CN102394009A - Assessing road traffic conditions using data from mobile data sources - Google Patents

Assessing road traffic conditions using data from mobile data sources Download PDF

Info

Publication number
CN102394009A
CN102394009A CN2011102216242A CN201110221624A CN102394009A CN 102394009 A CN102394009 A CN 102394009A CN 2011102216242 A CN2011102216242 A CN 2011102216242A CN 201110221624 A CN201110221624 A CN 201110221624A CN 102394009 A CN102394009 A CN 102394009A
Authority
CN
China
Prior art keywords
road
data
data samples
road segment
plurality
Prior art date
Application number
CN2011102216242A
Other languages
Chinese (zh)
Other versions
CN102394009B (en
Inventor
亚历克·巴克
克雷格·H·查普曼
奥利弗·B·唐斯
斯科特·R·兰弗
杰西·S·赫奇
米切尔·A·小博恩斯
罗伯特·C·卡恩
Original Assignee
因瑞克斯有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US77894606P priority Critical
Priority to US60/778,946 priority
Priority to US78974106P priority
Priority to US60/789,741 priority
Priority to US11/431,980 priority
Priority to US11/432,603 priority
Priority to US11/432,603 priority patent/US20070208501A1/en
Priority to US11/431,980 priority patent/US20070208493A1/en
Priority to US11/438,822 priority patent/US7831380B2/en
Priority to US11/438,822 priority
Priority to US11/444,998 priority
Priority to US11/444,998 priority patent/US8014936B2/en
Priority to US11/473,861 priority
Priority to US11/473,861 priority patent/US7912627B2/en
Priority to US60/838,700 priority
Priority to US83870006P priority
Priority to US11/540,342 priority
Priority to US11/540,342 priority patent/US7706965B2/en
Application filed by 因瑞克斯有限公司 filed Critical 因瑞克斯有限公司
Priority to CN200780015916.22007.03.02 priority
Publication of CN102394009A publication Critical patent/CN102394009A/en
Application granted granted Critical
Publication of CN102394009B publication Critical patent/CN102394009B/en

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions

Abstract

Techniques are described for assessing road traffic conditions in various ways based on obtained traffic-related data, such as data samples from vehicles and other mobile data sources traveling on the roads, as well as in some situations data from one or more other sources (such as physical sensors near to or embedded in the roads). The assessment of road traffic conditions based on obtained data samples may include various filtering and/or conditioning of the data samples, and various inferences and probabilistic determinations of traffic-related characteristics of interest from the data samples. In some situations, the inferences include repeatedly determining traffic flow characteristics for road segments of interest during time periods of interest, such as to determine average traffic speed, traffic volume and/or occupancy, and include weighting various data samples in various ways (e.g., based on a latency of the data samples and/or a source of the data samples).

Description

使用来自移动数据源的数据估算道路交通状况 Use data to estimate road traffic from mobile data sources

[0001] 本发明是申请号为200780015916. 2 ( “使用来自移动数据源的数据估算道路交通状况”)的专利申请的分案申请。 [0001] The present invention has application No. 200780015916.2 ( "Using the data from the mobile data sources to estimate road traffic conditions") divisional application of patent application.

技术领域 FIELD

[0002] 以下的公开文本总体上涉及一种从各种数据源获取的数据来估算道路交通状况的技术,例如通过基于反映了感兴趣道路上的实际行驶的数据样本来推断这些道路上有关交通的信息。 Relates to a data from various data sources to estimate the acquisition of road traffic conditions technology in general [0002] The following publications, for example, to infer about the traffic on these roads is reflected by the data samples based on real driving on the road of interest Information.

背景技术 Background technique

[0003] 由于道路交通以比道路容量更大地速率持续增加,激增的交通拥堵已经对商业和政府运作以及个人幸福感产生恶劣的影响。 [0003] due to road traffic to continue to increase road capacity greater than the rate, the surge of traffic congestion has produced adverse impact on business and government operations as well as personal well-being. 因此,以各种方式进行了各种努力来抗击激增的交通拥堵,诸如通过获取当前交通状况的信息并将信息提供给个人和组织。 Therefore, in various ways, all the efforts to combat the surge in traffic congestion, such as providing information to individuals and organizations to obtain current traffic conditions and information. 可以通过各种方式(例如,经由射频广播、互联网网站,互联网网站显示了地理区域的地图,其中该地理区域的一些主要道路上当前的交通拥堵由彩色编码信息表示,信息可以发送到蜂窝式移动电话和其它便携式消费设备等)将这样的当前交通状况信息提供给感兴趣方。 Can be a variety of ways (for example, via radio broadcasting, Internet websites, Internet web site shows a map of the geographical area in which some of the major roads in the geographical area of ​​the current traffic congestion is indicated by color-coded information, information can be sent to the cellular mobile phones and other portable consumer devices, etc.) such current traffic conditions information to interested parties.

[0004] 获取有关当前交通状况信息的一种来源包括人工提供的观测(例如,提供有关交通流量和事故一般信息的交通直升机,由司机经由移动电话发来的报告等),而在一些更大型的都市区域中,另一种来源是交通传感器网络,其能在区域中测量各种道路的交通流量(例如,通过嵌入在道路路面内的传感器)。 [0004] acquisition (such as transport helicopters, and provides information about traffic accidents general information, sent by the driver via a mobile phone reports, etc.) on the current traffic situation a source of information, including artificial observations provided, and in some larger urban area, another source sensor network traffic, various road traffic which can be measured (e.g., by embedding the sensors in the road surface) in the area. 尽管人工提供的观测可以在有限的情况下提供一些值,这样的信息通常每次仅限于少数区域并且通常缺乏足以使用的足够细节。 Although artificial observation may provide some value in limited circumstances, such information is generally limited to a small region, and each typically lack sufficient detail sufficient to use.

[0005] 在一些情况下,交通传感器网络可以提供一些道路交通状况的更详细的信息。 [0005] In some cases, the traffic sensor networks can provide some road traffic conditions for more detailed information. 但是这样的信息以及由其它类似的来源所提供的信息存在各种问题。 However, there are various problems such information, and information from other similar sources are provided. 例如,很多道路没有道路传感器(例如,没有道路传感器的地理区域和/或并未足够大到具有道路传感器而作为临近网络一部分的干道),甚至具有道路传感器的道路也可能经常不能提供精确的数据,这极大地削弱了交通传感器所提供的数据值。 For example, many roads no road sensors (for example, no road sensors geographical area and / or not large enough to have road sensors as part of the trunk road network close), and even has a road road sensors may also often fail to provide accurate data , which greatly weakened the value of the data provided by traffic sensors. 非精确和/或非可靠数据的一种原因包括交通传感器损坏,从而不能提供数据,或提供间断数据,或不能正确读取数据。 One cause imprecise and / or reliable data transport comprises a sensor is damaged, so that data can not be provided, or providing intermittent data, or data can not be read correctly. 非精确和/或非可靠数据的另一种原因包括在一个或多个传感器进行数据暂时传输的问题,导致间断传送,或延迟传送,或不传送数据。 Another reason for a non-accurate and / or reliable data transmission includes data temporarily in one or more sensor problems, resulting in intermittent transmission, or delayed delivery, or no data is transmitted. 此外,很多传感器没有配置或设计来报告有关驾驶者状态(例如,他们机能是否正常),即便报告了驾驶者的状态信息也可能不正确(例如,报告驾驶者机能正常但实际上却并非如此),这样就很难或不可能确定由交通传感器所提供的数据是否精确。 In addition, many sensors are not configured or designed to report the driver about the status (for example, their function is normal), even if the information reported on the status of the driver may not be correct (for example, report the driver function normally but in fact it is not true) it is therefore difficult or impossible to determine the data provided by the traffic sensor is accurate. 此外,有关交通的信息仅能以原始和/或离散的形式得到,从而使用有限。 In addition, traffic-related information obtained only in the form of the original and / or discrete, so that limited use.

[0006] 隐藏,提供一种改进的技术来获取并估算有关交通的信息并提供各种相关附加的能力是很有益处的。 [0006] to hide, to provide an improved technique to obtain information about traffic and estimate and to provide all relevant additional capacity is very helpful.

附图说明 BRIEF DESCRIPTION

[0007] 图1是图示了用于至少部分地基于从车辆和其它移动数据源所获取的数据来估 [0007] FIG. 1 is a diagram illustrating a method for at least partially based on data obtained from vehicles and other mobile data sources to estimate

8算道路交通状况的系统的实施例的组件之间的数据流的方框图。 A block diagram of the data flow between components of an embodiment of a system operator 8 road traffic conditions.

[0008] 图2A-2E图示了至少部分地基于从车辆和其它移动数据源获取的数据来估算道路交通状况的实例。 [0008] Figures 2A-2E illustrate at least partially based on data obtained from vehicles and other mobile data sources to estimate road traffic conditions in Examples.

[0009] 图3是图示了适于执行所描述的数据样本管理系统(Data Sample Manager System)实施例的计算系统的方框图。 [0009] FIG. 3 is a diagram illustrating the Data Sample Manager system is adapted to perform the described (Data Sample Manager System) is a block diagram of a computing system according to embodiments.

[0010] 图4是数据样本过滤器例程的示例性实施例的流程图。 [0010] FIG. 4 is a flowchart of an exemplary embodiment of a filter routine data sample.

[0011] 图5是数据样本异常值去除器(Outlier Eliminator)例程的示例性实施例的流程图。 [0011] FIG. 5 is a flowchart of an exemplary embodiment of the remover (Outlier Eliminator) routine data sample outlier.

[0012] 图6是数据样本速度估算器例程的示例性实施例的流程图。 [0012] FIG. 6 is a flowchart of an exemplary embodiment of a data sample rate estimator routine.

[0013] 图7是数据样本流量估算器例程的示例性实施例的流程图。 [0013] FIG. 7 is a flowchart of an exemplary embodiment of the data of Sample Flow Assessor routine.

[0014] 图8是移动数据源信息提供例程的示例性实施例的流程图。 [0014] FIG 8 is a flowchart of an exemplary embodiment of the mobile data source information providing routine.

[0015] 图9A-9C图示了获取并提供有关道路交通状况中移动数据源的动作实例。 [0015] Figures 9A-9C illustrate an example of operation to obtain and provide road traffic conditions in the mobile data source.

[0016] 图10A-10B图示了修正从道路交通传感器获取的数据样本的实例。 [0016] FIGS. 10A-10B illustrates an example of correction data samples obtained from road traffic sensors.

[0017] 图11是传感器数据读取错误检测器例程的示例性实施例的流程图。 [0017] FIG. 11 is a flowchart of an exemplary embodiment of the sensor data read error detector routine.

[0018] 图12是传感器数据读取错误校正器例程的示例性实施例的流程图。 [0018] FIG. 12 is a flowchart of an exemplary embodiment of the sensor data read error corrector routine.

[0019] 图13是传感器数据读取收集器例程的示例性实施例的流程图。 [0019] FIG. 13 is a flowchart of an exemplary embodiment of the read sensor data collector routines.

[0020] 图14是交通流量估算器例程的示例性实施例的流程图。 [0020] FIG. 14 is a flowchart of an exemplary embodiment of the Traffic Flow Estimator routine.

具体实施方式 Detailed ways

[0021] 基于获取的交通相关的数据,以各种方式来描述估算道路交通状况的技术,诸如来自在道路上行驶的车辆和其它移动数据源和/或来自交通传感器(例如,嵌入在道路内或附近的物理传感器)。 [0021] Based on the acquired traffic related data, in various ways to estimate road traffic conditions described in the art, such as from a vehicle traveling on a road and other mobile data sources and / or from the vehicle sensors (e.g., embedded in the road or physical sensor close). 此外,在至少一些实施例中,从移动数据源来的数据样本可以用从一个或多个其它来源的数据补充,诸如通过获取在道路附件或道路内的物理传感器读取的数据。 Further, in at least some embodiments, the data samples from mobile data sources may be supplemented with data from one or more other sources, such as a physical sensor data within a road or road attachment by acquiring read. 基于所获取的数据样本(例如,从道路交通传感器,从各个移动数据源或收集数据点读取的数据)对道路交通状况的估算可以包括数据样本和读数的各种过滤和/或调整,以及感兴趣的交通相关特征的各种推断和概率确定。 (For example, data is read from the road traffic sensors from various mobile data source or data collection points) based on the acquired data samples to estimate road traffic conditions may include various filtering and / or adjustment and reading data samples, and various inferences and probabilities traffic-related feature of interest is determined.

[0022] 如所述,在一些实施例中所获取的道路交通状况信息数据可以包括由移动数据源(例如,车辆)提供的多个数据样本,来自基于道路的交通传感器(例如嵌入在道路路面内的环形传感器)的数据读数,和来自其它数据源的数据。 [0022] As described, in some embodiments, the acquired road traffic condition information data may comprise a plurality of data samples provided by mobile data sources (e.g., vehicles), from the road-based traffic sensors (e.g., embedded in the road surface within the annular sensor) data readings, and data from other data sources. 数据可以以诸如估算的平均交通速度和所感兴趣的道路的特定部分内估算的总车辆总量等的各种方式分析以便于确定所感兴趣的交通状况特征,以便以实时或近于实时(例如在接收底层数据样本和/或读数) 的方式执行交通状况的确定。 The total amount of data may be various ways to estimate the average traffic speed, such as a road, and the estimated interest within a particular portion of the overall vehicle or the like is analyzed in order to determine the traffic condition characteristics of interest, so as to be real-time or near real-time (e.g. underlying data received samples and / or reading) performed in a manner determined traffic conditions. 例如,所获取的数据可以以各种方式调整以检测和/或校正在数据中的错误。 For example, the acquired data may be adjusted in various ways to detect and / or correct errors in the data. 如果所获取的道路交通状况信息是不精确的或不能代表所感兴趣的实际交通状况特征,则在各个实施例中还可以以各种方式进行过滤以去除数据,包括通过将至少部分基于道路的非感兴趣的数据样本与根据其它数据样本关联的数据样本和/或作为统计异常值的数据样本视为相同,在一些实施例中,过滤还可以包括执行将数据样本与特定道路的关联。 If the acquired road traffic condition information is inaccurate or the actual traffic situation can not represent the feature of interest, then in various embodiments also may be filtered to remove the data in various ways, including by way of at least in part, on a non- data samples considered in accordance with the interest of the other data samples associated with data samples and / or data as a statistical outlier samples of the same, in some embodiments, may further include filtering the data samples associated with performing a particular road. 过滤后的数据样本还可以包括其它反映车辆位置或非感兴趣的行为(例如,停泊的车辆,车辆在停车场或建筑中打转等)的数据样本和/或其它不能代表在感兴趣的道路上实际车辆行驶的数据样本。 The filtered data samples may also include a vehicle position or the behavior of other reflecting interest (e.g., vehicles parked in a parking lot or the vehicle spin out buildings, etc.) data samples and / or other non-representative of interest on the road data samples of actual vehicle travel. 在至少一些实施例中估算所获取的数据可以包括至少 Estimate acquired in at least some embodiments the data may include at least

9部分地基于所获取的数据样本确定用于在特定地理区域中道路网络各个部分的交通状况(例如,交通流量和/或平均交通速度)。 9 based in part on the acquired data samples for determining traffic conditions (e.g., traffic and / or average traffic speed) road network in various parts of a particular geographic area. 接着可以使用所估算的数据来执行涉及分析、预测,预报,和/或提供交通相关信息的其它功能。 Can then be performed using the analysis relates to estimating data, prediction, forecasting, and / or other functions related to providing traffic information. 在至少一些实施例中,数据样本管理系统使用至少一些所描述的技术来准备由交通数据客户端所使用的数据,诸如在未来多个时间产生交通状况的多个预报的预测交通信息提供系统,这将在以下详细描述。 In at least some embodiments, the Data Sample Manager system using at least some of the described techniques to prepare the data by the traffic data used by the client, such as the predicted traffic information providing system in a plurality of times to generate a plurality of prediction of future traffic conditions, this will be described in detail below.

[0023] 在一些实施例中,所获取数据样本的调整可以包括修正错误的数据样本,诸如通过以各种方式检测和/或校正当前数据中的错误(例如,从道路交通传感器接收的数据读数)。 [0023] In some embodiments, the adjusted correction data samples may include erroneous data sample acquisition, such as by a variety of ways to detect and / or correct errors in the current data (e.g., received from the road traffic sensor data readings ). 具体地,诸如基于由这些数据源提供的数据样本的分析,描述用于估算特定数据源(例如基于道路的交通传感器)的“健康”的技术以便确定数据源是否工作正常并可靠地提供精确数据样本。 Specifically, such a sample based on the analysis of data provided by these data sources is described for estimating a particular data source (e.g., based on the road traffic sensors) "healthy" technology to determine if the data source is functioning correctly and reliably provide accurate data sample. 例如,在一些实施例中,将由给定的交通传感器提供的当前数据读数与该交通传感器提供的以前的数据读数(例如,历史平均数据)进行比较,以确定当前交通数据读数是否与以前通常的数据读数显著不同,例如这可以由该交通传感器非正常工作和/或数据中的其它问题所导致,和/或可以替换来反映异常的当前交通状况。 For example, in some embodiments, the current data generated by a given traffic sensor provides readings previous data readings (e.g., the historical average data) provided by the traffic sensor to determine whether the current traffic data readings previously usual data reading is significantly different, for example, this may be caused by abnormal operation of the traffic sensor and / or other problems in the data, and / or may be substituted to reflect the abnormality of current traffic conditions. 在各个实施例中可以以各种方式来执行对特定数据源和/或当前交通数据读数中可能错误的这种检测和分析,这将在以下更详细讨论,包括至少部分基于诸如使用神经网络、贝叶斯分类器、决策树等的分类技术。 In various embodiments may be performed, as will be discussed for a particular data source / or detection and analysis of this current traffic data readings and possible errors in more detail below in various ways, such as comprising at least in part, on the use of neural networks, classification Bayesian classifier, decision tree, etc.

[0024] 在检测诸如到来自未正常工作的受损数据源的不可靠数据样本后,可以以这种方式校正或修正这种不可靠数据样本(以及丢失的数据样本)。 [0024] In the detection of such damage unreliable data samples from the data source is not operating normal after such a correction can be corrected or unreliable data samples (as well as missing data samples) in this manner. 例如在一些实施例中,可以通过使用相关信息的一个或其它来源来修正一个或多个数据源(例如,交通传感器)的丢失数据和不可靠数据,例如通过来自临近或其它正常工作的相关交通传感器的同时数据样本(例如,通过对由相邻交通传感器提供的数据读数取平均数),通过涉及丢失和不可靠数据样本的预见性信息(例如,通过使用这些数据源的预见性和/或预报性交通状况信息来确定一个或多个数据源的期望数据读数),经由一个或多个数据源的历史信息(例如,通过使用历史平均数据读数),经由使用有关一致偏差或导致错误能得以补偿的其它错误类型来调整以校正数据样本等。 For example, in some embodiments, one or more can be corrected by using a data source or other sources of relevant information (e.g., traffic sensors) unreliable data and missing data, for example, by correlation or other traffic from adjacent normal operation At the same time the sensor data samples (e.g., by the traffic data provided by the adjacent sensor readings were averaged), the predictive information relating to missing and unreliable data samples (e.g., by using the predictive data sources and / or predictability traffic condition information to determine a desired data reading one or more data sources), the history information via one or more data sources (e.g., by using historical average data readings), through the use of an error relating to uniform bias or cause can be other types of compensation to the error correction data to adjust the sample and the like. 涉及修正丢失和不可靠数据样本的其它细节将在以下详细描述。 Other details related to fix missing and unreliable data samples will be described in detail below.

[0025] 此外,描述的技术还用于以各种其它方式估算交通状况信息,诸如在当前可用的数据允许可靠地执行特定数据源(例如,特定交通传感器)的数据样本的修正的情况。 [0025] In addition, further techniques described for estimating traffic condition information in various other ways, such as allowing to reliably perform the correction of the particular data source (e.g., a particular traffic sensor) data samples in the current data available. 例如,多个未正常工作的不健康交通传感器的存在可能导致没有足够数据来对这些交通传感器中的各个充分可信地估算交通流量信息。 For example, there are a plurality of unhealthy traffic sensor is not working properly may result in not enough data to fully trusted traffic flow information for each traffic estimate these sensors. 在这种情况中,交通状况信息可能以各种其它方式来估算,包括基于相关交通传感器组和/或涉及道路网络结构的其它信息。 In this case, traffic condition information may be estimated in various other ways, including those based on the group associated traffic sensors and / or other information related to the road network configuration. 例如,如以下要更详细描述地,每个感兴趣的道路可以通过使用多个道路段来建模或表示,每个道路段可以有多个关联的交通传感器和/或从一个或多个其它数据源(例如,移动数据源)得到的数据。 For example, as described in greater detail hereinafter, each of the road of interest may be modeled or represented by the use of a plurality of road segments, each road segment may have a plurality of associated traffic sensors and / or from one or more other a data source (e.g., a mobile data source) data obtained. 假如这样的话,可以以各种方式针对特定道路段(或多个相关交通传感器的其它组)来估算道路交通状况信息,例如通过使用用于估算相邻道路段的交通状况信息、用于特定道路段的预测信息(例如,在诸如三小时等有限的未来时间段内产生,至少部分地基于当前和预定时间内近来的情况),对特定道路段的预报信息(例如,在诸如两周或更长时间的未来时间段内产生,以便不使用用于预测的当前和近来状况信息的一些或全部)、特定道路段的历史平均状况等。 If so, it is possible in various ways to estimate road traffic condition information for a particular road segment (or more other groups of related traffic sensors), for example, by using road traffic condition information estimation adjacent segments, for a particular road prediction information segments (e.g., three hours, etc., such as limited future period in which, at least in part, on the current situation, and recent predetermined time), the information on the prediction of the particular road segment (e.g., two weeks or more, such as long future period in which, in order not to use for the prediction of some or all of the current and recent) historical average conditions specific road segment status information, and so on. 通过使用这样的技术,即便在只有少量或没有一个或多个临近传感器或其它数据源的当前交通状况数据时也能提供交通状况信息。 By using such a technique, even if the traffic situation can also provide information on current traffic condition data at only a few or without one or more proximity sensors or other data sources. 涉及这样的交通状 It relates to traffic shape

10况信息估算的其它细节将在以下详细描述。 Other details of the information to estimate the condition 10 will be described in detail below.

[0026] 如前所述,在各种实施例中有关道路交通状况的信息可以从移动数据源以各种方式获得。 [0026] As described above, in this embodiment information about road traffic conditions in the various embodiments may be obtained from mobile data sources in a variety of ways. 在至少一些实施例中,移动数据源包括道路上的车辆,其每个包括一个或多个提供有关车辆移动数据的计算系统。 In at least some embodiments, the mobile data source comprises a vehicle on a road, each comprising a computing system data relating to vehicle movement in one or more providers. 例如,每部车辆可以包括GPS (“全球定位系统”)设备和/或其它能确定地理位置、速度、方向和/或其它表征或涉及车辆行驶的数据的地理定位设备, 并且有时车辆上的一个或多个设备(无论是否为地理定位设备或相异通信设备)可以将这样的数据(例如,通过无线链路)提供给一个或多个能使用这样的数据的系统(例如,数据样本管理系统,将在以下更详细描述)。 For example, each vehicle may include the GPS ( "Global Positioning System") device, and / or other can be determined geographical location, speed, direction, and / or characterization or other vehicle traveling data relates to a geographical positioning device, and sometimes on a vehicle or a plurality of devices (whether or dissimilar communications device geographical positioning device) may be such data (e.g., via a wireless link) to one or more systems can be used such data (e.g., the data sample Manager system , will be described in more detail below). 例如,这样的车辆可以包括由各个不相关的用户操作的车辆的分布式网络、车队(例如,用于快递公司(delivery company)、出租车和公交车公司、运输公司、政府部门或代理,车辆租赁服务的车辆等)、隶属提供相关信息(例如, OMtar服务)的商业网络的车辆、被操作来获取这样的交通状况信息的车辆组(例如,通过行驶预定的路线,或行驶在道路上动态改变方向,以获取有关所感兴趣的道路的信息)、装载有移动电话设备的车辆(例如,作为内置设备和/或拥有车载物(vehicle occupant)) 能提供位置信息(例如,基于设备的GPS能力和/或基于由移动网络提供的地理定位能力)寸。 For example, such a vehicle may include a vehicle by each user is not related to the operation of a distributed network, fleet (for example, for the express delivery company (delivery company), taxi and bus companies, transportation companies, government department or agency, vehicle vehicles and other leasing services), under the relevant information (for example, OMtar service) business network of the vehicle, is operated to obtain such traffic condition information of the vehicle group (for example, by the scheduled travel route, or driving dynamics on the road change direction, to obtain information about roads of interest), loaded with a mobile phone device of the vehicle (e.g., as a built-in device and / or have onboard thereof (vehicle occupant)) able to provide location information (e.g., based on GPS capabilities of the device and / or based geolocation capabilities provided by the mobile network) inch.

[0027] 在至少一些实施例中,移动数据源可以包括或基于计算设备和道路上行驶的用户的其它移动设备,诸如用户是道路上车辆的驾驶者和/或乘客。 [0027] In at least some embodiments, the mobile data sources may include or be based on the traveling road on a computing device and other mobile user devices, such as a user is on a road vehicle driver and / or passenger. 这样的用户设备可以包括具有GPS能力的设备(例如,移动电话和其它手持设备),或在其它实施例中位置和/或移动信息替换地也可以以其它方式产生。 Such devices may include user devices (e.g., mobile phones and other handheld devices) with GPS capabilities, or the position and / or movement information may alternatively be produced in other ways in other embodiments. 例如,在车辆和/或用户设备中的设备可以与能检测和跟踪有关设备信息的外部系统进行通信(例如,通过系统操作的网络中的多个发射机/接收机各自通过的设备),从而使得设备的位置和/或移动信息以具有各种细节水平的各种方式被确定,或者这样的外部系统还能检测和跟踪有关车辆和/或用户的信息而不与设备交互(例如,能观测并识别驾驶牌和/或用户面部的相机系统)。 For example, in the vehicle device and / or user equipment can communicate with an external system can detect and track information about the device (e.g., via a plurality of transmitters operating in a network system / receiver device through each), whereby so that the location of the device and / or movement information is determined in various ways with various levels of detail, or such external systems can detect and track information about the vehicle and / or information without user interaction device (e.g., can be observed and identify driving license and / or the user's face camera system). 例如,这样的外部系统可以包括移动电话塔和网络,其它无线网络(例如,Wi-Fi热点),使用各种通信技术的车辆换能器的检测器(例如,RFID,或“射频标识”),车辆和/或用户的其它检测器(例如,使用红外线,声纳,雷达或激光测距设备以确定车辆的位置和/或速度)等。 For example, such external systems may include a mobile phone network and towers, other wireless networks (e.g., Wi-Fi hotspots), using various communication technologies vehicle detector transducer (e.g., RFID, or "Radio Frequency Identification") , vehicles and / or users of other detectors (e.g., infrared, sonar, radar or laser distance measuring device to determine the location of the vehicle and / or velocity) and the like.

[0028] 可以以各种方式使用从移动数据源获得的道路交通状况信息,无论单独还是与来自一个或多个其它来源(例如,从道路交通传感器)的其它道路交通状况信息一起使用。 [0028] The use of the road may be obtained from mobile data sources traffic condition information in various ways, either alone or with (e.g., from road traffic sensors) used with one or more other sources from other road traffic condition information. 在一些实施例中,使用这样的从移动数据源获得的道路交通状况信息,来提供信息类似于来自道路传感器的数据,但对于没有运行的道路传感器的道路(例如,对于缺少传感器的道路,诸如对于没有道路传感器网络的地理区域和/或没有大到足以有传感器的干道,对于损坏的道路传感器等),以校验从道路传感器或其它来源接收的复制信息,从而识别提供非精确数据的道路传感器(例如,由于临时或当前问题)等。 In some embodiments, the use of such road traffic condition information obtained from mobile data sources, to provide similar information from the road sensor data, but the road is not running road sensors (e.g., for lack of a road sensor, such as a for road no road sensor network geographical areas and / or not large enough to have a sensor, a sensor for damage to roads, etc.), road sensors to verify the information copied or received from other sources, provide imprecise data to identify the road a sensor (e.g., due to temporary problems or current) and the like. 而且,道路交通状况可以以一种或多种方式测量或表示,无论是基于来自移动数据源和/或交通传感器数据读数的数据样本,例如在绝对方面中(例如,平均速度;所指示的时间段中的交通量;一个或多个交通传感器或道路上的其它位置的平均占用时间,例如以表示车辆通过或激活传感器时间的平均百分数;一个或多个道路拥堵的计算等级,例如基于一个或多个其它交通状况测量的; 等等)和/或在相对方面(例如,表示与通常情况或最大情况的差异)。 Moreover, road traffic conditions can be measured or represented, whether based on sample data from mobile data sources and / or traffic sensor data readings, such as in absolute terms (e.g., the average speed in one or more ways; indicated time the segment traffic; average occupancy time of one or more traffic sensors or other position on the road, for example, represent the mean percentage of the vehicle by a sensor or activation time; one or more computing road congestion levels, for example, based on one or other measurements of a plurality of traffic conditions; and the like) and / or relative terms (e.g., general or difference indicates the maximum condition).

[0029] 在一些实施例中,一些道路交通状况信息可以采取由各种数据源提供的数据样本 [0029] In some embodiments, some of the road traffic condition information may take the data samples provided by the various sources of data

11的形式,例如与车辆关联的数据源以报告车辆的行驶特征。 11 in the form of, for example, characteristics associated with a vehicle to report the vehicle data source. 各个数据样本可以包括变化的信息量。 Each data sample may include information changes. 例如,由移动数据源提供的数据样本可以包括一个或多个来源标识符、速度标识符、方位或方向指示、位置指示、时间戳和状态标识符。 For example, data samples provided by mobile data sources may include one or more source identifiers, rate identifier, indicating orientation or direction, the position indication, a time stamp and status identifiers. 来源标识符可以是标识作为数据源的车辆(或人和其它设备)的数字或串。 Source may be a vehicle identifier (human or other apparatus) as a data source identification numbers or strings. 在一些实施例中,移动数据源标识符可以与移动数据源永久或暂时关联(例如,对于移动数据源的寿命;对于一个小时;对于当前使用的会话,例如以便每一次开启车辆或数据源设备就分配一个新的标识符)。 In some embodiments, the mobile data source identifier may be permanently or temporarily associated with a mobile data source (e.g., for the lifetime of the mobile data source; for one hour; the use for the current session, for example to turn each source device or vehicle It allocates a new identifier). 在至少一些实施例中,来源标识符与移动数据源关联,以使涉及来自移动数据源的数据的私密关系最小化(无论是永久还是暂时关联),例如通过以阻止基于标识符来识别与该移动数据源与标识符关联的移动数据源的方式来创建和/或操作源标识符。 In at least some embodiments, the source identifier associated with the mobile data source, so that the relation relates to private data from the mobile data source is minimized (whether permanent or temporary association), such as are recognized by the identifier based on to block mobile data source identifier associated with the mobile manner to create a data source and / or the operation of a source identifier. 速度指示可以反映以各种方式表示的移动数据源的即时或平均速度(例如,英里每小时)。 Speed ​​indicator may reflect the average speed of the mobile immediate or data source represented in various ways (e.g., miles per hour). 方位可以反映行驶的方向,并且是以“度”表示的角度或其它度量(例如,基于罗盘的方位或弧度)。 It may reflect the orientation direction of travel, and at an angle "degrees" represents or other metrics (e.g., based on compass bearing or radian). 位置指示可以反映以各种方式表示的物理位置(例如纬度/经度对或Universal Transverse Mercator坐标)。 Position indication may reflect a physical location (e.g., latitude / longitude or Universal Transverse Mercator coordinates of) expressed in various ways. 时间戳可以指示移动数据源记录给定时间样本的时间,例如以本地时间或UTC(“UniversalCoordinated Time”)时间。 Timestamp may indicate that the mobile data source to a scheduled recording time samples, for example in local time or UTC ( "UniversalCoordinated Time") time. 状态标识符可以表示移动数据源的状态(例如,车辆在移动、停止、引擎运转着停止等)和/或感测、记录和/或发射设备的至少一些状态(例如,电量低、信号强度弱等)。 Identifier may indicate the state status of the mobile data source (e.g., the vehicle is moving, stopping, the stopping operation of the engine, etc.) and / or sensing, recording and / or transmitting at least some of the device state (e.g., low battery, the signal strength is weak Wait).

[0030] 在一些实施例中,在给定地理区域内的道路网络可以通过使用多个道路段来建模或表示。 [0030] In some embodiments, in a given geographical area using a road network may be represented by a plurality of road segments or modeled. 每个道路段可以用于表示道路(或多个道路)的一部分,例如通过将给定的物理道路分割成多个道路段(例如,每个道路段具有特定的长度,诸如一英里长的道路,或选择反映出类似的交通状况特征的道路部分作为道路段),这样的多个道路段可以是道路连续的部分,或替换地在一些实施例中,它们可以重叠或任何道路段都没有相互干扰的部分。 Each road segment can be used for the road portion represented by the road (or road), for example given by dividing into a plurality of physical road road segments (e.g., for each road segment having a particular length, such as a mile long or selected features reflect similar traffic condition as a part of a road road segment), and a plurality of road segments may be a continuous part of the road, or alternatively, in some embodiments, or they may overlap each other without any road segment part interference. 此外,道路段可以表示给定物理道路上的一个或多个行驶车道。 Further, a given road segment may represent one or more physical road traveling lane. 因此,在两个方向的每个上都有一个或多个行驶车道的特定多车道可以与至少两条道路段关联,其中至少一个道路段与一个方向上的行驶关联,而至少另一个与另一方向上的行驶关联。 Thus, in each of the two directions has a plurality of specific driving lane or multi-lane may be associated with at least two road segments, wherein the at least one road segment associated with the one direction, and the other with at least one other associated with one direction. 此外,在一些情况中,在单一方向上行驶的单一道路的多个车道可以由多个车道段表示,例如如果车道具有不同的行驶状况特征。 Further, in some cases, traveling in a single direction a plurality of single-lane road segments may be represented by a plurality of lanes, for example, if a lane has characteristics different driving conditions. 例如,给定的高速公路系统可以具有快速或高占用率(”H0V”)车道,其可以由与表示相同方向上行驶的常规(例如,非H0V)车道迥然不同的方式表示以作为快速或HOV车道。 For example, a given system may have fast highway or high occupancy ( "H0V") lane, which can be expressed with the same direction by a conventional (e.g., non-H0V) lane represents very different ways as fast or HOV Lane. 车道段还可以连接到其它相邻的道路段或与其它相邻的道路段关联,从而形成道路段网络。 Lane segments may also be connected to the other adjacent the associated road segment or road segments with adjacent other, thereby forming a network of road segments.

[0031] 图1是图示了用于至少部分地基于从车辆和其它移动数据源获取的数据估算道路交通状况的系统的实施例的组件之间的数据流的流程图。 [0031] FIG. 1 is a flowchart illustrating a part on data obtained from vehicles and other mobile data sources to estimate at least data between components of an embodiment of a system of road traffic flow conditions. 所示的数据流程图意欲反映在数据源,即数据样本管理系统的实施例的组件,和交通数据客户端之间的数据流的逻辑表示。 The data shown in the flowchart is intended to be reflected in the data source, i.e., a logical data flow between components of an embodiment of a Data Sample Manager system, and traffic data showing the client. 也就是说,实际的数据流可能经由各种机制而发生,包括直接流(例如,由通过参数实现或诸如消息的网络通信)和/或经由一个或多个数据库系统或其它诸如文件系统的存储系统的间接流。 That is, the actual data flow may occur via various mechanisms, including direct flow (e.g., a communication network such as a message or a parameter is achieved by a) or storage and / or via one or more other systems, such as a database file system indirect flow system. 所示的数据样本管理系统100包括数据样本异常值去除组件106、数据样本速度估算组件107、数据样本流估算组件108和可选传感器收集组件110。 Data Sample Manager system 100 shown includes a data Sample Outlier Eliminator component 106, Data Sample Speed ​​Assessor component 107, a stream of data samples to estimate the sensor assembly 108 and collector assembly 110 optionally.

[0032] 在所示的实施例中,数据样本管理系统100的组件104-108和110从各种数据源获取数据样本,这包括基于车辆的数据源101、道路交通传感器103和其它数据源102。 [0032] In the embodiment shown, the assembly 100 Data Sample Manager system 110 and 104-108 data samples acquired from various data sources, including the vehicle-based data sources 101, road traffic sensors 103 and other data sources 102 . 基于车辆的数据源101可以包括在一个或多个道路上行驶的多个车辆,其每个都可以包括一 The vehicle-based data sources 101 may include a plurality of one or more vehicles on the road, which may each comprise a

12个或多个计算系统和/或能提供有关车辆行驶数据的其它设备。 12 or more computing systems and / or to provide data relating to the vehicle running other devices. 如另外所要更详细描述地,每部车辆可以包括GPS和/或能确定有关车辆行驶的位置、速度和/或其它数据的地理定位设备。 As further be described in more detail, each vehicle may include a GPS unit and / or be able to ascertain the location of the vehicle is traveling, the speed and / or other geographical positioning device data. 这样的数据可以由所述数据样本管理系统的组件通过无线数据链路(例如,卫星上行链路和/或移动电话网络)或其它方式(例如,在车辆到达某个物理位置后,例如在车队回到其基地后进行物理有线/电缆连接)获得。 Such data may be data samples by the components of the management system of the wireless data link (e.g., satellite uplink and / or mobile telephone network) or other means (for example, after the vehicle arrives at a physical location, for example, in fleet physical wire / cable) obtained after return to its base. 道路交通传感器102可以包括安装在各个街道、高速公路或其它道路内、上或附近的多个传感器,例如嵌入在路面内的环形传感器能测量每单位时间通过该传感器上的车辆数量、车辆速度和/或涉及交通流量的其它数据。 Road traffic sensors 102 may include a mounting in various streets, highways, or other roads, on or near the plurality of sensors, for example, embedded in the annular sensor capable of measuring the road surface per unit time the number of vehicles on the sensor, vehicle speed, and / or involve other data traffic. 数据可以类似地从道路交通传感器102经由基于有线或无线的数据链路获得。 Data can be similarly obtained from road traffic sensors 102 via a wire-based or wireless data link. 其它数据源103可以包括各种其它类型的数据源,包括提供有关道路网络信息的地图服务和/或数据库,例如道路间的链接以及涉及该道路的交通控制信息(例如,交通控制信号的存在和/或位置和/或限速区域)。 Other data sources 103 may include various other types of data sources, including providing information about the road network map services and / or databases, links and traffic control information relating to the road between the road (e.g., traffic control signals and the presence of e.g. / or position and / or speed region).

[0033] 虽然在该实例中所示的数据源101-103将数据样本直接提供给数据样本管理系统100的各个组件104-108和110,但在其它实施例中数据样本也可以在被提供给这些组件之前先进行处理。 [0033] Although the data sources shown in this example 101-103 data samples directly to the respective components of the data management system 100 samples 104-108 and 110, but in other embodiments may also be implemented in the data samples provided to be prior to these components to be processed. 这样的处理可以包括基于时间、位置、地理区域和/或单个数据源的身份(例如,车辆、交通传感器等)组织和/或收集数据样本到逻辑集合中。 Such processing may include those based on time, location, and / or identity geographic area of ​​a single data source (e.g., vehicles, traffic sensors, etc.) tissue and / or collect data samples to a logical collection. 此外,这样的处理可以包括合并或组合数据样本到更高级的逻辑数据样本或其它值。 In addition, such processing can include a combination of combined data samples or to more advanced data samples or other logical value. 例如,从多个地理上协同定位的道路交通传感器获得的数据样本可以通过平均或其它收集方式合并入单个的逻辑数据样本。 For example, data samples from a plurality of geographically co-located road traffic sensors obtained may be incorporated into a single logical data samples by averaging or other collection methods. 此外,这样的处理可以包括基于一个或多个所获得的数据样本而导出或合成数据样本或数据样本的元素。 Furthermore, such processing may comprise one or more samples based on the data obtained or synthesized data elements derived samples or data samples. 例如,在一些实施例中,至少一些基于车辆的数据源的每个可以提供仅包括来源标识符和地理位置的数据样本,假如这样的话,那么以特定时间间隔或其它时间段而周期性提供的多个相异数据样本组就能与另一个关联而作为特定车辆所提供的。 For example, in some embodiments, at least some of the vehicle-based data sources may each provide the only source of data samples comprise a geographic location identifier and, if so, then at certain time intervals or other time periods periodically provided a plurality of distinct groups of data samples can be associated with another specific as provided by the vehicle. 还可以进一步处理这样的数据样本组来确定其它有关行驶的信息,例如每个数据样本的方位(例如,通过计算在数据样本的位置和先前和/或后继数据样本的位置间的角度)和/或每个数据样本的速度(例如,通过计算在数据样本的位置和先前和/或后继数据样本的位置之间的距离,并将距离除以相应的时间)。 This may be further processed to determine the data sample set with other relevant information such as orientation of each data sample (e.g., by calculating the angle between the position of the data sample and / or the position of the previous and subsequent data sample), and / or each data sample rate (e.g., the distance between the position data and the position of the previous sample and / or subsequent data sample is calculated and divided by the corresponding time distance).

