-
公开(公告)号：US20140164415A1
公开(公告)日：2014-06-12
申请号：US13708483
申请日：2012-12-07
Applicant: Google Inc.
Inventor： Krzysztof Duleba
IPC: G06F17/30
CPC classification number: G06F17/30241
Abstract: A computer-implemented method including obtaining a subject dataset including two or more features associated with a subject geographic object, obtaining a candidate dataset including two or more features associated with a candidate geographic object, comparing, using a computer, at least two features of the subject dataset to at least two corresponding features of the candidate dataset, at least one of the features compared comprising a geographic feature, and determining whether the candidate geographic object matches the subject geographic object based on the comparison.
Abstract translation: 一种计算机实现的方法，包括获得包括与主题地理对象相关联的两个或多个特征的主题数据集，获得包括与候选地理对象相关联的两个或多个特征的候选数据集，使用计算机比较所述候选数据集的至少两个特征 主题数据集到候选数据集的至少两个对应特征，比较的至少一个特征包括地理特征，以及基于该比较来确定候选地理对象是否与主题地理对象相匹配。
-
12.发明授权公开(公告)号：US09836819B1
公开(公告)日：2017-12-05
申请号：US14984628
申请日：2015-12-30
Applicant: Google Inc.
Inventor： Aaron Michael Donsbach , Benjamin Vanik , Jon Gabriel Clapper , Alison Lentz , Joshua Denali Lovejoy , Robert Douglas Fritz, III , Krzysztof Duleba , Li Zhang , Juston Payne , Emily Anne Fortuna , Iwona Bialynicka-Birula , Blaise Aguera-Arcas , Daniel Ramage , Hugh Brendan McMahan , Oliver Fritz Lange , Jess Holbrook
CPC classification number: G06T11/60 , G06K9/00221 , G06K9/00664 , G06T1/0007 , G06T2207/20084
Abstract: The present disclosure provides an image capture, curation, and editing system that includes a resource-efficient mobile image capture device that continuously captures images. The mobile image capture device is operable to input an image into at least one neural network and to receive at least one descriptor of the desirability of a scene depicted by the image as an output of the at least one neural network. The mobile image capture device is operable to determine, based at least in part on the at least one descriptor of the desirability of the scene of the image, whether to store a second copy of such image and/or one or more contemporaneously captured images in a non-volatile memory of the mobile image capture device or to discard a first copy of such image from a temporary image buffer without storing the second copy of such image in the non-volatile memory.
-
13.发明申请QUALITY VISIT MEASURE FOR CONTROLLING COMPUTER RESPONSE TO QUERY ASSOCIATED WITH PHYSICAL LOCATION 审中-公开质量访问控制计算机对物理位置相关查询的响应公开(公告)号：US20170069000A1
公开(公告)日：2017-03-09
申请号：US14849368
申请日：2015-09-09
Applicant: Google Inc.
Inventor： Krzysztof Duleba
CPC classification number: G06Q30/0282 , G06F16/23 , G06F16/24575 , G06F16/24578 , G06F16/248 , G06F16/9535 , G06F16/9537
Abstract: The response of a computer to a query associated with a physical location may be controlled using a quality visit measure that is based at least in part on the number and/or frequency of repeat visits by one or more individuals to that physical location.
Abstract translation: 计算机对与物理位置相关联的查询的响应可以使用至少部分地基于一个或多个个体重复访问到该物理位置的次数和/或频率的质量访问度量进行控制。
-
公开(公告)号：US09571589B2
公开(公告)日：2017-02-14
申请号：US14698081
申请日：2015-04-28
Applicant: GOOGLE INC.
Inventor： Krzysztof Duleba , Zhengrong Ji
CPC classification number: H04L67/18 , H04L61/2007 , H04L61/25 , H04L61/255 , H04L61/609 , H04L67/10 , H04L67/42
Abstract: A computer-implemented method that includes receiving a location from a location aware access device and an IP address of a network device to which the location aware access device is connected, receiving a request that includes the IP address of the network device from a location unaware access device that is connected to the network device, determining a geographic location for the location unaware access device based on the IP address of the network device and the location received from the location aware access device, selecting information responsive to the request from the location unaware access device based at least in part on the geographic location, and providing the selected information to the location unaware access device.
