-
公开(公告)号：US10007867B2
公开(公告)日：2018-06-26
申请号：US15089677
申请日：2016-04-04
Applicant: Google Inc.
Inventor： Qian Yu , Liron Yatziv , Yeqing Li , Christian Szegedy , Sacha Christopher Arnoud , Martin C. Stumpe
CPC classification number: G06K9/6259 , G06F16/337 , G06F16/51 , G06F16/583 , G06K9/3258 , G06K9/6215
Abstract: Systems and methods of identifying entities are disclosed. In particular, one or more images that depict an entity can be identified from a plurality of images. One or more candidate entity profiles can be determined from an entity directory based at least in part on the one or more images that depict the entity. The one or more images that depict the entity and the one or more candidate entity profiles can be provided as input to a machine learning model. One or more outputs of the machine learning model can be generated. Each output can include a match score associated with an image that depicts the entity and at least one candidate entity profile. The entity directory can be updated based at least in part on the one or more generated outputs of the machine learning model.
-
公开(公告)号：US20170039457A1
公开(公告)日：2017-02-09
申请号：US14821128
申请日：2015-08-07
Applicant: Google Inc.
Inventor： Qian Yu , Liron Yatziv , Martin Christian Stumpe , Vinay Damodar Shet , Christian Szegedy , Dumitru Erhan , Sacha Christophe Arnoud
CPC classification number: G06K9/66 , G06K9/3258 , G06K9/4628 , G06K9/6201 , G06K9/6256 , G06K9/6277 , G06N3/02 , G06N3/08
Abstract: Aspects of the present disclosure relate to a method includes training a deep neural network using training images and data identifying one or more business storefront locations in the training images. The deep neural network outputs tight bounding boxes on each image. At the deep neural network, a first image may be received. The first image may be evaluated using the deep neural network. Bounding boxes may then be generated identifying business storefront locations in the first image.
Abstract translation: 本公开的方面涉及一种方法，包括使用训练图像和识别训练图像中的一个或多个商业店面位置的数据来训练深层神经网络。 深层神经网络在每个图像上输出紧密的边界框。 在深神经网络中，可以接收第一图像。 可以使用深层神经网络来评估第一图像。 然后可以生成标识框，识别第一图像中的商店店面位置。
-
公开(公告)号：US20180189629A1
公开(公告)日：2018-07-05
申请号：US15394979
申请日：2016-12-30
Applicant: Google Inc.
Inventor： Liron Yatziv , Shlomo Krepner
CPC classification number: G06N3/006 , G06F16/00 , G06F21/60 , G06N5/04 , G06Q10/103 , G06Q30/0269
Abstract: In one example, a method includes generating, responsive to receiving a request for a recommendation for a group of users and based on first privacy level data for users of the group, an original list of recommendations for the group. In this example, the method further includes evaluating, by respective computational assistants associated with the users of the group and based on respective second privacy level data for the users of the group, recommendations from the original list of recommendations for inclusion in a pruned list of recommendations for the group, wherein the second privacy level is more restricted than the first privacy level. In this example, the method further includes, in response to the pruned list of recommendations including at least one recommendation, outputting, for presentation to the users of the group, the pruned list of recommendations.
-
Patent Agency Ranking
公开(公告)号：US20170286805A1
公开(公告)日：2017-10-05
申请号：US15089677
申请日：2016-04-04
Applicant: Google Inc.
Inventor： Qian Yu , Liron Yatziv , Yeqing Li , Christian Szegedy , Sacha Christopher Arnoud , Martin C. Stumpe
CPC classification number: G06K9/6259 , G06F17/30247 , G06F17/3028 , G06F17/30702 , G06K9/3258 , G06K9/6215
Abstract: Systems and methods of identifying entities are disclosed. In particular, one or more images that depict an entity can be identified from a plurality of images. One or more candidate entity profiles can be determined from an entity directory based at least in part on the one or more images that depict the entity. The one or more images that depict the entity and the one or more candidate entity profiles can be provided as input to a machine learning model. One or more outputs of the machine learning model can be generated. Each output can include a match score associated with an image that depicts the entity and at least one candidate entity profile. The entity directory can be updated based at least in part on the one or more generated outputs of the machine learning model.
-
公开(公告)号：US08868522B1
公开(公告)日：2014-10-21
申请号：US13691532
申请日：2012-11-30
Applicant: Google Inc.
