公开(公告)号：US20060167647A1

公开(公告)日：2006-07-27

申请号：US10994550

申请日：2004-11-22

申请人： John Krumm ,  Eric Horvitz ,  Ramaswamy Hariharan

发明人： John Krumm ,  Eric Horvitz ,  Ramaswamy Hariharan

IPC分类号： G01K1/00

CPC分类号： G01W1/17 ,  H04M1/72569 ,  Y02D70/142 ,  Y02D70/144 ,  Y02D70/164

摘要： Methods and systems that determine automatically the likelihood that a device is inside or outside of a structure or building. The system uses one or more sensors to detect ambient conditions, and make the determination. The inference can be used to save power or suppress services from certain devices, which are irrelevant, cannot be used effectively, or do not function under certain circumstances. In support thereof, the system includes one or more context sensors that measure parameters associated probabilistically with the context of a device. A context computing component considers one or more context sensors and facilitates determination of ideal actions, policies, and situations associated with the device. A service provided by the subject invention is the inference from one or more available observations the probability that the device is inside versus outside.

摘要翻译： 自动确定设备在结构或建筑物内部或外部的可能性的方法和系统。 该系统使用一个或多个传感器来检测环境条件，并进行确定。 推论可以用来节省电力或者抑制某些设备的服务，这些设备是无关紧要的，不能有效地使用，或者在某些情况下不起作用。 为了支持它，系统包括一个或多个上下文传感器，其测量与设备的上下文概率性相关联的参数。 上下文计算组件考虑一个或多个上下文传感器并且有助于确定与该设备相关联的理想动作，策略和情形。 由本发明提供的服务是从一个或多个可用观察结果推断设备在内部和外部的概率。

公开(公告)号：US20110161276A1

公开(公告)日：2011-06-30

申请号：US13040067

申请日：2011-03-03

申请人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

发明人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

IPC分类号： G06N5/02

CPC分类号： G06F17/30522 ,  G06F17/3087 ,  H04L67/18 ,  H04W4/02 ,  H04W4/029 ,  H04W4/18

摘要： Described are methods that utilize a geographic location technology (e.g., GPS) to determine user location data, and existing network-based websites (e.g., Internet websites) for searching and accessing data related to the location data such that the user context can be developed and stored. A location component is provided that determines location data of a wireless communications device of a user. A context component is provided that accesses context data based on the location data to define a context in which the device is located. Activities, goals, and overall context of a user can be inferred through statistical fusion of multiple sources of evidence. The context data is presented to the user via the wireless device such that the user can make decisions as to where to go, for example. User preferences can be accessed and applied to filter context data according to what the user desires to see and access.

摘要翻译： 描述的是利用地理位置技术（例如，GPS）来确定用户位置数据的方法以及用于搜索和访问与位置数据相关的数据的现有的基于网络的网站（例如，因特网网站），使得可以开发用户上下文 并存储。 提供了确定用户的无线通信设备的位置数据的位置组件。 提供了基于位置数据访问上下文数据以定义设备所在的上下文的上下文组件。 可以通过统计融合多种证据来推断用户的活动，目标和总体情境。 上下文数据经由无线设备呈现给用户，使得用户可以做出关于例如去哪里的决定。 用户偏好可以被访问并应用于根据用户期望查看和访问的内容过滤上下文数据。

公开(公告)号：US20070006098A1

公开(公告)日：2007-01-04

申请号：US11172474

申请日：2005-06-30

申请人： John Krumm ,  Eric Horvitz ,  Ramaswamy Hariharan

发明人： John Krumm ,  Eric Horvitz ,  Ramaswamy Hariharan

IPC分类号： H04M1/56

CPC分类号： G06F17/30522 ,  G06F17/3087 ,  H04L67/18 ,  H04W4/02 ,  H04W4/029 ,  H04W4/18

摘要： Described are methods that utilize a geographic location technology (e.g., GPS) to determine user location data, and existing network-based websites (e.g., Internet websites) for searching and accessing data related to the location data such that the user context can be developed and stored. A location component is provided that determines location data of a wireless communications device of a user. A context component is provided that accesses context data based on the location data to define a context in which the device is located. Activities, goals, and overall context of a user can be inferred through statistical fusion of multiple sources of evidence. The context data is presented to the user via the wireless device such that the user can make decisions as to where to go, for example. User preferences can be accessed and applied to filter context data according to what the user desires to see and access.