[0034] 在所示的实施例中,数据样本过滤组件104从基于车辆的数据源101和其它数据源102获取数据样本,并在将它们提供给数据样本异常值去除组件106以及可选地在提供给数据样本流估算组件108之前对所获取的数据样本过滤。 [0034] In the embodiment illustrated embodiment, the filter assembly 104 from the data samples of data samples 102 acquires the vehicle-based data sources 101 and other data sources and provide them to the Data Sample Outlier Eliminator component 106 and optionally It is supplied to the stream of data samples to estimate the component of the acquired data samples before filter 108. 如在别处将更详细讨论地,这样的过滤可以包括:将数据样本与相应于在地理区域中道路的道路段关联,和/或识别不相应于所感兴趣的道路段或反映不感兴趣的车辆位置或行为的数据样本。 As discussed in greater detail elsewhere, such filtering may include: the data samples associated with the road segment corresponding to road in the geographic area, and / or identification does not correspond to road segments of interest or of no interest to reflect the position of the vehicle or data samples behavior. 将数据样本与道路段关联可以包括:使用每个数据样本的报告位置和/或方位来确定该位置和方位是否相应于先前限定的道路段。 The data samples associated with the road segment may include: using the reported location of each data sample and / or orientation determines the position and orientation corresponding to whether the road segment previously defined. 识别不相应于所感兴趣的道路段的数据样本可以包括:去除或识别这样的数据样本以便不对它们建模、考量或由数据样本管理系统100的其它组件处理,要去除的这样的数据样本可以包括那些相应于不感兴趣的特定功能的道路类的道路(例如,居住区街道)的数据样本、那些相应于不感兴趣的道路的部分或区域的数据样本(例如,坡道和采集器/分流车道/告诉公路道路)等。 Identifying data samples do not correspond to road segments of interest may include: removing or identifying such data samples so that they are not modeled, or considered by the Data Sample Manager system 100, other components of the processing, such data may include a sample to be removed road corresponding to a particular function that is not of interest road classes (e.g., residential streets) data samples, those portions or areas of the sample data corresponding to the roads are not of interest (e.g., ramps and acquisition / lane splitter / tell highway road) and so on. 识别数据样本是否反映不感兴趣的车辆位置或行为可以包括:识别与处于空闲状态(例如,引擎开着停车)、在停车库驾驶(例如,以非常低的速度打转)等的车辆相对应的数据样本。 Identifying whether a data sample does not reflect the position of the vehicle of interest or behavior may include: identifying an idle state (e.g., open the engine stop), the driving garage (e.g., at very low speed spin) and the like corresponding to the vehicle data sample. 此外,在一些实施例中,过滤可以包括为呈现或进一步分析而识别道路段是(或不是)感兴趣的。 Further, in some embodiments, the filter may comprise as presentation or further analysis is to identify the road segment (or not) of interest. 例如,这样的过滤可以包 For example, such filtering may be coated

13括分析在特定时间段(例如,小时、天、星期)内交通流量的可变性和/或各条道路段的拥堵的程度,以便从进一步分析中排除具有低时间段内(intra-time period)可变性和/或低拥堵的一些或全部道路段(例如,对于传感器数据读数不可用或它们的功能性的道路类别表示更小或更少行驶道路的道路段)作为不感兴趣的道路和道路段。 And variability analysis comprising 13 or the degree of traffic congestion (e.g., hours, days, weeks) within a certain time period / the pieces of road segments, excluded from further analysis in order to have a low time period (intra-time period ) variability and / or some or all of the low congestion road segments (e.g., the sensor data readings are not available or their functional road class represents less traveling road or road segment less) as the road and the road is not of interest segment.

[0035] 传感器数据调整器105辅助修正错误的数据样本,例如通过检测和校正从道路交通传感器103获得的读数的错误。 [0035] Sensor 105 auxiliary data adjuster correcting erroneous data sample, for example obtained from road traffic sensors 103 read by detecting and correcting errors. 在一些实施例中,由传感器数据调整组件检测为不可靠的数据样本并不转发到其它组件来使用(或提供特定数据样本的非可靠表示,以便其它组件能处理这些数据样本),例如,不转发到数据样本异常值去除器106。 In some embodiments, the component is detected by the sensor data as unreliable data samples are not forwarded to other components used (or provide unreliable data representing a particular sample, so that other components can process the data samples), for example, no data is forwarded to sample outlier Eliminator 106. 假如这样的话,数据样本异常值去除组件接着可以确定是否有足够的可靠数据样本可用,如果不是的话,则发起校正行为。 If so, Data Sample Outlier Eliminator component may then determine whether sufficient reliable data samples are available, if not, corrective action is initiated. 替换地,在一些实施例和环境中,传感器数据调整组件还可以对数据样本执行一些校正,正如以下将要更详细讨论地,接着将校正后的数据提供给传感器收集组件110(并可选地提供给其它组件,例如数据样本异常值去除组件和/或数据样本流估算组件)。 Alternatively, in some embodiments, and environments, the Sensor Data Conditioner component may further data sample to perform some correction, as will be discussed in greater detail, and then the corrected data is supplied to the sensor collection assembly 110 (and optionally provide to other components, such as data sample outlier Eliminator component and / or the stream of data samples to estimate the component). 检测错误数据样本可以使用各种技术,包括统计测量,将由给定的道路交通传感器报告的当前数据样本的分布与在相应的时间段(例如,相同的星期天数和一天内相同的时间)内由该道路交通传感器报告的数据样本的历史分布进行比较。 Detecting the erroneous data samples may use various techniques, including statistical measures, and will be distributed in a time period corresponding to the current data sample of a given reporting road traffic sensors (e.g., the same number of Sunday and the same time of the day) by the historical data of the sample reported that road traffic sensors distributed for comparison. 实际和历史分布范围的差异可以由统计测量值计算,例如Kullkick-Leibler散度,其提供了在两个概率分布间的相似度的凸度测量,和/或统计信息熵。 The actual and historical distribution range difference can be calculated by the statistical measurement such Kullkick-Leibler divergence, which provides a projection of the measured similarity between two probability distributions, and / or statistical information entropy. 此外,一些道路传感器可以报告传感器健康的指示,还可以使用这样的指示来检测所获得的数据样本的错误。 In addition, some road sensors may report a healthy indication sensor can also be used to detect errors such indication data samples obtained. 如果在所获得的数据样本中检测出错误,则可以以各种方式修正出错的数据样本,包括利用来自确定无错的相邻/旁边道路传感器的相邻(例如,旁边)的数据样本的平均值来替换这样的数据样本。 If an error is detected average data samples obtained, the error can be corrected data samples in various ways, including the use of error-free is determined from the adjacent / next adjacent road sensors (e.g., next to) the data samples to replace the value of such data sample. 此外,可以通过使用诸如由预测交通信息系统提供的先前或同时预测和/或预测的值进行替换,来修正出错的数据样本。 Further, by using the prediction previously or simultaneously provide predictive traffic information systems, such as values ​​and / or predicted to be replaced, the error corrected data samples. 涉及预测交通信息提供的其它细节将另外提供。 Other details concerning predicted traffic information provided will additionally provided.

[0036] 数据样本异常值去除组件106从数据样本过滤组件104获得过滤后的数据样本和/或从传感器数据调整组件105获得调整或修正后的数据样本,接着识别并考虑去除那些不代表所感兴趣的道路和道路段上的实际车辆行驶的数据样本。 [0036] Data Sample Outlier Eliminator data samples of data samples from the filter assembly 106 to obtain data sample filter assembly 104 and / or the adjustment or correction is obtained from the sensor data adjustment component 105, and then to identify and remove those not reflect consideration of interest the actual roads and vehicles traveling on the road segment data samples. 在所示的实施例中,对于每个所感兴趣的道路段,组件分析在特定时间段内所记录并与道路段关联的数据样本组(例如,通过数据样本过滤组件104),以确定如果要去除,应当去除哪个。 In the embodiment shown, for each road segment of interest, component analysis of the data sample set is recorded in a specific time period and associated with the road segment (e.g., data sample through the filter assembly 104), if you want to determine removal, which should be removed. 可以以各种方式执行这样的对非代表性数据样本的确定,包括基于以下技术:相对于数据样本组中的其它数据样本,检测数据样本是统计异常值。 Such a determination may be performed on a non-representative sample of data in various ways, including based on the following technologies: with respect to other data samples in the sample set data, detection data sample is a statistical outlier. 涉及数据样本异常值去除的其它细节将另外提供。 Further details related to data sample outlier removal will be additionally provided.

[0037] 数据样本速度估算组件107从数据样本异常值去除组件106获得数据样本,以便在所示实施例中获得的数据样本表示在所感兴趣的道路和道路段上的实际车辆行驶。 [0037] Data Sample Speed ​​Assessor component 107 from data Sample Outlier Eliminator component 106 obtains data samples, data samples obtained in Examples represents the actual vehicles on roads and road segments of interest in order to travel in the illustrated embodiment. 数据样本速度估算组件107接着分析所获得的数据,以基于已经与该道路段(例如,通过数据样本过滤组件104,或通过从道路段部分的传感器来的读数)和时间段关联的数据样本组,估算在至少一个所感兴趣的时间段内所感兴趣的道路段的一个或多个速度。 Data Sample Speed ​​Assessor component 107 then analyzes the data obtained, based on the already time period associated with the data sample set with the road segment (e.g., via data sample filter assembly 104, or by from the sensor road segment portion readings) , in one or more speed estimates road segments of interest at least one time period of interest. 在一些实施例中,所估算的速度可以包括该组多个数据样本的速度平均值,也可以由数据样本的一个或多个属性加权(例如,年龄(age),以便给较新的数据样本较大的加权;和/或数据样本的来源或类型,以便从移动数据源或从道路传感器改变数据样本的加权来给具有较高预期可靠性或可用性的来源更大的加权)。 In some embodiments, the estimated average speed may include the speed of the set of the plurality of data samples, it may be by one or more attributes of the data samples weighted e.g., age (Age), in order to more recent data sample (a greater weight; and / or types of data sources or samples, so as to change the weighting of the data samples from mobile data sources from road sensors to or higher expected to have a greater reliability or availability of sources of weighting). 涉及从数据样本进行的速度估算的更多细节将在别处提供。 Relates to speed data from the estimated samples will be provided in more detail elsewhere.

14[0038] 数据样本流估算组件108在至少一个所感兴趣的时间段为所感兴趣的道路段估算交通流信息,以估算交通量(例如,表示为在诸如每分钟或每小时的特定时间量内到达或经过道路段的车辆总量或平均数)、估算交通密度(例如,表示为诸如每英里或公里等的每单位距离的车辆平均数或总量)和估算交通占用率(例如,表示为在例如每分钟或每小时等的特定时间量车辆占用特定点或区域的平均或总的时间量)等。 14 [0038] Sample Flow Assessor component 108 of data at least one time period of interest to estimate traffic flow information for road segments of interest to estimate the amount of traffic (e.g., as represented within a certain amount of time, such as per minute or hour or passes through the vehicle's total or average number of road segments), estimating traffic density (e.g., indicating that the vehicle such as a per unit or per mile or kilometer from the average of total) and the estimated occupancy of traffic (e.g., as represented by for example, an average or a total amount per hour or minute amounts of a specific time point or a specific region of a vehicle occupant of time). 在所示的实施例中,对交通流信息的估算至少部分地基于由数据样本速度估算组件107和数据样本异常值去除组件106提供的涉及交通速度的信息,可选地可以基于由传感器数据调整组件105和数据样本过滤组件104提供的交通数据样本信息。 In the illustrated embodiment, the estimation of traffic flow information based at least in part by the estimated velocity data samples and the data component 107 Sample Outlier Eliminator component 106 provides information relates to the speed of transport, can be optionally adjusted based on the sensor data assembly 105 and the data sample filtering traffic information data sample assembly 104 is provided. 涉及交通样本流估算的其它细节将在别处提供。 Other details relating to traffic flow sample estimate will be provided elsewhere.

[0039] 如果存在,则诸如在传感器数据调整组件已经去除了任何不可靠的数据样本和/或已经修正了任何丢失和/或非可靠数据样本后,传感器数据收集组件110收集由传感器数据调整组件105提供的基于传感器的交通状况信息。 [0039] If present, such as the Sensor Data Conditioner component has been removed any unreliable data samples and / or have modified any loss and / or reliability of data samples, the sensor data collection component 110 collects sensor data adjustment assembly based on traffic conditions sensor information provided by 105. 替换地,在其它实施例中,传感器数据收集组件可以替代地执行这种丢失和/或不可靠数据样本的去除和/或校正。 Alternatively, in other embodiments, the sensor data collection component can alternatively perform such loss and / or removal of unreliable data samples and / or correction. 在一些情况中,传感器数据收集组件110可以通过收集(例如,平均)由与每个道路段关联的多个单独交通传感器提供的信息为这些道路段的每个提供交通流信息。 In some cases, the sensor data collected by collection component 110 (e.g., average) information provided by a plurality of individual traffic sensors associated with each road segment to provide traffic flow information for each of these road segments. 同样地,如果存在,传感器数据收集组件110可以提供信息,以补充由例如数据样本速度估算组件107和/或数据样本流估算组件108等的组件提供的估算交通状况,或可以在来自移动数据源的数据样本根本不可靠或没有足够量的可靠数据样本来允许诸如数据样本速度估算组件107和数据样本流估算组件108等的其它组件提供精确的估算道路交通状况信息的情况下替换地使用。 Likewise, if present, the Sensor Data Aggregator component 110 may provide information to supplement estimate traffic conditions provided by, for example, data Sample Speed ​​Assessor component 107 and / or Data Sample Flow Assessor component 108 and other components, or may be from a mobile data source no reliable data samples or not a sufficient amount of reliable data samples to allow other components such as data sample speed Assessor component 107 and the stream of data samples to provide Assessor component 108, etc. Alternatively, using the precise estimation of the situation of the road traffic condition information.

[0040] 在所示的实施例中一个或多个交通数据客户端109获得由数据样本速度估算组件107和/或数据样本流估算组件108提供的估算的道路交通状况信息(例如,速度和/或流数据),并可以以各种方式使用这样的数据。 [0040] In an embodiment illustrated in one or more traffic data clients 109 traffic road condition information obtained from the estimated data Sample Speed ​​Assessor component 107 and / or stream of data samples provided by the Assessor component 108 (e.g., speed and / or streaming data), and you can use such data in various ways. 例如,交通数据客户端109可以包括其它组件和/或由数据样本管理系统100的操作者操作的交通信息系统,例如预见性交通信息提供系统,使用交通状况信息来产生在多个未来时间的未来交通状况预报的交通状况信息;和/或实时(或近于实时)的交通信息呈现系统获或提供系统,向终端用户和/或第三方客户端提供实时(或近于实时)的交通状况信息。 For example, traffic data clients 109 may include other components and / or the traffic information system data samples by an operator management system 100 operation, for example, predictive traffic information providing system, traffic condition information used to generate a plurality of future times in the future traffic conditions forecast traffic information; and / or real-time (or near real-time) traffic information presentation system obtain or provide systems to provide real-time (or near real-time) traffic information to end users and / or third-party client . 此外,交通数据客户端109可以包括由第三方操作的计算系统以向其客户提供交通信息。 Moreover, traffic data clients 109 may include providing traffic information to their customers by a computing system operated by third parties. 此外,在一些环境中(例如,在当不能为数据样本速度估算组件和/或数据样本流估算组件得到足够的数据来执行精确的估算,和/或当从基于车辆或其它数据源不能得到数据的情况下)该一个或多个交通数据客户端109可选地获得由传感器数据收集组件110提供的道路交通状况信息,可以替代来自数据样本速度估算组件和/或数据样本流估算组件来的数据,或在此之外额外获得。 Further, in some circumstances (e.g. in when it is not estimated as the data sample rate component and / or Data Sample Flow Assessor component to obtain sufficient data to perform accurate estimate, and / or when it is not obtained from the basis of the vehicle or other data source in the case of) the one or more traffic data clients 109 alternatively traffic condition information obtained by the sensor provided a road data collection component 110, a data component may be replaced and / or the stream of data samples to estimate the component of velocity estimated from data samples or in addition to this extra obtain.

[0041] 为了图示的目的,一些实施例在以下描述,其中以特定的方式估算特定类型的道路交通状况,并且以各种特定的方式使用这样的估算交通信息。 [0041] For purposes of illustration, in the following description of some embodiments, a particular way in which the estimated road traffic conditions of a specific type, and a variety of specific ways to use such information to estimate traffic. 但,应当理解的是,可以以其它方式并使用在其它实施例中其它类型的输入数据产生这样的交通状况估算,所描述的技术可以在非常广泛的其它情况中使用,并且本发明并不限于所提供的示例性细节。 However, it should be understood that other ways and may be used in other embodiments other types of input data generated in this embodiment to estimate traffic conditions, the described techniques may be used in a very wide range of other cases, and the present invention is not limited exemplary details provided.

[0042] 图2A-2E图示了基于从车辆和其它移动数据源获取的数据估算道路交通状况的实例,正如由所描述的数据样本管理系统所执行的那样。 [0042] Figures 2A-2E illustrate examples of assessing road traffic conditions based on data obtained from vehicles and other mobile data sources, as is the Data Sample Manager system described executed. 具体地,图2A图示了数据样本过滤的实例,用于具有数条道路201、202、203和204并具有指示朝北方向的图例指示309的实例区域200。 In particular, FIG. 2A illustrates an example of filtered data samples for the road 201, and having a number 204 and having a north direction indicated Legend 200 indicates the instance area 309. 在该实例中,道路202,诸如高速公路或交汇公路的受限进入道路(limited In this example, road 202, such as a highway or highway interchange limited access road (limited

15access road),被分成在西向和东向上分别行驶车辆的相异车道组20¾和202b。 15access road), is divided into distinct groups 20¾ lane to the west and east respectively upward travel of the vehicle and 202b. 车道组202a包括HOV车道202a2和多个其它常规车道20加1,车道组202b类似地包括HOV车道202b2和多个其它常规车道202bl。 Lane group 202a includes a plurality of HOV lane 202a2 and 20 plus other conventional lanes 1, lane group 202b similarly includes a plurality of HOV lane 202b2 and other conventional lanes 202bl. 道路201是穿行道路202 (例如,经由天桥或桥),道路204是斜坡弯道,其将道路201的北行车道201b连接到道路202的东行车道组202b。 201 is a road crossed the road 202 (e.g., via an overpass or bridge), is the slope curve path 204, which connects the road lane 201 North 202 East Road 201b to lane group 202b. 道路203是相邻道路202的当地沿街道路。 203 is a road adjacent road 202 local road along the street.

[0043] 可以以各种方式表示在图2A中所示的道路,以用于所描述的数据样本管理系统。 [0043] may represent a road shown in Figure 2A, data for a sample management system described in various ways. 例如,一个或多个道路段可以与每个物理道路关联,例如将北行和南行道路段分别与北行车道201a和南行车道202b关联。 For example, one or more road segments may be associated with each physical path, for example, the north and southbound carriageway road segment associated with each lane 201a, North and South lane 202b. 类似地,至少一个西行道路段和至少一个东行道路段可以分别与道路202的西行车道组20¾和东行车道组202b关联。 Similarly, at least one westbound 202b associated at least one road segment and the East-way street with a road segment 202 may each westbound and eastbound lane group 20¾ channel group. 例如,道路201的东行车道组202b东的部分可以是与道路201的西行车道组202b西的部分相独立的道路段,例如基于一般的道路交通状况或经常在道路段间改变(例如,由于通常车辆显著从斜坡弯道204流入到道路201的车道组202b,这样一般来说导致在到道路201东向的车道组202b上更大的拥堵)。 For example, road 201 east lane group 202b east part may be a part of the road 201 westbound lane group 202b West is separate from the road segment, for example, based on the general road conditions frequently change (for example, between road segment, due to the usually a significant inflow of vehicles from the road slope curve 204 to 201 of the lane group 202b, so that generally lead on the road 201 lane group 202b east to greater congestion). 此外,可以将一个或多个车道组分解到多个道路段中,例如如果不同的车道一般或经常具有不同的道路交通状况特征(例如,基于这些享有类似交通状况特征的车道将车道组202b的给定部分作为相应于车道202bl的第一道路段,而将由于其具有不同交通状况特征因而作为相应于HOV车道202b2的第二车道段)-在其它这种情况中,只有单个道路段可以用于这样的车道组,但在估算该车道组的的道路交通状况时一些数据样本(例如,相应于HOV车道的202b2的那些)可以从使用中排除(例如通过数据样本过滤组件和/或数据样本异常值去除组件)。 In addition, one or more lane group may be decomposed into a plurality of road segments, for example if a different lane or ships often have different road traffic condition characteristics (e.g., conditions based on these characteristics similar Related traffic lane to lane group 202b of as corresponding to the given portion 202bl first lane road segments, and the different conditions because of its traffic characteristics and thus a segment corresponding to the second lane of the HOV lane 202b2) - in other such cases, only a single road segment can be to such a lane group, but the number of data samples (e.g., those corresponding to HOV lane 202b2) may exclude (e.g., by data sample filter assembly and / or data samples from use in estimating road traffic conditions in the lane group of outlier Eliminator component). 替换地,一些实施例可以将多个给定道路的多个车道表示为单条道路段,即便该车道是在相反方向上行车,例如在两个方向上通常道路交通状况类似时——例如,沿街道路20¾可以具有两个相反的行车车道,但可以由一个道路段来表示。 Alternatively, some embodiments of the plurality of the plurality of lanes of a given road may be expressed as a single road segment, even though the traffic lane in the opposite direction is, for example, road traffic conditions generally similar in both directions - for example, street road 20¾ can have two opposite traffic lane, but can be represented by a road segment. 在至少一些实施例中道路段至少部分地可以以其它方式来确定,例如与地理信息关联(例如,物理维度和/或方位和/或交通相关信息(例如,限速)。 Road segment may be determined at least in part in other manners in at least some embodiments, for example, geographical information associated with (e.g., physical dimensions and / or orientation and / or traffic-related information (e.g., speed).

[0044] 图2A还描述了在特定时间间隔或其它时间段(例如,1分钟,5分钟,10分钟,15分钟等)期间行驶在区域200内的多个移动数据源(例如,车辆,未示出)所报告的多个数据样本20fe-k。 [0044] Figure 2A further describes a specific time interval or other time period (e.g., 1 minute, 5 minutes, 10 minutes, 15 minutes, etc.) during running in the region of a plurality of mobile data sources 200 (e.g., a vehicle, not shows a) a plurality of reported data samples 20fe-k. 在由多个移动数据源的一个报告时,数据样本的每个都被演示为箭头,其表示数据样本的方位。 When a report by a plurality of mobile data sources, each data sample have been demonstrated as an arrow, which represents the sample orientation data. 数据样本以这样的方式叠加在区域200上以便反映每个数据样本所报告的位置(例如,以维度和精度单位表示,诸如基于GPS读数),其在记录数据样本时可以与车辆的实际位置不同(例如,由于不精确或错误的读数,或由于所使用的位置传感机制固有的变量精度)。 Data samples in such a manner superimposed on the area 200 to reflect the reported location of each data sample (e.g., accuracy in dimensions and units, such as based on GPS readings), which may be different from the actual position of the vehicle at the time of recording data samples (e.g., false or inaccurate readings due, or due to the position of the sensing mechanism used in the variable inherent accuracy). 例如,数据样本205g显示了道路202b略北的位置,其可以反映被拖到车道202½北侧的车辆(例如,由于机械故障),或它可以反映在车道202b2或其它车道的东行方向上实际行驶的车辆的非精确位置。 For example, data sample 205g shows 202b road slightly north of the location, which may reflect on the north side of the vehicle is 202½ onto the lane (for example, due to mechanical failure), or it can be reflected in the eastbound lane 202b2 or other lane direction of actual travel the non-exact location of the vehicle. 此外,单个移动数据源可以是比所示的数据样本更多的数据样本的来源,例如如果样本205i和样本20¾都由在时间段内沿道路202东向行驶的单部车辆所报告(例如,通过包含用于多个先前时间点的多个数据样本的单一传输,以便每5分钟或每15分钟报告数据样本)。 Furthermore, a single mobile data source may be a source of data samples represented by more data than a sample, for example, if the sample and the sample 205i reported by 20¾ (e.g. single unit to the vehicle traveling along a road in a period of 202 East, by including a plurality of previously transmitted a plurality of data samples of a single point in time, so that each 5 minutes or report data samples every 15 minutes). 有关存储和提供多个所获取数据样本的更多细节将包括在以下的内容中。 For the acquired data samples and providing a plurality of storage will include more details in the following contents.

[0045] 在一些实施例中所述的数据样本管理系统可以过滤所获得的数据样本,以便将数据样本映射到预定的道路段和/或识别并不相应于所感兴趣的道路段的数据样本。 [0045] In some embodiments according to the Data Sample Manager system may filter data samples obtained, the sample data is mapped to a predetermined road segment and / or identification data samples do not correspond to road segments of interest. 在一些实施例中,如果报告位置在与道路段相对应的道路和/或车道的预定距离(例如,5米)内, In some embodiments, if the reported location and the predetermined distance from the road segment corresponding to road and / or lane (e.g. 5 meters),

16并且其方位在与该道路段相对应的道路和/或车道的方位的预定角度(例如正或负15度)内,则数据样本与道路段关联。 16 and its position in the road segment corresponding to a predetermined angular orientation and road and / or lane (e.g., plus or minus 15 degrees), the data samples associated with the road segment. 虽然在其它实施例中对道路段的数据样本的关联可以在数据样本可用于数据样本管理系统之前执行,所示实施例中的道路段与足够的基于位置的信息(例如,道路段的方位,道路段的物理范围等)关联,以作出这样的确定。 While in other embodiments be performed prior to the associated road segment data samples may be used to sample the data management system data samples, with the embodiment illustrated in sufficient information based on location, for example, orientation (road segment in the road segment embodiment, scope of the physical road segment) is associated, in order to make such a determination.

[0046] 如所示的实例,数据样本20¾可以与相应于道路203的道路段关联,因为其报告位置落在道路203的范围内并且其方位与关联道路203的至少一个方位相同(或近于相同)。 [0046] The example as shown, the data samples 203 may be identical 20¾ least one orientation associated with a respective road segment 203 to the road, because of its reported location 203 falls within the road range and azimuth with which the associated road (or nearly the same). 在一些实施例中,当使用单条道路段来表示在相反的方向上行驶的多个车道时,可以将数据样本的方位与道路段的两个方位比较以确定数据样本是否可以与该道路段关联。 In some embodiments, when a single road segment represented by a plurality of lanes in the opposite direction of travel, can be compared with the azimuth orientation of two road segment data samples to determine whether the data samples associated with the road segment . 例如,数据样本20¾具有大致与数据样本20¾相反的方位,但如果使用道路段来表示道路203的两个相反车道,则它也可以与相应于道路203的道路段关联。 For example, data samples having substantially opposite orientation 20¾ and 20¾ data sample, but if the road segment is used to represent two opposite lane of the road 203, it may be associated with a respective road segment 203 to the road.

[0047] 然而,由于道路203与车道组20¾接近,还可能的是,由于数据样本20¾的方位与车道组20¾的方位相同,则数据样本20¾反映在车道组20¾上行驶的车辆,例如如果数据样本20¾的报告位置在车道组20¾的一个或多个车道中行驶的车辆位置错误的空白处。 [0047] However, since the road 203 lane group 20¾ close, it is also possible, due to the same 20¾ azimuth data sample position and lane group 20¾, the data sample 20¾ reflected in the lane group 20¾ vehicles, for example, if the data report sample 20¾ position in one or more travel lanes in lane group 20¾ vehicle location error margin. 在一些实施例中,多个可能的道路段用于一个数据样本的情况可以基于与该数据样本关联的其它信息来去除。 In some embodiments, a plurality of possible road segments to be based on other information associated with the data sample to remove the case of a data sample. 例如,在这种情况中,数据样本20¾的报告速度的分析可以有助于这种去除,例如如果车道组20¾相应于65mph限速的高速公路,道路203为具有30mph限速的当地沿街道路,并且数据样本所报告的速度为75mph(导致与高速公路车道的关联比与当地沿街道路关联的可能性要大)。 For example, in this case, the speed of data analysis sample 20¾ can contribute to such removal, for example, if the lane group 20¾ corresponding to 65mph motorway speed limit of the road with 203 local roads 30mph speed limit along the street, and the speed of data samples reported to 75mph (highway lane associated with lead is larger than the possibility of association with local street road). 一般地说,如果数据样本20¾的报告速度相比车道组20¾的观测或发送速度更类似于道路203的观测或发送速度,则这样的信息可以用于部分地确定将数据样本与道路203关联而不是车道组202a。 In general, if the reported speed of data sample groups compared to the observed lane 20¾ transmission speed or a road 20¾ observed or more similar transmission speed of 203, then such information may be used in part to determine the data samples associated with the road 203 not lane group 202a. 替换地,如果数据样本20¾的报告速度相比于观测或发送的道路203的速度更类似于车道组20¾的观测或发送速度,则它就与车道组20¾关联而不是道路203。 Alternatively, if the reported speed of data sample 20¾ observed compared to the road 203 or the transmission speed or the transmission speed is more similar to the observed lane group of 20¾, it is associated with a 20¾ lane group 203 instead of the road. 其它类型的信息类似地也可作为于这种去除的一部分(例如,位置•'方位;状态;其它涉及数据样本的信息,例如从相同移动数据源来的其它新近数据样本等),例如作为加权分析的部分来反映数据样本信息类型与候选道路段的匹配程度。 Other types of information may similarly be removed as part of this to (e.g., location • 'orientation; state; other information related to data sample, for example, like other recent data samples from the same mobile data source), such as the weighting part of the analysis of sample data to reflect the degree of matching the type of information and road segment candidate.

[0048] 例如,对于将数据样本20¾与适合的道路段关联,它所报告的位置出现在车道201b和车道组20¾重叠的部分,并且它临近车道201a和其它道路。 [0048] For example, the position of the sample data with the road segment associated 20¾ suitable, reports appear in the lane and the lane group 201b 20¾ overlap, and it is close to the lane 201a and other roads. 但,数据样本所报告的方位(大致北行)相比于其它候选车道/道路的方位与车道201b的方位(北行)更接近,因此在这个实例中它很可能与相应于车道201b的道路段关联。 However, the azimuth (approximately northbound) data samples reported as compared to other candidates lane / road lane position and orientation of 201b (northbound) closer, so it is likely the corresponding road in this instance in the lane 201b segment association. 类似地,数据样本205c包括可以匹配多个道路/车道(例如车道201a,201b,和车道组202a)的报告位置,但它的方位(大致西行)可以用于选择用于车道组20¾的道路段作为用于该数据样本最合适的道路段。 Similarly, the sample data 205c comprises a plurality of road match / lanes (lanes e.g. 201a, 201b, and lane group 202a) of the reported location, its orientation (substantially westbound) may be used for lane road segment select group of 20¾ as the most suitable for the road segment data samples.

[0049] 还是这个实例,数据样本205d可以不与任何道路段关联,因为它的方位(大致东行)与相应于该数据样本的报告位置的车道组20¾(西行)的处于相反方向。 Lane group [0049] or in this example, data sample 205d may not be associated with any road segment, because of its orientation (generally east line) corresponding to the reported location of data sample 20¾ (westbound) in opposite directions. 如果没有其它合适的候选道路段,其与数据样本205d所报告的位置足够近(例如,在预定的距离内),例如如果具有类似方位的车道组202b太远,则在从该数据样本的分析的后续使用过滤期间排除该数据样本。 If no other suitable candidate road segment, 205d with the reported location of data sample sufficiently close (e.g., within a predetermined distance), for example, if the lane group 202b having a similar orientation too far, then the analysis of the data sample the sample data is excluded during subsequent use of the filter.

[0050] 数据样本20¾可以与相应于车道组20¾的诸如相应于HOV车道202a2的道路段的道路段关联,这是因为它的报告位置和方位相应于该车道的位置和方位,例如如果用于 [0050] may be associated with data samples corresponding to such 20¾ lane group 20¾ associated road segment corresponding to HOV lane 202a2 of the road segment, because it is reported to the position and orientation corresponding to the position and orientation of the lane, for example, if

17该数据样本的位置的基于位置的技术具有足够的分辨率来区分车道(例如,不同的GPSjl外线,声纳或雷达测距设备)。 17 position of the data sample location-based technologies have sufficient resolution to distinguish a lane (e.g., different GPSjl outside, sonar or radar distance measuring device). 数据样本还可以基于除了基于位置信息外的因素而与多车道道路的特定车道关联,例如如果车道具有不同的交通状况特征。 In addition to sample data can also be based on factors associated with a particular lane outside the location information based on multi-lane roads, for example, has a different lane if traffic characteristics. 例如,在一些实施例中,可以使用数据样本的报告速度来通过对用于每个这样的候选车道的数据样本所观测的速度(或交通流量的其它测量)的预期分布(例如,通常或高斯分布)建模,而将数据样本与特定车道相符或匹配。 For example, in some embodiments, may be used to report the speed of data samples by the expected velocity distribution (or other measure of traffic) data samples for each such candidate lane observed (e.g., typically a Gaussian or distribution) model, and the data samples matches or match with a particular lane. 例如,由于该数据样本所报告的速度相比于在常规车道202al上行驶的车辆的观测、推断或历史平均速度更接近于HOV车道202a2上行驶的车辆的观测、推断或历史平均速度,因此数据样本20¾可以与相应于HOV车道202a2的道路段关联,例如通过基于其它数据样本来确定观测或推断速度(例如,使用由一个或多个道路交通传感器提供的数据读数)和/或其它相关的当前数据的分析。 For example, since the speed of the data sample as compared to the observations reported in the conventional traveling vehicle lane 202al, inferred or historical average speed of the HOV lane 202a2 closer observation on a vehicle traveling, inferred or historical average speed, data (e.g. data readings, provided by the use of one or more road traffic sensors) 20¾ sample may be associated with a road segment corresponding to HOV lane 202a2, for example, be determined by the rate observed or inferred based on other data samples and / or other related current analysis of the data.

[0051] 以类似的方式,数据样本205f,205h, 205Ϊ和205 j可以分别与相应于车道201a,车道20加1,车道202bl和斜坡204的道路段关联,因为它们所报告的位置和方位相应于这些道路或车道的位置和方位。 [0051] In a similar manner, data samples 205f, 205h, 205Ϊ and 205 j may each corresponding, associated lane 201a, lane 20 plus 1 lane 202bl and the ramp 204 of road segments, since the position they reported and orientation of the respective to the position and orientation of these roads or lanes.

[0052] 即便它的报告位置在所示道路的范围外,数据样本205g也可以与相应于车道组202b的道路段关联(例如,用于HOV车道202½的道路段),这是因为报告位置可以在道路的预设距离(例如5米)内。 [0052] even if it is outside the range of the reported position of the road, the data sample 205g may be associated with a road segment corresponding to lane group 202b (e.g., for the 202½ HOV lane road segment), since the reported location may be in the preset distance roads (eg 5 meters). 替换地,如果数据样本20¾的报告位置远离道路,则它也可以不与任何道路段关联。 Alternatively, if the data sample report 20¾ location away from the road, it may not be associated with any road segment. 在一些实施例中,可以给由不同数据源提供的数据样本使用不同的预设距离,以便反映数据源公知或期望的精确度水平。 In some embodiments, the data samples may be provided by different data sources use different preset distance, in order to reflect the level of accuracy of the data source known or desired. 例如,由使用未校正GPS信号的移动数据源提供的数据样本可以使用相对高(例如,30米)的预设距离,而由使用差异校正GPS设备的移动数据源提供的数据样本可以相比较而言使用低(例如,1米)的预设距离。 For example, by the use of uncorrected GPS signals in the mobile data source may be used to provide data samples from a predetermined relatively high (e.g., 30 meters), and the data samples provided by using differential GPS correction mobile data source device may be compared made use of low (e.g., 1 m) of the predetermined distance.

[0053] 此外,数据样本过滤可以包括识别不与所感兴趣的道路段相对应的数据样本和/或不能代表在道路上行驶的实际车辆的数据样本。 [0053] In addition, the filter may include a data sample does not identify road segments of interest corresponding to the data samples and / or do not represent the actual vehicle traveling on a road data samples. 例如,可以根据考量去除一些数据样本,因为它们与数据样本管理系统不考虑的道路关联。 For example, you can remove some of the data samples based on considerations because the roads associate them with sample data management system is not considered. 例如,在一些实施例中,与次要功能道路类的道路(例如,居民区街道和/或干道)关联的数据样本可以被过滤掉。 For example, in some embodiments, the secondary function of the road data the road type (e.g., residential streets and / or roads) associated with the sample may be filtered out. 再返回图2A,例如,可以滤除数据样本20¾和/或20¾,因为道路203是位于非常低的功能分类的当地临街道路而不被数据样本管理系统所考虑,或者也可以滤除数据样本205j,因为斜坡弯道太短而并不与高速路分离。 Back to FIG 2A, for example, you may filter data samples 20¾ and / or 20¾, because the road 203 is located very low local frontage road classification function without being considered sample data management system, or may be filtered data sample 205j because the curve slope is too short to not be separated from the highway. 过滤还可以基于其它因素,例如在一个或多个道路段上其它移动数据源的推断或报告行为。 May also be filtered based on other factors, e.g. infer other mobile data sources in one or more road segments or the reporting behavior. 例如,与道路段关联并由单个移动数据源提供的全部都表示相同位置的一系列数据样本有可能表示该移动数据源已经停止了。 For example, by a single road segment associated with the mobile data source provides all represent the same series of data samples represents the possible location of the mobile data source has stopped. 如果与相同道路段关联的所有其它数据样本都表示移动的移动数据源,则相应于停止的移动数据源的数据样本可以由于不能表示在该道路段上行驶的实际车辆而被滤除,例如由于移动数据源是停泊的车辆。 If all the other data samples associated with the road segment are represented by the same moving mobile data source, the data corresponding to the moving source stops the data samples may be due not represent the actual vehicle travel on the road segment is filtered, for example due to mobile data source is a parked vehicle. 而且,在一些实施例中,数据样本可以包括车辆驱动状态的报告指示(例如,车辆传输为引擎开动的“泊车”,车辆停止以进行发送),如果这样的话,类似地可以使用这样的指示来滤除这样的不能表示实际行驶车辆的数据样本。 Further, in some embodiments, the data sample may include a report indicating a vehicle driving state (e.g., a vehicle transmission for the engine start of "parking" the vehicle is stopped to be transmitted), and if so, similarly may be used such indications to filter out such samples can not represent the actual data traveling vehicle.

[0054] 图2B图示了与在特定时间间隔或其它时间段内从多个数据源获得与一个道路段关联的多个数据样本的视图,其中数据样本标出在曲线210上,并且χ轴210b是测量的时间,y轴210a是测量的速度。 [0054] FIG. 2B illustrates the χ axis or at certain time intervals obtained from a plurality of other periods the data source view associated with a plurality of road segment data samples, wherein the data samples marked on the curve 210, and 210b is the measured time, y-axis is the measured speed 210a. 在这个实例中,从多个移动数据源以及一个或多个与道路段关联的道路交通传感器获得所示的数据样本,并在所示的图例中以不同的形状显示(即,黑实心菱形“ ♦ ”用于从道路交通传感器获得的数据样本,而空心方形“ 口”用于从移动数 In this example, from a plurality of mobile data sources and one or more road segments associated with a road traffic sensor data samples is obtained as shown in, and displays (i.e., black solid diamonds in different shapes shown in the legend " ♦ "for data samples obtained from road traffic sensors, and the open squares" mouth "for the number from the mobile

18据源获得的数据样本)。 According to the obtained data source 18 samples). 如参考图2A所述,所示的从移动数据源来的数据样本可以与道路段关联。 As described with reference to Figure 2A, from the mobile data source may be associated with the illustrated sample road segment.