Inventor： Marco Zennaro , Kong Man Cheung , Julian Ibarz , Liron Yatziv , Sacha Christophe Arnoud
IPC: G06F17/30
CPC classification number: G06F17/30241
Abstract: Systems and methods for updating geographic data based on a transaction are provided. In some aspects, one or more transaction records associated with a business are accessed from a memory. Each transaction record identifies a transaction time, geographic location data, and transaction information. A geocoded record of the business is selected to update, based on the geographic location data of the one or more transaction records. The selected geocoded record is updated based on at least one of the transaction time or the transaction information identified in the transaction records.
Abstract translation: 提供了基于事务更新地理数据的系统和方法。 在一些方面，与业务相关联的一个或多个事务记录从存储器访问。 每个交易记录标识交易时间，地理位置数据和交易信息。 根据一个或多个交易记录的地理位置数据，选择业务的地理编码记录来更新。 基于交易记录中识别的交易时间或交易信息中的至少一个来更新所选择的地理编码记录。
-
公开(公告)号：US20170109615A1
公开(公告)日：2017-04-20
申请号：US14885452
申请日：2015-10-16
Applicant: Google Inc.
Inventor： Liron Yatziv , Yair Movshovitz-Attias , Qian Yu , Martin Christian Stumpe , Vinay Damodar Shet , Sacha Christophe Arnoud
CPC classification number: G06F16/5866 , G06F16/583 , G06K9/00671 , G06K9/6267 , G06K9/6273 , G06K9/6282 , G06N3/0427 , G06N3/0454
Abstract: Computer-implemented methods and systems for automatically classifying businesses from imagery can include providing one or more images of a location entity as input to a statistical model that can be applied to each image. A plurality of classification labels for the location entity in the one or more images can be generated and provided as an output of the statistical model. The plurality of classification labels can be generated by selecting from an ontology that identifies predetermined relationships between location entities and categories associated with corresponding classification labels at multiple levels of granularity. Confidence scores for the plurality of classification labels can be generated to indicate a likelihood level that each generated classification label is accurate for its corresponding location entity. Associations based on the classification labels generated for each image can be stored in a database and used to help retrieve relevant business information requested by a user.
-
公开(公告)号：US09594984B2
公开(公告)日：2017-03-14
申请号：US14821128
申请日：2015-08-07
Applicant: Google Inc.
Inventor： Qian Yu , Liron Yatziv , Martin Christian Stumpe , Vinay Damodar Shet , Christian Szegedy , Dumitru Erhan , Sacha Christophe Arnoud
CPC classification number: G06K9/66 , G06K9/3258 , G06K9/4628 , G06K9/6201 , G06K9/6256 , G06K9/6277 , G06N3/02 , G06N3/08
Abstract: Aspects of the present disclosure relate to a method includes training a deep neural network using training images and data identifying one or more business storefront locations in the training images. The deep neural network outputs tight bounding boxes on each image. At the deep neural network, a first image may be received. The first image may be evaluated using the deep neural network. Bounding boxes may then be generated identifying business storefront locations in the first image.
Abstract translation: 本公开的方面涉及一种方法，包括使用训练图像和识别训练图像中的一个或多个商业店面位置的数据来训练深层神经网络。 深层神经网络在每个图像上输出紧密的边界框。 在深神经网络中，可以接收第一图像。 可以使用深层神经网络来评估第一图像。 然后可以生成标识框，识别第一图像中的商店店面位置。
-
公开(公告)号：US10699181B2
公开(公告)日：2020-06-30
申请号：US15394979
申请日：2016-12-30
Applicant: Google Inc.
Inventor： Liron Yatziv , Shlomo Krepner
Abstract: In one example, a method includes generating, responsive to receiving a request for a recommendation for a group of users and based on first privacy level data for users of the group, an original list of recommendations for the group. In this example, the method further includes evaluating, by respective computational assistants associated with the users of the group and based on respective second privacy level data for the users of the group, recommendations from the original list of recommendations for inclusion in a pruned list of recommendations for the group, wherein the second privacy level is more restricted than the first privacy level. In this example, the method further includes, in response to the pruned list of recommendations including at least one recommendation, outputting, for presentation to the users of the group, the pruned list of recommendations.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