摘要翻译： 描述的是利用地理位置技术（例如，GPS）来确定用户位置数据的方法以及用于搜索和访问与位置数据相关的数据的现有的基于网络的网站（例如，因特网网站），使得可以开发用户上下文 并存储。 提供了确定用户的无线通信设备的位置数据的位置组件。 提供了基于位置数据访问上下文数据以定义设备所在的上下文的上下文组件。 可以通过统计融合多种证据来推断用户的活动，目标和总体情境。 上下文数据经由无线设备呈现给用户，使得用户可以做出关于例如去哪里的决定。 用户偏好可以被访问并应用于根据用户期望查看和访问的内容来过滤上下文数据。

公开(公告)号：US20060085177A1

公开(公告)日：2006-04-20

申请号：US10968862

申请日：2004-10-19

申请人： Kentaro Toyama ,  Ramaswamy Hariharan

发明人： Kentaro Toyama ,  Ramaswamy Hariharan

IPC分类号： G06F9/45

CPC分类号： G01C21/26

摘要： A location history is a collection of locations over time for an object. By applying a recurring time period to a location history, it can be converted into a stochastic model of the location history. For example, a location history can be reorganized based on intervals that subside a recurring cycle. In a described implementation, training a location history model involves traversing each interval of multiple cycles of a target location history. After each object location at each interval is entered into a training matrix, the intervals can be normalized to determine relative probabilities per location for each interval of a designated cycle. The training and resulting location history model can be Markovian or non-Markovian. Applications include probabilistic location estimation, fusion of location estimates, location-history simulation, optimal scheduling, transition analysis, clique analysis, and so forth.

摘要翻译： 位置历史记录是对象的一段时间内的位置集合。 通过将周期性时间段应用于位置历史，可将其转换为位置历史的随机模型。 例如，位置历史记录可以根据周期性周期的间隔重新组织。 在所描述的实现中，训练位置历史模型涉及遍历目标位置历史的多个周期的每个间隔。 在每个间隔的每个对象位置被输入训练矩阵之后，可以对这些间隔进行归一化以确定每个指定周期的每个间隔的每个位置的相对概率。 训练和结果位置历史模型可以是马尔科夫或非马尔科夫。 应用包括概率位置估计，位置估计融合，位置历史模拟，最优调度，转换分析，集团分析等。

公开(公告)号：US20070085673A1

公开(公告)日：2007-04-19

申请号：US11558410

申请日：2006-11-09

申请人： John Krumm ,  Eric Horvitz ,  Ramaswamy Hariharan

发明人： John Krumm ,  Eric Horvitz ,  Ramaswamy Hariharan

IPC分类号： G08B19/00 ,  G08B21/00

CPC分类号： G01W1/17 ,  H04M1/72569 ,  Y02D70/142 ,  Y02D70/144 ,  Y02D70/164

摘要： Methods and systems that determine automatically the likelihood that a device is inside or outside of a structure or building. The system uses one or more sensors to detect ambient conditions, and make the determination. The inference can be used to save power or suppress services from certain devices, which are irrelevant, cannot be used effectively, or do not function under certain circumstances. In support thereof, the system includes one or more context sensors that measure parameters associated probabilistically with the context of a device. A context computing component considers one or more context sensors and facilitates determination of ideal actions, policies, and situations associated with the device. A service provided by the subject invention is the inference from one or more available observations the probability that the device is inside versus outside.

