公开(公告)号：US08718925B2

公开(公告)日：2014-05-06

申请号：US12466308

申请日：2009-05-14

申请人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

发明人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： G01C21/30

CPC分类号： G01C21/3484

摘要： A route-planning system is described that leverages a database of observations about routes taken by drivers in a region to generate context and/or preference sensitive routes. Contextual information such as time of day and day of week, along with such findings as the observed velocities on different roads and the efficiency of trips is noted from the database of trips to inform a route generation component. The route-generation component considers velocities, contextual information, and other findings to compute preferred routes for people requesting directions from a first geographical point to a second geographical point. In one usage, properties of a driver's own prior routes are used to generate personalized routes, including routes between previously unobserved starting and ending locations. In another application, sets of observed routes of other drivers are used in a collaborative manner to generate recommended routes for a specific driver based on inferred preferences of the driver.

摘要翻译： 描述了一种路线规划系统，其利用关于区域中的驾驶员所采取的路线的观测数据库来生成上下文和/或偏好敏感路线。 从数据库中注意到诸如一天中的时间和星期几的上下文信息以及观察到的不同道路上的速度和旅行效率的发现，以通知路线生成部件。 路线生成组件考虑速度，情境信息和其他发现，以计算从第一地理点到第二地理点的请求人的优选路线。 在一种使用中，使用驱动程序自己的先前路由的属性来生成个性化路由，包括之前未查看的起始和结束位置之间的路由。 在另一个应用中，以协作的方式使用其他驱动程序的观察路线集合，以基于推断的驱动程序的偏好来为特定的驱动程序生成推荐的路由。

公开(公告)号：US20090271104A1

公开(公告)日：2009-10-29

申请号：US12466308

申请日：2009-05-14

申请人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

发明人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： G01C21/36 ,  G08G1/00

CPC分类号： G01C21/3484

摘要： A route-planning system is described that leverages a database of observations about routes taken by drivers in a region to generate context and/or preference sensitive routes. Contextual information such as time of day and day of week, along with such findings as the observed velocities on different roads and the efficiency of trips is noted from the database of trips to inform a route generation component. The route-generation component considers velocities, contextual information, and other findings to compute preferred routes for people requesting directions from a first geographical point to a second geographical point. In one usage, properties of a driver's own prior routes are used to generate personalized routes, including routes between previously unobserved starting and ending locations. In another application, sets of observed routes of other drivers are used in a collaborative manner to generate recommended routes for a specific driver based on inferred preferences of the driver.

摘要翻译： 描述了一种路线规划系统，其利用关于区域中的驾驶员所采取的路线的观测数据库来生成上下文和/或偏好敏感路线。 从数据库中注意到诸如一天中的时间和星期几的上下文信息以及观察到的不同道路上的速度和旅行效率的发现，以通知路线生成部件。 路线生成组件考虑速度，情境信息和其他发现，以计算从第一地理点到第二地理点的请求人的优选路线。 在一种使用中，使用驱动程序自己的先前路由的属性来生成个性化路由，包括之前未查看的起始和结束位置之间的路由。 在另一个应用中，以协作的方式使用其他驱动程序的观察路线集合，以基于推断的驱动程序的偏好来为特定的驱动程序生成推荐的路由。

公开(公告)号：US07610151B2

公开(公告)日：2009-10-27

申请号：US11426903

申请日：2006-06-27

申请人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

发明人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： G01C21/30

CPC分类号： G01C21/3484

摘要： A route-planning system is described that leverages a database of observations about routes taken by drivers in a region to generate context and/or preference sensitive routes. Contextual information such as time of day and day of week, along with such findings as the observed velocities on different roads and the efficiency of trips is noted from the database of trips to inform a route generation component. The route-generation component considers velocities, contextual information, and other findings to compute preferred routes for people requesting directions from a first geographical point to a second geographical point. In one usage, properties of a driver's own prior routes are used to generate personalized routes, including routes between previously unobserved starting and ending locations. In another application, sets of observed routes of other drivers are used in a collaborative manner to generate recommended routes for a specific driver based on inferred preferences of the driver.

摘要翻译： 描述了一种路线规划系统，其利用关于区域中的驾驶员所采取的路线的观测数据库来生成上下文和/或偏好敏感路线。 从数据库中注意到诸如一天中的时间和星期几的上下文信息以及观察到的不同道路上的速度和旅行效率的发现，以通知路线生成部件。 路线生成组件考虑速度，情境信息和其他发现，以计算从第一地理点到第二地理点的请求人的优选路线。 在一种使用中，使用驱动程序自己的先前路由的属性来生成个性化路由，包括之前未查看的起始和结束位置之间的路由。 在另一个应用中，以协作的方式使用其他驱动程序的观察路线集合，以基于推断的驱动程序的偏好来为特定的驱动程序生成推荐的路由。

公开(公告)号：US20070299599A1

公开(公告)日：2007-12-27

申请号：US11426903

申请日：2006-06-27

申请人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

发明人： Julia M. Letchner ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： G01C21/00

CPC分类号： G01C21/3484

摘要： A route-planning system is described that leverages a database of observations about routes taken by drivers in a region to generate context and/or preference sensitive routes. Contextual information such as time of day and day of week, along with such findings as the observed velocities on different roads and the efficiency of trips is noted from the database of trips to inform a route generation component. The route-generation component considers velocities, contextual information, and other findings to compute preferred routes for people requesting directions from a first geographical point to a second geographical point. In one usage, properties of a driver's own prior routes are used to generate personalized routes, including routes between previously unobserved starting and ending locations. In another application, sets of observed routes of other drivers are used in a collaborative manner to generate recommended routes for a specific driver based on inferred preferences of the driver.