[0055] 示例性的数据样本包括道路交通传感器数据样本211a_c和移动数据源数据样本21h-d。 [0055] Exemplary road traffic sensor data samples includes data samples 211a_c mobile data source and data samples 21h-d. 给定的数据样本的报告速度和记录时间可以通过其在曲线图上的位置确定。 Given data sample report speed and recording time may be determined by its position on the graph. 移动数据源数据样本212d具有(或其它速度单位)15英里每小时的报告速度并相对于一些开始点在大约37分钟(或其它时间单位)被记录。 Mobile data source having a data sample 212d (or other unit of speed) reported speed of 15 miles per hour with respect to some of the recording start point is at about 37 minutes (or other unit of time). 如以下要更详细描述地,一些实施例可以在所示时间段内的特定时间窗中分析或处理所获得的数据,例如时间窗213。 As described in greater detail, some embodiments may analyze the data at a specific time window or time period as shown in process obtained, for example, the time window 213. 在这个实例中,时间窗213包含从时间30分钟到40分钟的10分钟的时间间隔内所记录的数据样本。 In this example, the time window containing 213 data samples from the interval time of 10 minutes 30 minutes to 40 minutes recorded. 此外,一些实施例还可以将在特定时间窗内产生的数据样本组分成两个或多个组,例如,组21½和组214b。 In addition, some of the data sample set embodiments may also be generated within a particular time window into two or more groups, e.g., groups and group 21½ 214b. 例如,应当注意的是,所示的数据样本表现为反映了报告速度的双模型(bi-modal)分布,其具有成批数据样本,报告在25-30英里每小时范围或0-8英里每小时范围内的速度。 For example, it should be noted that the performance of data samples as shown in the report model reflects the double speed (bi-modal) distribution, having a bulk sample of the data reported in the range of 25-30 miles per hour or miles per 0-8 speed range within hours. 可能产生速度的这种双模型或其它多模型(multi-modal)分布是因为,例如底层交通流量模式是非均一的,这里由于例如使得交通以停-走模式流动的交通控制信号,或道路段包括多个以不同速度移动的交通车道(例如,HOV车道或快速车道具有比其它非HOV车道相对高的速度)。 Such models may produce double speed or other multiple model (multi-modal) distribution is because, for example, the underlying non-uniform traffic patterns, for example, where due to that the traffic stop - go traffic control signals flow mode, or road segment comprising a plurality of moving at different speeds of traffic lanes (e.g., fast HOV lane or lanes having relatively higher than the speed of other non-HOV lanes). 在存在速度数据的这种多模型分布中,一些实施例可以将数据样本分成两个或多个组来处理,以便产生提高的处理精确度或分辨率(例如,通过计算更精确地反映各个交通流量速度的平均速度)以及所感兴趣的附加信息(例如,在HOV交通和非HOV交通间差异的速度),或识别数据样本组来排除(例如,不包括HOV交通作为后续分析的一部分)。 In this multi-speed data-model distribution is present, some embodiments may sample into two or more data sets processed to produce improved accuracy or resolution process (e.g., by calculation more accurately reflects the respective traffic the average flow velocity of the velocity) and the additional information of interest (e.g., vehicle speed and non-HOV traffic HOV difference), identification, or group of data samples to exclude (e.g., not including HOV traffic as part of subsequent analysis). 虽然这里没有图示,但数据样本的这种相异的组可以以各种方式识别,包括通过为每组观测速度的差异分布建模(例如正常或高斯分布)。 Although not shown, this disparate group of data samples can be identified in a variety of ways, including through the modeling of the distribution of the observed difference in each speed (e.g., normal or Gaussian distribution).

[0056] 图2C图示了对过滤器执行数据样本异常值去除或考量将不表示在特定道路段上行驶的车辆的数据样本排除的实例,在该实例中其基于用于数据样本的报告速度(虽然在其它实施例中数据样本的一个或多个可以替换来用作分析的一部分,而不论是替换还是排除所报告的速度)。 [0056] Figure 2C illustrates a filter for performing data Sample Outlier Eliminator considerations will not represent or instance data traveling on a particular road segment the vehicle is excluded samples, based on the reported speed for the data samples in this example (although may alternatively be used as part of an analysis in other embodiments, one or more data samples, replace or whether the reported negative speed). 具体地,图2C显示了表220,其图示了对于十个数据样本的实例组执行数据样本异常值去除(在实际使用中,被执行分析的数据样本的数量可以更大)。 In particular, FIG. 2C shows a table 220 which illustrates the execution data samples for the example set of ten data sample outlier removal (in actual use, the number of data samples is performed analysis may be greater). 所示的数据样本可以,例如,是在特定时间窗(例如图2B的时间窗213)内发生的所有数据样本,或替换地可以包括特定时间窗的数据样本的子集(例如在图2B的组21½或214b中所包括的)或者可以包括更长时间段内可以得到的所有数据样本。 Data samples can be shown, for example, all the data samples occurring within a particular time window (e.g., window time 213 in FIG. 2B), or alternatively may include a subset of data samples of a particular time window (e.g., in FIG. 2B 21½ group or all of the data samples 214b included) or may comprise a longer period of time can be obtained.

[0057] 在本实例中,在所确定的数据样本组中,通过从组中的其它数据样本的平均速度来确定数据样本组中每个速度样本的速度偏差,将非代表性的数据样本识别为相对于其它数据样本的统计异常值。 [0057] In the present example, the group of data samples determined by the average speed of the other data samples from the data set is determined for each sample set speed deviation of velocity samples, the non-representative sample of identification data statistical outliers with respect to other data samples. 可以测量每个速度样本的偏差,例如相对于在组中的其它数据样本的平均速度相差的标准差的数值,其偏差比预定阈值(例如2个标准差)大的数据样本被识别为异常值,并从进一步的处理中排除(例如,通过丢弃)。 May be measured deviation for each velocity sample, for example, relative to the average speed of the other data samples in the group phase difference standard deviation values, the deviation (e.g., two standard deviation) than a predetermined threshold value of the data sample is identified as an outlier and excluded from further processing (e.g., by dropping).

[0058] 表220包括方位行222,其描述了多个列221a_f的内容。 [0058] The table 220 includes a row orientation 222, which describes the contents of the plurality of columns 221a_f. 表220的每行223a_j图示了对于十个数据样本中一个相异数据样本的异常值去除分析,列221a表示要为每行分析的数据样本,由于要分析每行数据样本,因此将它从该组的其它样本中排除以确定该结果的差异。 Each row of table 220 illustrates 223a_j outliers ten data samples removed a distinct data analysis sample, the column 221a showing the data samples per line to be analyzed, since the sample to be analyzed for each row of data, so it from other samples in the set to determine the difference of the negative result. 行223a的数据样本可以参考为第一数据样本,行22¾的数据样本可以参考为第二数据样本等。 Data line 223a to the reference sample can be a first data sample, the data sample may be a reference line 22¾ second data samples and the like. 列221b包含每个数据样本的报告速度,其以多少英里每小时测量。 Column 221b contains the reporting rate for each data sample, which measures at how many miles per hour. 列221c列出了相对于要被比较的给定行的数据样本的、组中的其它数据样本,列221d列出了由列 221c column lists the data samples with respect to a given row to be compared to the other groups of data samples, column by column lists 221d

19221c指示的数据样本组的大致平均速度。 19221c generally indicated average speed data sample groups. 列221e包含了在从列221b排除的数据样本的速度和列出在列221d中的其它数据样本的平均速度之间的大致偏差,其以标准差测量。 Column 221e includes substantially excluded speed deviation between the data samples from the column 221b lists and other data samples in the column 221d of the average speed, which is the measurement standard deviation. 基于在列221e中列出的偏差是否比为该实例目的的1.5个标准差要大,列221f指示给定数据样本是否应当被去除。 Based on the deviation are listed in the column 221e for instance whether the object than 1.5 standard deviations to larger column 221f indicating whether a given data sample should be removed. 此外,用于所有10个数据样本的平均速度2M显示为大约25. 7英里每小时,而所有10个数据样本的标准差225显示为大约14. 2。 Further, the average velocity 2M for all 10 data samples is shown as approximately 25.7 mph, while the standard deviation of all 10 data samples 225 is shown as approximately 14.2.

[0059] 这样,例如,行223a图示了数据样本1的速度为沈英里每小时。 [0059] Thus, for example, line 223a illustrates the speed of data sample 1 is sink mph. 接下来,计算其它数据样本2-10的平均速度为大约25. 7英里每小时。 Next, calculate the average speed of the other data samples 2-10 is about 25.7 mph. 接着计算数据样本1的速度与其它数据样本2-10的平均速度的偏差大约为.02个标准差。 Then calculates the deviation of the mean velocity data samples with a speed of the other data samples 2-10 is approximately .02 standard deviations. 最后,由于数据样本1的偏差低于 Finally, since the deviation of the data samples is less than 1,

1. 5个标准差的阈值,因此确定数据样本1不是异常值。 1.5 standard deviation threshold, and therefore is not an abnormal value a data sample is determined. 此外,行223c图示了数据样本3的速度为0英里每小时,而其它数据样本1-2和4-10的平均速度被计算为大约28. 6英里每小时。 Further, the line 223c is illustrated sample data rate 3 is 0 miles per hour and the average speed of the other data samples 1-2 and 4-10 is calculated as approximately 28.6 mph. 接着计算数据样本3的速度与其它数据样本1-2和4-10的平均速度的偏差大约为 Then the speed deviation of the average velocity calculation data sample 3 with the other data samples 1-2 and 4-10 is approximately

2. 24个标准差。 2.24 standard deviation. 最后,由于数据样本3的偏差高于1. 5个标准差的阈值,因此确定数据样本3是异常值。 Finally, since the deviation data sample 3 is higher than 1.5 standard deviation threshold, it is determined data sample 3 is an abnormal value.

[0060] 更形式化地,给定N个数据样本Vtl,V1, V2, ... , Vn,在给定的时间段内记录并与给定的道路段关联,当前的数据样本Vn将被去除,如果 [0060] More formally, given N data samples Vtl, V1, V2, ..., Vn, in a given period of time and recorded to a road segment associated with a given current data sample to be Vn remove, if

V. — V. I V. - V. I

[0061] _σ, [0061] _σ,

[0062] 其中,Vi为被分析的当前数据样本的速度;K为其它数据样本(ν。,Vi+1,...,vn)的平均速度;Oi为其它数据样本的标准差;c为恒定阈值(例如,1.5)。 [0062] wherein, Vi is the velocity of the current data sample being analyzed; (. Ν, Vi + 1, ..., vn) K is the average speed of the other data samples; Oi other data samples for the standard difference; is C constant threshold value (e.g., 1.5). 此外,作为处理可能存在的除以零的特殊情况,如果其它数据样本的标准差σ i为零并且当前数据样本的速度并不等于其它数据样本的平均速度,则去除当前的样本〜。 Further, as a special case of possible division by zero, and if the standard deviation σ i of the other data samples zero and the current speed of the data samples is not equal to the average speed of the other data samples, the current sample is removed ~.

[0063] 对每个Vi要注意的是,并不一定要迭代所有的其它数据样本(Vtl,...,Vi^1,Vi+1, ...,vn)来计算平均K和标准差σ i。 [0063] Each Vi is to be noted that not necessarily all the other data samples iteration (Vtl, ..., Vi ^ 1, Vi + 1, ..., vn) to calculate the average and standard deviation K σ i. 其它数据样本V(l,...,Vi^1, vi+1, ...,Vn的平均K也可以如下表示: Other data samples V (l, ..., Vi ^ 1, vi + 1, ..., K Vn average may be expressed as follows:

[0064] V.=N~V~V' [0064] V. = N ~ V ~ V '

' NI 'NI

[0065] 并且其它数据样本Vtl,...,Vi^1, vi+1, ...,Vn的标准差ο i可以如下表示: [0065] and the other data samples Vtl, ..., Vi ^ 1, vi + 1, ..., Vn of ο i standard deviation can be expressed as follows:

[0066] σ = (Ν-Ϊ)σ2-Ν(ν' —V) [0066] σ = (Ν-Ϊ) σ2-Ν (ν '-V)

1 ]jJV-2 N-\ 1] jJV-2 N- \

[0067] 其中,N为数据样本的总数(包括当前的数据样本);Γ为所有数据样本Vo,V1,力,...,\的平均数%是当前数据样本,而σ是所有数据样本ν。 [0067] where N is the total number of data samples (including the current data sample); Gamma] for all data samples Vo, V1, force, ..., \% of the average of the current data sample, all data samples and σ ν. ,Vl,v2,...,Vn的标准差。 , Vl, v2, ..., Vn standard deviation. 通过使用上述公式,可以高效地计算平均值和标准差,并且具体地可以以恒定时间计算。 By using the above equation, average and standard deviation can be computed efficiently, and in particular can be computed in constant time. 由于上述的运算法则为每个道路段上的每个数据样本计算了平均值和标准差,因此该法则运行O(MN)时间,其中M是道路段数,N是每个道路段的数据样本数。 Since the above algorithms for each data sample on each road segment is calculated mean and standard deviation, so that the operation rules O (MN) time, where M is the number of road segments, N being the number of data samples per road segment .

[0068] 在其它实施例中,也可以使用其它异常值去除和/或数据去除运算法则,可以替代或是附加所描述的异常值检测,例如基于神经网络分类器,自然贝叶斯分类器,和/或回归模型技术,以及多个数据样本组一起考虑(例如,如果至少一些数据样本并不与其它数据样本独立)的技术。 [0068] In other embodiments, also other outlier removal and / or data removal algorithms may alternatively or additionally detected outlier described, for example based on neural network classifiers, naive Bayesian classifier, and / or regression techniques, as well as a plurality of sets of data samples considered together (e.g., if at least some of the data samples are not independent of the other data samples) technique.

20[0069] 图2D图示了使用数据样本执行平均速度估算的实例,并显示了类似于在图2B中所描述的用于特定道路段和时间段的实例数据样本。 20 [0069] Figure 2D illustrates an example of using an average speed estimation execution data samples and data samples show similar examples described in FIG. 2B for a particular road segment and time period. 数据样本已在曲线图230中标出,其在χ轴230b测量时间在y轴230a测量速度。 Data samples have been labeled in the graph 230, in which the shaft 230b χ y axis 230a in measuring time measurement speed. 在一些实施例中,给定道路段的平均速度可以按周期性基准(例如,每5分钟)计算。 In some embodiments, may be a periodic basis (e.g., every five minutes) calculating an average speed for a given road segment. 每次计算可以在诸如10分钟或15分钟的预定时间窗(或间隔)内考虑多个数据样本。 Each calculation can consider a plurality of data samples within a predetermined window of time such as 10 minutes or 15 minutes (or spacing). 如果在这样的时间窗上计算平均速度,例如在时间窗的末端或近于末端处,则当收集数据样本的速度时,在时间窗内的数据样本可以以各种方式加权,例如考虑数据样本的“年龄”(例如,基于对由于交通状况的改变,因此较老的数据样本不像在更接近当前时刻处记录的较新的数据样本那样能够提供关于时间窗末端或其他当前时刻的实际交通状况的精确信息这样的直觉或预期,而对较老的数据样本打折扣)。 If the average speed is calculated in this time window, for example, at the end of the time window, when the collection rate of the data samples, the data samples within the time window may be weighted at or near the end of a variety of ways, for example, consider the data samples "age" (for example, due to changes based on traffic conditions, so unlike in closer to the current record at the time of the newer data samples older data samples that can provide real time traffic on a window or other end of the current time accurate information on the status of such intuition or expected, while the older data samples discount). 类似地,在一些实施例中,当加权数据样本时可以考虑其它数据样本属性,例如数据源的类型或用于数据样本的特定数据源(例如,如果数据样本来自于比其它数据源更精确的或者能提供比其它数据源更好的数据的数据源类型或特定数据源,则对其的加权就更重),以及一个或多个其它加权因素类型。 Similarly, in some embodiments, the data samples may be weighted when considering other data samples attributes such as the type of data source or a data source for a particular sample (e.g., if the data to be more accurate than samples from other data sources or it can provide better data than other data source or a particular type of data source data source, even heavier weight thereof), and one or more other types of weighting factors.

[0070] 在所示的实例中,用于实例道路段的平均速度在15分钟的时间窗上每五分钟计算一次。 [0070] In the example shown, the average speed for the road segment instance computed once for 15 minutes in a time window every five minutes. 该实例描述了两个图示的数据样本231a和231b的相对权重,因为它们对两个时间窗23¾和23¾每个所计算的平均速度有贡献。 This example describes the relative weights of the two shown data samples 231a and 231b of the weight, because they contribute to 23¾ and 23¾ two time windows for each of the calculated average speed. 时间窗23¾包括在时刻30和45之间记录的数据样本,而时间窗23¾包括在时刻35和50之间记录的数据样本。 23¾ time window data samples including the recording time of between 30 and 45, and the time window data samples including 23¾ time between 35 and 50 record. 数据样本231a和231b都落在时间窗235a和235b内。 Data samples 231a and 231b fall within the time window 235a and 235b.

[0071] 在所示的实例中,在给定时间窗内的每个数据样本都与其年龄成比例加权。 [0071] In the example shown, each data sample within a given time window are weighted in proportion to their age. 也就是说,较老的数据样本相比于较新的数据样本权重较小(因此对平均速度的贡献较小)。 In other words, the older data samples compared to the newer data sample weights smaller (and therefore a smaller contribution to the average velocity). 具体地,在这个实例中给定数据样本的权重根据年龄指数性减少。 In particular, given the right to reduce the weight of the sample data in this example age exponentially. 这个衰变的加权功能通过分别相应于时间窗23¾和23¾的两个权重曲线23¾和232b图示。 The weighting function decays through time windows corresponding respectively to the two 23¾ and 23¾ 23¾ weight curve and 232b illustrated. 每个权重曲线23¾和232b在χ轴(水平)标出数据样本记录时间,在y轴(垂直)标出权重。 Each weighting curve and 232b in 23¾ χ axis (horizontal) mark recording time data samples in the y-axis (vertical) indicated weights. 在时间上较后(例如,更接近时间窗末端)记录的样本权重大于在时间上较早(例如,更接近时间窗开始)记录的样本。 Later in time (for example, closer to the end of the time window) sample weights recorded significant (eg beginning, closer to the time window) at an earlier time on the sample record. 给定数据样本的权重可以通过在曲线230上从数据样本向下绘垂直线到它与相应于所感兴趣的时间窗的权重图曲线相交的地方而看出。 A heavy weight for a given data sample to a vertical line drawn through it and see the right place corresponding to the time window of interest in the graph intersects the weight on the curve 230 downwardly from the data samples. 例如,权重图23¾相应于时间窗23¾,根据数据样本231a (较老)和231b (较新)的相对年龄,数据样本231a的权重233a少于数据样本231b的权重23北。 For example, the weights corresponding to FIG 23¾ 23¾ time window, according to (newer) the relative ages of the data samples 231a (older) and 231b, 231a of data sample weight sample weightings 233a and 231b is less than 23 weight North data. 此外,权重图232b相应于时间间隔235b,并且类似地可以看出数据样本231a的权重23½小于数据样本231b的权重234b。 Moreover, the weight corresponding to a time interval in FIG 232b 235b, and similarly the right can be seen that the sample data sample weights 231a and 231b is smaller than the data re-re-23½ 234b. 此外,很明显,对于后续时间窗,给定数据样本的权重随时间衰变。 Further, it is clear that, for the subsequent time window, a heavy weight for a given data sample decays over time. 例如,在时间窗23¾中的数据样本231b的权重23¾大于在后来的时间窗23¾中的相同数据样本231b的权重234b,因为数据样本231b在时间窗23¾期间相比于在时间窗23¾期间相对更新。 For example, the right sample 231b of the data in the time window 23¾ in heavy 23¾ larger than the same data at a later time window 23¾ the right sample 231b weights 234b, since the data samples 231b during the time window 23¾ compared to the relatively updated during the time window 23¾ .

[0072] 更正规地,在一个实施例中,对于相对于时刻T处的时间末端的时刻t所记录的数据样本的权重可以如下表示: [0072] More formally, in one embodiment, with respect to the timing for the end of time T at a time t of data sample weight recorded weight can be expressed as follows:

[0073] w(t)=[…) [0073] w (t) = [...)

[0074] 其中,e是公知的数学常量,α是可变的参数(例如,0.2)。 [0074] where, e is well-known mathematical constant, [alpha] is a variable parameter (e.g., 0.2). 给定以上,则在于时刻T处结束的时间间隔中N个数据样本Vtl,V1, V2,..., Vn的加权平均速度可以如下表述,其中、为数据样本Vi表示的时间(例如,其被记录的时间): Given the above, wherein the end of the time interval T at the N data samples Vtl, V1, V2, ..., Vn weighted average speed may be expressed as follows, wherein the time data sample is represented by Vi (e.g., which recorded time):

21[0075] 21 [0075]

Figure CN102394009AD00221

[0076] 而且,对所计算的平均速度的错误估计可以如下计算: [0076] Further, the error of the calculated average velocity estimate may be calculated as follows:

[0077] [0077]

Figure CN102394009AD00222

[0078] 其中,N为数据样本数而ο为从平均速度来的数据样本y0,V1, v2, . . . , Vn的标准偏差。 [0078] where, N is the number of data samples and the data samples ο y0 from the average speed, V1, v2,..., Vn is a standard deviation. 在其它实施例中类似地也可以为计算或产生的平均速度确定其它形式的置信值。 Similarly, other forms may also be determined confidence values ​​to calculate the average velocity or generated in other embodiments.

[0079] 如要注意地,无论替代或除了数据样本的年龄,数据样本可以基于其它因素加权。 [0079] To be noted, whether instead of or in addition to the age of data samples, the data samples may be weighted based on other factors. 例如,数据样本可以如上所述但同时使用不同的加权函数(例如,数据样本的权重随年龄线性减少而不是指数地减少)进行时间加权。 For example, data samples may be used as described above but different weighting functions (e.g., the right data sample weight decrease linearly with age rather than exponentially decreasing) the time weighted. 此外,数据样本加权还可以基于在所感兴趣的时间间隔内的数据样本的总数。 Further, also the total number of data samples weighted data samples in the time interval of interest may be based. 例如,上述的变量参数α可以取决于或基于数据样本的总数而变化,以便数据样本的数量越多则地较老的数据样本就产生越高的处罚(例如,较低的权重),以反映为计算平均速度的目的而得到更多的延迟(例如,较新)数据样本的增加的可能性。 For example, the above-described variables or parameters α may depend on the total number of data samples based on the change, so the more the number of data samples is the older data samples generated higher penalties (e.g., a lower weight), to reflect the for the purposes of calculating the average speed obtained more possibilities (e.g., newer) data samples of increased delay. 而且,数据样本可以基于包括数据源类型的其它因素而加权。 Furthermore, data samples may be weighted based on other factors including the types of data sources. 例如,可以是如下情况,特定的数据源(例如,特定的道路交通传感器,或特定网络的全部交通传感器)都是已知(例如,基于报告的状态信息)或预料(例如,基于历史观测)为不可靠或不精确的。 For example, may be the case, a particular data source (e.g., a specific road traffic sensors, all or specific network traffic sensors) are known (e.g., based on the status report information) or is expected (e.g., based on historical observations) unreliable or inaccurate. 在这样的情况下,从这样的道路交通传感器获得的数据样本(例如,图2Β的数据样本211a)可以比从移动数据源(例如图2B的数据样本212a)获得的数据样本加权少。 In such a case, the data samples can be less (e.g., data sample 211a of FIG 2Β) such road traffic sensor data obtained than sample obtained from mobile data sources (e.g., data sample 212a of Figure 2B) weighting.

[0080] 图2E简化了基于数据样本为道路段执行交通流量估算的实例,其例如可以包括推断交通量、密度和/或占用率。 [0080] FIG. 2E simplified example of traffic flow based on data samples for the road segment estimation performed, which may include, for example, inferring traffic, density, and / or occupancy. 在该实例中,给定道路段的交通量表述为在给定的时间窗内在流经道路段的车辆总量或在时间窗内在道路段上达到的车辆总量,给定道路段的交通密度可以表述为每单位距离(例如,英里或公里)的车辆总量,交通占用率可以表述为车辆占用道路段上的特定道路段或点的平均时间量。 In this example, a given traffic road segment is expressed as the total amount of the vehicle given time window of a vehicle passing through the inner section of the road or in the time window of the inner road segments achieved in a given section of road traffic density It can be expressed as the total vehicle per unit distance (for example, miles or kilometers), traffic occupancy rate can be expressed as the average vehicle occupancy amount of time a particular road segment or point on the road segment.

[0081] 给定多个要被观测来在给定的时间窗期间行驶过给定的道路段相异的移动数据源,和作为移动数据源的总的车辆的已知或预期百分比,则可以推断总的交通量——在时间窗期间行驶过道路段的车辆总数(包括不是移动数据源的车辆)。 [0081] a given percentage of the total plurality of known or expected to be observed for a vehicle to travel through a given road segment distinct mobile data sources during a given time window, and as the mobile data source may be inferred total traffic volume - with sections of the aisle during the time window of the total (not including mobile data source vehicles) vehicles. 从所推断的总的交通量,和在道路段上的车辆的估算的平均速度,就可以进一步计算交通密度以及道路占用率。 From the total traffic volume inferred, and the estimated average speed of vehicles on the road segment, we can further calculate traffic density and road usage.

[0082] 估算在特定时间窗期间特定道路段的总的交通量的一种简单的途径是简单地用预料要成为移动数据样本源的实际车辆的百分比去除该时间窗的移动数据源的数量——这样,例如,如果在时间窗内从25个移动数据源接收移动数据样本并且在道路段上预期总的车辆的10%要成为移动数据样本源,则为该时间窗的时间量估算的总量为250个实际车辆。 The number of mobile data sources percentage [0082] estimate during a specific time window having a total traffic volume of a particular road segment simple way is to simply use mobile data is expected to be the source of a sample of the actual vehicle to remove the time window - - Thus, for example, if the received data samples from mobile data sources 25 moves within a time window and on the road segment 10% of the total vehicle is expected to be mobile data sample sources, compared with the amount of time that the estimated total time window the actual amount to 250 vehicles. 但,由于车辆到达率的固有可变性,特别是如果移动数据样本源的预料百分比很小,则这种途径可能导致相邻时间窗总量估算的巨大变化。 However, due to the inherent variability of the vehicle reaches, especially if the expected percentage of mobile data sample sources is small, this approach may result in the dramatic changes of the total time window of neighboring estimation. 正如一种替换,其提供了更为复杂的分析,给定道路段的总的交通量可以如下推断。 As an alternative, it provides a more sophisticated analysis, given the total traffic volume road segment can be inferred as follows. 给定特定数量的相异移动数据源(例如,各部车辆)n,在长度1的道路段上,在给定的时间段τ中,使用贝叶斯统计来推断移动数据源到达的主要平均率(underlying means rate),λ。 Given a certain number of distinct mobile data sources (e.g., each of the vehicles) n, the length of a segment on a road in a given time period τ using Bayesian inference to the average rate of the main data source to the mobile (underlying means rate), λ. 在相应于道路段的一段道路上到达的移动数据源可以随机建模,按时离散处理,因此可以通过泊松统计来描述,即:[0083] Arrive at the road segment corresponding to the stretch of road can be mobile data sources stochastic modeling, discrete time process, and therefore can be described by the Poisson statistics, namely: [0083]

Figure CN102394009AD00231

[0084] 从以上的公式中,可以计算η个移动数据源被观测的可能性,给定的平均到达率λ和所观测的车辆数η。 [0084] From the above equation, [eta] may be calculated likelihood mobile data sources to be observed, given the number average vehicle arrival rate λ observed η. 例如,假定平均到达率λ = 10(车辆/单位时间)并且观测η =5部车辆,则替换产生: For example, assuming that the average arrival rate λ = 10 (vehicles / unit time) and the observation η = 5 vehicles, the replacement is generated:

[0085] [0085]

Figure CN102394009AD00232

[0086] 表示实际观测η = 5部车辆有3. 8%的可能性。 [0086] indicates the observed η = 5 vehicles have 3.8% of possibilities. 类似地,如果平均到达率是λ =10(车辆/单位时间)则实际观测到10部车辆达到(即,n = 10)的可能性是12. 5%。 Similarly, if the average arrival rate λ = 10 (vehicles / unit time) of the vehicle 10 actually reaches observed (i.e., n = 10) was 12.5% ​​probability.

[0087] 以上的公式可以与贝叶斯定理一起使用来来确定给定观测η的特定到达率λ的可能性。 Above [0087] Bayes theorem and equations can be used to determine the likelihood of a particular arrival rate of λ η given observation together. 如所知的,贝叶斯定理是: As is known, Bayes' theorem is:

[0088] [0088]

Figure CN102394009AD00233

[0089] 通过替换和常数去除,可以得到如下: [0089] and by replacing the constant removal, can be obtained:

[0090] [0090]

Figure CN102394009AD00234

[0091] 从以上中,给定观测η个移动数据源,可以计算到达率λ的成比例的或相对的可能性,提供了在给定η的各个观测值时,λ的可能值的概率分布。 [0091] From the above, a given observation η mobile data sources, or may be calculated in proportion to the relative likelihood of the arrival rate λ is provided at a respective predetermined value η is observed, the probability distribution of the possible values ​​of λ . 对于η的特定值,在各个到达率值上的可能性分布允许选择一个有代表性的到达率值(例如,平均值或中间值)并允许估算该值的置信度。 For a particular value of η, the possibility of reaching the respective values ​​in the distribution allows to select a value representative arrival rate (e.g., mean or median) and allowing the estimated confidence value.

[0092] 而且,给定在道路上作为移动数据源的总的车辆的已知百分比,也作为“渗透因子”,因此可以如下计算总的交通的到达率量: [0092] Further, a known percentage of the total vehicles on the road is set as the mobile data source, but also as a "permeability factor", it is possible to reach the total amount of traffic is calculated as follows:

[0093] [0093]

Figure CN102394009AD00235

[0094] 在一些实施例中,在时间段内道路段上的总的交通量替换地可以表达为在时间τ流过道路段的长度1的车辆的总量k。 [0094] In some embodiments, the total traffic volume on the road segment time period can alternatively be expressed as the total amount of time τ k to flow through the length of the section of the vehicle 1.

[0095] 图2E图示了给定观测样本尺寸,给定样本移动数据源渗透因子q = 0. 014 (1. 4% )的各种总的交通量的概率分布。 [0095] Figure 2E illustrates an observed sample of a given size, a given mobile data sample sources probability distribution permeability factor q = 0.014 (1.4%) of the total of the various traffic volume. 具体地,图2E图示了三维曲线图M0,其在y轴241上标出了观测到的移动数据源数(η),在χ轴242上标示了推断的交通到达率量,而在ζ轴243上标示了每个推断的交通量值的可能性。 In particular, Figure 2E illustrates a three-dimensional graph M0, which indicated the number of mobile data sources observed ([eta]) in the y-axis 241, the indicated amount of traffic arrival rate estimation on the χ shaft 242, while the ζ axis 243 indicate the possibility of traffic on the value of each inferred. 例如,该曲线图显示了给定移动数据源的的观测数η = 0,实际交通量在零附近的可能性约为0. 6 (或60% ),如由栏所示,而每单位时间实际交通量在143部车辆左右的可能性为大约0. 1,如栏M4b所示。 For example, the graph shows the number of mobile data sources of a given observation η = 0, the likelihood of near zero amount of the actual traffic is approximately 0.6 (or 60%), as indicated by the bar, and each unit of time the possibility of actual traffic amount around the vehicle 143 is about 0.1, as shown in column M4b. 而且,给定移动数据源的的观测数η =观,则每单位时间总实际交通量在2143部车辆左右(相应于每单位时间大约30个移动数据样本源,给定实例的渗透因子)的可能性为大约0. 1,如栏Mk所示,其显示了接近于总的实际交通量的中间值。 Moreover, a given number of mobile data sources observation η = View, per unit time is the total actual traffic volume of about 2143 of the vehicle (corresponding to the per unit time of approximately 30 mobile data sample sources, a given instance permeability factor) the possibility of about 0.1, as shown in column Mk, which shows an intermediate value closer to the actual total traffic volume.

[0096] 此外,可以使用用于给定道路段的推断的总交通到达率量(表示在道路段的时间τ内到达的车辆数k)、所估算的平均速度V,和平均车辆长度d来计算平均占用率和密度,则[0097] [0096] Further, the total rate may be used to infer the amount of a given road segment of traffic arrival (k represents the number of vehicles arrive within the time τ road segment), the estimated average velocity V, and the average length of the vehicle to d calculating the average occupancy rate and density, the [0097]

Figure CN102394009AD00236

[0098] Occupancy = md [0098] Occupancy = md

[0099] 如先前所述,在道路段上的车辆的平均速度ν可以通过使用速度估算技术来获得,例如参考图2D所作的描述。 [0099] As previously described, the average speed of the vehicle on a road segment ν estimation techniques can be obtained by using a speed, for example, described with reference to FIG 2D taken.

[0100] 图10A-10B图示了调整或修正来自道路交通传感器的例如不可靠和丢失数据样本等的错误数据样本的实例。 [0100] FIGS. 10A-10B illustrates an example of missing and unreliable data samples, and erroneous data correction or adjustment, for example, samples from road traffic sensors. 具体地,图IOA显示了在各个时间从多个交通传感器获得的多个实例数据读数,其被组织到表1000中。 In particular, FIG IOA show multiple instances of data readings at each time obtained from a plurality of traffic sensors, which are organized into tables 1000. 表1000包括多个数据读数行1004a-1004y,其每个包括唯一识别提供读数的交通传感器的交通传感器ID ( “标识符”)1002a,交通传感器数据读数值1002b包括由交通传感器报告的交通流量信息,交通传感器读数时间1002c反映了由交通传感器采集数据读数的时间,而交通传感器状态1002d包括交通传感器操作状态的指示。 Table 1000 includes a plurality of rows of data readings 1004a-1004y, each of which includes a unique identification traffic sensors provide sensor readings of traffic ID ( "Identifier") 1002a, 1002b traffic sensor data readings by the traffic includes traffic flow information reported by a sensor , 1002c traffic sensor read time reflects the time acquired by the traffic sensor data readings, and the traffic sensor state 1002d comprises a sensor indicating the operating state of the vehicle. 虽然在其它实施例中交通传感器可以报告其它类型的交通流量信息(例如,交通量和占用率),但在这个实例中仅显示了速度信息,而值也可以以其它格式报告。 Although traffic sensors may report to other types of traffic flow information (e.g., traffic and occupancy) In other embodiments, but in this example only shows the speed information, and the value can also be reported in other formats.

[0101] 在所示的实例中,数据读数1004a-1004y可以在各个时间由多个交通传感器采集并能够记录表示在表1000中。 [0101] In the example shown, the data readings 1004a-1004y may be collected and can be recorded by the plurality of traffic sensors at various times are shown in Table 1000. 在一些情况中,数据读数由交通传感器周期性(例如,每分钟,每五分钟等)采集并且/或者以这样的周期由该交通传感器报告。 In some cases, by the traffic sensor data readings periodically (e.g., every minute, every five minutes, etc.) acquired and / or in such a period reported by the traffic sensor. 例如,交通传感器123每五分钟采集数据读数,如数据读数10(Ma-1004d和1004f_1004i所示,其显示了由交通传感器123在10:25AM和10 : 40AM在独立的两天(在这个实例中是8/13/06和8/14/06)所采集的多个数据读数。 For example, traffic sensor 123 data readings every five minutes, such as 10 data readings (Ma-1004d and 1004f_1004i, showing by traffic sensor 123 at 10:25 AM and 10: 40AM separate two days (in this example and a plurality of data readings 8/13/06 8/14/06) collected.

[0102] 每个所示的数据读数10(Ma-1004y包括数据读数值1002b,其包括由数据传感器所观测或获得的交通流量信息。这样的交通流量信息可以包括行驶到达、临近或通过交通传感器的一个或多部车辆的速度。例如,数据读数10(Ma-1004y分别显示了传感器123在四个不同的时间观测到的车辆速度,34英里每小时(mph)、36mph,42mph和38mph。此外,交通流量信息可以包括行驶到达、临近或通过交通传感器的车辆总量或递增计数,而无论替代或除了速度和/或其它信息。总的数量可以是从交通传感器被安装或激活时起,交通传感器观测的车辆的累积量。递增计数可以是从传感器采集在先数据读数时起,由交通传感器观测的车辆的累积量。数据读数10(Mw-10(MX显示了在两个不同的时间传感器166分别统计了316辆车和389辆车。在一些情况中,所记录的数据读数可以不包括数据读数值 [0102] Each of the illustrated data readings 10 (Ma-1004y includes a data reading value 1002b, which includes traffic flow information observed by the sensors or the data obtained. Such information may include traffic to travel to reach near or through traffic sensors or a speed of the vehicle. For example, data readings 10 (Ma-1004y, respectively, show the sensor 123 at four different times observed vehicle speed, 34 mph (mph), 36mph, 42mph and 38mph. Further , traffic flow information may include travel reach, or near the vehicle by the total counts or the traffic sensor, and whether instead of or in addition to the starting time of the speed and / or other information. the total number may be mounted or activated from a traffic sensor, traffic observing the accumulated amount sensor of the vehicle. counts may be from when the sensor data readings from the previous acquisition, the accumulated amount of traffic observed by the vehicle sensor data readings 10 (Mw-10 (MX shows two different time of the sensor 166 vehicles 316 and 389 count the vehicles. in some cases, data readings recorded may not include a data reading value ,例如当给定的交通传感器出现了传感器故障,从而不能采集或记录观测或报告观测(例如,由于网络故障)。例如,数据读数1004k显示了交通传感器1¾在8/13/06这天的10:25AM不能提供数据读数值,如由“一”在数据读数值列1002b中所指示的。 For example, when a given traffic sensor has a sensor fault, which can not record or collect observed or reported observations (e.g., due to a network failure). For example, the data show the traffic sensor readings 1004k 1¾ in this day 10 8/13/06 : 25AM not provide data readings, such as the "a" column in the data reading value 1002b as indicated.

[0103] 此外,交通传感器状态1002d可以与至少一些数据读数关联,例如如果交通传感器和/或相应的通信网络提供了该交通传感器的操作状态的指示。 [0103] Further, traffic sensor state 1002d may be associated with at least some of the data reading, for example if the traffic sensor and / or a corresponding communications network provides an indication of the operating state of the traffic sensor. 在所示的实施例中,操作状态包括传感器功能正常的指示(例如,0K),传感器断电状态(例如,OFF)指示,传感器被操纵报告单个值(例如,STUCK)指示,和/或与网络的通信链路断开(C0M_D0WN)指示,如分别在数据读数10(Mm,1004k, 1004ο和1004s中所示。在其它实施例中,还可以提供涉及交通传感器的操作状态的其它和/或不同信息,或者可以不得到这种操作状态信息。其它交通传感器,例如在这个实施例中交通传感器123和166都不被配置来提供交通传感器状态指示,如在交通传感器状态列1002d中“一”所示。 In the embodiment illustrated, the normal operating state comprises an indication of a sensor function (e.g., 0K), the sensor-off state (e.g., OFF) indicating the sensor is a manipulation of a single value (e.g., STUCK) indication, and / or disconnecting the communication link to the network (C0M_D0WN) indicating, respectively, as shown in data readings 10 (Mm, 1004k, 1004ο and 1004s in other embodiments, may also be provided in the operating state relates to the other traffic sensors and / or different information may not be obtained or the operating state of this information other vehicle sensors, such embodiments are not traffic sensor 123 and 166 are configured to provide a status indication in the traffic sensor of this embodiment, as listed in a traffic sensor state 1002d "a" Fig.

[0104]行 1004e,1004j, 1004η, 1004q, 1004v 和1004y 和列1002e 指出在一些实施例中可 [0104] line 1004e, 1004j, 1004η, 1004q, 1004v and 1004y and column 1002e may be noted that some embodiments

以记录附加的交通传感器数据读数和/或可以提供附加的信息并/或将其记录为每个数据 Recording additional traffic sensor data readings and / or may provide additional information and / or data for each data record

24读数的一部分。 Part of 24 readings. 类似地,在一些实施例中,信息比使用在这里所描述的技术而显示的要少。 Similarly, in some embodiments, less information than the technique described herein and shown in use.

[0105] 图IOB图示了检测表示不能正确工作的不健康的交通传感器的交通传感器数据读数中的错误的实例。 [0105] FIG IOB illustrates an example of detecting a unhealthy traffic sensors does not work correctly in the traffic sensor data reading errors. 具体地,由于很多交通传感器可以不提供交通传感器状态的指示,并且由于在一些情况中这样的交通传感器状态的指示可能是不可靠的(例如,指示传感器功能不正常但实际上它是正常的,或指示传感器功能正常但实际上它不正常),因此可能需要使用统计和/或其它技术来基于所报告的数据读数值检测不健康的交通传感器。 In particular, because many traffic sensors may not provide an indication of traffic sensor state, and because in some cases such indication of a traffic sensor state may be unreliable (e.g., indicates that the sensor is not functioning properly, but actually it is normal, or indicates that the sensor functions properly, but actually it is not normal), it may require the use of statistical and / or other techniques based on the reported traffic sensor data readings detect unhealthy.

[0106] 例如,在一些实施例中,不健康的交通传感器可以通过将由给定的交通传感器在特定天中的时间段(例如,在4:00PM和7J9PM)内所报告的数据读数的当前分布与该传感器在过去的几天中(例如,过去的120天)的同一时间段内所报告的数据读数的历史分布进行比较而检测。 [0106] For example, in some embodiments, the unhealthy traffic sensor can be given by a traffic sensor in a specific period of days (e.g., at 4:00 PM and 7J9PM) the current distribution of data readings reported and history of the sensor for several days (e.g., past 120 days) in the same period of the past data readings reported by comparing the detected distribution. 这样的分布可以通过例如处理从诸如在图IOA中所示的交通传感器获得的多个数据读数而产生。 Such a distribution may be produced by, for example, processing a plurality of data readings obtained from traffic sensor such as that shown in the IOA FIG.

