , Andrew W. Hogue , John J. Lee
IPC分类号： G10L15/00 , G10L15/30 , G10L15/22 , H04M3/493
CPC分类号： G10L15/30 , G06F17/30867 , G10L15/22 , H04M3/493 , H04M3/4938
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine, a first input that specifies a question; providing, by the dialog engine, an answer to the question; receiving, by the dialog engine, a second input; and determining, by the dialog engine, that the second input is classified as feedback to the answer, then determining a feedback score associated with the second input.

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