摘要翻译： 描述了一种路线规划系统，其利用关于区域中的驾驶员所采取的路线的观测数据库来生成上下文和/或偏好敏感路线。 从数据库中注意到诸如一天中的时间和星期几的上下文信息以及观察到的不同道路上的速度和旅行效率的发现，以通知路线生成部件。 路线生成组件考虑速度，情境信息和其他发现，以计算从第一地理点到第二地理点的请求人的优选路线。 在一种使用中，使用驱动程序自己的先前路由的属性来生成个性化路由，包括之前未查看的起始和结束位置之间的路由。 在另一个应用中，以协作的方式使用其他驱动程序的观察路线集合，以基于推断的驱动程序的偏好来为特定的驱动程序生成推荐的路由。

公开(公告)号：US08645061B2

公开(公告)日：2014-02-04

申请号：US12816496

申请日：2010-06-16

申请人： Paul E. Newson ,  John C. Krumm ,  Eric J. Horvitz

发明人： Paul E. Newson ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： G01C21/00

CPC分类号： G01C21/30 ,  G01C21/3484

摘要： Systems, methods, and devices are described for implementing map matching techniques relating to measured location data. Probabilistic models, including temporal Bayesian network models and Hidden Markov Models, may be used for combining multiple classes of evidence relating to potential locations of points traversed on routes over time. Multiple route segments and overall routes may be maintained under relative uncertainty as candidates. The candidate route segments and overall routes may then be reduced into a smaller number of candidates or a single most likely route as a trip progresses. As the trip progresses, route segments in proximity to each location point are identified and candidate matches are determined. A probability of an entity traversing a candidate match at a given time and a probability of an entity traversing between a first candidate match at a first time and a second candidate match at a second time are determined based on a plurality of factors. Different modalities may be used to measure and transmit the location data.

摘要翻译： 描述了用于实现与测量的位置数据相关的地图匹配技术的系统，方法和设备。 包括时间贝叶斯网络模型和隐马尔可夫模型在内的概率模型可用于组合多个类别的证据，这些证据与路线上经过的点的潜在位置有关。 多个路线段和总体路线在相对不确定性的情况下可能被保持为候选。 然后随着行程的进行，候选路线段和总体路线可以被减少到更少数量的候选者或单个最可能的路线。 当行程进行时，识别每个位置点附近的路段，并且确定候选匹配。 基于多个因素来确定在给定时间穿过候选匹配的实体的概率和在第一时间与第一候选匹配之间的实体遍历的概率与第二候选匹配的概率。 可以使用不同的模式来测量和发送位置数据。

公开(公告)号：US08244240B2

公开(公告)日：2012-08-14

申请号：US11427778

申请日：2006-06-29

申请人： Dimitris Achlioptas ,  John C. Krumm ,  Eric J. Horvitz

发明人： Dimitris Achlioptas ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： H04W4/00 ,  H04W24/00 ,  H04B1/04

CPC分类号： H04W24/02 ,  G01S5/0236 ,  H04W16/00

摘要： The claimed subject matter provides systems and/or methods that facilitate automatically maintaining a database of base stations. A location component can obtain a query that includes a listing of detected base stations. Additionally, the location component can identify whether the detected base stations are included in a base station database. Further, the location component can generate an estimated location related to the query. Moreover, a database update component can modify the base station database based at least in part upon the query.

摘要翻译： 所要求保护的主题提供便于自动维护基站数据库的系统和/或方法。 位置组件可以获得包括检测到的基站的列表的查询。 另外，位置组件可以识别检测到的基站是否包括在基站数据库中。 此外，位置组件可以生成与查询相关的估计位置。 此外，数据库更新组件可以至少部分地基于查询来修改基站数据库。

公开(公告)号：US20110313648A1

公开(公告)日：2011-12-22

申请号：US12816496

申请日：2010-06-16

申请人： Paul E. Newson ,  John C. Krumm ,  Eric J. Horvitz

发明人： Paul E. Newson ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： G01C21/34

CPC分类号： G01C21/30 ,  G01C21/3484

摘要： Systems, methods, and devices are described for implementing map matching techniques relating to measured location data. Probabilistic models, including temporal Bayesian network models and Hidden Markov Models, may be used for combining multiple classes of evidence relating to potential locations of points traversed on routes over time. Multiple route segments and overall routes may be maintained under relative uncertainty as candidates. The candidate route segments and overall routes may then be reduced into a smaller number of candidates or a single most likely route as a trip progresses. As the trip progresses, route segments in proximity to each location point are identified and candidate matches are determined. A probability of an entity traversing a candidate match at a given time and a probability of an entity traversing between a first candidate match at a first time and a second candidate match at a second time are determined based on a plurality of factors. Different modalities may be used to measure and transmit the location data.

