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

WO2016176197A1 CLASSIFYING DOCUMENTS BY CLUSTER 审中-公开
标题翻译：按CLUSTER分类文件
公开(公告)号：WO2016176197A1
公开(公告)日：2016-11-03
申请号：PCT/US2016/029339
申请日：2016-04-26
申请人： GOOGLE INC.
发明人： BENDERSKY, Mike , YANG, Jie , SAIKIA, Amitabh , CARTRIGHT, Marc-Allen , RAVI, Sujith , MIKLOS, Balint , KRKA, Ivo , JOSIFOVSKI, Vanja , WENDT, James , PUEYO, Luis Garcia
IPC分类号： G06Q10/10
CPC分类号： G06F17/30705 , G06Q10/107
摘要： Methods, apparatus, systems, and computer-readable media are provided for classifying, or "labeling," electronic documents such as emails en masse based on association with a cluster/template. In various implementations, a corpus of documents may be grouped into a plurality of disjoint clusters of documents based on one or more shared content attributes. A classification distribution associated with a first cluster of the plurality of clusters may be determined based on classifications assigned to individual documents of the first cluster. A classification distribution associated with a second cluster of the plurality of clusters may then be determined based at least in part on the classification distribution associated with the first cluster and a relationship between the first and second clusters.
摘要翻译：提供了方法，装置，系统和计算机可读介质，用于基于与集群/模板的关联来整合或“标记”诸如电子邮件的电子文档。在各种实现中，基于一个或多个共享内容属性，文档的语料库可以被分组成多个不相交的文档簇。可以基于分配给第一集群的单个文档的分类来确定与多个集群中的第一集群相关联的分类分发。然后可以至少部分地基于与第一集群相关联的分类分布和第一和第二集群之间的关系来确定与多个集群中的第二集群相关联的分类分发。

2. 发明申请

WO2014210189A2 TRIGGERING COMPLETION STEP SUGGESTION FOR A TASK 审中-公开
标题翻译：触发完成步骤建议任务
公开(公告)号：WO2014210189A2
公开(公告)日：2014-12-31
申请号：PCT/US2014/044142
申请日：2014-06-25
申请人： GOOGLE INC.
发明人： TOMKINS, Andrew , HARRIS, Tristan , RAVIKUMAR, Shanmugasundaram , PANG, Bo , RAVI, Sujith , SAR, Can , DINARDI, Angelo
CPC分类号： G06Q10/063114 , G06F17/3087 , G06N99/005 , H04L67/22 , H04W4/02 , H04W4/021
摘要： Methods and apparatus related to providing one or more completion step suggestions for a task that is associated with a user. In some implementations, the completion step suggestions may be provided to the user based on the satisfaction of a trigger condition. In some implementations, a trigger condition may be based on a user geographic location. In some implementations, a trigger condition may be based on an action of the user. In some implementations, a trigger condition may be based on a time when the associated task may be completed.
摘要翻译：与为与用户相关联的任务提供一个或多个完成步骤建议相关的方法和装置。在一些实现中，可以基于触发条件的满足来向用户提供完成步骤建议。在一些实现中，触发条件可以基于用户地理位置。在一些实现中，触发条件可以基于用户的动作。在一些实现中，触发条件可以基于相关任务可以完成的时间。

3. 发明申请

WO2017117028A1 ORGANIZING IMAGES ASSOCIATED WITH A USER 审中-公开
标题翻译：组织与用户相关的图像
公开(公告)号：WO2017117028A1
公开(公告)日：2017-07-06
申请号：PCT/US2016/068428
申请日：2016-12-22
申请人： GOOGLE INC.
发明人： DUA, Robin , RAVI, Sujith
IPC分类号： G06F17/30
CPC分类号： G06K9/6267 , G06F17/30244 , G06K9/52 , G06Q30/0633
摘要： A method includes identifying images associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes for each of the images, determining one or more labels, wherein the one or more labels are based on at least one of metadata and a primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to corresponding images. The method also includes interacting with the user to obtain identifying information that is used to categorize one or more of the images.
摘要翻译：一种方法包括：识别与用户相关联的图像，其中该图像被识别为与用户相关联的用户设备捕获的，与用户相关联的用户设备上存储的和存储的至少一个在与用户相关联的云存储中。该方法还包括针对每个图像确定一个或多个标签，其中该一个或多个标签基于元数据和主要注释中的至少一个。该方法还包括生成一个或多个标签到一个或多个置信度分数的映射，其中一个或多个置信度分数指示一个或多个标签应用于对应图像的程度。该方法还包括与用户交互以获得用于分类一个或多个图像的识别信息。

4. 发明申请

WO2018057890A1 SMART REPLIES USING AN ON-DEVICE MODEL 审中-公开
标题翻译：使用在设备模型的智能答复
公开(公告)号：WO2018057890A1
公开(公告)日：2018-03-29
申请号：PCT/US2017/052958
申请日：2017-09-22
申请人： GOOGLE INC.
发明人： RAVI, Sujith , RUDICK, Thomas Matthew , BEACH, Nathan Dickerson , MCGREGOR, JR., John Patrick , RANIERI, Mirko
IPC分类号： G06Q10/10
摘要： A computing device may receive a communication sent from an external computing device. At least one processor of the computing device may determine, using an on-device machine-trained model and based at least in part on the communication, one or more candidate responses to the communication. The at least one processor may receive an indication of a user input that selects a candidate response from the one or more candidate responses. Responsive to receiving the indication of the user input that selects the candidate response, the at least one processor may send the candidate response to the external computing device.
摘要翻译：计算设备可以接收从外部计算设备发送的通信。计算设备的至少一个处理器可以使用设备上机器训练的模型并且至少部分地基于该通信来确定对通信的一个或多个候选响应。该至少一个处理器可以接收从一个或多个候选响应中选择候选响应的用户输入的指示。响应于接收到选择候选响应的用户输入的指示，至少一个处理器可以将候选响应发送到外部计算设备。