[0107] 图IOB显示了三个柱状图1020,1030和1040,其每个表示基于在所感兴趣的时间段内从交通传感器123所获得的数据读数的数据读数分布。 [0107] FIG IOB show three histograms 1020, 1030 and 1040, each of which represents a period of time based on data readings of interest obtained from traffic sensor data reading distribution 123. 在柱状图1020,1030和1040中表示的数据被分散到5英里每小时的间隔(例如,0至4英里每小时,5至9英里每小时,10至14英里每小时等)并标准化,以便每栏(例如栏1024)代表对于该栏车辆速度在5英里每小时桶(bucket)内的车辆速度发生在该时间段(例如,基于在落入该桶内的时间段内数据读数的百分比)内在0和1间的概率。 In the interval 5 mph histogram data 1020, 1030 and 1040 are represented dispersed (e.g., 0-4 mph, 5-9 mph, from 10 to 14 mph and the like) and normalized to each column (e.g., column 1024) representative of the vehicle speed to the column 5 miles bucket (bucket) per hour vehicle speed occurs within the time period (e.g., based on the percentage falls within the time period data readings tub) at 0 and a probability. 例如,栏IOM表示在50和M英里每小时之间的车辆速度由交通传感器123所观测,有大约0. 23的概率,例如基于从交通传感器123获得的数据读数的大约23% (含)具有在50和M英里每小时间的报告速度。 For example, IOM column represents a vehicle speed between 50 and 123 M mph observed by a traffic sensor, with a probability of about 0.23, for example about 23% based on data readings obtained from traffic sensor 123 (inclusive) having reported speed between 50 mph and M. 在其它实施例中,可以使用一个或多个其它桶尺寸,而无论除外或替换5mph的桶。 In other embodiments, may use one or more other bucket size, whether or alternatively except 5mph buckets. 例如,Imph桶可以提供更细的处理间隔,但如果在时间段内不能得到充足的数据读数,++则也可能导致在相邻桶间的巨大变化,而IOmph桶可以提供较小的变化但细节也少。 For example, Imph bucket may provide finer processing interval, if data reading can not be obtained in sufficient period of time, it can cause significant ++ change between adjacent bucket, the bucket may be provided IOmph minor variations but details less. 此外,虽然当前的实例使用平均速度作为数据读数分析和比较的量度,但其他实施例也可以使用一个或多个替换或除平均速度外的其他量度。 Further, while the present example uses average speed data readings as a measure of comparison and analysis, but other embodiments may use one or more substitutions in addition to, or other measure of the average velocity. 例如,在至少一些实施例中可以类似地使用交通量和/或占用率。 For example, traffic may be similarly used and / or occupancy in at least some embodiments.

[0108] 在这个实例中,柱状图1020表示了在过去120天的周一9 : OOAM至12 : 29PM间由交通传感器123所采集的数据读数的历史分布。 [0108] In this example, histogram 1020 shows the past 120 days Monday 9: 29PM historical distribution of traffic between the sensor 123 by the collected data readings: OOAM to 12. 柱状图1030表示当传感器123功能正常时在特定的周一的9:00AM至12:29PM间由传感器123所采集的数据读数的分布。 Histogram 1030 represents a normal function when the sensor 123 in a particular distributed between Monday 9:00 AM - 12:29 PM collected by the sensor 123 data readings. 可以清晰地看出,柱状图1030的形状与柱状图1020类似,假定在特定周一的交通模式预期与一般的周一的交通模式类似,则如以下所要讨论的,可以以各种方式计算相似的程度。 Can be clearly seen, the histogram 1030 is similar to the shape of histogram 1020, it is assumed that a particular Monday traffic pattern similar to the expected traffic patterns Monday general, as is discussed below, the degree of similarity may be calculated in various manners . 柱状图1040表示当传感器123功能不正常时在特定的周一的9:00AM至12:29PM间由交通传感器123所采集的数据读数的分布,并反而输出不能反映实际交通流量的数据读数。 Histogram 1040 represents when sensor 123 is not functioning properly acquired by the traffic sensor data readings 123 is distributed among particular Monday 9:00 AM to 12:29 PM, and outputs but does not reflect the actual traffic flow data readings. 正如所明显看出地,柱状图1040的形状明显地与柱状图1020的不同,其反映了由交通传感器123报告的错误的数据读数。 As evident, the shape of the histogram 1040 is significantly different from the histogram 1020, which reflects the erroneous data readings reported by the traffic sensor 123. 例如,在该分布中巨大的突起能在栏1048中看出,其可能表示在9:00AM至12:29PM间的至少一些时候传感器123被卡住了并报告了不能反映实际交通流量的大量恒定读数。 For example, it can be seen in huge projection column 1048 in the distribution, which may indicate that at least some of the time the sensor 123 is stuck and reported a number of constant not reflect the actual traffic between 9:00 AM to 12:29 PM reading.

[0109] 在一些实施例中,虽然可以使用在两个交通传感器数据分布间的Kullback-Leibler散度(divergence)来确定在两个分布间的相似度,但在其它实施例中在分布间的相似度或差异也可以以其它方式计算。 [0109] In some embodiments, although may be used in the Kullback-Leibler divergence (Divergence) between the two traffic sensor data to determine the distribution of the similarity between the two distributions, but in other embodiments the distribution between similarity or difference may be calculated in other ways. Kullkick-Leibler散度是两个概率分布P和Q的相似度的凸度量度。 Kullkick-Leibler divergence is a measure of the degree of similarity convex two probability distributions P and Q are. 它可以如下表示: It can be expressed as follows:

25[0110] 25 [0110]

Figure CN102394009AD00261

[0111] 其中Pi和Qi为离散的概率分布P和Q的值(例如,每个Pi和Qi为速度出现在第i个桶内的概率)。 [0111] wherein P and Pi and Qi distribution value Q for the probability of a discrete (e.g., each Pi and Qi in the speed occurs in the probability of the i-th bucket). 在所示的实例中,在柱状图1020中所示的数据读数分布和在柱状图1030中所示的数据读数分布间用于健康的交通传感器的Kullkick-Leibler散度(“DKL”) 1036为大约0. 076,而在柱状图1020中所示的数据读数分布和在柱状图1040中所示的数据读数分布间用于不健康的交通传感器的Kullkick-Leibler散度1046为大约0. 568。 In the example shown, Kullkick-Leibler divergence data is shown in the histogram and the data reading distribution shown in histogram 1020 1030 traffic sensor health for the inter-frequency distribution ( "DKL") 1036 to about 0.076, and Kullkick-Leibler divergence between the traffic sensor data reading distribution shown in histogram 1020 and the data reading distribution shown in histogram 1040 is approximately 1046 for unhealthy 0.568. 正如可能所预期的一样,DKL 1036明显小于DKL 1046 (在这种情况下,大约为DKL 1046的13% ),其反映了柱状图1030(例如,表示在其功能正常时交通传感器123的输出)相似于柱状图1020(例如,表示交通传感器123的平均行为)更甚于柱状图1040(例如,表示在其故障时的交通传感器12¾相似于柱状图1020。 As may be expected, like, DKL 1036 is significantly less than DKL 1046 (in this case, approximately 13% of the DKL 1046), which reflects the histogram 1030 (e.g., which represents an output function when normal traffic sensor 123) similar to the histogram 1020 (e.g., it represents the average behavior of traffic sensor 123) even more in the histogram 1040 (e.g., traffic sensor 12¾ indicates the failure at 1020 is similar to the histogram.

[0112] 此外,替代诸如从Kullkick-Leibler散度来的相似度量度或除此之外,一些实施例可以使用其它统计量度来检测由交通传感器提供的错误数据读数,例如统计信息熵。 [0112] In addition, as an alternative to the Kullkick-Leibler divergence from the similarity measure, or in addition, some embodiments may use other statistical measures to detect erroneous data readings provided by the traffic sensors, such as statistical information entropy. 概率分布的统计熵是概率分布的差异性的量度。 Statistical Entropy is a measure of the probability distribution of the difference of the probability distribution. 概率分布P的统计熵可以如下表示: Statistical entropy of the probability distribution P can be expressed as follows:

[0113] [0113]

Figure CN102394009AD00262

[0114] 其中,Pi为离散的概率分布P的值(例如,每个Pi是速度落在P柱状图的第i桶内的概率)。 [0114] wherein, Pi is the probability distribution P discrete values ​​(e.g., each Pi is the falling speed of the histogram probability P i-th tub). 在所示的实施例中,在柱状图1020中所示的分布的统计熵1022大约为2. 17,在柱状图1030中所示的分布的统计熵1032大约为2. 14,而在柱状图1040中所示的分布的统计熵1042大约为2. 22。 In the illustrated embodiment, the statistical entropy 1022 of the distribution shown in histogram 1020 is approximately 2.17, the statistical entropy 1032 of the distribution shown in histogram 1030 is approximately 2.14, whereas in the histogram statistical entropy 1042 of the distribution shown in 1040 is about 2.22. 正如可能预期地,统计熵1042比统计熵1032和统计熵1022都要大,这反映了在其故障时交通传感器123展示了更加混乱的输出模式。 As might be expected, the statistical entropy entropy 1032 and 1042 statistical entropy 1022 is bigger than the statistics, reflecting the traffic sensor failure when it showed 123 more chaotic output mode.

[0115] 此外,在两个统计熵量度间的不同可以通过计算熵差异度量来测量。 [0115] Further, between two different statistical entropy may be measured by the metric calculating the entropy difference measure. 在两个概率分布P和Q间的熵差异量度可以如下表示: The entropy difference measure between the distribution of the two probabilities P and Q are expressed as follows:

[0116] EM = I |H(P)-H(Q) | |2 [0116] EM = I | H (P) -H (Q) | | 2

[0117] 其中H(P)和H(Q)如上所述分别为概率分布P和Q的熵。 [0117] where H (P) and H (Q) as described above are probability distributions P and Q entropy. 在所示的实例中,在柱状图1020所示的分布和在柱状图1030中所示的分布间的熵差异量度('ΈΜ”) 1034大约为0. 0010,而在柱状图1020所示的分布和在柱状图1040中所示的分布间的熵差异量度1044大约为0.0023。正如可以预期地,熵差异量度1044明显比熵差异量度1034要大(在这个情况中大了两倍),这反映了柱状图1040中所示的分布的统计熵和在柱状图1020中所示的分布的统计熵间的差异相比于在柱状图1030中所示的分布的统计熵和在柱状图1020中所示的分布的统计熵间的差异要大。 In the example shown, the distribution shown in histogram 1020 and the entropy difference measure between the distribution shown in histogram 1030 ( 'ΈΜ ") 1034 is about 0.0010, and in the histogram 1020 shown in FIG. distribution and entropy difference between the distribution shown in histogram 1040 1044 measure approximately 0.0023. as can be expected, the entropy difference measure 1044 1034 significantly larger (twice as large in this case) than the entropy measure of the difference, which It reflects the statistical entropy statistical entropy distribution shown in histogram 1040 and the difference between statistical entropy distribution shown in the histogram in 1020 compared to 1030 as shown in the histogram of the distribution and the histogram 1020 the statistical difference between the entropy distribution shown to be large.

[0118] 可以以各种方式使用上述的统计量度来检测不健康的交通传感器。 [0118] unhealthy traffic sensor may be detected using the above-described statistical measures in various manners. 在一些实施例中,有关当前数据读数分布的各种信息可以提供为对传感器健康(或数据读数可靠性)分类器的输入,例如基于神经网络、贝叶斯分类器、决策树等。 In some embodiments, various information about the current data reading distribution may be provided as an input to the health sensor (or data reading reliability) classifier, for example based on neural network, Bayesian classifier, decision tree. 例如,分类器输入信息可以包括,例如,用于该交通传感器的历史数据读数分布和用于该道路传感器的当前数据读数分布间的Kullkick-Leibler散度,和当前数据读数分布的统计熵。 For example, the classifier input information may include, for example, historical data for the transportation and distribution of sensor readings for Kullkick-Leibler divergence between the distribution of the current data readings of the road sensors, and current data reading distribution of statistical entropy. 接着,分类器基于所提供的输入估算该交通传感器的健康,并提供表示健康或不健康传感器的输出。 Next, based on the input of the classifier estimates provided by the traffic sensor health, and providing a sensor output healthy or unhealthy. 在一些情况中,还提供附加的信息来作为分类器的输入,例如一天中的时间的指示(例如,从5 : OOAM到9:00AM的时间段),一周中的某天或某几天的指示(例如,从周一到周四,周五,周六或周日)和/或相应于当前和历史数据读数分布的一天中的时间或一周中的某天,mph组的尺寸等。 In some cases, additional information is also provided as an input to a classifier, such as time of day indication (e.g., from 5: OOAM period to 9:00 AM), the day of the week or days instructions (for example, from Monday to Thursday, Friday, Saturday or Sunday) and / day, group size mph or corresponding to current and historical data reading distribution of the time of day or week, etc. 分类器可以通过使用实际的先前数据读数而训练,诸如包括交通传感器状态的表示,正如在图IOA中所示。 The classifier may be trained by using the actual previous data readings, such as a traffic sensor comprising represents the state, as shown in the IOA FIG.

[0119] 在其它实施例中,不健康的交通传感器无需使用分类器就可被识别。 [0119] In other embodiments, the unhealthy traffic sensor without using a classifier can be identified. 例如,如果一个或多个统计量度大于预定的阈值,则可以确定交通传感器是不健康的。 For example, if one or more statistical measures greater than a predetermined threshold value, it may be determined to be unhealthy traffic sensor. 例如,如果在用于交通传感器的历史数据读数分布和用于该道路传感器的当前数据读数分布间的Kullback-Leibler散度大于第一阈值,如果当前数据读数分布的统计熵大于第二阈值,和/或如果在当前数据读数分布和历史数据读数分布间的熵差异量度大于第三阈值,则可以确定该交通传感器是不健康的。 For example, if the reading of the current data in the historical data reading distribution for the traffic sensor and a sensor for the road Kullback-Leibler divergence between the distributions is greater than a first threshold value, if the statistical entropy of the current data reading distribution is above a second threshold, and / entropy or if the difference between the current data reading distribution and the historical data reading distribution is a measure greater than the third threshold value, it may be determined that the traffic sensor is unhealthy. 此外,也可以使用其它非统计信息,诸如交通传感器是否报告了可以被认为是健康或不健康的传感器状态。 It is also possible to use other non-statistical information, such as whether to report the traffic sensors can be considered healthy or unhealthy sensor status.

[0120] 如先前所要注意地,虽然上述技术主要在报告车辆速度信息的交通传感器的上下文中进行了描述,但同样的技术也可以对其它交通流量信息使用,包括交通量、密度和占有率。 [0120] As previously to be noted that, although the above technique has been described primarily in the context of traffic sensor of vehicle speed information in the report, but the same technology can also be used for other traffic information, including traffic density and occupancy.

[0121] 图3是图示适于执行至少所述技术的一些的计算系统300的实施例的结构图,例如通过执行数据样本管理系统的实施例。 [0121] FIG. 3 is a block diagram illustrating an embodiment of a computing system at least some of the art 300 adapted to perform, for example, by performing the embodiment of the Data Sample Manager system. 计算系统300包括中央处理单元(“CPU”)335,各个输入/输出(“I/O”)组件305,存储器340和内存345,并且所示的I/O组件包括显示器310,网络连接315,计算机可读介质驱动器320以及其它I/O设备330 (例如,键盘、鼠标或其它点选设备、麦克风、扬声器等)。 The computing system 300 includes a central processing unit ( "CPU") 335, various input / output ( "I / O") component 305, memory 340 and memory 345, and I / O components include a display 310 as shown, a network connection 315, The computer-readable medium drive 320 and other I / O device 330 (e.g., keyboard, mouse or other pointing device, microphone, speaker, etc.).

[0122] 在所示的实施例中,在内存345中执行各种系统来执行至少所述技术的一些,包括数据样本管理系统350、预测交通信息提供系统360、关键道路标识符系统361、道路段确定系统362、RT信息提供系统363和由程序369提供的其它可选系统,这些各种执行系统通常在这里都称之为交通信息系统。 [0122] performed in the embodiment shown in the various systems in the memory 345 to perform at least some of the techniques, including the Data Sample Manager system 350, the predicted traffic information providing system 360, the key identifier road system 361, road period determination system 362, RT 363, and other system information providing alternative system 369 provided by the program, performing these various systems are generally referred to herein traffic information system. 计算系统300和它的执行系统可以经由网络380(例如,互联网、一个或多个移动电话网络等)与其它计算系统通信,例如各个客户端设备382、基于车辆的客户端和/或数据源384、道路交通传感器386、其它数据源388和第三方计算系统390。 The computing system 300 and its execution system can communicate with other computing systems, such as the respective client devices 382, ​​vehicle-based clients, and / or data source 384 via a network 380 (e.g., the Internet, one or more mobile telephone networks, etc.) , road traffic sensors 386, other data sources 388 and third-party computing systems 390.

[0123] 具体地,数据样本管理系统350从各个来源获得各种有关当前交通状况和/或先前观测的情况数据的信息,例如从道路交通传感器386、基于车辆的移动数据源384和/或其它移动或非移动的数据源388获得。 [0123] Specifically, the Data Sample Manager system 350 to obtain various information about the current traffic conditions and / or circumstances previously observed data from various sources, such as from road traffic sensors 386, vehicle-based mobile data sources 384 and / or other mobile or sources 388 to obtain data. 接着数据样本管理系统350通过过滤(例如,考虑去除数据样本)和/或调整(例如,校正错误)数据来为其它组件和/或系统的使用而准备获得的数据,接着使用所准备的数据来估算各条道路段的道路交通状况,例如交通流量和/或速度。 Next Data Sample Manager system 350 by filtering (e.g., consider removing data samples) and / or adjusted (e.g., correct an error) data prepared data obtained using other components and / or systems, and then use the data prepared by assessing road traffic conditions for each road segment, such as traffic flow and / or speed. 在这个所示的实施例中,数据样本管理系统350包括数据样本过滤组件352、传感器数据调整组件353、数据样本异常值去除组件354、数据样本速度估算组件356、数据样本流量估算组件358和可选的传感器数据收集组件355,其中组件352-358执行类似于前面在图1中的相应组件所描述的功能(例如,数据样本过滤组件104、传感器数据调整组件105、数据样本异常值去除组件106、数据样本速度估算组件107、数据样本流量估算组件108和可选的传感器数据收集组件110)。 In this embodiment illustrated embodiment, the Data Sample Manager system 350 includes a data sample filter assembly 352, the Sensor Data Conditioner component 353, Data Sample Outlier Eliminator component 354, a Data Sample Speed ​​Assessor component 356, Data Sample Flow Assessor component 358 and optional sensor data Aggregator component 355, wherein the components 352-358 perform functions similar to the corresponding components of the front in FIG. 1 as described (e.g., data sample filter assembly 104, the sensor data Conditioner component 105, a data sample outlier Eliminator component 106 data sample speed Assessor component 107, data sample flow Assessor component 108 and an optional sensor data Aggregator component 110). 此外,在至少一些实施例中,数据样本管理系统以基本实时或近似实时的方式执行道路交通状况的估算,例如在几分钟内获得底层数据(其自身可以从数据源以基本实时的方式获得)。 Further, in at least some embodiments, the Data Sample Manager system in substantially real-time or near real-time fashion to estimate road traffic conditions is performed, for example, the underlying data is obtained within a few minutes (which itself may be obtained from a data source in a substantially real time) .

[0124] 其它交通信息系统360-363和369和/或第三方计算系统390接着可以以各种方式使用由数据样本管理系统提供的数据。 [0124] Other data 369 and traffic information systems 360-363 and / or third-party computing systems 390 may then be used in various ways provided by the Data Sample Manager system. 例如,预测交通信息提供系统360可以获得(要 For example, the Predictive Traffic Information Provider system 360 can be obtained (to

27么直接地,或间接地经由数据库或存储设备)这种所准备的数据以在多个未来时间产生进一步的交通状况预测,并将预测信息提供给一个或多个其它接收端,例如一个或多个其它交通信息系统,客户端设备382,基于车辆的客户端384和/或第三方计算系统390。 27 it directly, or indirectly via a database or storage device) of such prepared data to produce further time traffic conditions at multiple future prediction, and the prediction information to one or more other receiving terminal, or for example a a plurality of other vehicle information system, the client device 382, ​​based on the customer's vehicle and / or third-party computing systems ends 384,390. 此外,RT信息提供系统363可以从数据样本管理系统获得有关所估算的道路交通状况的信息,并将道路交通状况信息以实时或近于实时的方式提供给它方(例如,客户端设备382,基于车辆的客户端384和/或第三方计算系统390)——当数据样本管理系统也以这种实时或近于实时的方式执行估算时,从RT信息提供系统来的数据的接收方可以基于在一条或多条道路段上的同时期的实际车辆行驶状况浏览和使用有关在这些道路段上的当前交通状况的信息(如由在这些道路段上行驶的移动数据源和/或传感器所报告的,并且其它数据源提供有关在这些道路段上的实际车辆行驶状况的信息)。 In addition, RT information system 363 can provide information about obtaining the estimated road traffic conditions from sample data management system and road traffic information in real-time or near real-time manner available to other parties (for example, a client device 382, based on the client side of the vehicle 384 and / or third-party computing systems 390) - if the data sample Manager system is also the recipient of such real-time or near real-time estimation of execution, there is provided a data system may be based on information from the RT of the actual vehicle while on the road segment or a strip running condition browse and use information about the current traffic situation on the road segment (e.g. by a traveling road segments on those mobile data sources and / or reported by the sensor , and other data sources provide information about the actual vehicle on the road segment driving conditions).

[0125] 在各个实施例中客户端设备382可以采用各种形式,并通常可以包括任何通信设备和其它能产生请求给交通信息系统和/或从交通信息系统接收信息的任何计算设备。 [0125] In various embodiments, client device 382 may take various forms, and may generally include a traffic information system and / or any computing device receives the information from the traffic information system, and any other communication device capable of generating a request. 在一些情况中,客户端设备可以执行用户可以使用的交互控制应用程序(例如,Web浏览器)以产生对涉及交通的信息的请求(例如,预测的未来交通状况信息,实时或近于实时的当前交通状况信息等),而在另一些情况中,至少一些这样的涉及交通的信息可以被自动地从一个或多个交通信息系统发送到客户端设备(例如,文本消息、新的Web页面,特定的程序数据更新等)。 In some cases, the client device can perform interactive control applications (eg, Web browsers) users can use to generate a request for information related to traffic (for example, future traffic condition information forecasting, real-time or near real-time current traffic conditions information, etc.), while in other cases, at least some of the traffic is directed to such information may be automatically transmitted from the one or more traffic information system to the client device (e.g., a text message, a new Web page, specific program data update, etc.).

[0126] 道路交通传感器386包括多个安装在诸如一个或多个地理区域的各个街道、高速路或其他道路内、上、或附近的传感器。 [0126] 386 includes a plurality of road traffic sensor mounted in each street, such as one or more geographic areas, highway or other roads, on or near the sensor. 这些传感器可以包括环形传感器,能测量每单位时间通过这些传感器的车辆的数量、车辆的速度和/或涉及交通流量的其它数据。 These sensors may comprise an annular sensor that can measure the number of vehicles per unit time of these sensors, the speed of the vehicle and / or other data related to traffic flow. 此外,这样的传感器可以包括照相机、运动传感器、雷达测距设备、基于RFID的设备和位于紧邻或靠近道路的其它类型的传感器。 Moreover, such sensors may include a camera, a motion sensor, a radar ranging device, an RFID-based and other types of devices located proximate or near a road sensor. 道路交通传感器386可以周期性地或连续地通过基于有线或基于无线的数据链路通过使用一个或多个数据交换机制(例如,推、拉、令牌、请求-应答、点对点等)的网络380将测量的数据读数提供给数据样本管理系统350。 Road traffic sensors 386 may periodically or continuously by a wire-based or wireless-based data link by using one or more data exchange mechanism (e.g., push, pull, the token, a request - reply, point, etc.) of the network 380 the measured data readings provided to the data sample Manager system 350. 此外,虽然这里没有示出,但在一些实施例中,这样的道路交通传感器信息的一个或多个收集者(例如,操作传感器的政府交通部门)可以替换来获得原始数据并使数据对交通信息系统来说是可用的(无论是原始的形式还是在其被处理后)。 Furthermore, although not shown, in some embodiments, a collector or plurality of such road traffic sensor information (e.g., operation of the sensor government transportation departments) may alternatively be obtained original data and traffic data the system is available (either in original form or after it is processed).

[0127] 其它数据源388包括多种类型的其它数据源,其可以由一个或多个交通信息系统使用来给用户、消费者和/或其它计算系统提供有关交通的信息。 [0127] Other types of data sources 388 include a variety of other data sources that can provide traffic information to the user, the consumer, and / or other computing systems used by one or more of the traffic information system. 这样的数据源包括能提供有关道路网络信息的地图服务和/或数据库,例如各条道路彼此的连通性以及涉及这样的道路的交通控制信号(例如,交通控制信号和/或限速区的存在和位置)。 Such data sources include providing information about the road network map services and / or databases, for example, the presence of the roads as well as communication with another traffic control signal relates to a road (e.g., traffic control signals and / or speed zones and location). 其它数据源还可以包括有关影响和/或反映交通状况的事件和/或状况的信息的来源,例如短期和长期天气预报、学校日程和/或日历、事件日程和/或日历、由人为操作者(例如,第一出席人员、执法人员、高速路员工、新闻媒体、旅行者等)提供的交通事故报告、道路工作信息、假日安排等。 Other data sources may also include a source of information on the impact of events and / or reflect traffic conditions and / or conditions, such as short-term and long-term weather forecasts, school schedules and / or calendars, event schedules and / or calendars by human operator (For example, the first attendance, law enforcement officers, highway employees, the news media, travelers, etc.) accident report, the road work information, holiday arrangements.

[0128] 在这个实施例中的基于车辆的客户端/数据源384每个都可以是位于车辆内将数据提供给一个或多个交通信息系统和/或从一个或多个这些系统接收数据的计算系统和/或通信系统。 [0128] In this embodiment, the vehicle-based clients / data sources 384 can each be located within the vehicle to provide data to one or more traffic information systems and / or from one or more of these systems receive data computing system and / or communications systems. 在一些实施例中,数据样本管理系统350可以使用为交通信息系统的使用而提供涉及当前交通状况的信息的基于车辆的移动数据源和/或其它基于用户的移动数据 In some embodiments, the Data Sample Manager system 350 may be used as a traffic information system used to provide information relating to the current traffic conditions of the vehicle mobile data sources and / or other mobile data based on user-based

28源(未示出)的分布式网络。 28 source (not shown) of the distributed network. 例如,每部车辆或其它移动数据源可以具有GPS( “全球定位系统”)设备(例如,具有GPS功能的移动电话、独立的GPS设备等)和/或其它能确定地理位置的地理定位设备,并可能还有其它信息,例如速度、方向、海拔和/或其它涉及车辆行驶的数据,并且地理定位设备或其它相异通信设备有时获得并提供这样的数据给一个或多个交通信息系统(例如,通过无线链路)。 For example, each vehicle or other mobile data sources may have a GPS ( "Global Positioning System") device (e.g., a GPS-enabled mobile phone, GPS device independent, etc.) and / or other geographic location can determine the geographical positioning device, and possibly other information such as speed, direction, altitude and / or other vehicle running data relates, and the geo-location device, or other communication device may obtain distinct and provide such data to one or more traffic information systems (e.g. , over a wireless link). 这样的移动数据源将在别处更详细地讨论。 Such mobile data sources are discussed in more detail elsewhere.

[0129] 替换地,基于车辆的客户端/数据源384的一些或全部每个都可以具有位于车辆内的计算系统和/或通信系统以从一个或多个交通信息系统获得信息,例如为了车辆使用者的使用。 [0129] Alternatively, based on the customer's side of the vehicle / data source 384 of some or all of a computing system can each located within a vehicle and / or the communication system to obtain information from one or more of the traffic information systems, for example for vehicle use the user. 例如,车辆可以包含具有安装的Web浏览器或其它控制应用程序的内嵌仪表盘(in-dash)导航系统,用户可以使用该系统来从交通信息系统之一(例如预测交通信息提供系统和/或RT信息提供系统)请求交通相关信息,或者这些请求可以由车辆中的用户的便携式设备发出。 For example, the vehicle may comprises a Web browser installed dashboard or other embedded control applications (in-dash) navigation system, the user can use the system (e.g., predicted traffic information providing system and from one of the traffic information system / RT or information providing system) requests the traffic information, or the requests may be issued by the portable device in the vehicle of the user. 此外,一个或多个交通信息系统可以基于更新信息的接收或产生自动地将涉及交通的信息传输到这样的基于车辆的客户端设备。 In addition, one or more traffic information system may receive information based on the updated or generated automatically transmit information about traffic to the client device based on such a vehicle.

[0130] 第三方计算系统390包括一个或多个可选的计算系统,其由诸如从一个或多个交通信息系统接收有关交通的数据的一方和以某种方式使用数据的一方等的他人而不是交通信息系统的操作者操作。 [0130] a third-party computing systems 390 include one or more optional computing system such as the receiving side data on traffic from one or more of the traffic information systems and data in some way to use one and others like not a traffic information system operated by the operator. 例如,第三方计算系统390可以是这样的系统,它从一个或多个交通信息系统接收交通信息,并将所涉及的信息(无论是所接收的信息还是基于所接收的信息的其它信息)提供给用户或他人(例如,通过Web入口或订阅服务)。 For example, third-party computing systems 390 may be a system that receives traffic information from one or more of the traffic information system, and relates the information (whether the received information or other information based on the received information) provided to the user or others (for example, through a Web portal or subscription services). 替换地,第三方计算系统390可以由其它类型的一方来操作,例如给消费者收集和报告交通状况的媒体组织,或给他们的用户提供有关交通的信息来作为旅行计划服务一部分的在线地图公司。 Alternatively, third-party computing system 390 may be operated by one of the other types, such as media organizations to consumers to collect and report traffic conditions, or to provide information about their users to transport services as part of the online mapping company travel plans .

[0131] 正如前面所要注意地,预测交通信息提供系统360可以使用由数据样本管理系统350和在所示实施例中的其它组件所准备的数据以产生多个将来时间的将来交通状况预测。 [0131] As is to be noted previously, the predicted traffic information providing system 360 may be used by the Data Sample Manager system 350 and other data components of the embodiments shown in the embodiment prepared a plurality of future times to generate future traffic condition predictions. 在一些实施例中,预报的产生使用了概率技术,其合并了各种类型的输入数据以为多条道路段的每个反复产生一系列将来时间预报,例如基于在给定地理区域内的道路网络的不断改变的当前状况而以实时的方式。 In some embodiments, the use of prediction probability generation technology, which incorporates various types of input data for each of a plurality of road segments are repeatedly generated future time series forecasting, for example, based on the road network within a given geographic area the current situation and the changing real-time manner. 而且,在至少一些实施例中,为在给每个感兴趣的地理区域的未来交通状况预测中使用而自动创建一个或多个预测性贝叶斯或其它模型(例如,决策树),例如基于这些地理区域的所观测的历史交通状况。 Further, in at least some embodiments, automatically create one or more predictive Bayesian or other models (e.g., decision trees) for use in a future traffic conditions of a geographical area of ​​interest for each prediction, based e.g. the observed historical traffic conditions of these geographic areas. 预测性的未来交通状况信息可以以各种方式使用以帮助旅行或其它目的,以便基于多个未来时间的道路的交通状况的预测计划通过道路网络的最优路线。 Predictive traffic information in the future can be used in various ways to help travel or other purposes, in order to plan based on predicted traffic conditions on the road of multiple future times through the optimal route of the road network.

[0132] 而且,道路段确定系统362可以使用提供涉及在一个或多个地理区域内道路网络的信息的地图服务和/或数据库以自动确定并管理涉及可能被其它交通信息系统所使用的有关道路的信息。 [0132] Furthermore, the road section determination system 362 can use involved in one or more geographic regions road network map service information and / or database to automatically identify and involve management may be used by other traffic information systems on road Information. 这样的有关道路的信息可以包括要被作为感兴趣的道路段的道路的特定部分的确定(例如,基于这些道路部分和其它相邻道路部分的交通状况),以及在给定的道路网络的道路段和所感兴趣的其它信息指示(例如,道路交通传感器的物理位置,事件点、地标;有关功能道路类和其它有关交通特征的信息;等)间自动产生的关联或关系。 Such information may include about road determination (e.g., based on these roads and traffic conditions of other adjacent portions road portion), and a road in the road network given as a road to be the road segment of interest a specific portion of association or relationship between the automatically generated fields, and other information indicating interest (like e.g., the physical location of road traffic sensors, event point landmarks;; functional road class, and other relevant information about the traffic characteristics). 在一些实施例中,道路段确定系统362可以周期性执行并为了其它交通信息系统的使用而在存储器340或数据库(未示出)中存储它产生的信息。 In some embodiments, the road segment 362 may periodically perform determination system and to use the information system and other vehicle (not shown) in memory 340, or it generates database information is stored.

[0133] 此外,关键道路标识符系统361使用表示给定地理区域和用于那个地理区域的交通状况信息的道路网络,以为跟踪和估算道路交通状况而自动识别所感兴趣的道路,例如为其它交通信息系统和/或交通数据客户端的使用。 [0133] In addition, a key road system identifier 361 representing a given geographic area and the road network traffic conditions for that geographic area information, tracking and estimated that road traffic conditions and automatically identify the road of interest, such as other vehicles information systems and use / or traffic data clients. 在一些实施例中,所感兴趣的道路(或 In some embodiments, the path of interest (or

29道路的一条或多条道路段)的自动识别可以至少部分地基于如下的因素,例如峰值交通量或其它流量的量值,峰值交通拥堵的量值,交通量或其它流量的当天变化,道路拥堵的当天变化,交通量或其它流量的日间(inter-day)变化,和/或道路拥堵的日间变化。 29 one or more roads of the road segment) automatic recognition may at least partially based on the following factors, such as changes in the magnitude of peak traffic volume or other flow, the magnitude of peak traffic congestion, traffic volume or other flow of the day, road congestion of the day change, traffic, or other traffic during the day (inter-day) changes and / or changes in daytime road congestion. 这样的因子可以通过例如主要组件(principal component)分析来分析,例如通过首先计算在给定地理区域中用于所有道路(或道路段)的交通状况信息的协方差矩阵S,接着计算协方差矩阵S的本征分解。 Such factors may be analyzed by, for example, the major components (principal component) analysis, for example, the covariance matrix S of all roads (or road segments) of the traffic condition information in a given geographical area is calculated by first, followed by calculation of the covariance matrix S intrinsic decomposition. 接着在特征值的降序中,S的特征矢量表示独立地对所观测的交通状况的变化有着最强的贡献的道路(或道路段)的组合。 Next, in descending order of feature value, the feature vector S independently represents a combination of the observed changes in traffic conditions has the strongest contribution to road (or road segments).

[0134] 此外,实时交通信息提供或呈现系统可以由RT信息提供系统,或者替换地由一个或多个其它程序369提供。 [0134] In addition, real-time traffic information providing system or by the presentation system may provide information RT, or alternatively be provided by one or more other programs 369. 信息提供系统可以使用由数据样本管理系统350和/或其它组件(例如预测交通信息提供系统360)分析和提供的数据来为操作或使用客户端设备382、基于车辆的客户端384、第三方计算系统390等的消费者和/或商业实体提供交通信息服务,以便至少部分地基于从车辆和其它移动数据源获得的数据样本以实时或近于实时的方式提供数据。 The system may be used by the information providing / or other components, and the Data Sample Manager system 350 (e.g., predicted traffic information providing system 360) to provide a data analysis and 382, ​​based on the customer's side of the vehicle 384 or to operate using a client device, third-party computing system 390 and other consumer and / or business entity for providing traffic information service, to at least partially based on the data sample obtained from vehicles and other mobile data sources in real time or near real time data provided.

[0135] 可以预见,所示的计算系统仅是示意性的且并不试图限制本发明的范围。 [0135] It is foreseeable that the computing system shown is illustrative only and are not intended to limit the scope of the invention. 计算系统300可以与其它未示出的设备连接,包括通过一个或多个例如互联网的网络或经由ffeb。 The computing system 300 may be connected to other devices (not shown), including through one or more networks such as the Internet or via a ffeb. 一般地说,“客户端”或“服务器”计算系统或设备,或交通信息系统和/或组件,可以包括能交互和执行所述类型功能的硬件和软件的任意组合,包括但不限于桌面或其它计算机、数据库服务器、网络存储设备和其它网络设备、PDA、蜂窝式移动电话、无线电话、传呼机、电子管理器、互联网应用程序、基于电视的系统(例如,使用机顶盒和/或个人/数字视频记录器)和包括具有合适的交互通信能力的各种其它消费产品。 In general, "client" or "server" computing system or device, or traffic information systems and / or components may include any combination of hardware and software that can interact and perform the function of the type, including but not limited to desktop or other computers, database servers, network storage devices and other network devices, PDA, cellular phones, wireless phones, pagers, electronic organizers, Internet applications, television-based systems (e.g., using set-top boxes and / or personal / digital video recorder), and includes a variety of other consumer products with suitable interactive communication capability. 此外,在一些实施例中由所示的系统组件提供的功能可以被合并到更少的组件中或被分布到附加的组件中。 Further, in some embodiments, the function provided by the illustrated system components may be combined into fewer components or distributed in additional components. 类似地,在一些实施例中所示的组件中的一些的功能可以不被提供和/或可以得到其它附加功能。 Similarly, some of the functional components illustrated in some embodiments may not be provided and / or other additional functionality may be obtained.

[0136] 此外,虽然在使用的同时各种项目如所示的可以存储在存储器或存储装置中,但为了存储器管理和/或数据完整性的目的,这些项目或它们的部分可以在存储器和其它存储设备间传输。 [0136] In addition, while the various items used at the same time as shown may be stored in memory or storage devices, but for memory management and / or data integrity purposes, these items or portions thereof may be in a memory and other transmission between the storage device. 替换地,在其它实施例中软件组件和/或模块的一些或全部可以在另一设备上的存储器中执行并通过计算机间的通信而与所示的计算系统通信。 Alternatively, in other embodiments the software components and / or modules and embodiments some or all communicate with the computing system illustrated by communication between the computer may execute in memory on another device. 系统组件或数据结构的一些或全部也可以存储在计算机可读介质(例如,作为软件指令或结构化数据),例如由适当的驱动器或通过适当的连接读取的硬盘、存储器、网络或便携式媒体介质。 System components or data structures, some or all may be stored in a computer-readable medium (e.g., as software instructions or structured data), for example, by an appropriate drive or via an appropriate connection of the hard disk is read, memory, network, or a portable media medium. 系统组件和数据结构在各种计算机可读传输介质上也可以被传输为所产生的数据信号(例如,作为载波或其它模拟或数字传播信号的一部分),包括基于无线和基于有线/电缆的介质,并能采用各种形式(例如,作为单个或复用模拟信号的一部分,或作为多个离散数字数据包或帧)。 The system components and data structures in a variety of computer-readable transmission medium can be transmitted as a data signal (e.g., as a carrier wave or other analog or digital propagated signal part) generated, including wireless-based and wired / cable medium and can take various forms (e.g., as part of a single or multiplexed analog signal, or as multiple discrete digital packets or frames). 在其它实施例中,这样的计算机程序产品还可以采用其它形式。 In other embodiments, such computer program product may also take other forms. 因此,本发明也能以其它计算机系统结构实现。 Accordingly, the present invention can also be implemented in other computer system configurations.

[0137] 图4是数据样本过滤器例程400的示例性实施例的流程图。 [0137] FIG. 4 is a flowchart of an exemplary embodiment of a filter routine data samples 400. 该例程可以由例如图3的数据样本过滤组件352和/或图1的数据样本过滤组件104的实施例的执行来提供,以便接收相应于在地理区域内道路的数据样本,并为后面的估算过滤掉不感兴趣的数据样本。 The sample may be filtered by the routine of FIG. 3, for example, data of component data 352 and / or the sample of FIG. 1 embodiment performs filter assembly 104 is provided for receiving data samples corresponding to the roads within a geographical area, and for the following estimate filter out data samples are not interested. 过滤的数据样本接着可以以各种方式随后使用,例如使用过滤的数据样本来计算所感兴趣的特定道路段的平均速度并为这样的道路段计算其它有关交通流量的特征。 The filtered data samples may then be subsequently used in various ways, for example using the filtered data samples to calculate the average speed of a specific road segment of interest and calculating a feature for such traffic flows or other road segment.

[0138] 例程在步骤405开始,这里为特定时间段的地理区域接收数据样本组。 [0138] routine begins at step 405, where the reception data sample set to a geographic area of ​​a specific time period. 在步骤 In step

30410,例程接着可选地基于其它有关数据样本为这些数据样本的一些或全部产生附加信息。 30410, the routine then optionally based on other related data samples of some or all of the additional information to generate data samples. 例如,如果用于车辆或其它移动数据源的特定数据样本缺少所感兴趣的信息(例如移动数据源的速度和/或方位或方向),则这样的信息可以结合对相同移动数据源的先前和后继数据样本之一或二者而确定。 For example, if the data for a particular vehicle or other mobile data sources of interest samples missing information (e.g., velocity of the mobile data sources and / or orientation or direction), then such information may bind to the same mobile data source previous and subsequent one or both of the data samples is determined. 此外,在至少一些实施例中,可以收集从多个数据样本来的用于特定移动数据源的信息来估算关于该数据源的附加信息类型,以便估算在横跨多个数据样本的时间段内的数据源的行为(例如,来确定是否车辆已经停车几分钟而不是临时停一两分钟来作为交通的正常车流,例如遇见停车信号或停车灯)。 Further, in at least some embodiments, information may be collected from the plurality of data samples for a particular mobile data source to estimate additional information about the types of data sources, in order to estimate the time period spanning a plurality of data samples behavior of the data source (for example, to determine whether the vehicle has been parking a few minutes rather than a temporary stop for a minute or two as the normal traffic flow of traffic, for example, met a stop sign or stop light).

