-
公开(公告)号：US20150088792A1
公开(公告)日：2015-03-26
申请号：US14037332
申请日：2013-09-25
Applicant: Google Inc.
Inventor： Thomas Germano O'Neill , Brian Patrick Williams
CPC classification number: G06N99/005 , G06K9/6256 , G06N5/025 , G06N7/005 , H04L67/10
Abstract: Methods and apparatus are directed to geofencing applications that utilize machine learning. A computing device can receive a plurality of geofence-status indications, where a geofence-status indication includes training data associated with a geofence at a first location. The geofence is associated with a geographical area. The computing device trains a geofence-status classifier to determine a geofence status by providing the training data as input to the geofence-status classifier. The training data includes data for a plurality of training features. After the geofence-status classifier is trained, the computing device receives query data associated with a second location. The query data includes data for a plurality of query features. The query features include a query feature that corresponds to a training feature. The query data is input to the geofence-status classifier. After providing the query data, the trained geofence-status classifier indicates the geofence status.
Abstract translation: 方法和设备涉及利用机器学习的地理围栏应用。 计算设备可以接收多个地理围栏状态指示，其中地理围栏状态指示包括与第一位置处的地理围栏相关联的训练数据。 地理围栏与地理区域相关联。 计算设备通过提供训练数据作为地理围栏状态分类器的输入来训练地理围栏状态分类器来确定地理位置状态。 训练数据包括用于多个训练特征的数据。 在地理围栏状态分类器被训练之后，计算设备接收与第二位置相关联的查询数据。 查询数据包括多个查询特征的数据。 查询功能包括对应于训练功能的查询功能。 将查询数据输入到地理围栏状态分类器。 在提供查询数据之后，经过训练的地理位置状态分类器指示地理位置状态。
-
32.发明申请Decomposition of Error Components Between Angular, Forward, and Sideways Errors in Estimated Positions of a Computing Device 审中-公开在计算设备的估计位置中的角度，前向和侧向错误之间的误差分量的分解公开(公告)号：US20170010128A1
公开(公告)日：2017-01-12
申请号：US15275648
申请日：2016-09-26
Applicant: Google Inc.
Inventor： Etienne Le Grand , Brian Patrick Williams
CPC classification number: G01C25/00 , G01C19/00 , G01C21/12 , G01C22/006 , G01C25/005 , G01S5/02 , G01S19/13 , G01S19/49 , H04W4/026 , H04W4/027 , H04W4/029
Abstract: Examples include systems and methods for decomposition of error components between angular, forward, and sideways errors in estimated positions of a computing device. One method includes determining an estimation of a current position of the computing device based on a previous position of the computing device, an estimated speed over an elapsed time, and a direction of travel of the computing device, determining a forward, sideways, and orientation change error component of the estimation of the current position of the computing device, determining a weight to apply to the forward, sideways, and orientation change error components based on average observed movement of the computing device, and using the weighted forward, sideways, and orientation change error components as constraints for determination of an updated estimation of the current position of the computing device.
Abstract translation: 示例包括用于在计算设备的估计位置的角度，前向和侧向误差之间分解误差分量的系统和方法。 一种方法包括基于计算设备的先前位置，经过的时间的估计速度和计算设备的行进方向来确定计算设备的当前位置的估计，确定前向，侧向和定向 改变计算装置的当前位置的估计的误差分量，基于计算装置的平均观察运动确定应用于向前，侧向和方向改变误差分量的权重，以及使用加权的向前，侧向和 取向变化误差分量作为用于确定计算设备的当前位置的更新估计的约束。
-
33.发明授权Determining and aligning a position of a device and a position of a wireless access point (AP) 有权确定和对齐设备的位置和无线接入点（AP）的位置公开(公告)号：US09544871B2
公开(公告)日：2017-01-10
申请号：US14509189
申请日：2014-10-08
Applicant: Google Inc.
Inventor： Etienne Le Grand , Brian Patrick Williams
CPC classification number: H04W64/003 , G01S5/0252 , G01S19/01 , H04W4/04 , H04W64/006 , H04W88/08
Abstract: Examples describe systems and methods for iteratively determining a signal strength map for a wireless access point (AP) aligned to position coordinates, positions of a device, and positions of the wireless APs. An example method includes selecting traces and a wireless AP among the traces for which data is indicative of a threshold amount of information to estimate a position of the device and a position of the wireless AP, selecting first characteristics from the traces to remain constant and second characteristics to be variable, and selecting a localization constraint that provides boundaries on the position of the device and the position of the wireless AP. The method also includes performing a simultaneous localization and mapping (SLAM) optimization of the position of the device and the position of the wireless AP based on the localization constraint with the first characteristics held constant and the second characteristics allowed to vary.
Abstract translation: 示例描述用于迭代地确定与位置坐标，设备的位置和无线AP的位置对准的无线接入点（AP）的信号强度图的系统和方法。 示例性方法包括在迹线中选择迹线和无线AP，数据指示阈值信息量以估计设备的位置和无线AP的位置，从迹线中选择第一特性以保持恒定，并且第二 特征是可变的，并且选择在设备的位置和无线AP的位置上提供边界的定位约束。 该方法还包括基于定位约束执行设备的位置和无线AP的位置的同时定位和映射（SLAM）优化，其中第一特性保持恒定，并且允许第二特性变化。
-
公开(公告)号：US20160337599A1
公开(公告)日：2016-11-17
申请号：US14708955
申请日：2015-05-11
Applicant: Google Inc.