Abstract translation: 一种计算机实现的方法，其包括从位置感知访问设备接收位置和所述位置感知访问设备连接到的网络设备的IP地址，从不知情的位置接收包括所述网络设备的IP地址的请求 连接到所述网络设备的接入设备，基于所述网络设备的IP地址以及从所述位置感知接入设备接收到的位置确定所述不知情的接入设备的地理位置，响应于所述不知情的位置的请求选择信息 访问设备至少部分地基于所述地理位置，并且将所选择的信息提供给所述位置不知道的访问设备。
-
公开(公告)号：US20160179843A1
公开(公告)日：2016-06-23
申请号：US15054716
申请日：2016-02-26
Applicant: Google Inc.
Inventor： Lukasz Andrzej Heldt , Krzysztof Duleba , David Robert Bailey
IPC: G06F17/30
CPC classification number: G06F17/30241 , G06F17/3053 , G06F17/30598 , G06F17/30601 , G06F17/30864 , G06F17/30867 , G06F17/3087
Abstract: Systems and methods for approximating a user location are provided. For instance, historical location data and internet protocol address data can be analyzed to identify a plurality of locations. A confidence score for each of the plurality of locations can be determined. Two or more locations of the plurality of locations that form a cluster can be identified and the confidence scores for each of the two or more locations that form a cluster can be modified by adjusting each confidence score by a weight associated with the cluster.
Abstract translation: 提供了用于近似用户位置的系统和方法。 例如，可以分析历史位置数据和因特网协议地址数据以识别多个位置。 可以确定多个位置中的每一个的置信度。 可以识别形成集群的多个位置中的两个或多个位置，并且可以通过将每个置信度得分调整与集群相关联的权重来修改形成集群的两个或多个位置中的每一个的置信度分数。
-
Patent Agency Ranking
公开(公告)号：US20150244819A1
公开(公告)日：2015-08-27
申请号：US14698081
申请日：2015-04-28
Applicant: GOOGLE INC.
Inventor： Krzysztof Duleba , Zhengrong Ji
CPC classification number: H04L67/18 , H04L61/2007 , H04L61/25 , H04L61/255 , H04L61/609 , H04L67/10 , H04L67/42
Abstract: A computer-implemented method that includes receiving a location from a location aware access device and an IP address of a network device to which the location aware access device is connected, receiving a request that includes the IP address of the network device from a location unaware access device that is connected to the network device, determining a geographic location for the location unaware access device based on the IP address of the network device and the location received from the location aware access device, selecting information responsive to the request from the location unaware access device based at least in part on the geographic location, and providing the selected information to the location unaware access device.
Abstract translation: 一种计算机实现的方法，其包括从位置感知访问设备接收位置和所述位置感知访问设备连接到的网络设备的IP地址，从不知情的位置接收包括所述网络设备的IP地址的请求 连接到所述网络设备的接入设备，基于所述网络设备的IP地址以及从所述位置感知接入设备接收到的位置确定所述不知情的接入设备的地理位置，响应于所述不知情的位置的请求选择信息 访问设备至少部分地基于所述地理位置，并且将所选择的信息提供给所述位置不知道的访问设备。
-
17.发明申请SYSTEMS, METHODS, AND COMPUTER-READABLE-MEDIA FOR DETERMINING A MULTILOCATION PREDICTED CLICK-THROUGH RATE FOR ADVERTISEMENTS 审中-公开用于确定用于广告的多重预测点击率的系统，方法和计算机可读介质公开(公告)号：US20150120436A1
公开(公告)日：2015-04-30
申请号：US13656387
申请日：2012-10-19
Applicant: Google Inc.
Inventor： Krzysztof Duleba , Ingemar Eriksson
IPC: G06Q30/02
CPC classification number: G06Q30/0246 , G06Q30/0256
Abstract: Provided are systems and methods for determining a multilocation predicted click-through rate (pCTR) for advertisements. The multilocation pCTR may be used to select and rank advertisements for advertisement auctions presented to potential advertisers. The multilocation pCTR may be based on a set of locations and probabilities for an estimation of a user's location, such by internet protocol (IP) address geolocation. The multilocation pCTR for an advertisement and a location set may then be determined from the single location pCTR for each location of the location set and the probability associated with each location.