摘要翻译： 自动确定设备在结构或建筑物内部或外部的可能性的方法和系统。 该系统使用一个或多个传感器来检测环境条件，并进行确定。 推论可以用来节省电力或者抑制某些设备的服务，这些设备是无关紧要的，不能有效地使用，或者在某些情况下不起作用。 为了支持它，系统包括一个或多个上下文传感器，其测量与设备的上下文概率性相关联的参数。 上下文计算组件考虑一个或多个上下文传感器并且有助于确定与该设备相关联的理想动作，策略和情形。 由本发明提供的服务是从一个或多个可用观察结果推断设备在内部和外部的概率。

公开(公告)号：US08539380B2

公开(公告)日：2013-09-17

申请号：US13040067

申请日：2011-03-03

申请人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

发明人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

IPC分类号： G06F3/048 ,  G06F3/14

CPC分类号： G06F17/30522 ,  G06F17/3087 ,  H04L67/18 ,  H04W4/02 ,  H04W4/029 ,  H04W4/18

摘要： Described are methods that utilize a geographic location technology (e.g., GPS) to determine user location data, and existing network-based websites (e.g., Internet websites) for searching and accessing data related to the location data such that the user context can be developed and stored. A location component is provided that determines location data of a wireless communications device of a user. A context component is provided that accesses context data based on the location data to define a context in which the device is located. Activities, goals, and overall context of a user can be inferred through statistical fusion of multiple sources of evidence. The context data is presented to the user via the wireless device such that the user can make decisions as to where to go, for example. User preferences can be accessed and applied to filter context data according to what the user desires to see and access.

摘要翻译： 描述的是利用地理位置技术（例如，GPS）来确定用户位置数据的方法以及用于搜索和访问与位置数据相关的数据的现有的基于网络的网站（例如，因特网网站），使得可以开发用户上下文 并存储。 提供了确定用户的无线通信设备的位置数据的位置组件。 提供了基于位置数据访问上下文数据以定义设备所在的上下文的上下文组件。 可以通过统计融合多种证据来推断用户的活动，目标和总体情境。 上下文数据经由无线设备呈现给用户，使得用户可以做出关于例如去哪里的决定。 用户偏好可以被访问并应用于根据用户期望查看和访问的内容来过滤上下文数据。

公开(公告)号：US07925995B2

公开(公告)日：2011-04-12

申请号：US11172474

申请日：2005-06-30

申请人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

发明人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

IPC分类号： G06F3/048 ,  G06F3/14

CPC分类号： G06F17/30522 ,  G06F17/3087 ,  H04L67/18 ,  H04W4/02 ,  H04W4/029 ,  H04W4/18

摘要： Described are methods that utilize a geographic location technology (e.g., GPS) to determine user location data, and existing network-based websites (e.g., Internet websites) for searching and accessing data related to the location data such that the user context can be developed and stored. A location component is provided that determines location data of a wireless communications device of a user. A context component is provided that accesses context data based on the location data to define a context in which the device is located. Activities, goals, and overall context of a user can be inferred through statistical fusion of multiple sources of evidence. The context data is presented to the user via the wireless device such that the user can make decisions as to where to go, for example. User preferences can be accessed and applied to filter context data according to what the user desires to see and access.

摘要翻译： 描述的是利用地理位置技术（例如，GPS）来确定用户位置数据的方法以及用于搜索和访问与位置数据相关的数据的现有的基于网络的网站（例如，因特网网站），使得可以开发用户上下文 并存储。 提供了确定用户的无线通信设备的位置数据的位置组件。 提供了基于位置数据访问上下文数据以定义设备所在的上下文的上下文组件。 可以通过统计融合多种证据来推断用户的活动，目标和总体情境。 上下文数据经由无线设备呈现给用户，使得用户可以做出关于例如去哪里的决定。 用户偏好可以被访问并应用于根据用户期望查看和访问的内容来过滤上下文数据。

公开(公告)号：US07868786B2

公开(公告)日：2011-01-11

申请号：US10968861

申请日：2004-10-19

申请人： Kentaro Toyama ,  Ramaswamy Hariharan ,  Ross G. Cutler ,  John R. Douceur ,  Nuria M. Oliver ,  Eric K. Ringger ,  Daniel C. Robbins ,  Matthew T. Uyttendaele

发明人： Kentaro Toyama ,  Ramaswamy Hariharan ,  Ross G. Cutler ,  John R. Douceur ,  Nuria M. Oliver ,  Eric K. Ringger ,  Daniel C. Robbins ,  Matthew T. Uyttendaele