[0139] 在步骤410后,虽然例程继续到步骤415以试图将每个数据样本与在该地理区域内的道路和该道路的特定道路段关联,但在其它实施例中这步可以不被执行或以其它方式执行,例如如果至少数据样本与道路和/或道路段的初始关联是在步骤405中接收的,或替换地如果整个例程针对一条道路段执行一遍,从而在步骤405中接收的所有数据样本作为一个组来相应于一条道路段。 [0139] After step 410, the routine continues to step 415 while attempting to associate with each data sample to a road and the roads in the geographic area of ​​a particular road segment, but in other embodiments this step may not be or performed in other ways, for example, if the original samples and at least data associated with a road / or road segment is received in step 405, or alternatively, if the entire routine is performed again for a road segment, in step 405 so as to receive All data samples as a group corresponding to a road segment. 在所示的实施例中,数据样本与道路和道路段的关联可以以各种方式执行,例如单独基于与该数据样本关联的地理位置而进行初始关联(例如,将数据样本与最近的道路和道路段关联)。 In the illustrated embodiment, the data samples associated with the road and road segments may be performed in various ways, such as a separate geographic location based on data associated with the sample and the initial association (e.g., the data sample with the nearest road, and associated road segment). 而且,该关联可以可选地包括附加的分析以精练或修订初始关联——例如,如果基于位置的分析指示对于数据样本具有多个可能的道路段(例如多条道路段用于一条特定的道路,或替换地多条道路段用于临近但不相关的道路),则这样的附加分析可以使用诸如速度和方向的其它信息来影响关联(例如,通过以加权的方式合并位置信息和一个或多个其它这样的因素)。 Moreover, the association may optionally include additional analysis or scouring revised initial association - e.g., if the indicated position based on the analysis of data samples for the road segment having a plurality of possible (e.g. multiple road segments for a particular road , or alternatively a plurality of road segments, but not relevant for a road approaching), additional analysis may be used such as the speed and direction of impact associated with other information (e.g., by a weighted manner or a combined location information and one other such factors). 这样,例如,如果数据样本的报告位置在高速路和相邻的临街道路之间,则就可以使用有关数据样本的所报告速度的信息来帮助将该数据样本与合适的道路关联(例如,通过确定与70英里每小时的速度关联的数据样本不可能源于具有25英里每小时限速的临街道路)。 Thus, for example, if the reported location of data sample between the adjacent street and highway road, you can use the reported information about the speed of data samples to data samples associated with the help of a suitable road (e.g., by determining the data samples associated with the 70 mph speed possible from frontage road with 25 miles per hour speed limit). 此外,在道路或其它道路部分的特定延展与多条相异的道路段(例如,对于双车道的道路,其中在一个方向上的行驶被建模为第一道路段而在另一个方向上的行驶被建模为相异的第二道路段,或替换地对于多车道的高速路,HOV车道被建模为与一条或多条相邻的非HOV车道独立的道路段)相关联的情况下,可以使用诸如速度和/或方向等有关数据样本的附加信息来选择对于该数据样本来说最有可能道路的道路段。 Further, in a particular road or other road extending portions and a plurality of distinct road segments (e.g., for a two-lane road, traveling in one direction which is modeled as a first road segment in the other direction and is modeled with a second road segment as distinct, or alternatively, for a multi-lane highway, the HOV lane is modeled) at one or more of the adjacent independent non-HOV lane road segment associated with the case can use additional information about the data samples, such as speed and / or direction of selected for that data sample is the most likely way road segment.

[0140] 在步骤415后,例程继续到步骤420以为后续的处理过滤掉不与所感兴趣的道路段关联的任何数据样本,包括不与任何道路段关联的数据样本(如果有)。 [0140] After step 415, the routine continues to step 420 for subsequent processing of the sample to filter out any data not associated with the road segments of interest, including the data samples are not associated with any road segment (if any). 例如,特定道路或道路的部分可能不是后续分析所感兴趣的,例如排除特定功能道路类的道路(例如,如果道路的尺寸和/或交通量不足以大到能有所感兴趣),或由于诸如高速路坡道或专用路或交汇/分叉路等这样的道路部分的交通特征不能反映作为整体的高速路,因此排除这样的道路部分。 For example, a road or a specific part of a road may not be of interest for subsequent analysis, for example to exclude certain functional road classes of road (e.g., if the size of the road and / or traffic not large enough to be able to be of interest), or due to a high speed such road traffic characteristics of this part of the road or private road or ramp intersection / fork in the road and so does not reflect the highway as a whole, and therefore exclude this part of the road. 类似地,在多条道路段与路的特定部分关联的情况下,一些道路段可能也不是某些目的所感兴趣的,例如如果只有非HOV车道的行为是特定目的所感兴趣的,或如果两个方向的车道只有一个方向是感兴趣的,则为高速路排除HOV车道。 Similarly, in the case associated with a particular part of the multiple road segments of the road, some road segments may not be of interest for some purposes, for example, if only the non-HOV lanes behavior is of interest to a particular purpose, or if two lane direction is only one direction of interest, was excluded highway HOV lane. 虽然在步骤420后,例程继续到步骤425以确定是否基于数据源的行为过滤数据样本,但在其它实施例中这样的过滤也可以不被执行或也可以一直执行。 Although After step 420, the routine continues to step 425 to determine if the data source based on behavior data sample filtering, but such filtering may not be performed or may have been performed in other embodiments. 在所示的实施例中,如果基于来源的行为执行过滤,则例程继续到步骤430以执行这样的过滤,例如去除相应于其行为不能反映要被测量的所感兴趣的交通流量行为的数据源的数据样本(例如,排除在延长时间段内引擎开动着停车的车辆,排除在延长的时间段内在停车地或停车场或其它小区域内打转的车辆等)。 In the illustrated embodiment, if the filtering is performed based on the behavior of the source, the routine continues to step 430 to perform such filtering, such as removal corresponding to its behavior can not be the data source to reflect the behavior of interest traffic measured data samples (e.g., out of the extended period of time the vehicle is parked with the engine start, the extended period of time in the excluded vehicles parking or other parking lot, or a small area is spinning). in

31步骤430后,或如果替换地在步骤425中确定不基于数据源的行为过滤,则例程继续到步骤490以为后续的使用存储过滤的数据,但在其它实施例中过滤的数据替换地可以直接提供给一个或多个客户端。 31 after step 430, or alternatively, if determined in step 425 based on the behavior of the data source is not filtered, the routine continues to step 490 that the subsequent data is stored in the filter, the filter but in other embodiments the data may be alternatively directly to one or more clients. 接着例程继续到步骤495以确定是否继续。 Then the routine continues to step 495 to determine whether to continue. 如果继续,则例程返回到步骤405,如果不继续,则到步骤499并结束。 If you continue, the routine returns to step 405, if you do not continue, and to step 499 and ends.

[0141] 图5是数据样本异常值去除器例程500的示例性实施例的流程图。 [0141] FIG. 5 is a flowchart of an exemplary embodiment of the removal of the routine 500 data sample outlier. 该例程可以由例如执行图3的数据样本异常值去除组件3M和/或图1的数据样本异常值去除组件106的实施例而提供,从而相对于道路段的其它数据样本去除对于该道路段来说是异常值的数据样本。 The routine may consist of, for example, executes outlier removal assembly 3 data samples and data samples 3M / or FIG. 1 embodiment outlier removal assembly 106 is provided, so that with respect to other data of the road segments of the road segment for sample removal it is the data sample outliers.

[0142] 该例程在步骤505开始,在其中接收用于道路段和时间段的一组数据样本。 [0142] The routine begins at step 505 in which a set of data samples for receiving road segment and time period. 所接收的数据样本可以是,例如从数据样本过滤器例程的输出获得的过滤的数据样本。 The received data samples may be, for example, data samples obtained from the output data sample filter routine filtration. 在步骤510,例程接着可选地将数据样本分成多个组以反映道路段相异部分和/或相异的行为。 In step 510, the routine then optionally be divided into a plurality of groups of data samples in order to reflect the distinct portions of road segments and / or different acts. 例如,如果多条高速路车道被包括在一起作为单条道路段的一部分并且这些多条车道包括至少一条HOV车道和一条或多条非HOV车道,则如果在时间段内的交通流量在HOV和非HOV车道间显著不同,则在HOV车道上的车辆可以与在其它车道上的车辆分离。 For example, if a plurality of highway lanes are included together as part of a single road segment and the at least comprising a plurality of lanes HOV lane and one or more non-HOV lanes, if the period of time in the traffic and non-HOV significantly different between the HOV lane, the vehicle may be in the HOV lane on the vehicle separated from the other lanes. 可以以各种方式执行这样的分组,例如将数据样本拟合为多条曲线,每条曲线代表特定数据样本组中的典型数据样本变化(例如,正态或高斯曲线)。 May be performed in various manners such packets, for example, data samples into a plurality of fitting curves, each data sample represents the typical variations (e.g., normal or Gaussian curve) of a particular group of data samples. 在其它实施例中,也可以不执行这样的分组,例如如果替换地分割道路段以便用于该道路段的所有数据样本都反映类似的行为(例如,如果具有HOV车道和其它非HOV车道的高速路替换地被分裂成多条道路段)。 In other embodiments, such a packet may not be performed, for example, if the road segment divided alternatively in order for all of the road segment data samples reflect similar behavior (e.g., if high speed and with other non-HOV lanes HOV lanes Alternatively road is split into multiple road segments).

[0143] 例程继续到步骤515,为一个或多个数据样本组的每个(如果没有执行步骤510的数据样本的分离,则所有的数据样本被视为一个组),计算所有数据样本的平均交通状况特征。 [0143] routine continues to step 515, for each of the one or more sets of data samples (separated data samples if step 510 is not performed, all the data samples are considered as a group), calculated for all the data samples The average characteristics of the traffic situation. 这种平均交通状况特征可以包括,例如,平均速度,以及诸如相对于中值的标准差等相应的统计信息。 This average traffic condition characteristics may include, for example, the standard average speed, and the relative value of such poor respective statistics. 例程接着继续到步骤520,对该一个或多个数据样本组的每个,连续地执行去除一个(leave-one-out)分析以便选择特定的要被暂时去除的目标数据样本并为剩余的交通状况特征确定平均交通状况特征。 Then the routine continues to step 520, the one or more data samples per group, continuously performing a removal (leave-one-out) the data samples analyzed in order to select a particular target to be temporarily removed and the remainder The average traffic condition characteristics determine traffic characteristics. 在用于剩余数据样本的平均交通状况特征和从步骤515来的用于所有数据样本的平均交通状况特征间的差别越大,则被去除的目标数据样本是不能反映其它剩余数据样本的公共特征的异常值的可能性就越大。 In common feature for the average traffic condition characteristics from the remaining data samples and 515 steps for the greater the difference between the average traffic condition characteristics for all data samples, the samples were removed target data can not reflect other remaining data samples the possibility of outliers greater. 在步骤525,例程接着可选地执行一个或多个附加类型的异常值分析,从而连续去除两个或多个目标数据样本的组从而估算它们的共同效应,但在一些实施例中也可以不执行这样的附加异常值分析。 In step 525, the routine then optionally performs one or more outliers additional types of analysis, so that continuous removal of two or more target groups of data samples to estimate their common effect, in some embodiments, may also be such additional outlier analysis is not performed. 在步骤522后,例程继续到步骤590以去除在步骤520和/或525中被识别为异常值的数据样本,并为后续的使用而存储剩余的数据样本。 After step 522, the routine continues to step 590 in order to remove the step and / or 525 520 is identified as an outlier sample data, and stored for subsequent use of the remaining data samples. 在其它实施例中,例程替换地可以将剩余的数据样本转发给一个或多个客户端所使用。 In other embodiments, the routine may be alternatively forwarded to the rest of the data samples to one or more clients are used. 例程接着到步骤595以确定是否继续。 Then the routine to step 595 to determine whether to continue. 如果继续,则例程返回到步骤505,如果不继续,则例程继续到步骤599并结束。 If you continue, the routine returns to step 505, if you do not continue, the routine continues to step 599 and ends.

[0144] 图6是数据样本速度估算器例程600的示例性实施例的流程图。 [0144] FIG. 6 is a flowchart of an exemplary embodiment of a data Sample Speed ​​Assessor routine 600. 该例程可以通过执行例如图3的数据样本速度估算组件356和/或图1的数据样本速度估算组件107来提供,例如基于用于道路段的各个数据样本在时间段内估算该道路段的当前平均速度。 The routine may FIG. 3 data samples velocity estimated velocity data sample component 356 and / or the estimation component 107 of FIG. 1 is provided by performing, for example, the estimated time period, for example, in the sample based on the road segment data for each road segment The current average speed. 在这个示例性实施例中,例程在时间段内为多个时间间隔或时间窗的每个执行道路段平均速度的连续计算,但在其它实施例中例程的每个调用替换地可以是用于单个时间间隔的(例如,经由多个例程调用估算多个时间间隔)。 In this exemplary embodiment, the continuous calculation routine for the plurality of time intervals within a time period or time window for each road segment average speed of execution, but each call other routines alternative embodiment may be for a single time interval (e.g., via a plurality of routine calls a plurality of estimated time intervals). 例如,如果时间段是三十分钟,则可以每五分钟执行新的平均速度计算,例如以5分钟的时间间隔(并且因此每个时间间隔与先前或后继 For example, if the time period is thirty minutes may be performed a new average speed is calculated every five minutes, for example, at 5 minute intervals (and thus with each time interval preceding or subsequent

32的时间间隔不重叠),或以10分钟的时间间隔(因此与相邻的时间间隔重叠)。 32 time intervals do not overlap), or at 10-minute intervals (and thus overlaps adjacent time intervals).

[0145] 该例程在步骤605开始,接收指示,其指示在时间段内道路段的数据样本(例如,从移动数据源和物理传感器的数据读数来的数据样本),或指示在时间段内道路段的不充足的数据,但在一些实施例中只能从移动数据源和传感器数据读数中接收一个数据样本。 [0145] The routine begins at step 605, receiving an indication that indicates the road segment data sample time period (e.g., data readings from physical sensors and mobile data sources to the data samples), or indicated period insufficient road segment data, but only receives a data sample from the mobile data source and sensor data readings in some embodiments. 所接收的数据样本可以是,例如,从数据样本异常值去除器例程的输出获得的。 The received data samples may be, for example, from the output data sample outlier removal routine obtained. 类似地,可以从数据样本异常值去除器例程获得不充足数据的指示。 Similarly, the data from the Sample Outlier Eliminator routine obtain an indication of insufficient data. 在一些情况中,不充足数据的指示可以基于具有不足量的数据样本,例如当在时间段内从与道路段关联的移动数据源没有来数据样本和/或当道路段的一些或全部数据读数丢失或已经被检测为是错误的(例如,通过图1的传感器数据调整组件10¾。在这个实例中,例程在步骤610继续以确定是否接收到了数据不够的指示。如果是,则例程继续到步骤615,如果不是,则例程继续到步骤625。 In some cases, the indication of insufficient data may be, for example, when a period of time without some or all data samples and data reading to / from the road or in power associated with the road segment based on the mobile data source data having insufficient amount of sample has been detected as missing or wrong (e.g., in this example, the routine continues to determine whether the received data in step 610 by adjusting the sensor assembly of FIG. 1 10¾ indicating insufficient data. If so, the routine continues to step 615, if not, the routine continues to step 625.

[0146] 在步骤615,例程执行交通流量估算器例程的实施例(参考图14描述)以获得时间段内道路段的估算的平均交通速度。 [0146] In step 615, the routine performs traffic estimation routine embodiment (described with reference to FIG. 14) to obtain an average traffic speed estimated road segment period. 在步骤620,例程接着提供估算的平均速度的指示。 Then provides estimated at step 620, the routine average speed indication. 在步骤625,例程开始于第一个时间间隔并为要被估算的平均速度选择下一个时间间隔或时间窗。 In step 625, the routine begins at a first time interval and the average speed for the next selection is to estimate a time interval or time window. 在步骤630,例程接着在该时间间隔内为数据样本计算加权的平均交通速度,并基于一个或多个因素对数据样本加权。 In step 630, the routine then calculates the weighting within the sample interval the average traffic speed data, and based on one or more factors weighted data sample. 例如,在所示的实施例中,对每个数据样本的加权基于数据样本的等待时间而改变(例如,以线性的,指数的,或步进式方式),例如给靠近时间间隔末端的数据样本较大的权重(因为它们更能反映在时间间隔末端的实际平均速度)。 For example, in the embodiment shown, the data samples based on the latency varies weighting each data sample (e.g., linear, exponential or stepped manner), for example close to the end of time interval data sample larger weight (because they better reflect the actual average speed at the end of the time interval). 此外,在所示的实施例中数据样本还可以进一步基于数据的来源而加权,例如无论偏重或偏少,对从物理传感器来的数据读数加权不同于对从车辆和其它移动数据源来的数据样本加权。 Further, in the embodiment illustrated embodiment the data samples may further be weighted based on the source data, such as whether emphasis or less than normal, the weighted data readings from physical sensors is different data from vehicles and other mobile data sources of sample weights. 此外,在其它实施例中,在加权中可以使用各种其它因素,包括基于每个样本——例如,对从一个物理传感器来的数据读数加权可以不同于对从另一个物理传感器来的数据读数加权,从而反映有关传感器的可以得到的信息(例如,物理传感器中的一个是间歇性错误的或比另一个传感器具有较不精确的数据读数分辨率),并且从一部车辆或其它移动数据源来的数据样本可以类似地基于有关移动数据源的信息以与从另一个这样的车辆或移动数据源来的数据样本不同地加权。 Further, in other embodiments, the weighting may be used in a variety of other factors, including on a per sample - e.g., for reading data from a physical sensor weighting may be different to the data from another physical sensor reading weighted to reflect the information can be obtained about the sensor (e.g., a physical sensor is intermittent errors or reading data with less accurate resolution than another sensor), and from a vehicle or other mobile data source the data samples may be based on information about the mobile data source to be weighted similarly to the vehicle or from another such mobile data source data samples differently. 在一些实施例中可以在加权中使用的因素的其它类型包括置信值或在特定数据样本中可能错误的其它估算,特定数据应当与特定道路段等关联的程度。 In some embodiments, other types of factors that may be used include the degree of weighting associated confidence values ​​or other estimates may be wrong in a particular data sample, the data should be specific to a particular road segment and the like.

[0147] 在步骤630后,例程继续到步骤635以提供时间间隔内平均计算交通速度的指示,例如为后续的使用存储该信息和/或将给信息提供给客户端。 [0147] After step 630, the routine continues to step 635 to provide an indication of the average time interval calculated transport speed, for example, the information and / or information will be provided to the client for subsequent storage use. 在步骤640,例程随后可选地获得时间段内在步骤605接收信息之后可获得的附加的数据样本。 In step 640, the routine then optionally obtain additional data sample period of time after the step 605 receives the information available. 在步骤645中接着确定是否在时间段内要计算更多的时间间隔,并且如果这样,则例程返回到步骤625。 In step 645 then determines if the time period to be calculated more time intervals, and if so, the routine returns to step 625. 如果替换地没有更多的时间间隔,或在步骤620后,则例程继续到步骤695以确定是否继续。 Alternatively, if there is no more time intervals, or after step 620, the routine continues to step 695 to determine whether to continue. 如果继续,则例程返回到步骤605,并且如果不,则继续到步骤699并结束。 If you continue, the routine returns to step 605, and if not, proceed to step 699 and ends.

[0148] 图7是数据样本流量估算器例程700的示例性实施例的流程图。 [0148] FIG. 7 is a flowchart of an exemplary embodiment of a data Sample Flow Assessor routine 700. 例程可以通过,例如,执行图3的数据样本流量估算组件358和/或图1的数据样本流量估算组件108的实施例而提供,以便估算交通状况流量特征而不是在特定时间段内特定道路段的平均速度。 Routine can, for example, executes data samples to estimate the flow rate of Example 3 data components 358 and / or FIG. 1 Sample Flow Assessor component 108 is provided in order to estimate the traffic flow characteristic instead of a specific road in a specific time period the average speed of the segment. 在这个示例性实施例中,要被估算的流量特征包括在时间段内在特定道路段上到达或存在的车辆总量(或其它移动数据源),和在时间段内道路段的百分占用率以反映道路段的点或区域被车辆所覆盖的时间百分比。 In this exemplary embodiment, the flow characteristic to be estimated include the arrival or presence of a total amount of the vehicle (or other mobile data sources) within a time period on a particular road segment, the road segment and the percent occupancy period in the percentage of time the vehicle is covered in spots or areas reflect road segment.

33[0149] 例程在步骤705开始,在其中接收指示,其指示时间段的道路段的数据样本和在时间段内道路段的平均速度,或时间段内道路段的不足数据。 33 [0149] Routine 705 begins in a step in which the receiving indication that indicates the road segment data sample period and the average speed of the road segment period, or a period of insufficient road segment data. 数据样本可以从,例如,数据样本异常值去除器例程的输出获得,而平均速度可以从,例如数据样本速度估算器例程的输出获得。 Data samples may be from, for example, the output data sample outlier removal routine is obtained, the average speed may be estimated, for example, the output speed of data sample is obtained from the routine. 不足数据的指示可以从,例如数据样本异常值去除器例程的输出获得。 Indicating insufficient data may be obtained from, for example, the data output of Sample Outlier Eliminator routine. 在一些情况中,不足数据的指示可以基于具有不足量的数据样本,例如当在时间段内从与道路段关联的移动数据源没有来数据样本或当用于道路段的一些或全部传感器数据读数丢失或已被检测为是错误的(例如,通过图1的传感器数据调整组件10¾。例程接着在步骤706中继续以确定是否接收到了不足数据指示。如果是,则例程继续到步骤750,如果不是,则例程继续到步骤710。 In some cases, the indication of insufficient data may be, for example, when there is no time period to sample data based on data from samples with insufficient amount of the road segment associated with the mobile data sources or when some or all sensor data readings for the road segment missing or have been detected to be erroneous (e.g., 10¾. routine then continues to determine whether it has received in step 706 of FIG. 1 sensor data Conditioner component indicating insufficient data. If so, the routine continues to step 750, If not, the routine continues to step 710.

[0150] 在步骤750,例程执行交通流量估算器例程(参考图14描述)的实施例以获得在时间段内道路段的估算的总量和占用率。 [0150] In step 750, the routine performs traffic estimation routine embodiment (described with reference to FIG. 14) to obtain the estimated total volume and occupancy period road segment. 在步骤755,例程接着提供估算的总量和占用率的指示。 Then provides estimated at step 755, and the routine indicating the total occupancy.

[0151] 在步骤710,例程确定提供数据样本的车辆数(或其它移动数据源),例如通过将每个数据样本与特定的移动数据源关联。 [0151] In step 710, the routine determines the number (or other mobile data sources) providing data samples of a vehicle, for example, each data sample associated with a particular mobile data source through. 在步骤720,例程接着在概率上部分基于所确定的车辆数确定提供该数据样本的车辆的道路段最有可能的到达率。 In step 720 the road segments, the routine then provides the data portion of the sample based on the determined number of the probability of the vehicle determines that the vehicle is most likely to reach. 在一些实施例中,概率确定还进一步使用有关这样的车辆数量的先验概率和特定到达率的先验概率的信息。 In some embodiments, the probability is determined further using the information about the number of a priori probabilities such vehicles and a priori probability of a particular arrival rate. 在步骤730,例程接着例如基于车辆所确定的数量和有关提供数据样本的车辆占车辆总数的百分比推断在时间段内通过道路段的所有车辆的总数,并进一步估算推断的总量的置信区间。 Confidence Intervals 730, the routine then determined for example based on the number of vehicles and vehicle-related data samples provided the total number of all the vehicles in the vehicle percentage of the total time period inferred by road segments, and further estimate the total amount estimation step . 在步骤740,例程接着基于所推断的总量、平均速度和平均车辆长度推断在时间段内道路段的百分比占用率。 In step 740, the routine then inferred based on the total, average speed and an average vehicle length estimation road segment percentage occupancy period. 在其它实施例中类似地也可以估算所感兴趣的其它类型的交通流量特征。 In other embodiments can be similarly estimated traffic flow characteristics of other types of interest. 在所示的实施例中,例程接着继续到步骤790以提供推断的总量和推断的百分比占用率的指示。 In the illustrated embodiment, the routine then continues to step 790 to provide an indication of the percentage of occupancy estimation and inference of the total amount. 在步骤755或790后,如果在步骤795中确定继续;则例程返回到步骤705 ;如果不继续,则继续到步骤799并结束。 After step 755 or 790, if it is determined to continue at step 795; the routine returns to step 705; if not to continue, then continues to step 799 and ends.

[0152] 图11是传感器数据读数错误检测器例程1100的示例性实施例。 [0152] FIG. 11 is a sensor data reading routine error detector 1100 of the exemplary embodiment. 例程可以由,例如,执行图3的传感器数据调整组件353和/或图1传感器数据调整组件105提供,从而来确定一个或多个交通传感器的健康。 The routine may, for example, executes the Sensor Data Conditioner component 3533 and / or FIG sensor data provided by the adjustment assembly 105 to determine the health of one or more traffic sensors. 在这个示例性实施例中,基于在所指示的时间段内新近获得的交通传感器读数,在一天的各个时间执行该例程以确定一个或多个交通传感器的健康。 In this exemplary embodiment, sensor readings based on traffic period indicated in the newly acquired, this routine is executed at various times of the day to determine the health of one or more traffic sensors. 此外,在各种实施例中,用于一个或多个各个类型的交通状况量度而由交通传感器输出的数据可以由该例程分析,例如交通速度、数量、占用率等。 Further, in various embodiments, one or more traffic conditions for each type of measurements and can be analyzed by the traffic sensor data outputted by the routine, e.g. traffic speed, amount, occupancy rate. 而且,用于至少交通状况的一些的数据可以以各种方式测量和/或收集,例如以各种间隔水平(例如,用于速度信息的数据组的5mph桶),并且在一些实施例中该例程可以以一个或多个用于一个或多个交通状况量度的每个的间隔水平的每个(或其它组合水平)为特定的交通传感器分析数据。 Further, the data for at least some of the traffic conditions may be measured and / or collected in various ways, for example, the level at various intervals (e.g., data set for the 5mph buckets speed information), and that in some embodiments routines may be used for each of one or more (or other combination level) interval of each of the horizontal traffic conditions one or more metrics for a particular traffic sensor data analysis.

[0153] 该例程在步骤1105开始,并接收一个或多个交通传感器和所选时间类别(例如最近时间类别,如果例程在每个时间类别后执行来以近于实时的方式提供结果,或一个或多个为分析而选择的先前时间类别)的指示,但在其它实施例中多个时间分类替换地可以被指示。 [0153] The routine begins in step 1105 and receives one or more traffic sensors and the selected time category (e.g., the most recent time category to a near-real-time mode if the routine performed after each time to provide results category, or for the analysis of one or more selected categories of previous time) indication, but a plurality of embodiments may alternatively be classified time indicated in the other. 在一些实施例中,时间可以通过其每个都包括时间点类别(例如,12:00AM-5:29AM和7:30PM-11:59PM,5:30AM-8:59AM,9:00AM-12:29PM,12:30PM-3:59PM,4:00PM-7:29PM,和12:00AM-11 : 59PM)和/或日期类别(例如,周一至周四,周五,周六和周日,或替换地具有周六和周日一起成组)的时间类别而建模。 In some embodiments, the time by which each include the sort of time (e.g., 12: 00 AM-5: 29AM and 7:30 PM-11:59PM,5:30AM-8:59AM,9:00AM-12: 29 PM,12:30PM-3:59PM,4:00PM-7:29PM, and 12:00 AM-11: 59PM) and / or date of categories (for example, Monday to Thursday, Friday, Saturday and Sunday, or Alternatively category with a time Saturday and Sunday together in groups) are modeled. 在各个实施例中可以以各种方式选择特定的时间 In various embodiments, a specific time may be selected in various manners

34分类,包括反映在其期间交通预料具有类似特征的时间段(例如,基于通信时间和模式,或其它反映交通的一致行为),例如如果交通在傍晚和清晨相对稀少,则将它们在一起组成一组。 Classification period 34, having similar features including traffic expected during which reflected (e.g., based on a communication mode and time, or reflect the same behavior of other traffic), for example if the vehicle is relatively rare in the evening and early morning, they are together to form One group. 此外,在一些实施例中,可以通过分析历史数据来确定具有相似的交通流量特征的时间段,从而无论以人工还是自动的方式选择时间类别来区分不同的交通传感器(例如,通过地理区域、道路、单个传感器等)。 Further, in some embodiments, the time period may be determined with similar characteristics by analyzing historical traffic data, whether manually or automatically so that the mode selection time to distinguish between different categories of traffic sensors (e.g., by geographical area, the road single sensor, etc.).

[0154] 在步骤1110至1150中,例程接着执行循环,在其中它分析从用于所指示的时间类别的所指示的一个或多个交通传感器的每个来的交通传感器数据读数以确定在该时间类别期间每个交通传感器的交通传感器健康状态。 [0154] In step 1110 through 1150, the routine then execution cycle, where it analyzes the traffic sensor data readings for each of the one or more traffic sensors from time categories indicated for the indicated to determine during this time traffic sensor health status of each category of traffic sensors. 在步骤1110中,从第一个交通传感器开始,例程选择所指示的一个或多个交通传感器中的下一个交通传感器,并选择所指示的时间类别(或,如果替换地在步骤1105指示了多个时间类别,则为交通传感器和所指示的时间类别的下一个组合)。 In step 1110, a traffic from the first sensor, a sensor next traffic or more traffic sensors in the indicated routine selects and select the indicated time category (or, alternatively, if in step 1105 indicates that a plurality of time categories, for the traffic sensor and the time categories indicated in a combination). 在步骤1115,例程在所选定的时间类别中检索用于交通传感器的平均历史数据读数分布。 In step 1115, the routine at the selected time category retrieve historical average traffic sensor data reading distribution. 在一些实施例中,历史数据读数分布可以基于由交通传感器在所选定的时间类别中提供的数据读数(例如,在跨过了诸如最近的120天或近来的120天周期等的延长的时间段包括了周一至周四的日期上的4:00PM和7:^PM之间)。 In some embodiments, the historical data reading distribution may be based on data readings provided in the selected time category by the traffic sensors (e.g., such as the recent time crossed the 120-day or 120-day period and the like have recently extended segment includes 7 4:00 PM on Monday through Thursday and date: ^ between PM).

[0155] 在步骤1120,例程继续为所选定的交通传感器和选定的时间类别确定目标交通传感器数据分布。 [0155] In step 1120, the routine continues to the selected traffic sensor and selected time category determination target traffic sensor data distribution. 在步骤1125,例程接着确定目标交通传感器数据读数分布和历史交通传感器数据读数分布的相似度。 In step 1125, the routine then determines the similarity of the target traffic sensor data reading distribution and the historical traffic sensor data reading distribution. 如别处更详细的描述,在一些实施例中,在这样的相似度的度量可以通过计算在目标交通传感器数据读数分布和历史交通传感器数据读数分布间的Kullback-Leibler散度而确定。 As described in more detail elsewhere, in some embodiments, it may be determined by calculating the target traffic sensor data Kullback-Leibler divergence between the reading distribution and the historical traffic sensor data reading distribution in such a similarity metric. 在步骤1130,如在别处更详细讨论地,例程接着确定目标交通传感器数据读数分布的信息熵。 In step 1130, as discussed in greater detail elsewhere, the routine then determines the information entropy target traffic sensor data reading distribution.

[0156] 在步骤1135,例程接着通过使用各种信息为所选定的时间类别估算所选定的交通传感器的健康以执行健康分类(例如,指示“健康”或“不健康”,或在“健康”尺度上的值,例如从1到100),其在这个实施例中包括所确定的相似度、所确定的熵、和所选定的时间类别(例如,所选定的钟点时刻类别,例如4:00PM到7J9PM,和/或所选定的日期类别,诸如周一至周四)。 [0156] In step 1135, the routine then by using various information of the selected time estimates healthy traffic sensors in the selected category to perform a health classification (e.g., indicating "healthy" or "unhealthy", or " health "value scale, for example from 1 to 100), which embodiment includes the determined degree of similarity in this embodiment, the determined entropy, and the selected time category (e.g., the selected time category hour, such as 4:00 PM to 7J9PM, and / or the date selected categories, such as Monday to Thursday). 在其它实施例中,可以使用其它信息类型,例如要被测量的数据的间隔程度的指示(例如,对于速度信息的数据组的5mph桶)。 In other embodiments, other types of information, such as the degree to be indicative of the measured data interval (e.g., speed information for the data set 5mph buckets). 在一个实施例中,可以使用神经网络来分类,而在其它实施例中,可以使用其它分类技术,包括决策树、贝叶斯分类器等。 In one embodiment, the neural network may be used to classify, while in other embodiments, other classification techniques, including decision trees, Bayesian classifiers.

[0157] 在步骤1140,例程接着基于估算的交通传感器健康和/或其它因素为所选定的交通传感器和所选定的时间类别确定交通传感器健康状态(在本示例中为健康或不健康)。 [0157] In step 1140, the routine followed by the selected traffic sensor and selected time category traffic sensor health status is determined based on the estimated traffic sensor health, and / or other factors (in the present example is healthy or unhealthy) . 在一些实施例中,无论何时用于所选定的时间类别的交通传感器的健康在步骤1135中被估算为健康,则用于交通传感器的健康状态都可以被认为是健康的。 In some embodiments, whenever the traffic sensor health for the selected time category is estimated at step 1135 for health, for the traffic sensor health status may be considered to be healthy. 此外,无论何时用于所选定的时间类别的交通传感器的健康被估算为不健康(例如,在步骤1135),并且所选定的时间类别具有关联的覆盖足够大的时间段(例如至少12或M小时)的钟点时刻类别,则用于交通传感器的健康状态都可以认为是不健康的。 In addition, whenever a traffic sensor health selected time category is estimated to be unhealthy (e.g., in step 1135) to cover, and the selected time category has an associated period of time sufficient (e.g., at least 12 or M-hour) time part-time category, for the health of traffic sensors can be considered to be unhealthy. 而且,在一些实施例中,可以检索和使用有关涉及时间类别的信息(例如用于一个或多个先前和/或后继的时间段),从而在较长的时间段(例如,一天)内对交通传感器的健康分类。 Further, in some embodiments, can be used to retrieve information about and relates to time category (e.g., for one or more previous and / or subsequent time periods), thereby a longer period of time (e.g., one day) health Categorization traffic sensors. 这样的逻辑降低了基于传感器精确报告的临时异常交通模式而对传感器健康状态进行错误负面确定(例如当实际上交通传感器是健康的时确定交通传感器的健康状态为不健康的)的风险。 This logic reduces the risk of error determining negative (for example, to determine the health status of unhealthy traffic sensor when the sensor is actually traffic is healthy when) the state of health of the sensor based on the temporary abnormal traffic patterns sensor accurate reporting of.

[0158] 例如,由于因外部因素(例如,交通事故、天气事故等)而在数据读数中显著的当 [0158] For example, since due to external factors (e.g., accidents, weather, accidents, etc.) in the data readout when a significant

35天变化可能产生错误的负面确定。 35 days to determine the changes could have a negative error. 例如,特定交通传感器处或其附近发生的车祸可能导致交通传感器在相对短的时间段(例如,一到两小时)内提供异常和不规则的数据读数。 For example, a car accident or a traffic sensor at a vicinity of a particular traffic sensor may result in abnormal and irregular data providing readings (e.g., one to two hours) within a relatively short period of time. 如果传感器健康状态的确定仅仅基于主要在由交通事故所引起的分布时间内所获得的数据读数,则就有可能导致错误的负面确定。 If it is determined sensor health status based solely on data readings mainly in the distribution of traffic accidents caused by the time obtained, then it may lead to false negative OK. 通过基于从相对较大的时间段(例如,12或对小时)所获得的数据读数来确定不健康的传感器的状态,可以降低这样的错误负面确定的风险。 To determine the status of an unhealthy-based sensor data readings obtained from a relatively large period of time (e.g., hours or 12), you can reduce the risk of such errors negative determination. 另一方面,错误的负面确定(例如当实际上交通传感器是健康的时确定交通传感器的健康状态为不健康的)一般来说可能性很低,因为故障的交通传感器不可能提供类似于历史数据读数(例如,反映一般的交通模式)的数据读数。 On the other hand, false negative is determined (for example, to determine the health status of traffic sensor when the sensor is actually healthy when traffic is unhealthy) in general is very low possibility of failure because of traffic sensor data readings can not provide similar history (for example, reflect the general traffic patterns) data readings. 同样地,可以基于相对较短的时间段适当地确定交通传感器的健康状态是健康的。 Similarly, the health state can be appropriately determined traffic sensor health is based on the relative short period of time.

[0159] 一些实施例可以通过以反映较短时间段的时间类别在每天多次执行所示的例程(例如,以具有延长过先前三小时的钟点时刻类别的时间分类,每三小时执行一次例程)和以反映整个先前日子的时间类别在每天至少执行一次例程(例如,以延长过先前M小时的钟点时刻类别的时间类别,在午夜执行例程)而实现这种不同的逻辑。 [0159] Some embodiments may reflect by shorter period of time in the execution of the routine shown in the category multiple times per day (e.g., having extended over three hours prior time hour time category classification, performed once every three hours routine) and to reflect the entire time of the day previous category routine executed at least once daily (e.g., to extend over the previous hour time categories hour time M categories, execution routine at midnight) to achieve such a different logic.

[0160] 此外,传感器状态的确定可以基于其它因素,例如是否为所选定的时间类别获得足够数量的数据读数(例如,因为传感器间歇地报告数据读数)和/或基于由交通传感器提供的传感器状态的指示(例如,交通传感器被卡住)。 [0160] Further, the determination may be based on the state of the sensor other factors, such as whether a sufficient number of categories of data readings for the selected time (e.g., because the sensor data readings reported intermittently) and / or based on sensors provided by the traffic sensor indication of the status (e.g., traffic sensor is stuck).

[0161] 在步骤1145,例程提供了所确定的交通传感器的健康状态。 [0161] Providing the traffic sensor health status as determined in step 1145, the routine. 在一些实施例中,可以为由其它组件(例如,图1的传感器数据收集组件110)的后续使用而存储交通传感器健康状态(例如,存储在数据库或文件系统中)和/或将其直接提供给其它组件(例如,数据样本异常值去除组件)。 In some embodiments, it may be by other components (e.g., the Sensor Data Aggregator component 110 of FIG. 1) is stored for subsequent use traffic sensor health status (e.g., stored in a database or file system) and / or directly provide to other components (e.g., data sample outlier Eliminator component). 在步骤1150,例程确定是否存在更多个传感器(或交通传感器和时间类别的组合)要处理。 In step 1150, the routine determines whether there are more sensors (or a combination of traffic sensors and time categories) to be processed. 如果是,则例程继续到步骤1110继续,如果不是,则继续到步骤11¾以执行其它合适的动作。 If so, the routine continues to step 1110 to continue, if not, proceed to step 11¾ to perform other appropriate actions. 这种其它动作可以包括,例如,为用于多个交通传感器的每个的一个或多个时间类别的每个来周期性(例如,每天一次,每周一次等)反复计算历史数据读数分布(例如,至少120天)。 Such other actions may include, for example, one for each of the plurality of traffic sensors periodically or each time a plurality of categories (e.g., once a day, once a week, etc.) is repeatedly calculated historical data reading distribution ( For example, at least 120 days). 通过周期性反复计算历史数据读数分布,面对逐渐变化的交通状况,例程可以继续提供精确的交通传感器健康状态的确定。 Repeatedly calculate historical data reading distribution through periodic, face gradually changing traffic conditions, the routine may determine to continue to provide accurate traffic sensor health status. 在步骤1155后,例程继续到步骤1199并返回。 In Step 1155, the routine continues to step 1199 and returns.

[0162] 图12是数据读数错误校正器例程1200的示例性实施例的流程图。 [0162] FIG. 12 is a flowchart of an exemplary embodiment of a data reading error correction routine 1200. 该例程可以通过例如,执行图3的传感器数据调整组件353和/或图1的传感器数据调整组件105而提供,从而确定用于一个或多个与道路段关联的交通传感器的校正后的数据读数。 The routine may, for example, executes the Sensor Data Conditioner component 3533 and the sensor data to adjust the components and / or 105 of Figure 1 is provided by, the corrected data to determine one or more traffic sensors associated with a road segment for reading. 在所示的示例性实施例中,这个例程可以被周期性执行(例如每五分钟)以校正用于已经由传感器数据读数错误校正器例程识别为不健康的交通传感器的数据读数。 In the exemplary embodiment shown, this routine may be executed periodically (e.g., every five minutes) has been used to correct the sensor data readings by the error correction routine identification data reading unhealthy traffic sensor. 在其它实施例中,可以按需执行该例程,例如通过传感器数据收集器例程,以获得用于特定道路段的校正后的数据读数,或替换地在各种环境中可以不被使用。 In other embodiments, the routine may be performed on demand, e.g., by the Sensor Data Aggregator routine to obtain the data for correcting the readings of the particular road segment, or alternatively may not be used in various environments. 例如,一般来说通过确定用于特定道路段的所有数据样本(例如,从多个数据源来的,例如可以包括交通传感器和一个或多个相异类型的移动数据源的多种类型)是否提供了足够的数据来分析该道路段的交通流量状况来执行数据的分析和校正,如果不是,则不执行从各个交通传感器来的数据的校正。 For example, in general, all of the data samples by determining for a particular road segment (e.g., from a plurality of data sources, for example, may include various types of traffic sensors and one or more types of distinct mobile data sources) is provide sufficient data to analyze the traffic conditions of the road segments and the correction data analysis is performed, if not, the traffic coming from the respective sensor data correction is not performed.