5. 发明申请

WO2017180212A1 RELATED ENTITY DISCOVERY 审中-公开
标题翻译：相关实体发现
公开(公告)号：WO2017180212A1
公开(公告)日：2017-10-19
申请号：PCT/US2016/069404
申请日：2016-12-30
申请人： GOOGLE INC.
发明人： BENDERSKY, Mike , GARG, Vijay , RAVI, Sujith , LI, Cheng
IPC分类号： G06F17/30
CPC分类号： G06F16/9024 , G06F16/24578 , G06F16/951 , G06N5/022 , G06N20/00 , G06Q10/1095
摘要： A computing device may generate, a graph that includes a plurality of nodes, wherein the plurality of nodes includes a plurality of entity nodes representing a plurality of entities and a plurality of feature nodes representing a plurality of features, and wherein each of the plurality of entity nodes is connected in the graph to one or more of the plurality of feature nodes. The computing device may perform label propagation to associate a distribution of labels with each of the plurality of nodes. The computing device may be configured to receive an indication of at least one of a feature of interest or an entity of interest. The computing device may further be configured to output an indication of one or more related entities that are related to the feature of interest or the entity of interest.
摘要翻译：计算设备可以生成包括多个节点的图，其中多个节点包括表示多个实体的多个实体节点以及表示多个特征的多个特征节点并且其中所述多个实体节点中的每一个在所述图中被连接到所述多个特征节点中的一个或多个。计算设备可以执行标签传播以将标签的分布与多个节点中的每一个相关联。计算设备可以被配置为接收感兴趣特征或感兴趣实体中的至少一个的指示。计算设备还可以被配置为输出与感兴趣特征或感兴趣实体有关的一个或多个相关实体的指示。

6. 发明申请

WO2017117027A1 GENERATING LABELS FOR IMAGES ASSOCIATED WITH A USER 审中-公开
标题翻译：为与用户关联的图片生成标签
公开(公告)号：WO2017117027A1
公开(公告)日：2017-07-06
申请号：PCT/US2016/068426
申请日：2016-12-22
申请人： GOOGLE INC.
发明人： DUA, Robin , RAVI, Sujith
IPC分类号： G06F17/30
CPC分类号： G06F17/30675 , G06F17/241 , G06F17/30244 , G06F17/30268 , G06F17/30917 , G06K9/00677 , G06K9/2081
摘要： A method includes identifying an image associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes determining one or more labels for the image, where the one or more labels are based on at least one of metadata, a primary annotation, and a secondary annotation and the secondary annotation is generated by performing label expansion on at least one of the metadata and the primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to the image.
摘要翻译：一种方法包括：识别与用户相关联的图像，其中该图像被识别为存储在与用户相关联的用户装置上的与用户相关联的用户装置捕获的至少一个;以及存储在与用户相关联的云存储中。该方法还包括确定图像的一个或多个标签，其中一个或多个标签基于元数据，主要注释和次要注释中的至少一个，并且次要注释是通过对至少一个的元数据和主注释。该方法还包括生成一个或多个标签到一个或多个置信度分数的映射，其中一个或多个置信度分数指示一个或多个标签应用于图像的程度。

7. 发明申请

WO2014210188A2 DETERMINING ADDITIONAL INFORMATION FOR AN INTENDED ACTION OF A USER 审中-公开
标题翻译：确定用户的预期行为的附加信息
公开(公告)号：WO2014210188A2
公开(公告)日：2014-12-31
申请号：PCT/US2014/044139
申请日：2014-06-25
申请人： GOOGLE INC.
发明人： TOMKINS, Andrew , RAVIKUMAR, Shanmugasundaram , PANG, Bo , RAVI, Sujith , SAR, Can , DINARDI, Angelo , HARRIS, Tristan
CPC分类号： H04L51/20
摘要： Methods and apparatus related to receiving user task information indicative of an intended action of a user, determining additional information related to completion of the intended action, determining a completion step for the intended action based on the additional information, and providing the completion step to the user. The user task information may be received from a first source and the additional information may be determined from one or more additional sources that are distinct from the first source. Additional sources may include, for example, user data associated with the user and/or one or more non-user specific databases such as an entity database. Whether a completion step is provided to a user may be dependent on one or more factors such as, for example, the source of the user task information, the source of the additional information, and/or a trigger associated with the completion step.
摘要翻译：与指示用户的预期动作的用户任务信息的接收相关的方法和装置，确定与预期动作的完成相关的附加信息，基于附加信息确定预期动作的完成步骤，并将完成步骤提供给用户。可以从第一源接收用户任务信息，并且可以从与第一源不同的一个或多个附加源来确定附加信息。附加源可以包括例如与用户相关联的用户数据和/或一个或多个非用户特定数据库，例如实体数据库。是否向用户提供完成步骤可以取决于一个或多个因素，例如，用户任务信息的来源，附加信息的来源和/或与完成步骤相关联的触发。

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