Inventor： Brian Patrick Williams , Ryan Michael Hickman
CPC classification number: H04N5/262 , G01C21/28 , G06K9/00268 , G06K9/00671 , G06T1/0007 , G06T7/246 , G06T7/55 , G06T17/05 , G06T2200/04 , G06T2200/08 , G06T2207/20024 , G06T2207/20224 , G06T2207/30201 , G06T2207/30204 , H04W64/00
Abstract: A mobile device includes at least one imaging sensor to capture imagery of an environment of the mobile device, a privacy filter module, a spatial feature detection module, an assembly module, and a network interface. The privacy filter module is to perform at least one image-based privacy filtering process using the captured imagery to generate filtered imagery. The spatial feature detection module is to determine a set of spatial features in the filtered imagery. The assembly module is to generate an area description file representative of the set of spatial features. The network interface is to transmit the area description file to a remote computing system. The assembly module may select only a subset of the set of spatial features for inclusion in the area description file.
Abstract translation: 移动设备包括至少一个成像传感器以捕获移动设备的环境的图像，隐私过滤器模块，空间特征检测模块，组装模块和网络接口。 隐私过滤器模块是使用所捕获的图像来执行至少一个基于图像的隐私过滤处理，以生成过滤的图像。 空间特征检测模块是确定滤波图像中的一组空间特征。 组装模块是生成表示该组空间特征的区域描述文件。 网络接口将区域描述文件传送到远程计算系统。 组装模块可以仅选择该组空间特征的子集以包含在区域描述文件中。
-
35.发明申请公开(公告)号：US20160335497A1
公开(公告)日：2016-11-17
申请号：US14708877
申请日：2015-05-11
Applicant: Google Inc.
Inventor： Brian Patrick Williams , Ryan Michael Hickman , Laurent Tu , Esha Nerurkar , Simon Lynen
CPC classification number: G06K9/00671 , G01C21/206 , G06F17/30256 , G06T7/74 , G06T2207/10004 , G06T2207/10028
Abstract: A computing system includes a network interface, a first datastore, a second datastore, and a merge module. The merge module is to receive a set of one or more area description files from a set of one or more first mobile devices. Each area description file represents a point cloud of spatial features detected by a corresponding first mobile device at an area. The computing system further includes a localization module and a query module. The localization generation module is to generate a localization area description file for the area from the set of one or more area description files and to store the localization area description file in the second datastore. The localization area description file represents a point cloud of spatial features for the area. The query module is to provide the localization area description file to a second mobile device via the network interface.
Abstract translation: 计算系统包括网络接口，第一数据存储区，第二数据存储区和合并模块。 合并模块是从一个或多个第一移动设备的集合接收一组一个或多个区域描述文件。 每个区域描述文件表示在一个区域由相应的第一移动设备检测到的空间特征的点云。 计算系统还包括定位模块和查询模块。 本地化生成模块是从一个或多个区域描述文件的集合中生成针对该区域的定位区域描述文件，并将定位区域描述文件存储在第二数据存储区中。 定位区域描述文件表示该区域的空间特征的点云。 查询模块是通过网络接口向第二移动设备提供定位区描述文件。
-
Patent Agency Ranking
公开(公告)号：US09386417B1
公开(公告)日：2016-07-05
申请号：US14720825
申请日：2015-05-24
Applicant: Google Inc.
Inventor： Andrew Ames Bunner , Alan Lee Gardner, III , Mohammed Waleed Kadous , Brian Patrick Williams , Marc Stogaitis , Nadav Aharony , Brian Duff , Pascal Tom Getreuer , Zhentao Sun , Daniel Estrada Alva , Ami Patel , Benjamin Razon , Richard Daniel Webb , Tony Weber , Thomas Yuchin Chao , Ryan Michael Rifkin , Richard Francis Lyon , Liem Tran , Joseph A. Farfel
Abstract: The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: process one or more signals to determine coarse grain location information of a first device and a second device; determine whether the first device and the second device are copresent based on the coarse grain location information; in response to determining that the first device and the second device are copresent based on the coarse grain location information, transmit a signal to the second device to alert the second device to listen for a fine grain copresence token from the first device; and refine copresence based on receiving an indication that the second device has received the fine grain copresence token.
-
37.发明申请公开(公告)号：US20160157059A1
公开(公告)日：2016-06-02
申请号：US15018936
申请日：2016-02-09
Applicant: Google Inc.