[0163] 该例程在步骤1205开始,其中它接收与一个或多个交通传感器关联的道路段的指示(例如,通过从传感器数据读数错误检测器例程来的、一个或多个所关联的交通传感器已经被分类为不健康的结果),并可选地接收要被处理的一个或多个时间类别(例如,其 [0163] The routine begins at step 1205, where it is indicated (e.g., by reading the data from the sensor to the error detector routine receives traffic associated with the one or more sensors of road segments, a plurality of associated or traffic sensors have been classified as unhealthy results), and optionally receive one or more time categories to be processed (e.g., which

36中在关联的交通传感器的至少一个已经被分类为至少潜在地为不健康的时间类别)的指示。 36 in the associated traffic sensors have been classified as at least one of at least potentially unhealthy time categories) indication. 在其它实施例中,所感兴趣的一个或多个交通传感器可以以其它方式指示,例如通过直接接收一个或多个交通传感器的指示。 In other embodiments, the one or more traffic sensors of interest may be indicated in other ways, for example by directly receiving an indication of one or more traffic sensors. 在步骤1210至1235,例程执行一个循环,其中它处理在所指示的道路段上不健康的交通传感器,以在一个或多个时间类别期间(例如在步骤1205中所指示的时间类别)为这些交通传感器确定并提供校正后的数据读数。 In step 1210-1235, the routine performs a loop in which it handles traffic sensors in the indicated road segment unhealthy, a plurality of times in order to, during, or categories (e.g., time categories indicated in step 1205) of these provides traffic sensor data readings determined and corrected.

[0164] 在步骤1210,从第一个开始,例程选择在所指示的道路段中的下一个不健康的交通传感器。 [0164] In step 1210, starting from the first one, the routine selects the next unhealthy traffic sensors in the indicated road segment. 该例程还通过选择一个或多个在其期间交通传感器先前被指派为不健康的时间类别等来选择要使用的时间类别,例如一个或多个在步骤1205中所指示的时间类别,。 The routine further by selecting one or more traffic sensors during which time previously assigned to categories unhealthy selected time category, etc. to be used, for example, one or more time categories indicated in step 1205, the. 在步骤1215,例程确定在所指示的道路段是否具有足够的其它健康的并可以被用来辅助用于所选时间类别的不健康传感器的读数校正的交通传感器。 In step 1215, the routine determines whether sufficient other health in the indicated road segment and may be used to assist reading of unhealthy traffic sensor for the selected time category sensor correction. 这个确定可以基于在所选的时间类别期间的指示道路段中是否存在至少预定数据量(例如,至少两个)和/或预定百分比(例如,至少30% )的健康交通传感器,并还可以考虑在指示的道路段中健康交通传感器的相对位置(例如,相邻或附近的交通传感器可以优于远离不健康交通传感器的传感器)。 This determination may be whether there is at least a predetermined amount of data (e.g., at least two) and / or a predetermined percentage (e.g., at least 30%) healthy traffic sensors in the indicated road segment based on the category selected period of time, and may also be considered in the relative position healthy traffic sensors in the indicated road segment (e.g., adjacent or nearby traffic sensors may be better than the unhealthy traffic sensor away from the sensor). 如果在步骤1215中确定存在足够的健康交通传感器,则例程继续到步骤1220,在这里基于从在用于所选定的时间类别的道路段中其它健康交通传感器来的数据读数确定用于不健康交通传感器的校正数据读数。 If it is determined that there is sufficient healthy traffic sensors in step 1215, the routine continues to step 1220, where based on the traffic sensors to determine other health data readings in the road segment for the selected time category for unhealthy correction data traffic sensor readings. 可以以各种方式确定校正数据读数,例如通过计算从在所选定时间类别的指示道路段中的健康交通传感器获得的两个或更多的数据读数的平均数。 Reading the correction data may be determined in various ways, for example, the average of two or more data readings obtained from a healthy traffic sensors in the indicated time category selected by calculating the road segment. 在一些实施例中,所有的健康交通传感器都可以用于求平均数,但在其它实施例中只能使用所选定的健康交通传感器。 In some embodiments, all healthy traffic sensors may be used for averaging, but only selected healthy traffic sensors in other embodiments. 例如,如果在所指示的道路段中的交通传感器的预定百分比(例如,至少30% )在所选定的时间类别期间是健康的,则可以使用所有的健康交通传感器来求平均数,否则只能使用最近的预定数量(例如,至少两个)的健康交通传感器。 For example, if a predetermined percentage of traffic sensors in the indicated road segment (for example, at least 30%) during the selected time category is healthy, you can use all the healthy traffic sensors for averaging, otherwise only You can use the most recent predetermined number (e.g., at least two) healthy traffic sensors.

[0165] 如果替换地在步骤1215中确定在用于选定时间类别的指示道路段中没有足够的健康交通传感器,则例程继续到步骤1225,在这里它试图基于涉及该交通传感器/或道路段的其它信息确定用于不健康交通传感器的校正数据读数。 [0165] Alternatively, if it is determined in step 1215 not enough healthy traffic sensors in the indicated road segment for the selected time category, the routine continues to step 1225, where it relates to the traffic sensor based attempts / or road other pieces of information is determined for correcting the unhealthy traffic sensor data readings. 例如,这样的信息可以包括用于道路段和/或不健康交通传感器的预测交通状况信息,用于道路段和/或不健康交通传感器的预报交通状况信息,和/或用于道路段和/或不健康交通传感器的历史平均交通状况信息。 For example, such information may include the road segment and / or a predicted traffic condition information unhealthy traffic sensor for the road segment and / or unhealthy traffic sensor forecast traffic condition information, and / or for the road segment and / or unhealthy historical average traffic condition information traffic sensors. 可以执行各种逻辑来反映各种信息类型的相对可靠性。 You may perform various logic to reflect the relative reliability of the various types of information. 例如,在一些实施例中,使用预测交通状况信息(例如,只要可以得到)可以优先于预报交通状况信息,使用预报交通状况信息又可以优先于历史平均交通状况信息。 For example, in some embodiments, using the predicted traffic condition information (for example, as long as you can get) priority to forecast traffic condition information, the use of traffic information and forecasts may take precedence over historical average traffic condition information. 涉及预测和预报未来交通流量状况的附加细节可以在2006年3 月3 日提交,并且题为“Dynamic Time Series Prediction Of FutureTraffic Conditions”的美国专利申请No. 11/367,463中得到,其全部内容合并在此作为参考。 Involving future traffic flow conditions and forecasts predict additional details can be submitted in March 3, 2006, and entitled "Dynamic Time Series Prediction Of FutureTraffic Conditions" US Patent Application No. 11 / 367,463 to get its entirety incorporated herein by reference. 在其它实施例中,可以不执行步骤1215和1225,例如如果在步骤1220中的数据读数校正总是基于从在所选的时间类别和/或相关的时间类别期间其它健康交通传感器得到的最好的数据而执行。 In other embodiments, it may not perform step 1215 and 1225, for example, if the correction data readings in step 1220 is always based on the selected time category and / or related time categories during other healthy traffic sensors is preferably obtained the data is performed. 例如,如果在所选定的时间类别的指示道路段中所有的健康交通传感器的至少预定百分比(例如,至少30%)是健康的,则数据读数校正可以基于所有的这些交通传感器,否则基于在所选定的时间类别和/或相关的时间类别期间所指示和/或临近的道路段中最临近的健康交通传感器。 For example, if at least a predetermined percentage (e.g., at least 30%) in the indicated road segment selected time category all healthy traffic sensors is healthy, the corrected data readings may be based on all these traffic sensors, or based on the selected time category and / or during the relevant time category and / or in adjacent road segments nearest health traffic sensor indicates.

[0166] 在步骤1220或1225后,例程进行到步骤1230并提供所确定的交通传感器数据读数作为用于在所选定时间类别期间的交通传感器的校正读数。 [0166] After the step 1220 or 1225, the routine proceeds to step 1230 and provides the determined traffic sensor data readings for correcting the readings as a traffic sensor during the selected time category. 在一些实施例中,所确定的 In some embodiments, the determined

37交通传感器数据读数可以为其它组件(例如,图1的传感器数据收集组件110)的后续使用而存储(例如,存储在数据库或文件系统中)。 37 traffic sensor data readings may be stored as other components (e.g., the Sensor Data Aggregator component 110 of FIG. 1) subsequent use (e.g., stored in a database or file system). 在步骤1235,例程确定是否有要被处理的交通传感器和时间类别的附加组合。 In step 1235, the routine determines whether there are additional traffic sensor combination and time category to be treated. 如果有,则例程返回到步骤1210,如果没有则进行到步骤1299并结束。 If so, then the routine returns to step 1210, if not then proceeds to step 1299 and ends.

[0167] 图13是传感器数据读数收集器例程1300的示例性实施例的流程图。 [0167] FIG. 13 is a flowchart of sensor data readings to an exemplary embodiment of the trap routine 1300. 该例程可以通过,例如,执行图3的传感器数据读数收集组件355和/或图1传感器数据读数收集组件110来提供,例如确定并提供用于在特定时间类别或其它时间段内多个交通传感器(例如与特定道路段关联的多个交通传感器)的交通状况信息。 The routine can, for example, executes data reading sensor 355 collecting assembly 3 and / or Figure 1 sensor assembly 110 to collect data readings provided, for example, to determine and provide the specific time period or other multiple traffic classes sensor traffic condition information (e.g., a plurality of traffic sensors associated with a particular road segment) of. 在所示的示例性实施例中,该例程为特定道路段而执行,但在其它实施例中可以从其它类型的多个交通传感器组收集信息。 In the exemplary embodiment shown, this routine is executed for a particular road segment, it can collect information from a plurality of sensor groups of other types of transport in other embodiments. 此外,这个例程可以提供补充由执行交通状况信息的估算的其它例程(例如,数据样本流量估算器例程)提供的信息的交通状况信息,从而在其它例程不能提供精确的估算(例如由于数据不足)的情况下提供交通状况信息。 Also other routines, the routine can be executed by a supplementary estimate of traffic condition information (e.g., Data Sample Flow Assessor routine) traffic information is provided, and thus can not provide accurate estimates (e.g., in other routines providing traffic information in the data due to the lack of) situation.

[0168] 该例程在步骤1305开始并接收一条或多条段和一个或多个时间类别或其它时间段的指示。 [0168] The routine begins in step 1305 and receives one or more segments of the bar and one or more time categories or other time periods. 在步骤1310,例程从第一个开始选择一个或多个所指示的道路段的下一条道路段。 In step 1310, the next road segment road segments starting from the first routine to select one or more indicated. 在步骤1315,例程获得由与该道路关联的所有交通传感器在所指示的时间段内采集的一些或全部可得的交通传感器数据读数。 In step 1315, the routine to obtain some or all of the available traffic sensor data readings of all road traffic sensors associated with the time period indicated in the collection. 这样的信息例如可以从图1的传感器数据调整组件105和/或图3的传感器数据调整组件353获得。 Such information may be obtained from the sensor 353 of FIG. 1 Data Conditioner component 105 of the Sensor Data Conditioner component and / or 3. 具体地,在一些情况下例程可以为被确定为健康的交通传感器获得交通传感器数据读数和/或从被确定为不健康的交通传感器获得校正的交通传感器数据读数,例如那些由图12的传感器数据读数错误校正器例程提供或确定的。 Specifically, the routine may in some cases be determined to obtain traffic sensor data readings and / or obtained from the correction is determined to be unhealthy traffic sensor data readings for the traffic sensor healthy traffic sensors, such as those of the data generated by the sensor 12 of FIG. reading the error correction routines provided or determined.

[0169] 在步骤1320,例程接着以一种或多种方式收集所获的数据读数,从而确定在所指示的时间段内用于道路段的平均速度、量、和/或占用率。 [0169] In step 1320, the routine then collect data readings obtained in one or more ways to determine the time period for the indicated average speed, volume, and / or occupancy road segment. 平均速度可以例如通过对反映经过一个或多个交通传感器的车辆速度的数据读数求平均数而确定。 The average speed may be determined, for example, by reading data reflecting traffic through one or more vehicle speed sensors averaging. 交通量可以根据报告车辆数量的数据读数确定。 Traffic can be determined based on the number of reports vehicle data readings. 例如,给定报告从传感器被激活开始通过传感器的车辆累积数量的环形传感器,则交通量可以通过减去在所指示的时间段内所获得的两个数据读数并由在数据读数间的时间间隔去除结果而简单地推断。 For example, given a report from the cumulative number of the sensor has already been activated by the vehicle sensor of the sensor ring, the traffic can be time by the interval between the data by subtracting the readings in period of two data readings obtained indicated result of the removal simply inferred. 此外,密度可以基于所确定的平均速度、量和平均车辆长度而确定,如在别处更详细地描述。 Furthermore, the density can be determined based on the determined average speed, and average length of the vehicle, as described in more detail elsewhere. 在一些情况中,数据读数可以以各种方式加权(例如,通过年龄),以便在平均流量确定中越近的数据读数具有比越老的数据读数更大的影响。 In some cases, data readings may be weighted in a variety of ways (e.g., by age), in order to determine the more recent data readings older having a greater than the average flow rate in the impact data readings.

[0170] 在步骤1325,例程接着确定是否有多条道路段(或多个交通传感器的其它组)要处理。 [0170] In step 1325, the routine then determines whether a plurality of road segments (or other groups of multiple traffic sensors) to be processed. 如果有,则例程返回到步骤1310,否则进行到步骤1330以提供所确定的交通流量信息。 If so, the routine returns to step 1310, otherwise proceeds to step to provide the determined traffic flow information 1330. 在一些实施例中,可以存储所确定的流量信息(例如,存储在数据库或文件系统中)以便后续提供给图1的交通数据客户端109和/或图3的RT信息提供系统363。 In some embodiments, the determined flow rate may store information (e.g., stored in a database or file system) for subsequent traffic data is provided to the customer information terminal of FIG. 1 RT 109 and / or providing system 363 of FIG. 3. 接下来,例程继续到步骤1339并返回。 Next, the routine continues to step 1339 and returns.

[0171] 图14是交通流量估算器例程1400的示例性实施例的流程图。 [0171] FIG. 14 is a flowchart of an exemplary embodiment of the Traffic Flow Estimator routine 1400. 该例程可以通过例如执行交通流量估算组件(未示出)而提供,从而以各种方式估算用于道路段的各种类型的交通流量信息。 The routine may be provided by, for example, performing traffic estimation component (not shown), so that the estimated in various ways for various types of traffic information of the road segments. 在这个示例性实施例中,例如在当这些例程不能为精确地执行它们各自的估算而获得足够的数据的情况中,例程可以由图6的数据样本速度估算器例程调用以获得平均速度的估算和/或由图7的数据样本流量估算器例程调用以获得量和/或占用率的 In this exemplary embodiment, for example, in the case when these routines can not be accurately estimated and perform their respective sufficient data, the routine may be called by the routine of FIG speed estimator data samples to obtain an average of 6 estimating and / or routine calls to obtain the amount and / or rate of occupancy by the data flow of the sample estimator of FIG. 7

38估算。 Estimate 38.

[0172] 该例程在步骤1405开始并接收道路段、一个或多个时间类别或其它时间段,和一个或多个诸如速度、量、密度、占用率等一个或多个类型的交通流量信息的指示。 [0172] The routine begins in step 1405 and receives a road segment, one or more types of the one or more time categories or other time periods, such as one or more speed, volume, density, traffic flow information occupancy rate instructions. 在步骤1410,例程确定是否基于一个或多个有关道路段来估算指示类型的交通流量信息,例如,基于这样的道路段在一个或多个所示的时间段内是否具有用于一个或多个类型的交通流量信息的精确信息。 In step 1410, the routine determines whether based on one or more related road segments to estimate traffic flow information indicating the type, for example, based on whether the road segments having one or more for a period of time or more of the illustrated accurate information about types of traffic flow information. 相关的道路段可以以各种方式识别。 Related road segments can be identified in various ways. 例如,在一些情况中,有关道路段的信息可以包括有关在道路段间关系的信息,例如第一道路段通常具有类似于第二(例如,相邻)的道路段的交通模式,从而用于第二道路段的交通流量信息可以用来估算在第一道路段上的交通流量。 For example, in some cases, information about a road segment may include information about the relationship between the road segments, such as a first road segment having a mode of transportation generally similar to the second road segment (e.g., adjacent) to a road traffic information of the second segment may be used to estimate the traffic flow on the first road segment. 在一些情况中,无论分析是预先和/或动态执行的,都可以自动确定这样的关系,例如基于在两条道路段上各自的交通流量模式的统计分析(例如,类似于先前讨论的关于识别给定交通传感器在不同时间类似的数据分布,但替换地分析在两个或多个不同传感器在诸如同一时间间的相似度)。 In some cases, whether it is analyzed in advance and / or performed dynamically, it can automatically determine such a relationship, for example, a statistical analysis based on the two respective road segment of traffic patterns (e.g., similar to that discussed previously regarding the recognized similar given traffic sensor data distribution at different times, but alternatively, such as analysis of the similarity between the two at the same time or in a plurality of different sensors). 替换地,可以选择一个或多个相邻的道路段来关联所指示的道路段而无需在已经执行的道路段间特定关系的任何确定。 Alternatively, it is possible to select one or more neighboring road segments to associate the indicated road segment without any particular relationship between the determined road segment has been executed. 如果确定基于相关道路段估算交通流量信息,则例程进行到步骤1415并基于用于一个或多个相关道路段的相同类型交通流量信息估算用于所指示类型的交通流量信息的值。 If the road segment is determined based on the correlation estimate traffic flow information, the routine proceeds to step 1415 and the same traffic flow type information for the road segment estimate value indicating the type of traffic flow information based on one or more. 例如,基于一个或多个相邻道路段的平均交通速度确定该道路段的平均速度(例如,通过使用从一个相邻道路段来的交通速度,或对从两个或多个相邻道路段来的交通速度求平均数)。 For example, determining the average velocity of the road segment based on one or more of the average road traffic speed adjacent segments (e.g., segments of a road traffic speed from a neighbor by the use, or from two or more neighboring road segments to the speed of traffic averaging).

[0173] 如果替换地在步骤1410中确定并不基于相关道路段估算用于所指示道路段的交通流量信息,则例程继续到步骤1420并确定是否在一个或多个所指示时间段内基于用于该指示道路段和指示时间段的预测信息为所指示的道路段估算交通流量信息。 [0173] Alternatively, if the road segments is determined not based on a correlation estimate traffic flow information for the indicated road segment in step 1410, the routine continues to step 1420 and determines whether one or more indicated time periods based on the indication for the road segment and the prediction information indicating a time period for the indicated road segment estimate traffic flow information. 在一些实施例中,这样的预测信息可能仅在特定的情况下得到,例如如果针对多个未来时刻重复进行预测(例如针对接下来的3个小时每15分钟一次)同时获得精确的当前数据。 In some embodiments, such information may be obtained prediction only under certain circumstances, for example if the prediction is repeated for a plurality of future time (e.g. every 15 minutes for the next three hours) while obtaining accurate current data. 同样地,如果在延长时间内(例如,超过三个小时)用于产生预测的精确输入数据是可以得到的,则可以无需获得由该例程所使用的未来交通状况信息的预测。 Similarly, if the input data is accurate over an extended period (e.g., more than three hours) for generating a prediction it is available, it may not need to predict future traffic condition information obtained by the routines used. 替换地,在一些实施例中,这样的预测的未来交通状况信息由于其它一些原因而不可得,例如由于在该实施例中没有使用。 Alternatively, in some embodiments, future traffic condition information such as predicted for some other reason is not available, for example, since this embodiment is not used in the embodiment. 如果在步骤1420中确定基于预测信息估算交通流量信息,则例程进行到步骤1425,并基于从例如图3的预测信息提供系统360所获得的预测信息而为指示的道路段和指示的时间段估算交通流量信息的指示类型。 If it is determined based on the estimated traffic flow information prediction information, the routine proceeds to step 1425, and provides the prediction based on the information obtained, for example, system 360 of FIG. 3 and prediction information for the indicated road segment and indicated time period in step 1420 estimates indicate the type of traffic flow information. 涉及预测和预报未来交通流量状况的附加细节在于2006年3 月3 日提交的题为“Dynamic Time Series Prediction Of Traffic Conditions” 的美国专利申请No. 11/367,463中可以得到,其全部内容合并在此作为参考。 Involving future traffic flow conditions and forecasts predict that additional details are entitled March 3, 2006 filed "Dynamic Time Series Prediction Of Traffic Conditions" US Patent Application No. 11 / 367,463 can be obtained, the entire contents of which are incorporated herein Reference.

[0174] 如果替换地在步骤1420中确定并不基于预测信息为所指示道路段估算交通流量信息(例如,由于该信息得不到),则例程继续到步骤1430并确定是否基于用于该道路段和时间段的预报信息在一个或多个指示的时间段内为所指示的道路段估算交通流量信息。 [0174] Alternatively, if the determination is not based on prediction information indicative of an estimated road segment traffic flow information (e.g., because the information is not), the routine continues to step 1430 and determines whether the basis for the step 1420 in road segment and time period forecast information in one or more of the indicated time period to the indicated road segment estimate traffic flow information. 在一些实施例中,可以为超出能预测交通状况的未来时间预报交通状况,例如在不使用至少一些当前状况信息的方式中。 In some embodiments, the embodiment may be able to predict the traffic situation prediction for the future time exceeds the traffic conditions, such as not using at least some of the current status information. 同样地,如果不能得到预测信息(例如,由于用于产生预测的精确输入数据超过三个小时就不可得了),则仍然可以使用预报信息,例如明显预先产生的信息。 Similarly, if the prediction information can not be obtained (e.g., due to the accurate input data for generating a prediction over three hours had not), you can still use the forecast information, such as information previously generated significantly. 如果在步骤1430中确定基于预报信息估算交通流量信息,则例程进行到步骤1435并基于从例如预测交通信息提供系统360获得的预报信息为所指示的道路段和时间段估算指示类型的交通流量信息。 If it is determined based on the forecast information estimated traffic flow information in step 1430, the routine proceeds to step 1435 based on the estimated traffic flow type indicating, for example, from the information systems provide forecasts obtained predicted traffic information 360 road segment and time period indicated information.

39[0175] 如果替换地在步骤1430中并不基于预报信息而为所指示的道路段估算交通流量信息(例如,由于该信息不可得),则例程继续到步骤1440并基于用于所指示道路段的历史平均流量信息为所指示的道路段和时间段估算指示类型的交通流量信息(例如,对于相同或相应的时间段,例如基于包括钟点时刻类别和/或日期类别的时间类别)。 39 [0175] Alternatively, if in step 1430 is not based on the estimated traffic flow forecast information for the indicated road segment information (e.g., since the information is not available), the routine continues to step 1440 and indicated based on a historical average flow information indicating the type of road segment estimate of traffic flow information for the road segment and indicated time period (e.g., the same or corresponding time period, for example, based on a part-time categories category and time / date or category). 例如,如果预报信息是不可得的(例如,由于比产生最近预测和预报的周期更长的时间的输入数据是不可得的,因此既不能产生新的预测也不能产生新的预报),则例程可以使用用于所指示道路段的历史平均流量信息。 For example, if the broadcast information is not available (e.g., the input data is longer than the latest generation of the prediction and prediction time period is not available, and therefore neither generate new predictions can not produce new prediction), the Example Cheng can use the historical average flow information for the indicated road segment. 涉及产生历史平均流量信息的附加细节可以在同时提交的题为"Generating Repre sentative Road Traffic Flow Information From Historical Data,,的美国专利申请(代理案卷号为480234. 410P1)中得到,其全部内容合并在此作为参考。 Entitled involves generating historical average flow information Additional details can be submitted at the same time "Generating Repre sentative Road Traffic Flow Information From Historical Data ,, US Patent Application (Attorney Docket No. 480234. 410P1) obtained, incorporated in its entirety herein by reference.

[0176] 在步骤1415、1425、1435或1440后,例程进行到步骤1445并为所指示的道路段和所指示的时间段提供所指示类型的估算交通流量信息。 [0176] After step 1415,1425,1435 or 1440, the routine proceeds to step 1445 and provide the estimated traffic flow information indicating the type of road segment and indicated time period indicated. 所提供的信息可以例如被返回到调用该例程的例程(例如,数据样本流量估算器例程)和/或为了后续使用而被存储(例如,存储在数据库或文件系统中)。 The information provided may be, for example, the routine returns to the calling routine (e.g., Data Sample Flow Assessor routine) and / or be stored for later use (e.g., stored in a database or file system). 在步骤1445后,例程继续到步骤1499并返回。 In Step 1445, the routine continues to step 1499 and returns.

[0177] 图9A-9C图示了在获得和提供有关道路交通状况信息中的移动数据源的动作实例。 [0177] Figures 9A-9C illustrate an example of operation in the mobile data source is obtained and road traffic condition information in the. 有关道路交通状况的信息可以以各种方式从移动设备(无论基于车辆的设备还是用户设备)获得,例如通过使用无线链路(例如,卫星上行链路、蜂窝网络、WI-FI、分组无线等)传输和/或在设备达到适当的对接(docking)或其它连接点时物理进行下载(例如,一旦返回操作的主要基地或具有能执行信息下载的适当设备的其它目的就从车队下载信息)。 Information about road traffic conditions may be (whether the vehicle-based device or user equipment) is obtained from the mobile device in various ways, such as by using a wireless link (e.g., satellite uplink, cellular networks, WI-FI, packet radio, etc. ) transmission and / or physically when it has reached an appropriate abutment (docking) or other connection point for download (e.g., other objects upon return to the main base of operation or with a suitable apparatus capable of executing the downloaded information on the download information from the team). 虽然在明显晚于第二时间获得的第一时间的有关道路交通状况的信息提供了各种益处(例如,修正第一时间的预测,为随后使用所观测情况的数据改进了预测处理等),例如可以是从设备物理下载信息的情况,当以实时或近于实时的方式获得时,这样的道路交通状况信息提供了附加的益处。 While providing information about the various benefits in road traffic conditions significantly later than the first time obtained a second time (for example, correcting the first time forecast, the forecast improved as the data is then processed using the observed cases), for example, may be downloaded from a situation of physical device information, when in real-time or near-real-time way to get such a road traffic condition information provides additional benefits. 因此,在至少一些实施例中,具有无线通信能力的移动设备可以频繁地提供至少一些所需的有关道路交通状况的信息,例如周期性地(例如,每30分钟,1分钟,5分钟等)和/或当可以足够量的所需信息可用时(例如,对于与道路交通状况信息相关的每个数据点;对于每N个这样的数据,例如其中N是可配置的数;当所获取数据达到特定的存储和/或传输尺寸等)。 Thus, in at least some embodiments, a mobile device with wireless communication capabilities may provide some information regarding the frequently desired road traffic conditions at least, for example, periodically (e.g., every 30 minutes, 1 minute, 5 minutes, etc.) and / or it may be available when a sufficient amount of the desired information (e.g., for each data point associated with the road traffic condition information; for every N number of such data, for example, where N is configurable; when the acquired data is reached specific storage and / or transmission size, etc.). 在一些实施例中,所获取的道路交通状况信息的这种频繁的无线通信还可以在其它时间通过附加的所获道路交通状况信息来补充(例如,从设备的连续物理下载,经由包含更大量数据的少频(less-frequency)无线通信),例如包括相应于每个数据点的附加数据,包括有关多个数据点的收集信息等。 In some embodiments, such frequent radio communication acquired road traffic condition information may also be supplemented by additional road traffic condition information obtained at other times (e.g., consecutive physical downloaded from the device, via a larger amount comprising low frequency data (less-frequency) radio communication), including, for example corresponding to the additional data for each data point, comprises a plurality of collecting information about the data points and the like.

[0178] 虽然通过从移动设备以实时或其它频繁的方式获得所获取的道路交通状况信息提供了各种好处,在一些实施例中这样的所获道路交通状况信息的无线通信可以以各种方式约束。 [0178] Although providing obtained by obtaining in real time or from other mobile devices frequently way road traffic condition information of the various benefits, in some embodiments, such road traffic condition information obtained in the wireless communication may be various ways to constraint. 例如,在一些情况中,从移动设备经由特定无线链路(例如,卫星上传)传输数据的成本结构可以是以少频间隔(例如,每15分钟)发生的传输,或者移动设备可以被预先编程来以这样的间隔传输。 For example, in some cases, from a mobile device (e.g., satellite uploading) via a radio link specific cost structure of the transmission data may be based on a frequency interval less (e.g., every 15 minutes) of the transmission occurs, or the mobile device may be pre-programmed to transmit at such intervals. 在其它一些情况中,移动设备可能暂时丢失通过无线链路传输数据的能力,例如由于在移动设备所在的区域缺少无线覆盖(例如,由于没有临近的蜂窝无线电话接收机基站),由于由移动设备或设备的用户执行的其它动作,或由于移动设备或关联发射机的暂时问题。 In some other cases, the mobile device is temporarily lost the ability to transmit data through a wireless link, for example due to a lack of radio coverage area of ​​the mobile device is located (e.g., because there is no adjacent base station receiver of a cellular radio telephone), since the mobile device other user actions performed or equipment, mobile or temporary problems due to or associated transmitter.

[0179] 因此,在一些实施例中至少一些这样的移动设备可以被指派或配置成存储多个数据样本(或使得这样的多个数据样本存储在其它关联设备中),以便用于多个数据样本的 [0179] Thus, in some embodiments at least some of such mobile devices may be assigned or configured to store a plurality of data samples (or so that such a plurality of data samples stored in other associated equipment), so that a plurality of data samples

40至少一些信息可以在一个无线传输中一起被传输。 At least some of the information 40 may be transmitted together in a wireless transmission. 例如,在一些实施例中至少一些移动设备被配置成在移动设备不能通过无线链路传输数据(例如,移动设备通常单独传输每个数据样本,例如每30秒或1分钟)时的周期内存储所获道路交通状况信息数据样本,并接着在出现下一个无线传输的时间期间将这些所存储的数据样本一起传输。 For example, in some embodiments at least some of the mobile device is configured to cycle when the mobile device is unable to transmit data over a wireless link (e.g., mobile devices typically transmit each data sample individually, for example, every 30 seconds or 1 minute) in the memory acquired road traffic condition information data samples, and then a transfer of the stored data samples together under these occurred during the time of the wireless transmission. 一些移动设备还可以被配置成执行周期性(例如每15分钟,或当指定量的数据可用于传输时)无线传输,并在至少一些实施例中还可以被配置成在无线传输之间的时间间隔期间获得并存储道路交通状况信息的多个数据样本(例如以预定的取样率,例如30秒或一分钟),并接着类似地在下一个无线传输期间将这些所存储的数据样本一起传输(或这些样本的子集和/或集合)。 Some mobile devices may also be configured to perform a periodic (e.g., every 15 minutes, or when a specified amount of data available for transmission) wireless transmission, and may also be configured to the time between wireless transmissions in at least some embodiments obtaining and storing road traffic condition information during an interval of a plurality of data samples (e.g., at a predetermined sampling rate, such as 30 seconds or one minute), and then similarly a next transmission during wireless transmission of data stored in these samples together (or a subset of these samples, and / or collection). 如一个实施例,如果多达1000个信息单位的无线传输成本是$0. 25并且每个数据样本的尺寸是50个单位,则每分钟取样并每20分钟发送包括20个样本的数据组(而不是每分钟单独地发送每个样本)是很有益处的。 As one example, if the information is up to 1,000 units of wireless transmission cost is $ 0.25, and the size of each data sample is 50 units, and transmits the sampled per minute every 20 minutes, the data set comprising 20 samples (the not be sent separately per minute per sample) is very helpful. 在这样的实施例中,虽然数据样本可能轻微延迟(在周期性传输的实例中,延迟了传输之间的时间段的平均一半,假定定期获得数据样本),则从传输获得的道路交通状况信息仍然提供近于实时的信息。 In such an embodiment, although the data sample may be a slight delay (in the example of the periodic transmissions, the delay time half the average period between the transmission of data samples is obtained assuming periodically), transfer from road traffic condition information obtained still provides near real-time information. 而且,在一些实施例中可以由移动设备基于多个所存储的数据样本产生并提供附加的信息。 Further, the sample can be generated and provided additional information, in some embodiments a plurality of the mobile device based on the stored data. 例如,如果特定的移动设备在每个数据样本期间仅能获得有关当前即时位置的信息,但不能获得诸如速度和/或方向的附加相关信息,则这样的附加相关信息可以基于多个后续的数据样本而被计算或确定。 For example, if a particular mobile device can only obtain information about the current position of real time during each data sample, such as but not be obtained and / or direction of the velocity of the additional information, the additional information may be based on such a plurality of subsequent data the sample is calculated or determined.

[0180] 具体地,图9A描述了具有几个相互连接的道路925、930、935和940,和指示道路北向方向的图例指示950的示例性区域955(道路925和935南北向走,而道路930和940东西向走)。 [0180] In particular, Figure 9A depicts a diagram of a road having several interconnected 925,930,935 and 940, and a pointing direction of the road north exemplary region indicative 955,950 (road 925 and 935 go ​​from north to south, and the road 930 and 940 things to go). 虽然仅显示了有限数量的道路,但它们可以表示广大的地理区域,例如横跨几英里相互连接的高速路,或跨了几个区的城市街道的子集。 Although only a limited number of roads, but they can represent large geographical area, such as across the highway a few miles of interconnected, or a subset of city streets across several areas. 在这个实例中,移动数据源(例如,车辆,未示出)在30分钟的周期内从位置94¾到945c行驶,并被配置成每15分钟获得并传输表示当前交通状况的数据样本。 In this example, the mobile data source (e.g., a vehicle, not shown) to travel from the position 945c within 94¾ period of 30 minutes, and every 15 minutes configured to obtain and transmit data representing the samples of the current traffic conditions. 因此,当移动数据源开始行驶时,它在位置94¾获得并传输第一个数据样本(如在这个实例中用星号“★”所示),15分钟后在位置94¾获得并传输第二个数据样本,并在总共30分钟后在位置945c获得并传输第三个数据样本。 Thus, when the mobile data source starts running, it 94¾ obtained and transfers the first sample of data (in this example, as shown with an asterisk "★") in position, after 15 minutes in position 94¾ and second transmission data samples, and a total of 30 minutes and 945c to obtain the third data sample transfer position. 在这个实例中,每个数据样本包括当前位置的指示(例如,在GPS坐标中)、当前方向(例如,北向)、当前速度(例如,30分钟每小时)和当前时间,如使用数据值I^DaJa和Ta的945a的传输所表示的,并可选地也可以包括其它信息(例如,指示移动数据源的标识符)。 In this example, each data sample includes indicating the current location (e.g., in GPS coordinates), current direction (e.g., north), current speed (e.g., 30 minutes per hour) and the current time, such as using the data values ​​I ^ DaJa transmission and Ta, represented by 945a, and optionally also may include other information (e.g., indicating the identifier of the mobile data sources). 虽然这样的获得并提供的当前交通状况信息提供了更多的益处,但从这样的数据不能确定多个细节,包括从位置94¾到945c的路线是否部分地沿道路930或940。 Although the current traffic conditions obtain and provide information such as provide more benefits, but such data can not be determined more details, including whether to 945c from the position 94¾ route partly along the road 930 or 940. 而且,这样的样本数据不允许,例如将在位置94¾和94¾间的道路925的部分作为可以报告并预测的相异交通状况的相异道路段。 Moreover, such a sample data does not allow, for example, it will be reported as a distinct and predictable road segment different traffic conditions and roads in some locations 94¾ 925 between 94¾.

[0181] 以与图9A类似的方式,图9B描述了实例905,其在30分钟的周期内移动数据源从位置94¾至945c行驶过相互连接的道路925、930、935和940,并且移动数据源每15分钟发送有关交通状况的信息(如在位置94如、94恥和945c所示的星号所表示的)。 [0181] In a similar manner to FIG. 9A, 9B depicts an example 905 mobile data source over a 30 minute cycle from the position 945c to 94¾ traveled road 925,930,935 and 940 are interconnected and mobile data source information transmitted every 15 minutes about traffic conditions (e.g., at position 94, and 94 shame asterisk represented 945c shown). 但,在这个实例中,移动数据源被配置成每分钟获取并存储数据样本,后续传输包括在前15分钟来自每个数据样本的数据。 However, in this example, the mobile data source is configured to acquire and store data samples every minute, 15 minutes subsequent transmission including data from each data sample preceding. 因此,当移动数据源在位置94¾和94¾间行驶时,移动数据源获取15个数据样本910bl至910bl5的组910b,并且在这个实例中,利用数据样本的时间处以移动数据源的方向指示的箭头来指示每一个数据样本。 Thus, when the mobile data source location 94¾ and 94¾ room with the mobile data source acquires 15 data sample set 910b 910bl to 910bl5, and in this example, using the time data samples impose mobile data source in the direction indicated by the arrow to indicate that each data sample. 在这个实例中,每个数据样本类似地包括当前位置、当前方向、当前速度和当前时间的指示,并且在位置94¾的连续传输包括 In this example, each data sample similarly includes a current location, current direction, current speed and the current time indicated, and includes a continuous transfer position in 94¾

41用于数据样本910b的每个的这些数据值。 41 for each of the data values ​​of the data samples 910b. 类似地,如移动数据源在位置94¾和945c间行驶,则移动数据源获得15个数据样本910cl-910cl5,并且在位置945c的后续传输包括用于15个数据样本的每个的所获取数据值。 Similarly, as the mobile data source traveling position between 94¾ and 945c, the mobile data source 15 data samples obtained 910cl-910cl5, and 945c in position comprises means for subsequent transmission of the acquired 15 sample data of each data value . 通过提供这样的附加数据样本,可以获得各种附加的信息。 By providing such additional data samples, various additional information may be obtained. 例如,现在很容易确定从位置94¾至945c的路线是部分地沿道路930而不是道路940,并允许将相应的交通状况信息用于道路930。 For example, it is now easy to determine from the position 945c to 94¾ route along a road 930 in part 940 rather than the road, and allows appropriate for a road traffic condition information 930. 此外,特定的数据样本和它们相邻的数据样本可以提供有关道路较小部分的各种信息,例如允许在位置94¾和94¾间的道路925被表示成例如多达15个相异道路段(例如,通过将每个数据样本与相异道路段关联),其每个都具有可能相异的道路交通状况。 Furthermore, the particular data sample and their adjacent data samples may provide various information about the smaller portion of the road, for example, allowing a road between positions 94¾ and 94¾ 925 is represented as e.g. up to 15 distinct road segments (e.g. , by associating with a different sample each road segment data), each having a distinct possibility of road traffic conditions. 例如,可以直观地观察出,用于数据样本910Μ-91(Λ6的平均速度大致为静态的(由于大致均等地间隔数据样本),而用于数据样本9101-910b8的平均速度增加(由于数据样本对应于渐远隔开的各个位置,反映了在给定的1分钟间隔中在用户这个实例的数据样本间行驶过的距离变大),以及数据样本910bl-910bl5的平均速度下降。虽然在这个实例中的数据样本直接提供了有关这样的速度的信息,但其它实施例中这样的数据信息可以从仅包括当前位置的数据样本信息中获得。[0182] 图9C描述了第三个实例990,其中移动数据源在30分钟的周期内从位置96¾至965c行驶过相互连接的道路部分,并且移动数据源每15分钟传输有关交通状况的信息(如在位置96如、96恥和965c中星号所示)。如在图9C所示,在这个实例中移动数据源被配置成每分钟获得并存储数据样本,并且后续传输 For example, can be visually observed that, for the mean velocity data samples 910Μ-91 (Λ6 substantially static (due substantially equally spaced data samples), the average speed for the data samples of increased 9101-910b8 (since the data samples corresponding to the respective position spaced further away, the reflected given one minute intervals traveled between data samples in this example the user increases the distance), and the average speed data samples is decreased 910bl-910bl5. Although in this examples of data samples directly provides information about this rate, but in other embodiments such data may include data samples obtained from a current position information only. [0182] FIG. 9C depict a third example 990, wherein the mobile data source over a 30 minute period traveled each road portion connecting from the position 96¾ to 965c, and the mobile data source information (e.g., at position 96, such as 96 shame and 965c every 15 minutes transmission about traffic conditions asterisk shown). as shown in FIG. 9C, in this example the mobile data source is configured to acquire and store data samples every minute, and the subsequent transmission 括前15分钟内来自至少一些数据样本的每个的数据。因此,如移动数据源在位置96¾和96¾间行驶,则移动数据源获得15个数据样本960bl-960bl5的组960b。但,正如通过共同定位的数据样本960b5_bl3 (由于没有针对这些数据样本检测到移动,因此在这个实例中所使用的是环形而不是箭头,但为了清楚起见将其单独显示而不是在彼此的上面),在这个实施例中移动数据源在道路925的一侧停了大约9分钟(例如,在咖啡店停下)。因此,当在位置96¾产生下一个传输时,在一些实施例中传输可以包括用于所有数据样本的所有信息,或替换地可以省略至少一些信息(例如,省略数据样本960b6-960bl2的信息,这是因为如果知道移动数据源在数据样本960b5和960bl3之间仍然不移动,则在这个情况中它们不提供附加的有用信息)。而且,虽然这里没有示出,但在其它实施例中可 At least some of the data of each of the data samples including from 15 minutes before. Thus, as the mobile data source traveling position 96¾ and 96¾ between the mobile data source 15 to obtain data samples 960b 960bl-960bl5 the group, but, as indicated by co-located data samples 960b5_bl3 (since no movement is detected for the data samples, and therefore in this example, used is a ring instead of arrows, but for clarity it is shown separately, rather than on top of each other), in this embodiment Examples mobile data source on one side of the road 925 is stopped for about 9 minutes (e.g., stop at the coffee shop). Thus, when a transfer position at 96¾ produced, in some embodiments all of the data samples for transmission may comprise embodiment all the information, or alternatively, at least some of the information may be omitted (e.g., data sample information 960b6-960bl2 is omitted, because if the data source is still not know whether the mobile moves between data samples 960b5 and 960bl3, they in this case It does not provide additional useful information). Further, although not shown here, but in other embodiments 省略一个或多个这样的数据样本的信息,并可以延迟后续的传输直到要被传输的15个数据样本都是可用的(例如,如果基于要被发送的数据量而不是时间来执行周期性传输)。而且,如移动数据源在位置96¾和965c之间行驶,则移动数据源在无线通信当前不可用的区域中获取数据样本960cl3和960cl4(如在这个实施例中用开圆而不是箭头所示)。在其它实施例中,其中当获取但不存储时每个数据样本都是单独传输,这些数据样本会丢失,但在这个实例中,相反在位置965c是存储并与其它数据样本960cl至960cl2—起传输。 Omit one or more such message data samples, and may be delayed until a subsequent transmission to be transmitted 15 data samples are available (e.g., if performed based on the amount of data to be transmitted rather than periodic transmission time ). Further, as the mobile data source travels between location 96¾ and 965c, the mobile data source acquires data samples and 960cl4 960cl3 in a wireless communication area that is currently unavailable (as used in this embodiment instead of open circle arrows shown). in other embodiments, wherein when the acquired without storing each data sample is individually transmitted, the data sample will be lost, but in this example, at a position opposite to and 965c is stored with the other data samples to 960cl 960cl2- from the transmission. 虽然这里没有示出,但在一些情况中移动数据源还可以暂时失去使用数据获取的基本装置获取一个或多个数据样本的能力(例如,如果移动数据源失去获取GPS读数的能力几分钟)——如果这样,则在一些实施例中移动数据源可以报告其它所获取的数据样本而无需进一步的反应(例如,如果需要则允许接收方插入或估算这些数据样本),虽然在其它实施例中可以试图以其它方式获得数据样本(例如,通过使用不够精确的机制来确定位置,例如蜂窝移动电话塔三角测量,或通过基于先前已知的位置和后续的平均速度和方位估算当前位置,例如通过航位推测法),即便这些数据样本具有较低的精密性或精确度(例如,可以通过包括对这些数据样本的较低可信程度或较高的可 Although not shown here, but in some cases, the mobile data source may also be temporarily lost basic data acquisition means acquiring the ability to use one or more data samples (e.g., if the mobile loses the ability to obtain GPS data source readings minutes) - If so, then in some embodiments, the mobile data sources may report the other data sample acquired without further reactions (e.g., if necessary allow the recipient to insert or estimated data samples), although in other embodiments may attempt to otherwise obtain data samples (e.g., to determine the location by using a less accurate mechanism, such as a cellular mobile telephone tower triangulation, or by estimating the current location based on a previously known location and subsequent average speed and position, for example by presumed dead France), even if those data samples having a lower precision or accuracy (e.g., by including a low credibility of the data samples may be higher or

42能错误的程度,或通过包括指示这些和/或其它数据样本是如何产生的)。 42 degrees can be wrong, or by including an indication of these and / or other data is how to generate samples).