IPC分类号： G08G1/123

CPC分类号： G06Q30/02

摘要： A location history is a collection of locations over time for an object. A stay is a single instance of an object spending some time in one place, and a destination is any place where one or more objects have experienced a stay. Location histories are parsed using stays and destinations. In a described implementation, each location of a location history is recorded as a spatial position and a corresponding time at which the spatial position is acquired. Stays are extracted from a location history by analyzing locations thereof with regard to a temporal threshold and a spatial threshold. Specifically, two or more locations are considered a stay if they exceed a minimum stay duration and are within a maximum roaming distance. Each stay includes a location, a starting time, and an ending time. Destinations are produced from the extracted stays using a clustering operation and a predetermined scaling factor.

摘要翻译： 位置历史记录是对象的一段时间内的位置集合。 逗留是在一个地方花费一些时间的对象的单个实例，目的地是一个或多个对象经历了逗留的任何地方。 使用停留和目的地解析位置历史记录。 在描述的实现中，将位置历史的每个位置记录为空间位置和获取空间位置的对应时间。 通过相对于时间阈值和空间阈值分析其位置，从位置历史中提取静止。 具体来说，如果两个或多个位置超过最小停留持续时间并处于最大漫游距离内，则将其视为停留。 每个住宿包括一个位置，一个起始时间和一个结束时间。 使用聚类操作和预定缩放因子从所提取的逗留中产生目的地。

公开(公告)号：US07720652B2

公开(公告)日：2010-05-18

申请号：US10968862

申请日：2004-10-19

申请人： Kentaro Toyama ,  Ramaswamy Hariharan

发明人： Kentaro Toyama ,  Ramaswamy Hariharan

IPC分类号： G06F7/60 ,  G06F17/10

CPC分类号： G01C21/26

摘要： A location history is a collection of locations over time for an object. By applying a recurring time period to a location history, it can be converted into a stochastic model of the location history. For example, a location history can be reorganized based on intervals that subside a recurring cycle. In a described implementation, training a location history model involves traversing each interval of multiple cycles of a target location history. After each object location at each interval is entered into a training matrix, the intervals can be normalized to determine relative probabilities per location for each interval of a designated cycle. The training and resulting location history model can be Markovian or non-Markovian. Applications include probabilistic location estimation, fusion of location estimates, location-history simulation, optimal scheduling, transition analysis, clique analysis, and so forth.

摘要翻译： 位置历史记录是对象的一段时间内的位置集合。 通过将周期性时间段应用于位置历史，可将其转换为位置历史的随机模型。 例如，位置历史记录可以根据周期性周期的间隔重新组织。 在所描述的实现中，训练位置历史模型涉及遍历目标位置历史的多个周期的每个间隔。 在每个间隔的每个对象位置被输入训练矩阵之后，可以对这些间隔进行归一化以确定每个指定周期的每个间隔的每个位置的相对概率。 训练和结果位置历史模型可以是马尔科夫或非马尔科夫。 应用包括概率位置估计，位置估计融合，位置历史模拟，最优调度，转换分析，集团分析等。

公开(公告)号：US07327245B2

公开(公告)日：2008-02-05

申请号：US10994550

申请日：2004-11-22

申请人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

发明人： John C. Krumm ,  Eric J. Horvitz ,  Ramaswamy Hariharan

IPC分类号： G08B23/00

CPC分类号： G01W1/17 ,  H04M1/72569 ,  Y02D70/142 ,  Y02D70/144 ,  Y02D70/164

摘要： Methods and systems that determine automatically the likelihood that a device is inside or outside of a structure or building. The system uses one or more sensors to detect ambient conditions, and make the determination. The inference can be used to save power or suppress services from certain devices, which are irrelevant, cannot be used effectively, or do not function under certain circumstances. In support thereof, the system includes one or more context sensors that measure parameters associated probabilistically with the context of a device. A context computing component considers one or more context sensors and facilitates determination of ideal actions, policies, and situations associated with the device. A service provided by the subject invention is the inference from one or more available observations the probability that the device is inside versus outside.