Abstract translation: 提供了用于确定广告的多位置预测点击率（pCTR）的系统和方法。 多位置pCTR可用于选择和排列向潜在广告商呈现的广告拍卖的广告。 多位置pCTR可以基于用于估计用户位置的一组位置和概率，例如通过因特网协议（IP）地址地理位置。 然后可以从位置集合的每个位置和与每个位置相关联的概率的单个位置pCTR确定用于广告和位置集合的多位置pCTR。
-
公开(公告)号：US20150006526A1
公开(公告)日：2015-01-01
申请号：US13930608
申请日：2013-06-28
Applicant: Google Inc.
Inventor： Krzysztof Duleba , Mark Mao , Finnegan Southey , Chengling Chan , Lukasz Andrzej Heldt , Jason Luther Smart
IPC: G06F17/30
CPC classification number: G06F16/29
Abstract: Provided are systems, methods, and computer-readable media for determining locations of interest to a user. User activity over a period of time is obtained and used to determine geographic entities (e.g., locations) of interest. The user activity is aggregated by geographic entity and a relevancy score is calculated for each geographic entity. The geographic entity having the highest score is stored as a location of interest in a location profile for the user. Multiple geographic entities having the highest specified number of relevancy scores may also be stored.
Abstract translation: 提供了用于确定用户感兴趣的位置的系统，方法和计算机可读介质。 获得一段时间内的用户活动并用于确定感兴趣的地理实体（例如，位置）。 用户活动由地理实体聚合，并为每个地理实体计算相关性分数。 具有最高分数的地理实体作为感兴趣的位置存储在用户的位置简档中。 具有最高指定数量的相关性得分的多个地理实体也可以被存储。
-
公开(公告)号：US09420426B2
公开(公告)日：2016-08-16
申请号：US14329086
申请日：2014-07-11
Applicant: Google Inc.
Inventor： Krzysztof Duleba , Lukasz Andrzej Heldt , Ankit Gupta
Abstract: Systems and methods for inferring a current location of a user or device based on an analysis of a user location history are provided. In particular, when the current location of a device requesting a location-enhanced service cannot be determined with sufficient precision, a plurality of historical locations provided by the user location history can be scored according to a variety of parameters. The historical location receiving the highest score can be inferred to be the current location of the user, permitting the requested location-enhanced service to be performed.
Abstract translation: 提供了用于基于用户位置历史的分析来推断用户或设备的当前位置的系统和方法。 特别地，当无法以足够的精度确定请求位置增强服务的设备的当前位置时，可以根据各种参数对用户位置历史记录提供的多个历史位置进行评分。 可以将获得最高分数的历史位置推定为用户的当前位置，允许执行所请求的位置增强服务。
-
公开(公告)号：US09298831B1
公开(公告)日：2016-03-29
申请号：US14105255
申请日：2013-12-13
Applicant: Google Inc.
Inventor： Lukasz Andrzej Heldt , Krzysztof Duleba , David Robert Bailey
IPC: G06F17/30
CPC classification number: G06F17/30241 , G06F17/3053 , G06F17/30598 , G06F17/30601 , G06F17/30864 , G06F17/30867 , G06F17/3087
Abstract: Systems and methods for approximating a user location are provided. For instance, historical location data and internet protocol address data can be analyzed to identify a plurality of locations. A confidence score for each of the plurality of locations can be determined. Two or more locations of the plurality of locations that form a cluster can be identified and the confidence scores for each of the two or more locations that form a cluster can be modified by adjusting each confidence score by a weight associated with the cluster.
Abstract translation: 提供了用于近似用户位置的系统和方法。 例如，可以分析历史位置数据和因特网协议地址数据以识别多个位置。 可以确定多个位置中的每一个的置信度。 可以识别形成集群的多个位置中的两个或多个位置，并且可以通过将每个置信度得分调整与集群相关联的权重来修改形成集群的两个或多个位置中的每一个的置信度分数。
-
-
-
-
-
-
-
-
-
Search Results
31
records
(took 0.019 seconds)