[0183] 虽然在图9B和9C的每个中,示例性数据样本为了简明起见仅图示了一辆车辆或一个其它移动数据源,但在其它实施例中,可以不使用用于特定移动数据源的多个数据样本来确定由该移动数据源所采集的特定路线,并且更具体地,甚至可以不与每个其它关联(例如,如果每个移动数据样本的来源是匿名的,或与其它来源没有什么不同)。 [0183] Although in each of FIGS. 9B and 9C, the exemplary data samples for brevity only one is illustrated a vehicle or other mobile data sources, but in other embodiments may not be used for a particular mobile data a plurality of sources of data samples is determined by the particular route acquired the mobile data source, and more particularly, may not even be associated with each other (e.g., if each mobile data sample sources are anonymous, or with other sources no different). 例如,如果从特定移动数据源来的多个数据样本并不由接收方使用于产生涉及这些数据样本的集合数据(例如,基于仅提供位置信息的连续的数据样本产生速度和/或方向信息),例如当这样的收集数据包括每个数据样本或不被使用时,在一些实施例中可以不提供这样的接收方来识别涉及移动数据样本来源和/或指示多个数据样本从相同的移动数据源(例如,基于设计决定来增加涉及移动数据源的私密性)。 For example, if for a particular mobile data source from the plurality of data samples are not used by the receiver to produce a set of data relates to the data samples (e.g., sample generating a speed and / or direction information based on the continuous data providing only the position information), when such data collection, for example, each data sample comprises or may not be used, in some embodiments, it may not be provided to identify the recipient of such a mobile data sample sources and / or data indicating a plurality of samples from the same mobile data source (e.g., determined based on the design relates to mobile data sources to increase privacy).

[0184] 替换地,在至少一些这样的实施例中,多个移动数据源被一起用于确定所感兴趣的道路状况信息,例如针对特定道路段(或道路的其它部分)使用从所有移动数据源来的多个数据样本以确定该道路段的收集信息。 [0184] Alternatively, in at least some such embodiments, a plurality of mobile data sources are used to determine road condition information of interest with, for example, for a particular road segment (or other portions of the road) from all mobile data sources to determine the number of data samples to collect information for the road segment. 这样,例如,在所感兴趣的时间段(例如,1分钟、5分钟、15分钟等)内,多个不相关的移动数据源的每个都可以提供一个或多个涉及在该时间段内在特定道路段上其自己行驶的数据样本,并且如果每个这样的数据样本包括速度和方向信息(例如),则为该时间段以及用于所有数据源的通常在相同方向上移动的道路段可以确定平均收集速度,例如以类似于为多个经过传感器的车辆收集信息的道路交通传感器的方式。 Thus, for example, in the time period of interest (e.g., 1 minute, 5 minutes, 15 minutes, etc.), a plurality of unrelated mobile data sources may each provide one or more in particular relates to the time period on the road segment data samples with its own, and if each such data sample including speed and direction information (e.g.), and for the period of time was typically moves in the same direction all the data sources may be determined road segment the average collection rate, for example manner similar to road traffic sensors to collect information for multiple vehicles passing sensor. 特定的数据样本可以以各种方式与特定道路段关联,例如通过将数据样本位置与具有最近位置的道路(或道路段)关联(无论对于任意道路,或仅对满足特定标准的道路,例如属于一个或多个所指示功能的道路类别)并且接着为该道路选择适当的道路段,或通过使用由移动数据源与所关联道路(或道路段)的数据样本一起提供的指示。 Particular data sample may be associated in various ways with a particular road segment, for example, by having data sample positions nearest position road (or road segment) linked (whether for any road or road only meet specific standards, such as belonging to one or more functional road class indication) and then select the appropriate road segment for a road, or by using a mobile data source indicated by the data samples associated with the road (or road segment) is provided with. 此外,在至少一些实施例中,为了给道路指派数据样本的目的以及其它目的(例如,将高速路北向车道作为与高速路的南向车道不同的相异车道),将除了单行道外的道路作为相异道路,并且如果这样,则用于移动数据样本的方向还可以被用于确定与数据样本关联的适当的道路——但,在其它实施例中,可以以其它方式建模,例如将双向城市街道作为一个道路(例如,根据为在两个方向上移动的车辆而报告和预测的平均交通状况),以将多车道的高速路的每个车道或其它道路作为相异逻辑道路等。 Further, in at least some embodiments, in order to give way objects and other objects of the data samples is assigned (e.g., high speed northbound lane of as a South highway lane of different distinct lanes), the addition to the road outside the one-way as different road, and if so, the direction of movement of the data samples may also be used for determining the proper path associated with the data sample - but, in other embodiments, may be modeled in other manners, for example, two-way city ​​streets as a way (for example, according to the vehicle moving in both directions and reports and forecasts of average traffic conditions) to each lane of multi-lane highway or other roads as distinct logic roads.

[0185] 在一些实施例中,为了便于使用多个移动数据源来确定所感兴趣的道路状况信息,车队可以以各种方式配置成提供所使用的道路样本。 [0185] In some embodiments, in order to facilitate the use of a plurality of mobile data sources to determine road condition information of interest, the team may be configured to provide the sample path used in various ways. 例如,如果每个大型车队都在每天的类似时间离开相同的出发点,则各部车辆都可以被不同配置成涉及多快和多久开始提供数据样本,例如最小化处于单个出发点附近所有的大量数据和/或提供在获得和传输数据样本时的变化。 For example, if each of a large fleet will leave the same starting point in a similar time of day, then each of the vehicles may be variously configured relates to how fast and how long started to provide data samples, e.g. minimized at all in the vicinity of a single starting point a large amount of data and / or to provide variation in obtaining and transmitting data samples. 更具体地,移动数据源设备可以以各种方式被配置成进行如何以及何时获取数据样本,包括基于从开始点(例如对于车队组的出发点)开始覆盖的总距离,从最后的数据样本获取和/或传输开始覆盖的距离,从开始时间(例如车辆从出发点离开的时间)经历的总时间,从最后的数据样本获取和/或传输经历的时间,产生有关一个或多个所指示位置(例如,通过、到达、离开等)的指示关系等。 More specifically, the mobile data source device may be configured in various ways for how and when to obtain the data samples, including based on total distance from the start point (e.g., the starting point for the team group) began to cover acquires data from the last sample and / or distance or a transmission start covered experience from the start time (e.g. time of the vehicle away from the starting point) of the total time, sample acquisition and / or time transmission experienced last data, generates about one or more indicated positions ( For example, the arrival, departure, etc.) indicating the relationship. 类似地,移动数据源设备可以以各种方式被配置成进行如何和何时传输或提供一个或多个所获取的数据样本,例如当统计预定条件时,包括基于从开始点起覆盖的总距离,从最后的数据样本获取和/或传输起覆盖的距离,从开始时间起经历的总时间,从最后的数据样本获取和/或传输起经历的时间,产生有 Similarly, a mobile data source device may be configured to count when a predetermined condition, based on the total distance including how and when to transfer or provide one or more acquired sample data, for example, from the starting point to cover various manners , sample acquisition and / or transmission time from the total distance covered from the start time experience last data sample acquisition from the time and / or transmission of data from the last experience, produce

43关一个或多个所指示位置的指示关系,已经收集的多个数据样本的指示数目,已经收集的所指示的数据量(例如,填满或实质上填满在移动设备上存储数据样本的缓存器的数量,或例如填满或实质上填满用于传输的指示时间量的数量)等。 43 indicating the relationship between the position of the indicated one or more closed, the amount of data indicating the number of the plurality of data samples have been collected, it has been collected as indicated (e.g., to fill or substantially fill the data stored on the mobile device of the sample the number of buffers, for example, or to fill or substantially fill a number indicating the amount of time of transmission) and the like.

[0186] 图8是移动数据源信息提供例程800的示例性实施例的流程图,例如可以通过操作用于图3的一个或多个基于车辆的数据源384和/或其它数据源388 (例如,用户设备)和/或图1的基于车辆的数据源101和/或图1的其它数据源102的每个的移动数据源设备来提供。 [0186] FIG 8 is a flowchart of a mobile data source information providing routine exemplary embodiment 800 of the exemplary embodiment, for example, by operation of one or more data sources in FIG. 3 based on the vehicle 384 and / or other data sources 388 ( for example, user equipment) and / or FIG. 1 of the vehicle-based data sources 101 and other data sources / or FIG. 1 of each mobile device 102. the data source is provided. 在这个实例中,该例程为特定移动数据源获得数据样本来指示当前的交通状况,并适当地存储数据样本以便后续传输可以包括用于多个数据源的信息。 In this example, the routine to obtain data for a particular mobile data source sample to indicate the current traffic conditions, and appropriately stores the data samples for subsequent transmission may include information for a plurality of data sources.

[0187] 该例程在步骤805开始,其中检索要被使用于作为数据样本获取和提供的一部分的参数,例如配置参数用于指示何时应当获取数据样本和何时应当产生相应于一个或多个数据样本的信息的传输。 [0187] The routine begins at step 805 wherein the key data to be used for sample acquisition and parameters as part of the offer, for example, the configuration parameters used to indicate when data should be obtained and when samples should be generated corresponding to one or more transmission of information data samples. 例程进行到步骤810等待,直到是时候获取数据样本,例如基于所检索的参数和/或其它信息(例如,已经经过先前数据样本获取的所指示的时间量,已经行驶过先前数据样本获取的所示距离,指示以实质上连续的方式获取数据样本等)。 The routine proceeds to step 810 to wait until it is time to obtain data samples, for example, based on the retrieved parameters and / or other information (e.g., data sample acquired previously has elapsed amount of time indicated by the data sample has traveled previously acquired FIG distance, indicating a substantially continuous manner to obtain data samples, etc.). 例程接着继续到步骤815以基于当前位置和移动数据源的移动获取数据样本,并在步骤820中存储数据样本。 Then the routine continues to step 815 based on the current position and to move the mobile data source acquires data samples, and storing the data samples in step 820. 如果在步骤825中确定还没有到传输数据的时间,例如基于所检索的参数和/或其它信息(例如已经经过先前传输的指示时间量,已经行驶过先前传输的指示距离,指示只要其可用或以实质上连续的方式传输数据样本等),则例程返回步骤810。 If it is determined yet the time to transmit data, for example based on the retrieved parameters and / or other information (e.g., has been subjected to a previous indication time of transmission, it has traveled previously indicated transmission distance in step 825, indicating as long as it is available or in a substantially continuous transmission of data samples, etc.), the routine returns to step 810.

[0188] 否则,例程继续到步骤830以检索并选择任何所存储的由于先前传输(或从开始,从第一次传输)的数据样本。 [0188] Otherwise, the routine continues to step 830 to retrieve and select any stored data samples since previous transmission (or from the beginning, from the first transmission) is. 例程接着可选地在步骤835中基于多个所选定的数据样本(例如,用于所有数据样本的全部平均速度,如果所获取的信息仅提供位置信息,则为用于每个数据样本的平均速度和方向等)产生所收集的数据。 The routine then optionally based on the selected plurality of data samples (e.g., for all samples the average speed of all the data, if the acquired information to provide location information only in step 835, for each data sample was the average data generating speed and direction) collected. 但在其它实施例中,也可以不执行这样的收集的数据的产生。 However, in other embodiments, it may not generate such data collection is performed. 在步骤840,例程接着可选地从所选数据样本组中去除用于一些或全部数据样本的一些或全部所获信息(例如,仅传输用于每个数据样本的所选类型,去除那些出现异常值或错误的数据样本,去除那些并不相应于移动数据源的实际移动的数据样本等),在其它实施例中,也可以不执行这样的信息去除。 In step 840, the routine then optionally removed from the selected group of data samples for some or all of the data samples of some or all of the obtained information (e.g., transmit only selected types for each data sample, removing those abnormal data sample values ​​or incorrect, removal of those data samples do not correspond to the actual movement of the mobile data source, etc.), in other embodiments may not perform such information is removed. 在步骤845,例程接着向接收方传输在数据样本当前组中的当前信息和将要以适当的方式使用的任何收集的信息。 In step 845, the routine then transmitted to the receiver in the current group of data samples and current information to be used in an appropriate manner any of the information gathered. 在步骤895中,例程确定是否继续(例如移动数据源是否继续使用和是可移动的),并且如果是,则返回到步骤810。 In step 895, the routine determines whether to continue (e.g., whether to continue using the mobile data source and is movable), and if so, the process returns to step 810. 否则,例程继续到步骤899并结束。 Otherwise, the routine continues to step 899 and ends. 在移动数据源不能传输数据的实施例和情况中,无论是否由于暂时的状况还是替换地反映了移动数据源首先的配置,步骤830-845都可以不被执行直到移动数据源可以传输数据或提供(例如,经由物理下载)由于先前的传输而已经被获得并存储的数据样本的一些或全部。 In an embodiment of the mobile data source and data can not be transmitted, whether due to a temporary condition or alternatively the first reflection configuration of the mobile data source, step 830-845 may not be performed until the mobile data source data can be transferred or provided (e.g., via physical download) since the previous transmission have been obtained and some or all of the stored data samples.

[0189] 正如先前所注意到地,一旦以及获得了有关道路交通状况的信息,例如从一个或多个移动数据源和/或一个或多个其它来源,则可以以各种方式使用道路交通状况信息,例如以基本实时的方式报告当前道路交通状况,或使用过去和当前的道路交通状况信息来在多个未来时间的每个预测未来交通状况。 [0189] As previously noted, once and obtain information about road traffic conditions, for example, from one or more mobile data sources and / or one or more other sources, road traffic conditions can be used in various manners information, such as a substantially immediate way to report current road traffic conditions, or use past and current road traffic condition information to each of the predicted future traffic conditions at multiple future times. 在一些实施例中,用于产生未来交通状况预测的输入数据的类型可以包括各种当前、过去和预期的未来状况,并且从预测处理来的输出可以包括对于在预定时间间隔(例如,三个小时,或一天)内的多个未来时间的每个(例如,未来每5、15或60分钟)在所感兴趣的多个目标道路段的每个上所产生的预期交通状况的预测,如在别处所更详细地描述。 In some embodiments, the type used to generate future traffic condition predictions may include various input data of the current, past and expected future state, and the output from the prediction processing may include for a predetermined time interval (e.g., three hours, or one day each of the plurality of future time) within (for example, to predict every 5, 15 or 60 minutes) the expected traffic situation on each of the plurality of target road segments of interest arising in the future, as in described in more detail elsewhere herein. 例如,输入数据的类型可以包括以下:有关用于在地 For example, the type of input data may include the following: for the related

44理区域内所感兴趣的各个目标道路段的当前和过去交通量的信息,例如在地理区域内所选道路的网络;有关当前和近来交通事故的信息;有关当前、近来和未来道路工程的信息;有关当前、过去和预期外来天气情况的信息(例如,降水、温度、风向、风速等);有关至少一些当前、过去和未来安排的事件的信息(例如,事件的类型,时间预期的开始和结束时间,和/或时间的地点或其它位置等,例如用于所有事件,指示类型的事件,很重大的事件,例如具有预期在所指示阈值之上(例如1000或5000预期的出席者)的出席等);和有关学校安排的信息(例如,学校是否上课和/或一个或多个学校的位置)。 Current and past traffic information, such as selected road network within the geographic area within 44 geographic regions of interest each target road segment; recent road works and information about the current and future; information about the current and recent traffic accident ; about the current, and the information in the past expected foreign weather conditions (for example, precipitation, temperature, wind direction, wind speed, etc.); begin some of the current, and information about at least past and future scheduled events (for example, type of event, time expectations and end time, and / or time or place other locations such as, for example, for all events, indicating the type of event, a very important event, for example, is expected to have a threshold indicated above (such as 1000 or 5000 expected attendees) of and information about the school arrangements (for example, whether school classes and / or one or more of school location); attendance, etc.). 此外,虽然在一些实施例中,预测未来交通状况的多个未来时间是按时的每点,但在其它实施例中这样的预测替换地可以表示多个时间点(例如,时间段),例如通过表示在这些多个时间点期间的未来交通状况的平均或收集度量。 Further, although in some embodiments, the prediction of future traffic conditions multiple future times per point in time, but in other embodiments such predictions may alternatively represent multiple time points (e.g., time period), e.g., by or collecting metric represents the average of future traffic conditions during those multiple time points. 而且,输入数据的一些或全部可以是已知的并用改变确定的程度来表示(例如,预期的天气),并且可以产生附加的信息来表示在用于所产生的预测中和/或其它元数据的可信程度。 Moreover, some or all of which may be known and determined by the degree of change is expressed (e.g., the expected weather), and may generate additional information to represent the prediction for the generated and / or other metadata data input of credibility. 此外,为各种原因以及在各个时间都可以初始化未来交通状况的预测,例如在周期性方式中(例如,每5分钟),当接收到任何或足够新的输入数据,响应从用于来的请求等。 Furthermore, for a variety of reasons and at various times are initialized to predict future traffic conditions, for example in a periodic manner (e.g., every 5 minutes), or any sufficient when receiving new input data, the response from the means for requests, etc.

[0190] 在一些实施例中可以使用输入数据的相同类型的一些来类似地产生未来交通状况的较长期限的预报(例如,未来一周,或未来一个月),但这样的较长期限的预报也可以不使用一些类型的输入数据,例如有关在预报产生的时间的当前状况(例如,当前交通、天气、或其它状况)的信息。 [0190] Some forecasts may be used the same types of input data to generate future traffic condition similarly the longer term (e.g., the next week, or the next month), in some embodiments, but such a long term prediction You may not use some type of input data, such as information about the time of the forecast produced by the current situation (for example, current traffic, weather, or other conditions) of. 此外,这样的较长期限的预报可以以比较短期限的预报更低地频率产生,并可以被产生来比较短期限的预报更能反映不同的未来时间段(例如,每小时而不是每15分钟)。 Further, such longer-term forecasts may be at a lower frequency to generate forecasts relatively short period, and may be compared to generate short-term forecasts better reflect different future time period (e.g., per hour instead of 15 minutes) .

[0191] 还可以以各种方式选择用于产生未来交通状况预测和/或预报的道路和/或道路段。 [0191] can also choose a variety of ways to predict future traffic conditions and / or road forecasts and / or road segments for production. 在一些实施例中,为多个地理区域(例如,市区)的每个产生未来交通状况预测和/或预报,其中每个地理区域具有多个互连的道路网络——可以以各种方式选择这样的地理区域,例如基于当前交通状况信息轻易可用(例如,基于在该区域中至少一些道路的道路交通传感器网络)和/或其中的交通拥堵是个显著问题。 In some embodiments, generating the predicted future traffic conditions and / or forecast, wherein each geographic region having a plurality of interconnected road network for each of a plurality of geographic areas (e.g., urban area) of - in various ways such selected geographical area, for example, based on current traffic condition information easily available (e.g., road traffic sensors in the road network based on at least some of the area) and / or where the traffic congestion is a significant problem. 在一些这样的实施例中,用于产生未来交通状况预测和/或预报的道路包括那些很容易得到当前交通状况信息的道路,而在其它实施例中,这样的道路的选择可以至少部分地基于一个或多个其它因素(例如,基于道路的尺寸或容量,例如包括高速路和主要公路;基于承载交通的道路交通规则,例如包括能主要替换到诸如高速路和主要公路等较大容量的道路的一级公路和封闭道路;基于道路的功能类别,例如由联邦高速路管理局所指定等)。 In some such embodiments, for generating road traffic conditions future prediction and / or forecast include those road traffic condition information is readily available current, while in other embodiments, such a selection path may be based at least in part one or more other factors (e.g., based on the size or capacity of the road, for example, including highway and major highways; based on the rules of the road traffic carrier, for example, it can include replacing the main road such as a larger capacity of the main highway roads and the like the highway and road closures; road based on functional categories, such as designated by the Federal Highway Administration, etc.). 在其它实施例中,可以为一个道路产生未来交通状况预测和/或预报,而无论它的尺寸和/或与其它道路的相互关系。 In other embodiments, the prediction of future traffic conditions may be generated and / or prediction of a road, regardless of its size and / or the relationship with other roads. 此外,可以以各种方式选择用于产生未来交通状况预测和/或预报的道路段,例如将每个道路交通传感器作为相异的段;为每个道路段而将多个道路交通传感器放在一起组成组(例如,降低产生独立预测和/或预报的数量,例如通过将特定数量的道路交通传感器放在一起组成组);选择道路段以便反映交通状况相同或充分类似(例如,强烈关联)的道路的逻辑相关部分;例如基于从交通传感器和/或其它来源(例如,从车辆和/或在道路上行驶的用户产生的数据,如在别处更详细所讨论地)来的交通状况信息;等。 Further, various manners can be selected for generating a predict future traffic conditions and / or forecast road segments, such as road traffic sensors each distinct section; and a plurality of road traffic sensors on each road segment together form the group (e.g., reduce the generation of the number of independent prediction and / or forecast, for example, by a certain number of road traffic sensors put together form the group); selecting road segments reflect the same or substantially similar to (e.g., strongly associated) traffic logically related part of the road; for example based on the traffic sensors and / or other sources (as discussed e.g., data generated from a vehicle and / or on the road users, as described in more detail elsewhere ground) to the traffic information; Wait.

[0192] 此外,在各个实施例中可以以不同的方式使用未来交通状况预测和/或预报信息,如在别处更详细所讨论地,包括在各个时间以各种方式(例如,通过将信息传输给蜂窝 [0192] Further, in various embodiments may be used in future traffic condition predictions and / or forecast information in a different manner, as described in more detail as discussed elsewhere, including, for example, by transmitting information in various ways (at various times to honeycomb

45移动电话和/或其它便携式消费设备;通过给用户显示信息,例如通过Web浏览器和/或应用程序;通过将信息提供给其它组织和/或给用户提供至少一些信息的实体,例如在分析和修改信息后执行信息提供的第三方等)将这样的信息提供给用户和/或组织(例如,响应请求,通过周期性发送信息等)。 45 the mobile phone and / or other portable consumer devices; by displaying information to the user, for example via a Web browser and / or application; by providing information to other tissues and / or entities to provide at least some information to the user, for example in the analysis and performing the modification information provided by third-party information, etc.) such information to the user and / or tissue (e.g., in response to the request, transmits information periodically, etc.). 例如,在一些实施例中,使用预测和/或预报信息来确定建议的行驶路线和/或时间,例如在开始位置和终点位置间通过道路网的最优路线和/或执行所示行驶的最优时间,并且这样的确定基于为一个或多个道路和/或道路段的多个未来时间的每个的预测和/或预报信息。 For example, in some embodiments, a prediction and / or forecast information to determine the recommended travel route and / or time, for example between the start position and end position by the road network optimum route and / or perform best shown with excellent time, and such a determination based on one or more roads and / or each of the plurality of predicted future time of the road segment and / or forecast information.

[0193] 此外,各种实施例为用户和其它客户端提供了各种机制来与一个或多个交通信息系统(例如,图3的数据样本管理系统350、RT信息提供系统363,和/或预测信息提供系统360等)交互。 [0193] Furthermore, various embodiments provide mechanisms for users and clients to other one or more of the traffic information systems (e.g., FIG. 3 of the Data Sample Manager system 350, RT information providing system 363, and / or prediction information providing system 360, etc.) interactions. 例如,一些实施例可以为产生请求并接收相应的响应的客户端提供交互控制(例如,客户端程序提供交互的用户界面,基于Web浏览器界面等),例如请求涉及当前和/或预测交通状况的信息和/或请求分析、选择,和/或提供涉及行驶路线的信息。 For example, some embodiments may provide interactive control to generate a request and receive client corresponding response (e.g., a client program providing an interactive user interface, Web browser-based interface, etc.), for example, the request relates to current and / or predicted traffic conditions information and / or request analysis, selection, and / or provide travel route information relates. 此外,一些实施例提供API ( “应用程序接口”),其允许客户端计算系统可编程地进行一些或全部请求,例如通过网络消息协议(例如,Web服务)和/或其它通信机制。 Further, some embodiments provide the API ( "application program interface"), which allows the client computing system to perform some or all of the programmable request, for example via a network messaging protocol (e.g., Web services) and / or other communication mechanisms.

[0194] 本领域的技术人员也能理解,在一些实施例中如上所讨论地由例程所提供的功能可以以替换地方式提供,例如可以分割到多个例程中或集中到几个例程。 [0194] Those skilled in the art can also be appreciated, as discussed above may alternatively be provided by the function routine manner provided in some embodiments, for example, may be divided into a plurality of routines or concentrated several embodiments Cheng. 类似地,在一些实施例中所示的例程可以提供比所描述的更多的功能,例如当其它所示的例程替换地分别缺少或包括这样的功能时,或当所提供的功能数量可选时。 Similarly, the routine shown in some embodiments may provide more functionality than is described, such as when other illustrated routines alternatively lack or include such functionality, or when the number of functions can be provided when the election. 此外,虽然各种操作都可以如所示地以特定方式(例如串行或并行)和/或特定顺序执行,但本领域的技术人员可以理解在其它实施例中这些操作也可以以其它顺序和方式执行。 In addition, while various operations may be performed as shown in a particular manner (e.g., serial or parallel) and / or a particular order, those skilled in the art will be appreciated that in other embodiments these operations may also be implemented in other orders and implementation. 本领域的技术人员还还能理解的是,上述讨论的数据结构可以以不同方式构建,例如将单个数据结构分割到多个数据结构中或将多个数据结构集中到一个数据结构中。 Those skilled in the art can also be appreciated that the data structures discussed above may be constructed in different ways, for example, a single data structure split into multiple data structures or data structure will be focused to a plurality of data structure. 类似地,在一些实施例中所示的数据结构可以存储比所述更多或更少的信息,例如当其它所示的数据结构替换地分别缺少或包括这样的信息时,或当所存储的信息的数量或类型可选时。 Similarly, the data structures shown in some embodiments may store more or less than the information, such as when other illustrated data structures instead lack or alternatively include such information, or when the stored information when the number or type of optional.

[0195] 从上述可以理解的是,尽管为示例的目的而在此描述了特定的实施例,但在不背离本发明的精神和范围的情况下可以进行各种修改。 [0195] It will be appreciated from the foregoing that, although for the purposes of illustration and described herein specific embodiments, but without departing from the spirit and scope of the present invention may be variously modified. 因此,本发明除所附权利要求及其在此引证元素外均不受限。 Accordingly, the present invention is in addition to the appended claims and outer elements cited herein are not limited. 此外,尽管本发明的特定方面以给定权利要求的形式进行了论述,但发明人设想以任何可用的权利要求形式涵盖本发明的各个方面。 In addition, while a particular aspect of the present invention are discussed in the form of a given claim, the inventors contemplated in any available claim form cover all aspects of the present invention. 例如,虽然本发明的一些方面当前仅可以被叙述为嵌入在计算机可读介质中,但类似的其它方面也可以包含。 For example, although some aspects of the present invention, the current can only be described as embodied in a computer-readable medium, but other similar aspects may be included.

46 46

Claims (56)