摘要翻译： 描述了用于实现与测量的位置数据相关的地图匹配技术的系统，方法和设备。 包括时间贝叶斯网络模型和隐马尔可夫模型在内的概率模型可用于组合多个类别的证据，这些证据与路线上经过的点的潜在位置有关。 多个路线段和总体路线在相对不确定性的情况下可能被保持为候选。 然后随着行程的进行，候选路线段和总体路线可以被减少到更少数量的候选者或单个最可能的路线。 当行程进行时，识别每个位置点附近的路段，并且确定候选匹配。 基于多个因素来确定在给定时间穿过候选匹配的实体的概率和在第一时间与第一候选匹配之间的实体遍历的概率与第二候选匹配的概率。 可以使用不同的模式来测量和发送位置数据。

公开(公告)号：US07532113B2

公开(公告)日：2009-05-12

申请号：US11188951

申请日：2005-07-25

申请人： Eric J. Horvitz ,  John C. Krumm

发明人： Eric J. Horvitz ,  John C. Krumm

IPC分类号： G08B1/08

CPC分类号： G01S5/0252 ,  G01C21/206 ,  H04L29/06 ,  Y10S707/99937

摘要： A location system for locating and determining the motion and velocity of a wireless device. The methods include direct inferences about whether a device is in motion versus static based on a statistical analysis of the variation of radio signal strengths over time. The system is trained according to a sparse set of identified locations from which signal strengths are measured. The system uses the signal properties of the identified locations to interpolate for a new location of the wireless device. The system uses a probabilistic graph where the identified locations of the floor plan, expected walking speeds of pedestrians, and independent inference of whether or not the device is in motion are used to determine the new location of the device.

摘要翻译： 用于定位和确定无线设备的运动和速度的定位系统。 这些方法包括基于无线电信号强度随时间的变化的统计分析，关于设备是否运动与静态的直接推断。 根据测量信号强度的识别位置的稀疏集合对系统进行训练。 该系统使用所识别的位置的信号属性来内插无线设备的新位置。 该系统使用概率图，其中识别的平面图的位置，行人的预期步行速度以及设备是否运动的独立推断被用于确定设备的新位置。

公开(公告)号：US20080249667A1

公开(公告)日：2008-10-09

申请号：US11733701

申请日：2007-04-10

申请人： Eric J. Horvitz ,  John C. Krumm

发明人： Eric J. Horvitz ,  John C. Krumm

IPC分类号： G06F19/00

CPC分类号： B60W40/072 ,  B60W40/076 ,  B60W40/12 ,  G06N20/00

摘要： There is employment of machine learning, reasoning, and optimization included in a multi-attribute utility framework to learn and control energy systems to enhance the efficiency of vehicles. This can include energy systems included in vehicles that employ multiple energy sources. There is construction of models that provide inferences given historical information and/or real-time sensing of contextual information that are used in optimization. Such inferences about such key uncertainties as that route being taken are used in optimizing the expected utilities.

摘要翻译： 机器学习，推理和优化包括在多属性实用框架中，用于学习和控制能源系统，以提高车辆的效率。 这可以包括使用多种能源的车辆中包括的能源系统。 有建模的模型提供给定历史信息和/或实时感测优化中使用的上下文信息的推论。 对这样的关键不确定性的这种推论被用于优化预期效用。

公开(公告)号：US20080004037A1

公开(公告)日：2008-01-03

申请号：US11427778

申请日：2006-06-29

申请人： Dimitris Achlioptas ,  John C. Krumm ,  Eric J. Horvitz

发明人： Dimitris Achlioptas ,  John C. Krumm ,  Eric J. Horvitz

IPC分类号： H04Q7/20

CPC分类号： H04W24/02 ,  G01S5/0236 ,  H04W16/00

摘要： The claimed subject matter provides systems and/or methods that facilitate automatically maintaining a database of base stations. A location component can obtain a query that includes a listing of detected base stations. Additionally, the location component can identify whether the detected base stations are included in a base station database. Further, the location component can generate an estimated location related to the query. Moreover, a database update component can modify the base station database based at least in part upon the query.

摘要翻译： 所要求保护的主题提供便于自动维护基站数据库的系统和/或方法。 位置组件可以获得包括检测到的基站的列表的查询。 另外，位置组件可以识别检测到的基站是否包括在基站数据库中。 此外，位置组件可以生成与查询相关的估计位置。 此外，数据库更新组件可以至少部分地基于查询来修改基站数据库。