Inventor： Mohammed Waleed Kadous , Marc Stogaitis , Brian Patrick Williams , Etienne Le Grand
Abstract: The present disclosure describes methods, systems, and apparatuses for determining the likelihood that two wireless scans of a mobile computing device were performed in the same location. The likelihood is determined by scanning for wireless networks with a computing device. The scanning includes a receiving a plurality of network attributes for each wireless networks within the range of the mobile computing device. Further, the likelihood is determined by comparing the plurality of network attributes from the scanning with a reference set of network attributes. The comparing of network attributes is used to determine an attribute comparison. Finally, the likelihood between a position associated with the reference set of network attributes and the computing device, based on the attribute comparison, determines a position associated with the network.
-
38.发明授权Methods and systems for signal diffusion modeling for a discretized map of signal strength 有权用于信号强度离散映射的信号扩散建模的方法和系统公开(公告)号：US09357520B2
公开(公告)日：2016-05-31
申请号：US14169175
申请日：2014-01-31
Applicant: Google Inc.
Inventor： Etienne Le Grand , Brian Patrick Williams
CPC classification number: H04W64/003 , G01S5/0252 , H04W4/06 , H04W84/12 , H04W92/10
Abstract: Examples herein include methods and systems for signal diffusion modeling for a discretized map of signal. An example method includes receiving data related to RSSI for a wireless AP for a plurality of locations of an area, associating the data to a diagram of the area based on the plurality of locations of the area, determining a given partition of the diagram in which a magnitude of a given RSSI associated with the given partition is greater than or equal to a highest magnitude of a given RSSI associated with any partitions of the plurality of partitions, assigning a location of the wireless AP to be within the given partition, and applying a constraint such that a magnitude of a given RSSI associated with other respective partitions is less than or equal to a highest magnitude of a given RSSI associated with neighboring partitions of the other respective partitions.
Abstract translation: 本文的示例包括用于信号的离散映射的信号扩散建模的方法和系统。 一个示例性方法包括接收关于区域的多个位置的用于无线AP的RSSI的数据，基于该区域的多个位置将该数据与该区域的图相关联，确定该图的给定分区，其中 与给定分区相关联的给定RSSI的大小大于或等于与多个分区中的任何分区相关联的给定RSSI的最大幅度，将无线AP的位置分配给在给定分区内，以及应用 约束使得与其他相应分区相关联的给定RSSI的幅度小于或等于与其他相应分区的相邻分区相关联的给定RSSI的最大幅度。
-
39.发明授权公开(公告)号：US09294877B2
公开(公告)日：2016-03-22
申请号：US13972713
申请日：2013-08-21
Applicant: Google Inc.
Inventor： Mohammed Waleed Kadous , Marc Stogaitis , Brian Patrick Williams , Etienne Le Grand
Abstract: The present disclosure describes methods, systems, and apparatuses for determining the likelihood that two wireless scans of a mobile computing device were performed in the same location. The likelihood is determined by scanning for wireless networks with a computing device. The scanning includes a receiving a plurality of network attributes for each wireless networks within the range of the mobile computing device. Further, the likelihood is determined by comparing the plurality of network attributes from the scanning with a reference set of network attributes. The comparing of network attributes is used to determine an attribute comparison. Finally, the likelihood between a position associated with the reference set of network attributes and the computing device, based on the attribute comparison, determines a position associated with the network.
-
40.发明申请Data Driven Evaluation and Rejection of Trained Gaussian Process-Based Wireless Mean and Standard Deviation Models 有权基于训练高斯过程的无线平均和标准偏差模型的数据驱动评估和拒绝公开(公告)号：US20160080908A1
公开(公告)日：2016-03-17
申请号：US14843955
申请日：2015-09-02
Applicant: Google Inc.
Inventor： Brian John Julian , Etienne Le Grand , Brian Patrick Williams
CPC classification number: H04W4/029 , H04L41/142 , H04L43/08 , H04W4/023
Abstract: Disclosed are apparatus and methods for providing outputs; e.g., location estimates, based on trained Gaussian processes. A computing device can determine trained Gaussian processes related to wireless network signal strengths, where a particular trained Gaussian process is associated with one or more hyperparameters. The computing device can designate one or more hyperparameters. The computing device can determine a hyperparameter histogram for values of the designated hyperparameters of the trained Gaussian processes. The computing device can determine a candidate Gaussian process associated with one or more candidate hyperparameter value for the designated hyperparameters. The computing device can determine whether the candidate hyperparameter values are valid based on the hyperparameter histogram. The computing device can, after determining that the candidate hyperparameter values are valid, add the candidate Gaussian process to the trained Gaussian processes. The computing device can provide an estimated location output based on the trained Gaussian processes.
Abstract translation: 公开了用于提供输出的装置和方法; 例如，基于经训练的高斯过程的位置估计。 计算设备可以确定与无线网络信号强度相关的经训练的高斯过程，其中特定训练高斯过程与一个或多个超参数相关联。 计算设备可以指定一个或多个超参数。 计算设备可以确定训练高斯过程的指定超参数的值的超参数直方图。 计算设备可以确定与指定的超参数的一个或多个候选超参数值相关联的候选高斯过程。 计算设备可以基于超参数直方图来确定候选超参数值是否有效。 在确定候选超参数值有效之后，计算设备可以将候选高斯过程加到经过训练的高斯过程中。 计算设备可以基于经过训练的高斯过程来提供估计的位置输出。
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.035 seconds)