1. 一种计算机执行的方法,用于估算代表了在道路上行驶的车辆的数据样本,所述方法包括:接收一个或多个道路的一个或多个道路段的指示,每个道路段都具有多个关联的数据样本,每个数据样本都由多部车辆中的一个报告并指示了与所述道路段相对应的车辆的报告位置;和对于所述道路段的至少一个的每个,自动分析该条道路段的多个关联数据样本,来确定那些数据样本中不代表在所述道路段上实际车辆行驶状况的一个或多个,所确定的数据样本的至少一个的每个指示了报告数据样本的车辆的报告位置,而该报告位置并不相应于在所述道路段上的实际车辆行驶状况,并且所确定的数据样本的至少一个的每个都具有报告所述数据样本的车辆的关联方位而该关联方位并不相应于在所述道路段上的实际车辆行驶状况;和提供一个或多个指示来从后续 1. A computer-implemented method for estimating data sample represents a vehicle traveling on a road, the method comprising: receiving one or more road segments indicating one or a plurality of roads, each road segment a plurality of data samples associated with a report each data sample by multiple vehicles and indicates the position report with the road segment corresponding to the vehicle; and at least one for each of the road segment, automatic analysis of multiple associated data samples for the road segment piece of data samples to determine those data samples do not represent the road segment on the one or more actual vehicle driving condition, the determined at least one of each of the indicated sample reports report data of the vehicle position, and the report do not correspond to the actual location of the vehicle on the road segment driving condition, and the determined data samples each having at least one data sample reporting vehicle the orientation of the associated orientation does not correspond to the association of the road segment on the actual vehicle traveling condition; and providing one or more indications from the subsequent 用中去除所确定的数据样本,以便其它数据样本可用于辅助在所述道路段上的行驶。 Removing the determined data samples used in the other data samples may be used to assist in driving on the road segment.
2.根据权利要求1的方法,其中,对于至少一个道路段的一个或多个的每个,提供指示来为后续使用去除所确定的数据样本包括分析道路段的除了所确定的数据样本之外的关联数据样本,以确定在道路段上行驶的车辆的平均速度,并且包括指示所确定的平均速度以用来辅助在道路段上其它车辆的行驶。 2. The method of claim 1, wherein the at least one for each of a plurality of road segments or to provide an indication to use the data samples for subsequent removal than the determined data samples comprises in addition to analyzing the determined road segments associated data samples to determine an average speed of vehicles traveling on the road segment, and includes indicating the determined average speed to be used to assist in the travel of other vehicles on the road segment.
3.根据权利要求2的方法,其中,对于一个或多个道路段的每个,提供指示来为后续使用去除所确定的数据样本包括:分析道路段的除了所确定的数据样本之外的关联数据样本,以确定在道路段上行驶的车辆的交通流量,并且指示所确定的交通流量以用来辅助在道路段上其它车辆的行驶。 3. The method as claimed in claim 2, wherein, for each of the one or more road segments, used to provide an indication of the determined data samples removed for subsequent comprising: analyzing the associated data samples except the determined road segment data samples to determine the traffic flow on the road segment travel of the vehicle, and indicates the determined traffic volume to be used to assist in other vehicles traveling on the road segment.
4.根据权利要求1的方法,其中,对于一个或多个道路段的每个,确定道路段的不代表在道路段上的实际车辆行驶状况的一个或多个数据样本包括:确定那些数据样本的报告车辆位置相应于代表道路段上的实际车辆行驶状况的不感兴趣的部分道路。 4. The method of claim 1, wherein, for each of the one or more road segments, road segments determined driving situation does not represent one or more data samples of actual vehicle on a road segment comprising: determining those data samples the part of the road driving conditions are not interested in reporting on the location of the vehicle corresponds to a road segment represents the actual vehicle.
5.根据权利要求4的方法,其中,对于一个或多个道路段的至少一个的每个,所述道路部分至少是去往和/或来自所述道路段的低容量道路的一部分。 5. The method as claimed in claim 4, wherein, for at least one of each of the one or more road segments, at least part of the road to and / or from the low-capacity road portion of the road segment.
6.根据权利要求4的方法,其中,对于所述一个或多个道路段的至少一个的每个,所述道路部分是在所述道路段附近的相异道路的一部分。 6. The method as claimed in claim 4, wherein, for at least one of each of the one or more road segments, the road section is a distinct part of the road in the vicinity of the road segment.
7.根据权利要求4的方法,其中,对于所述一个或多个道路段的至少一个的每个,所述道路部分是作为所述道路段一部分的多个车道的子集。 7. The method as claimed in claim 4, wherein, for at least one of each of the one or more road segments, the road as the road segment is part of the subset of the portion of the plurality of lanes.
8.根据权利要求4的方法,其中,对于所述一个或多个道路段的至少一个的每个,所述道路部分是所述道路段向上和/或向下的坡道、与所述道路段的道路关联的交汇/分叉道路、与所述道路段的道路关联的交汇和/或分叉车道、与所述道路段的道路关联的支线车道、所述道路段的道路的路肩、和用于所述道路段的道路的故障区域的一个或多个中的至少一部分。 8. The method according to claim 4, wherein, for at least one of each of the one or more road segments, the road segments of the road section is upward and / or downward slope, the road associated road segment intersection / branching road, a road shoulder of a road and the road segment associated with the intersection and / or diverging lane, the road segment associated with the feeder lanes of the road, the road segment, and at least a portion of one or more defective area of ​​the road for the road segment.
9.根据权利要求4的方法,其中,对于所述一个或多个道路段的一个,所述不感兴趣的部分道路是所述一个道路段的一部分。 9. The method as claimed in claim 4, wherein, for the one or more road segments, the part of the road is not interested in a portion of the road segment.
10.根据权利要求4的方法,其中,对于所述一个或多个道路段的一个,所述不感兴趣的部分道路是与所述一个道路段相异的另一个道路段的至少一部分。 10. The method according to claim 4, wherein, for the one or more road segments, the part of the road is not of interest at least a portion of the road segment to another road segment distinct.
11.根据权利要求1的方法,其中,对于所述至少一个道路段的一个,与所述一个道路段关联的多个数据样本的一些还与一个或多个其它相异道路段关联,并且所确定的用于所述一个道路段的一个或多个数据样本来自所述至少一些数据样本。 11. The method of claim 1, wherein the number is also associated with one or more other distinct road segments for a road segment associated with said at least one of a plurality of road segment data samples, and the determined for the one or more data samples for a road segment from said at least some of the data samples.
12.根据权利要求1的方法,还包括对于所述道路段的一个,至少部分地基于并不感兴趣的一个道路段,自动确定用于所述不感兴趣的一个道路段的多个关联的数据样本,并提供一个或多个指示来为后续使用去除所述多个关联的数据样本。 12. The method of claim 1, further comprising a road segment for the, at least in part, on a section of road is not of interest, automatically determining a plurality of associated data samples for a road segment of interest is not the and providing one or more indications of the plurality of data samples are removed for subsequent use associated.
13.根据权利要求12的方法,其中,至少部分地基于作为不感兴趣的功能道路类来确定所述一个道路段是不感兴趣的。 13. The method of claim 12, wherein, at least in part as the functional road classes are not of interest to determine the one road segment based is not of interest.
14.根据权利要求12的方法,其中,至少部分地基于在所述一个道路段上的实际车辆交通量来确定所述一个道路段是不感兴趣的。 14. The method of claim 12, wherein the at least partially based on a road segment of the actual vehicle traffic to determine the one road segment is not of interest.
15.根据权利要求12的方法,其中,至少部分地基于对在所述一个道路段上车辆交通的当日(intra-day)变化量的确定和/或对在所述一个道路段上车辆交通的日间(inter-day)变化量的确定,来确定所述一个道路段是不感兴趣的。 15. The method of claim 12, wherein, at least in part based on the determination (intra-day) the amount of change of a road segment on the day of vehicular traffic and / or the vehicle on a road segment of traffic (inter-day) determining the amount of change during the day, to determine the one road segment is not of interest.
16.根据权利要求12的方法,其中,至少部分地基于对在所述一个道路段上实际的交通拥堵量来确定所述一个道路段是不感兴趣的。 16. The method of claim 12, wherein at least part of the actual amount of traffic congestion on the one road segment to determine the one road segment based is not of interest.
17.根据权利要求12的方法,其中,至少部分地基于对在所述一个道路段上交通拥堵的当日变化量的确定和/或对在所述一个道路段上交通拥堵的日间变化量的确定来确定所述一个道路段是不感兴趣的。 17. The method of claim 12, wherein, at least in part based on the determination of the amount of change in a day of traffic congestion road segment and / or the amount of change of the traffic congestion on a road segment Day determining a determination of the road segment is not of interest.
18.根据权利要求1的方法,还包括自动确定不与不感兴趣的任意道路段关联的一个或多个数据样本,并提供一个或多个指示来为后续使用去除所述一个或多个数据样本。 18. The method of claim 1, further comprising automatically determining not associated with any road segment of interest is not one or more data samples and provides one or more indications to remove said one or more data samples for subsequent use .
19.根据权利要求1的方法,其中,对于所述至少一个道路段的一个或多个的每个,对道路段的不代表在所述道路段上的实际车辆行驶状况的一个或多个数据样本的确定包括: 至少部分地基于一个或多个数据样本的报告位置确定不具代表性的一个或多个数据样本。 19. The method of claim 1, wherein for each of said at least one or a plurality of road segments of the road segment does not represent an actual vehicle on the road segment or a plurality of traveling condition data determining a sample comprising: determining at least partially the one or more data samples are unrepresentative based on reported locations of one or more data samples.
20.根据权利要求19的方法,其中,对于所述一个或多个道路段的每个,所述道路段的多个关联数据样本的每个都指示了报告数据样本的车辆的速度,并且对所述道路段的不具代表性的一个或多个数据样本的确定还至少部分地基于由所述一个或多个数据样本所指示的速度。 20. The method of claim 19, wherein, for each of the one or more road segments, the plurality of associated data samples for the road segment indicates the speed of the vehicle, each report data sample, and for determining one or more data samples are not representative of the road segment further based at least in part by the speed of the one or more data samples indicated.
21.根据权利要求20的方法,还包括为所述一个或多个道路段的至少一个的每个,为所述道路段的多个关联数据样本的至少一些的每个,通过使用由报告所述数据样本的车辆报告的多个数据样本指示的报告位置来估算所述数据样本的指示速度。 21. The method of claim 20, further comprising at least one of the one or each of the plurality of road segments, each of at least some of the plurality of associated data samples for the road segment by using the report report the vehicle position data reported by said plurality of data samples indicative of the sample to estimate the speed of the data samples indicate.
22.根据权利要求19的方法,其中,对于所述一个或多个道路段的每个,用于所述道路段的多个关联数据样本每个都具有报告所述数据样本的车辆的关联方位,并且其中确定所述道路的一个或多个数据样本是不具有代表性的还至少部分地基于与所述一个或多个数据样本关联的方位。 Associated with the orientation of the vehicle 22. The method as claimed in claim 19, wherein, for each of the one or more road segments, a plurality of data samples for the road segment associated with each of said data samples having a reporter and wherein said determining a plurality of road data or samples are not representative of the orientation of at least a further part associated with the data samples based on one or more.
23.根据权利要求22的方法,还包括对于所述一个或多个道路段的至少一个的每个, 以及对于用于所述道路段的多个关联数据样本的至少一些的每个,通过使用由报告所述数据样本的车辆报告的多个数据样本指示的报告位置来估算与所述数据样本关联的方位。 23. The method of claim 22, further comprising using for said each of the at least one or a plurality of road segments, and for each of at least some of the plurality of associated data samples for the road segment by reporting location reports reported by the plurality of data samples of said data indicative of the vehicle to estimate the sample orientation data associated with the sample.
24.根据权利要求22的方法,其中,所述一个或多个道路段的一个是包括在两个相反方向上行驶的车辆的道路的一部分,其中所述一个道路段相应于在所述两个方向上的一个上行驶的车辆,至少部分地基于与所述一个或多个数据样本关联的方位确定所述道路段的不具有代表性的一个或多个数据样本包括:确定其关联方位与在所述两个方向的另一个上的行驶相对应的数据样本对所述一个道路段不具有代表性。 24. The method of claim 22, wherein the one or more road segments are part comprises two opposite directions in a vehicle traveling road, wherein the road segment corresponding to one of the two a vehicle traveling direction, at least partially determined based on the road segment associated with the one or more data samples bearing one or more data samples are not representative comprising: determining the orientation of its associated with the the two directions of travel on another data corresponding sample is not representative of the one road segment.
25.根据权利要求22的方法,其中,所述一个或多个道路段的一个是包括具有在多个方向上行驶的车辆的多个车道的道路的一部分,所述一个道路段相应于具有在所述多个方向的一个或多个上行驶的车辆的多个车道的子集,至少部分地基于与所述一个或多个数据样本关联的方位确定所述一个道路段的不具有代表性的一个或多个数据样本包括:确定其关联方位并不相应于所述一个或多个方向的数据样本对所述一个道路段不具有代表性。 25. The method of claim 22, wherein the one or more road segments comprising a part having a plurality of lanes in the traveling direction of the vehicle of the plurality of road, a road segment corresponding to the having subset of the one or more directions on a plurality of vehicles traveling in lanes of a plurality of at least partially determining the road segment is not a representative based on the orientation associated with the one or more data samples are one or more data samples comprises: determining the orientation of its associated or not data corresponding to said sample a plurality of directions of the road segment does not have a representative.
26.根据权利要求22的方法,其中,所述一个或多个道路段的一个与一个或多个其它道路的一个或多个其它道路段重叠,在所述一个道路段上行驶的车辆行驶在与在所述其它道路段上行驶的车辆的一个或多个其它方向相异的一个或多个方向上,并且至少部分地基于与所述一个或多个数据样本关联的方位确定所述一个道路段的一个或多个数据样本不具有代表性的包括:确定其关联方位不相应于所述一个道路段的所述一个或多个方向的数据样本对所述一个道路段不具有代表性。 26. The method of claim 22, wherein the one or more road segments with one or more of a plurality of other roads or other road segments overlap, traveling on a road segment the vehicle is traveling one or more of a direction different from the traveling road segment on the other vehicle or more other directions, and based in part on a determination of the azimuth associated with the road data of at least one or more of the sample one or more data segments are not representative samples comprises: determining the orientation of its associated does not correspond to a road segment of the data sample one or more directions of the one road section is not representative.
27.根据权利要求1的方法,其中,对于所述至少一个道路段的一个或多个的每个,对所述道路段的不代表在所述道路段上实际车辆行驶状况的一个或多个数据样本的确定包括将所述一个或多个数据样本与所述道路段的其它数据样本的至少一些进行比较。 27. The method of claim 1, wherein, for each of said at least one or a plurality of road segments, does not mean that one or more of the road segment in the road segment on the actual vehicle driving condition determining the data sample comprises comparing at least some of the other data samples and the one or more data samples for the road segment.
28.根据权利要求1的方法,其中,对于所述至少一个道路段的一个或多个的每个,对所述道路段的不代表在所述道路段上实际车辆行驶状况的一个或多个数据样本的确定包括:识别在感兴趣或不感兴趣的道路段上的实际车辆行驶状况的子集,并确定所述一个或多个数据样本是否相应于所识别的子集。 28. The method of claim 1, wherein, for each of said at least one or a plurality of road segments, does not mean that one or more of the road segment in the road segment on the actual vehicle driving condition determining the data samples comprises: identifying a subset of interest on the road segment or not interested in the actual running condition of the vehicle, and determining whether the one or more data samples corresponding to the identified subset.
29.根据权利要求1的方法,还包括接收对其每个都指示车辆的报告位置的多个数据样本的一个或多个指示,至少部分地基于与至少一个道路段各自的关联一个或多个位置相对应的数据样本的报告位置,将所述多个数据样本中的至少一些中的每个与所述道路段的至少一个关联。 29. The method of claim 1, further comprising a plurality of data indicative of one or more samples each receive a report indicating its position in the vehicle, based on at least one road segment associated with a respective one or more at least partially report position corresponding data samples, at least one associated with each of the road segment at least some of said plurality of data samples.
30.根据权利要求四的方法,其中,所述多个数据样本每个都具有所述数据样本的车辆的关联方位,将数据样本与道路段关联还至少部分地基于与所述道路段的关联一个或多个方位相对应的所述数据样本的车辆的关联方位。 30. The method as claimed in claim IV, wherein said plurality of data samples each having the orientation of the vehicle associated with data samples, the data samples associated with the road segment associated with the further at least partially based on the road segment orientation of the vehicle associated with the one or more data samples corresponding to the orientation.
31.根据权利要求30的方法,还包括为多个数据样本的至少一些的每个,使用由相应于数据样本的车辆的多个数据样本所指示的报告位置估算与所述数据样本关联的方位。 At least some of each of the estimates using the associated position data reported by the sample data samples corresponding to a plurality of data samples of the vehicle indicated by an orientation 31. The method of claim 30, further comprising a plurality of data samples .
32.根据权利要求四的方法,其中,将数据样本与道路段关联还至少部分地基于所述数据样本除了报告位置之外的车辆的一个或多个车辆行驶特征。 32. The method according to claim four, wherein the data samples associated with the road segment further at least partially based on one or more vehicle data samples except the reported position of the vehicle running characteristics.
33.根据权利要求四的方法,其中,将数据样本与道路段关联还至少部分地基于将与所述道路段关联的一个或多个位置延伸一个或多个距离,所述一个或多个距离至少部分地基于报告位置的精确性而确定。 33. The method according to claim four, wherein the one or more locations associated with the road segment data samples further at least partially based on the road segment associated with the one or more distances extending, the one or more distance at least in part determined based on the accuracy of the reported position.
34.根据权利要求33的方法,其中,针对数据样本将与道路段关联的一个或多个位置延伸的一个或多个预定距离至少部分地基于数据样本源的类型。 34. The method of claim 33, wherein the data samples for at least a part associated with a road segment or a plurality of positions extending in a predetermined distance or more samples based on a type of data source.
35.根据权利要求1的方法,其中,对于至少一些道路段的一个或多个的每个,所述道路段的多个关联数据样本还包括多个数据样本,其每个都由监视所述道路段的交通传感器报告,并且每个都反映了所述道路段上的相应于所述交通传感器的一个或多个位置。 35. The method of claim 1, wherein, for at least some of the one or more road segments associated with each of a plurality of data samples, the road segment further comprising a plurality of data samples, each by monitoring the traffic sensor reports road segments, and each reflects a corresponding sensor to the vehicle on the road segment or a plurality of positions.
36.根据权利要求35的方法,还包括接收对多个数据样本的一个或多个指示,每个数据样本都由监视多个道路段的多个交通传感器报告,调整所述多个数据样本的至少一些以统计报告这些数据样本的交通传感器,并且为所述多个数据样本的至少一些的每个,至少部分地基于由匹配与所述至少一个道路段的每个关联的一个或多个位置的数据样本所反映的一个或多个位置,将所述数据样本与所述道路段中的至少一个关联。 36. The method of claim 35, further comprising receiving one or more indications of a plurality of data samples, each data sample by a plurality of monitoring traffic sensors report plurality of road segments, a plurality of adjusting the data samples at least some of these statistical reports traffic sensor data samples and for each of at least some of said plurality of data samples, at least in part on a match by each associated with the at least one road segment or a plurality of positions one or more locations reflected in data samples, at least one of the data samples associated with the road segment.
37.根据权利要求1的方法,其中,对于至少一个道路段的一个或多个的每个,对所述道路段的不代表在所述道路段上实际车辆行驶状况的一个或多个数据样本的确定还包括识别由在所述道路段上行驶的单部车辆所报告的多个数据样本,并基于来自所识别的多个数据样本的合并信息确定识别出的多个数据样本不具代表性。 37. The method of claim 1, wherein the at least one for each of a plurality of road segments, or on the road segment does not mean that the road segment on the actual vehicle driving condition or a plurality of data samples determining a plurality of data samples further includes identifying a plurality of data samples from a single vehicle traveling on the road segment is reported, based on the merge information from the identified plurality of data samples to determine the identified unrepresentative.
38.根据权利要求1的方法,其中,对于至少一个道路段的一个或多个的每个,所述道路段的多个关联数据样本每个还反映了数据样本的车辆在其报告位置处的报告时间,对所述道路的所述多个关联数据样本的自动分析还相应于预定时间段,以便在所述道路段上的实际车辆行驶状况是在预定时间段内的行驶状况。 38. The method of claim 1, wherein the plurality of associated data samples for each of the one or more of the at least one road segments, the road segment data for each sample is also reflected at the vehicle in its reported location reporting time, the automatic analyzer of the plurality of road associated data samples corresponding to a further predetermined period of time, so that on the road segment is actual running condition of the vehicle running condition at a predetermined period of time.
39.根据权利要求1的方法,还包括,对于多个相异时间段的每个,接收所述道路段中的一个的多个关联数据样本,每个关联数据样本都反映了在所述时间段内在所述道路段上的报告时间处的车辆的报告位置,并且其中为所述时间段的每个执行用于所述的一个道路段的自动分析,该自动分析基于其报告时间在所述时间段内的数据样本。 39. The method of claim 1, further comprising, for each of a plurality of distinct time periods, receiving a plurality of associated data samples for a road segment, each associated sample data are reflected in the time internal report the position of the vehicle at the time of the report on the road segment, and wherein each of the automatic analyzer is executed for the time period of the segment of a road, the automatic analyzer based on their reported time period in the period of data samples.
40.根据权利要求1的方法,其中,对于至少一个道路段的一个或多个的每个,以基本上实时的方式执行对所述道路段的不代表在所述道路段上实际车辆行驶状况的一个或多个数据样本的确定。 40. The method of claim 1, wherein, for each of one or more of the at least one road segments, performing a substantially real time manner for the road segment does not represent actual vehicle travel on the road segment determining one or more data samples.
41.根据权利要求40的方法,其中,在由车辆报告数据样本前,通过行驶在所述道路段上的车辆获取与所述道路的至少一些关联的多个数据样本的至少一些,在获取了至少一个数据样本的一个或多个后以基本上实时的方式产生至少一些数据样本的报告。 41. The method of claim 40, wherein, before the data samples reported by the vehicle, by traveling on the road segment of the road vehicle to acquire at least some of at least some of the plurality of data samples associated in the acquired at least one of the one or more data samples generating at least some data samples reported in substantially real-time manner.
42. 一种被配置来估算代表行驶车辆的数据样本的计算系统,包括:第一组件,其被配置来为多个道路的每个接收对道路的多个数据样本的指示,每个数据样本反映道路附近的车辆位置;和数据样本过滤组件,其被配置来为多个道路的至少一些,自动确定所述道路的多个数据样本中的其所反映的车辆位置并不相应于在所述道路上所感兴趣的车辆行驶状况的一个或多个数据样本;和提供对除了所确定的数据样本之外的所述道路的多个数据样本的一个或多个指示,以便所指示的数据样本能被使用来辅助在道路上的行驶。 42. A computing system configured to estimate data samples representing traveling vehicles, comprising: a first component, each of which is configured to indicate the reception of a plurality of roads on the road a plurality of data samples, each data sample reflecting the nearby road vehicle position; data samples and filter assembly, which is configured to at least some of the plurality of the road, automatically determining a plurality of vehicle position they reflect the data samples is not a road corresponding to the or a running condition of the vehicle on a road more data samples of interest; and providing a plurality of data samples for the road in addition to the determined data sample of one or more indications to the data samples can be indicated It is used to assist in travel on the road.
43.根据权利要求42的计算系统,其中,对于多个道路的一个或多个的每个,对所述道路的其所反映的车辆位置并不相应于在所述道路上所感兴趣的车辆行驶状况的数据样本的确定包括:确定反映了不与道路的预定位置相匹配的车辆位置。 43. The computing system of claim 42, wherein, for each one of a plurality of one or more roads, the road vehicle position they reflect not corresponding to the vehicle traveling on a road of interest determine the status of data samples comprises: determining vehicle position does not reflect the position of the predetermined road matches.
44.根据权利要求42的计算系统,其中,所述数据样本过滤组件还被配置来为至少一个多个道路的一个或多个的每个,至少部分地基于所述道路的一个或多个预定方位,自动确定所述道路的所反映的一个或多个车辆行驶方位并与在所述道路上所感兴趣的车辆行驶方位的一个或多个数据样本相对应。 44. The computing system of claim 42, wherein the data component is further configured to filter samples to each of a plurality of at least partially at least one road based on one or more of said plurality of predetermined road or position, automatically determining one or more of the road vehicle running direction and reflected on the road with the vehicle travel of interest orientation of one or more corresponding data samples.
45.根据权利要求42的计算系统,其中,所述第一组件和所述数据样本过滤组件每个都包括在所述计算系统的存储器中执行的指令。 45. The computing system of claim 42, wherein said first component and said data sample filter assembly each include instructions for execution in memory of the computing system.
46.根据权利要求42的计算系统,其中,所述第一组件包括接收装置,用于针对多个道路的每个,接收对所述道路的多个数据样本的指示,每个数据样本反映在所述道路附近的车辆的位置,并且其中所述数据样本过滤组件包括装置,其为所述多个道路的至少一些的每个,自动确定所述道路的多个数据样本中的其所反映的车辆位置并不相应于在所述道路上所感兴趣的车辆行驶状况的一个或多个数据样本,并提供对除了所确定的数据样本之外的所述道路的多个数据样本的一个或多个指示,以便所指示的数据样本能被使用来辅助在道路上的行驶。 46. ​​The computing system of claim 42, wherein said first component comprises a receiving means for each of said receiving an indication of a plurality of road data samples for a plurality of roads, each data sample is reflected in the position of the vehicle in the vicinity of roads, and wherein said filter assembly comprises a data sample means that each of at least some of the plurality of road, automatically determining a plurality of data samples for the road in which it is reflected do not correspond to the position of the vehicle on the road the vehicle of interest or a plurality of traveling condition data samples, and provides a road in addition to said data samples of the plurality of the determined one or more data samples indicating, to assist in driving on the road indicated by the data samples to be used.
47. 一种计算机执行的方法,用于估算由在道路上行驶的车辆所报告的数据样本,该数据样本包括有关车辆行驶状况的信息,所述方法包括:接收对一个或多个道路的多个道路段的指示;接收有关多个道路段的当前交通状况的信息,所接收的信息包括多个数据样本,每个数据样本都由多个车辆中的一个报告,并且反映该车辆在报告地理位置处的报告速度,还反映该车辆的报告行驶方位;和对于多个道路段的每个,通过以下步骤,基于被识别来代表所述道路段上的行驶状况的数据样本,而为所述道路段估算交通状况:从多个数据样本中识别一组多数据样本,该组数据样本所报告的地理位置在相对于所述道路段的一个或多个预定地理位置的预定距离内,并且该组数据样本所报告的行驶方位在相对于所述道路段的一个或多个预定方位的预定偏差内;至少部 47. A computer-implemented method for estimating the data samples by a vehicle traveling on a road in the reported sample data includes information about the running condition of the vehicle, the method comprising: receiving a plurality of the one or more roads indicating a road segment; receiving current traffic conditions of the multiple road segments of information, the received information includes a plurality of data samples, each data sample by a report plurality of vehicles, and the vehicle is reflected in the geographic report velocity at the position report, the report also reflects the orientation of the traveling vehicle; and for each of the plurality of road segments, by the following steps, based on the identified data samples to represent the driving situation on the road segment, and to the estimating road traffic conditions segments: identifying a set of multiple data samples from the plurality of data samples, the set of data samples reported location within a predetermined distance with respect to a plurality of the predetermined road segment or geographic location, and the set of data samples with the reported position within a predetermined deviation with respect to one of said plurality of road segments or predetermined orientation; at least a portion 分地基于所确定的不与感兴趣的车辆行驶状况所在的道路段的预定部分相对应的数据样本的报告地理位置,自动确定该组的一个或多个数据样本不代表所述道路段上的实际车辆行驶状况;从所述组去除所确定的不代表所述道路段上的实际车辆行驶状况的数据样本;和在去除后,使用在组中剩余的数据样本推断在所述道路段上行驶的所有车辆的交通状况,以便可以得到基于数据样本所推断的交通状况而使用来辅助在所述道路段上的行驶。 Partially based on a predetermined portion of the determined road segment the vehicle is not traveling condition of interest location where the report corresponding to the data samples, determining the automatic road segment does not represent one or more of the group of data samples actual vehicle travel; removing data samples do not represent the actual vehicle on the road segment is determined from the traveling condition of the group; and after removal, used in the group with the remaining data samples estimation on the road segment all traffic conditions of the vehicle, so that the sample can be obtained based on the data with the traffic situation estimation is used to assist in the road segment.
48.根据权利要求47的方法,其中,多个道路段的一个道路段相应于具有多个车道的高速路的第一部分,其中用于所述一个道路段的预定地理位置包括覆盖用于所述第一部分的高速路的多个车道的地理区域,所述地理区域延伸的预定距离至少部分地基于用于确定为所述一个道路段识别出的组的至少一些数据样本的报告地理位置的那种位置确定设备的精度,其中用于所述一个道路段的预定方位包括与所述高速路的第一部分的多个车道上行驶的车辆的方向相对应的一个或多个方位,并且相对于所述一个道路段的一个或多个预定方位的预定偏差至少部分地基于方位确定设备的精确度,所述方位确定设备用于针对所述一个道路段识别出的组的至少一些数据样本来确定报告行驶方位。 48. The method of claim 47, wherein a plurality of road segment corresponding to road segments of a first portion having a plurality of lanes of the highway, wherein a predetermined location for the road segments comprising a cover for the geographic area of ​​the plurality of highway lane first portion of the predetermined distance from the geographic area that extends at least partially based on the report of the determined geographic location for a road segment identified group of at least some of the data samples location determination accuracy of the device, wherein a predetermined orientation for the road segment comprises one or more orientation directions of the first portion of the plurality of lanes of the highway corresponding to a vehicle traveling, and with respect to the a road segment of a predetermined deviation or more predetermined orientation at least partially based on the accuracy of the position-determining device, a device for determining the orientation of at least some of the data of the group of a road segment identified in the report is determined with a sample orientation.
49.根据权利要求48的方法,其中,所感兴趣的车辆行驶状况所在的所述一个道路段的预定部分包括高速路的一个或多个车道,为所述一个道路段识别出的被确定为不能代表在所述一个道路段上的实际车辆行驶状况的组的数据样本中的一个是其报告地理位置被确定为与在高速路的上和/或下的坡道相对应的数据样本。 49. The method of claim 48, wherein the vehicle traveling condition of interest located a predetermined portion of a road segment comprises one or more lanes of the highway, a road segment for said identified is determined to not be data samples representative of a road segment on the actual vehicle behavior is set in a location which is determined to report the data samples with the ramp and / or on the highway at the corresponding.
50.根据权利要求48的方法,其中,所述感兴趣的车辆行驶状况所在的所述一个道路段的预定部分包括所述高速路的一个或多个车道,并且其中为所述一个道路段识别出的被确定为不能代表在所述一个道路段上的实际车辆行驶状况的组的数据样本中的一个是其报告地理位置被确定为与交汇/分叉道路或高速路附近的车道相对应的数据样本。 50. The method of claim 48, wherein the vehicle traveling condition of interest located a predetermined portion of a road segment comprises one or more lanes of the highway, and wherein said identifying a road segment the data samples is determined not represent the one road segment in the actual vehicle behavior is set in a location which is determined to report the intersection / diverging lane highway or near a road corresponding data samples.
51.根据权利要求48的方法,其中,所述感兴趣的车辆行驶状况所在的所述一个道路段的预定部分包括所述高速路的车道的子集,并且其中为所述一个道路段识别出的被确定为不能代表在所述一个道路段上的实际车辆行驶状况的组的数据样本中的一个是其报告地理位置被确定为与不在车道的子集中的高速路的车道的相对应数据样本。 51. The method of claim 48, wherein the vehicle traveling condition of interest located a predetermined portion of the subset of road segments comprises the highway lane, and wherein said identified one road segment data samples is determined to be not representative of a road segment on the actual vehicle driving condition is set in a location which is determined as the report data corresponding to the sample lane and the lane is not in the subset highway .
52.根据权利要求48的方法,其中,为所述一个道路段识别出的被确定为不能代表在所述一个道路段上的实际车辆行驶状况的组的数据样本中的一个是来自行驶在与所述高速路的相异的第二部分相对应的另一道路段上的车辆、并被确定为与所述一个道路段不正确地关联的数据样本。 52. The method of claim 48, wherein said identified one road segment is determined as not representative of sample data on a road segment of the actual vehicle travel in a group from traveling with the distinct second portion corresponding to a highway vehicle on the road segment to another, and data samples incorrectly identified as associated with the one road segment.
53.根据权利要求48的方法,其中,所述位置确定设备的类型是全球定位系统(GPS)设备类型,并且所述地理区域延伸的预定距离对应于这样的距离,在该距离内来自所述类型的GPS设备的读数是精确的。 53. The method of claim 48, wherein said type of location determining device is a global positioning system (GPS) device type, and the predetermined distance corresponding to the geographic region extending to such a distance, the distance from the inside reading type of GPS devices are accurate.
54.根据权利要求47的方法,其中,对于所述多个道路段的一个或多个的每个,自动确定组中的一个或多个数据并不代表在所述道路段上的实际车辆行驶状况还至少部分地基于:报告那些数据样本的车辆的除了报告地理位置之外的一个或多个行驶特性,所述一个或多个行驶特性包括那些数据样本的报告速度所反映的车辆速度。 The actual vehicle 54. The method according to claim 47, wherein, for each of a plurality of said plurality of road segments or, automatically determining one or more of the group does not represent the data in the traveling on the road segment Availability is also at least partially based: in addition to the reported location of one or more characteristics of the vehicle running data samples reported that, with the one or more characteristics include those reported speed of data sample reflected vehicle speed.
55.根据权利要求47的方法,其中,多个数据样本的每个还指示了与数据样本的报告速度、报告地理位置和报告行驶方位相关联的报告时间,其中在多个相异时间段的每个执行多个道路段的每个的交通状况的估算,还执行在时间段内对道路段的数据样本的组的识别,以便所识别的组的数据具有相应于所述时间段的报告时间。 55. The method of claim 47, wherein each of the plurality of data samples and further indicates the reported speed of data sample, and reporting location reports associated with position reporting time, wherein a plurality of distinct time periods each execution of the estimation of each of the plurality of traffic conditions of the road segments, also performs the identification of the set of data samples in the road segment period, so that the identified data set having a period corresponding to the time of the report .
56.根据权利要求47的方法,其中,反复接收与所述多个道路段的当前交通状况相关的数据样本以反映不断改变的交通状况,其中以实时的方式为近来接收的数据样本执行对所述多个道路段的每个的交通状况的估算,使用所述组中剩余的数据样本来推断在所述道路段上行驶的所有车辆的交通状况包括:确定剩余的数据样本的平均速度,基于所确定的平均速度推断在所述道路段上行驶的所有车辆的平均速度,并将有关所推断的平均速度的信息提供给一个或多个考虑将要在所述道路段上行驶的人。 56. The method according to claim 47, wherein the sample is repeatedly received data relating to the current traffic condition of the plurality of road segments to reflect changing traffic conditions, which the real time data samples is performed on the recent received Estimation of said traffic conditions of each of the plurality of road segments, the group using the remaining data samples to infer the traffic situation for all vehicles traveling on the road segment comprises: determining an average velocity of the remaining data samples, based on the determined average velocity inferred average speed of all vehicles traveling on the road section, and provided to one or more considered to be traveling on the road segment information about the person inferred average speed.
CN201110221624.2A 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources CN102394009B (en)

Priority Applications (19)

Application Number Priority Date Filing Date Title
US77894606P true 2006-03-03 2006-03-03
US60/778,946 2006-03-03
US78974106P true 2006-04-05 2006-04-05
US60/789,741 2006-04-05
US11/431,980 2006-05-11
US11/432,603 2006-05-11
US11/432,603 US20070208501A1 (en) 2006-03-03 2006-05-11 Assessing road traffic speed using data obtained from mobile data sources
US11/431,980 US20070208493A1 (en) 2006-03-03 2006-05-11 Identifying unrepresentative road traffic condition data obtained from mobile data sources
US11/438,822 US7831380B2 (en) 2006-03-03 2006-05-22 Assessing road traffic flow conditions using data obtained from mobile data sources
US11/438,822 2006-05-22
US11/444,998 US8014936B2 (en) 2006-03-03 2006-05-31 Filtering road traffic condition data obtained from mobile data sources
US11/444,998 2006-05-31
US11/473,861 US7912627B2 (en) 2006-03-03 2006-06-22 Obtaining road traffic condition data from mobile data sources
US11/473,861 2006-06-22
US83870006P true 2006-08-18 2006-08-18
US60/838,700 2006-08-18
US11/540,342 US7706965B2 (en) 2006-08-18 2006-09-28 Rectifying erroneous road traffic sensor data
US11/540,342 2006-09-28
CN200780015916.22007.03.02 2007-03-02

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN 200780015916 Division CN101438335B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources

Publications (2)

Publication Number Publication Date
CN102394009A true CN102394009A (en) 2012-03-28
CN102394009B CN102394009B (en) 2014-05-14

Family

ID=38181159

Family Applications (6)

Application Number Title Priority Date Filing Date
CN201110221617.2A CN102394008B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources
CN 201110220737 CN102254434B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources
CN201110221624.2A CN102394009B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources
CN 200780015916 CN101438335B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources
CN201110221478.3A CN102289935B (en) 2006-03-03 2007-03-02 Use the data estimation road traffic condition from Mobile data source
CN201110221620.4A CN102289936B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources

Family Applications Before (2)

Application Number Title Priority Date Filing Date
CN201110221617.2A CN102394008B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources
CN 201110220737 CN102254434B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources

Family Applications After (3)

Application Number Title Priority Date Filing Date
CN 200780015916 CN101438335B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources
CN201110221478.3A CN102289935B (en) 2006-03-03 2007-03-02 Use the data estimation road traffic condition from Mobile data source
CN201110221620.4A CN102289936B (en) 2006-03-03 2007-03-02 Assessing road traffic conditions using data from mobile data sources

Country Status (7)

Country Link
EP (2) EP2278573B1 (en)
JP (1) JP2009529187A (en)
CN (6) CN102394008B (en)
AT (1) AT523869T (en)
AU (1) AU2007224206A1 (en)
ES (2) ES2373336T3 (en)
WO (1) WO2007103180A2 (en)

Families Citing this family (83)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6587781B2 (en) 2000-08-28 2003-07-01 Estimotion, Inc. Method and system for modeling and processing vehicular traffic data and information and applying thereof
US7620402B2 (en) 2004-07-09 2009-11-17 Itis Uk Limited System and method for geographically locating a mobile device
JP4924407B2 (en) 2007-12-25 2012-04-25 富士通株式会社 Sensor diagnostic method and sensor diagnostic apparatus
JP4935704B2 (en) * 2008-02-14 2012-05-23 アイシン・エィ・ダブリュ株式会社 Parking lot congestion state determination device, parking lot congestion state determination method, and computer program
JP4983660B2 (en) 2008-03-14 2012-07-25 アイシン・エィ・ダブリュ株式会社 Navigation system and route search method
GB0901588D0 (en) 2009-02-02 2009-03-11 Itis Holdings Plc Apparatus and methods for providing journey information
JP5378002B2 (en) * 2009-02-19 2013-12-25 アイシン・エィ・ダブリュ株式会社 Vehicle motion estimation device, vehicle motion estimation method, and vehicle motion estimation program
DE112009004441T5 (en) * 2009-03-03 2012-08-09 Toyota Jidosha K.K. The vehicle drive assist device
CN101694743B (en) 2009-08-25 2011-09-21 北京世纪高通科技有限公司 Method and device for predicting road conditions
CN102032911B (en) * 2009-09-29 2014-05-28 宏达国际电子股份有限公司 Vehicle navigation method, system and computer program product
CN102262819B (en) 2009-10-30 2014-10-15 国际商业机器公司 Method and device for determining real-time passing time of road based on mobile communication network
US9406229B2 (en) * 2009-11-12 2016-08-02 Gm Global Technology Operations, Llc Travel lane advisor
US8620569B2 (en) 2009-12-17 2013-12-31 Toyota Jidosha Kabushiki Kaisha Vehicle control device
CN101782396B (en) * 2010-03-05 2011-12-28 中国软件与技术服务股份有限公司 A navigation method and a navigation system
JPWO2011125185A1 (en) * 2010-04-07 2013-07-08 トヨタ自動車株式会社 Vehicle travel support device
JP5195848B2 (en) * 2010-08-31 2013-05-15 株式会社デンソー Traffic situation prediction device
KR101506927B1 (en) * 2010-09-16 2015-04-06 에스케이플래닛 주식회사 System for collecting of traffic information, revision device of valid sampling and method for measurement of each average velocity of group, and recording medium thereof
KR101776807B1 (en) 2010-09-16 2017-09-19 에스케이텔레콤 주식회사 System for collecting of traffic information, revision device of valid sampling and method for measurement of velocity, and recording medium thereof
CN102446413A (en) * 2010-09-30 2012-05-09 西门子公司 Method and device for acquiring path information based on switching information of mobile terminal
BE1019524A3 (en) * 2010-09-30 2012-08-07 Be Mobile Nv System and method for travel time measurement.
KR101508136B1 (en) * 2010-10-22 2015-04-06 에스케이플래닛 주식회사 System for collecting of traffic information, revision device of valid sampling and method for revision of valid sampling
JP5601177B2 (en) * 2010-11-30 2014-10-08 アイシン・エィ・ダブリュ株式会社 Position specifying device, position specifying method, and position specifying program
CN102044153B (en) * 2010-12-22 2015-11-25 广州通易科技有限公司 The method and system of the unobstructed grade evaluation of a kind of traffic flow
JP5739182B2 (en) * 2011-02-04 2015-06-24 インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation Control system, method and program
JP5731223B2 (en) 2011-02-14 2015-06-10 インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation Abnormality detection device, monitoring control system, abnormality detection method, program, and recording medium
JP5689333B2 (en) 2011-02-15 2015-03-25 インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation Abnormality detection system, abnormality detection device, abnormality detection method, program, and recording medium
CN102157070B (en) * 2011-03-31 2013-01-09 天津大学 Road traffic flow prediction method based on cell phone data
CN102169630B (en) * 2011-03-31 2013-04-24 上海电科智能系统股份有限公司 Quality control method of road continuous traffic flow data
GB2492369B (en) 2011-06-29 2014-04-02 Itis Holdings Plc Method and system for collecting traffic data
CN102360529B (en) * 2011-09-20 2013-07-24 张忠义 Method for directly acquiring traffic speed of urban road
CN102521985A (en) * 2012-01-06 2012-06-27 北京捷易联科技有限公司 Traffic information evaluation method and device
WO2013108406A1 (en) * 2012-01-20 2013-07-25 トヨタ自動車 株式会社 Vehicle behavior prediction device and vehicle behavior prediction method, and driving assistance device
CN102568207A (en) * 2012-02-02 2012-07-11 北京捷易联科技有限公司 Traffic data processing method and device
US9132742B2 (en) * 2012-02-23 2015-09-15 International Business Machines Corporation Electric vehicle (EV) charging infrastructure with charging stations optimumally sited
GB201205348D0 (en) 2012-03-27 2012-05-09 Tomtom Belgium Nv Digital location-based data methods and product
CN102779410B (en) * 2012-07-19 2014-08-06 杭州师范大学 Parallel implementation method of multi-source heterogeneous traffic data fusion
CN102867421B (en) * 2012-09-24 2014-07-09 东南大学 Method for identifying outlier data in effective parking lot occupancy
US20140143184A1 (en) * 2012-11-21 2014-05-22 Microsoft Corporation Turn restriction inferencing
CN103888893A (en) * 2012-12-19 2014-06-25 中国移动通信集团公司 System and method for obtaining traffic state information
US9195938B1 (en) 2012-12-27 2015-11-24 Google Inc. Methods and systems for determining when to launch vehicles into a fleet of autonomous vehicles
CN104952270A (en) * 2012-12-28 2015-09-30 观致汽车有限公司 Traffic jam message advance notice method and system
US9014957B2 (en) 2012-12-29 2015-04-21 Google Inc. Methods and systems for determining fleet trajectories to satisfy a sequence of coverage requirements
EP2948932A1 (en) 2013-01-24 2015-12-02 Roger Andre Eilertsen A traffic surveillance and guidance system
CN104123833B (en) * 2013-04-25 2017-07-28 北京搜狗信息服务有限公司 A kind of planning method and device of condition of road surface
KR101338496B1 (en) * 2013-07-18 2013-12-10 주식회사 로드코리아 Load monitoring method
CN104376712B (en) * 2013-08-16 2017-10-13 株式会社日立制作所 Lack transport information complementing device and its method
CN103473928B (en) * 2013-09-24 2015-09-16 重庆大学 Based on the urban traffic blocking method of discrimination of RFID technique
CN104580292B (en) * 2013-10-16 2019-03-05 电信科学技术研究院 A kind of acquisition methods of running condition information, report method and equipment
MX344376B (en) * 2013-10-17 2016-12-13 Ford Global Tech Llc Road characteristic prediction.
CN103561123B (en) * 2013-10-28 2017-05-10 北京国双科技有限公司 Method and device for determining IP segment affiliation
JP5613815B1 (en) * 2013-10-29 2014-10-29 パナソニック株式会社 Residence status analysis apparatus, residence status analysis system, and residence status analysis method
CN103578274B (en) * 2013-11-15 2015-11-04 北京四通智能交通系统集成有限公司 A kind of traffic flow forecasting method and device
EP2887332B1 (en) * 2013-12-23 2016-09-07 Siemens Aktiengesellschaft Method and system for detection of a traffic situation on a stretch of road
CN105091889B (en) * 2014-04-23 2018-10-02 华为技术有限公司 A kind of determination method and apparatus of hotspot path
CN105303820A (en) * 2014-07-18 2016-02-03 中兴通讯股份有限公司 Traffic condition information providing method and device and server
CN104182618B (en) * 2014-08-06 2017-06-30 西安电子科技大学 A kind of method for early warning that knocks into the back based on Bayesian network
JP6079721B2 (en) 2014-08-07 2017-02-15 トヨタ自動車株式会社 Vehicle driving support system
EP3186662B1 (en) * 2014-08-26 2019-03-20 Microsoft Technology Licensing, LLC Measuring traffic speed in a road network
KR101673307B1 (en) 2014-12-19 2016-11-22 현대자동차주식회사 Navigation system and path prediction method thereby, and computer readable medium for performing the same
JP6229981B2 (en) 2014-12-26 2017-11-15 パナソニックIpマネジメント株式会社 Vehicle detector abnormality detection device, traffic condition analysis device, vehicle detector abnormality detection system, traffic condition analysis system, and program
CN104599499B (en) * 2015-01-12 2017-08-29 北京中交兴路车联网科技有限公司 A kind of method and device of distributed statistics traffic location
CN104778834B (en) * 2015-01-23 2017-02-22 哈尔滨工业大学 Urban road traffic jam judging method based on vehicle GPS data
CN106156966A (en) 2015-04-03 2016-11-23 阿里巴巴集团控股有限公司 Logistics monitoring method and equipment
CN104751644B (en) * 2015-04-14 2017-02-22 无锡物联网产业研究院 Traffic detection method and traffic detection device
CN104933860B (en) * 2015-05-20 2017-07-11 重庆大学 Bus traffic congestion delay time at stop Forecasting Methodology based on gps data
US9911327B2 (en) 2015-06-30 2018-03-06 Here Global B.V. Method and apparatus for identifying a split lane traffic location
US9640071B2 (en) 2015-06-30 2017-05-02 Here Global B.V. Method and apparatus for identifying a bi-modality condition upstream of diverging road segments
CN108140320A (en) * 2015-10-30 2018-06-08 三菱电机株式会社 Notify control device and notification control method
CN105404772A (en) * 2015-11-04 2016-03-16 成都天衡电科科技有限公司 Segmented system memory effect based adaptive historical data analysis method
CN105303833B (en) * 2015-11-05 2017-06-20 安徽四创电子股份有限公司 Overpass accident method of discrimination based on microwave vehicle detector
CN105389980B (en) * 2015-11-09 2018-01-19 上海交通大学 Short-time Traffic Flow Forecasting Methods based on long short-term memory recurrent neural network
CN106683447B (en) * 2015-11-11 2019-11-19 中国移动通信集团公司 A kind of traffic lamp control method and device
CN105575155B (en) * 2016-01-08 2018-09-18 上海雷腾软件股份有限公司 Method and apparatus for determining vehicle traveling information
CN105486322A (en) * 2016-01-14 2016-04-13 上海博泰悦臻网络技术服务有限公司 Regional road condition information acquisition method and system
CN105679055A (en) * 2016-04-01 2016-06-15 深圳市智汇十方科技有限公司 Road status prediction method and prediction system
US10068470B2 (en) 2016-05-06 2018-09-04 Here Global B.V. Determination of an average traffic speed
US10147315B2 (en) 2016-07-27 2018-12-04 Here Global B.V. Method and apparatus for determining split lane traffic conditions utilizing both multimedia data and probe data
US10198941B2 (en) 2016-07-27 2019-02-05 Here Global B.V. Method and apparatus for evaluating traffic approaching a junction at a lane level
CN106781489B (en) * 2016-12-29 2019-07-26 北京航空航天大学 A kind of road network trend prediction method based on recurrent neural network
US10262479B2 (en) * 2017-02-24 2019-04-16 Huf North America Automotive Parts Mfg. Corp. System and method for communicating with a vehicle
CN106846816B (en) * 2017-04-12 2019-09-17 山东理工大学 A kind of discretization traffic state judging method based on deep learning
CN107180530B (en) * 2017-05-22 2019-09-06 北京航空航天大学 A kind of road network trend prediction method based on depth space-time convolution loop network
CN107978153B (en) * 2017-11-29 2019-07-26 北京航空航天大学 A kind of multimode traffic factors influencing demand analysis method based on space vector autoregression model

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998054682A1 (en) * 1997-05-30 1998-12-03 Booth David S Generation and delivery of travel-related, location-sensitive information
JPH11328571A (en) * 1998-02-13 1999-11-30 Daimler Chrysler Ag Method and device for determining traffic condition on traffic route network
US20030171870A1 (en) * 2002-03-05 2003-09-11 Triangle Software Llc Personalized traveler information dissemination system
WO2004021305A2 (en) * 2002-08-29 2004-03-11 Itis Holdings Plc Apparatus and method for providing traffic information
CN1645402A (en) * 2005-01-19 2005-07-27 北京交通大学 Road traffic flow data quality controlling method and apparatus

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5590217A (en) * 1991-04-08 1996-12-31 Matsushita Electric Industrial Co., Ltd. Vehicle activity measuring apparatus
DE19631630C2 (en) 1996-08-05 2001-05-31 Homag Maschinenbau Ag Processing machine with a Saugspanneinrichtung
JPH10160494A (en) * 1996-11-29 1998-06-19 Toyota Motor Corp On-vehicle communication processing system
CA2290301A1 (en) 1999-03-05 2000-09-05 Loran Network Management Ltd. A method for detecting outlier measures of activity
CA2266208C (en) * 1999-03-19 2008-07-08 Wenking Corp. Remote road traffic data exchange and intelligent vehicle highway system
DE19928082C2 (en) * 1999-06-11 2001-11-29 Ddg Ges Fuer Verkehrsdaten Mbh Filtering methods or timetables for determining travel speeds and domain residual velocities
US6490519B1 (en) * 1999-09-27 2002-12-03 Decell, Inc. Traffic monitoring system and methods for traffic monitoring and route guidance useful therewith
JP3990641B2 (en) * 2002-03-27 2007-10-17 松下電器産業株式会社 Road information providing system and apparatus and road information generation method
US20040034467A1 (en) * 2002-08-09 2004-02-19 Paul Sampedro System and method for determining and employing road network traffic status
JP3874745B2 (en) * 2003-01-22 2007-01-31 松下電器産業株式会社 Traffic information providing method, traffic information providing system and apparatus
JP2004280521A (en) * 2003-03-17 2004-10-07 Matsushita Electric Ind Co Ltd Method and device for transmitting traveling track in probe car system
JP4255007B2 (en) * 2003-04-11 2009-04-15 株式会社ザナヴィ・インフォマティクス Navigation device and travel time calculation method thereof
JP4392747B2 (en) 2003-12-24 2010-01-06 アイシン・エィ・ダブリュ株式会社 Navigation system
CN100337256C (en) * 2005-05-26 2007-09-12 上海交通大学 Method for estimating city road network traffic flow state

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998054682A1 (en) * 1997-05-30 1998-12-03 Booth David S Generation and delivery of travel-related, location-sensitive information
JPH11328571A (en) * 1998-02-13 1999-11-30 Daimler Chrysler Ag Method and device for determining traffic condition on traffic route network
US20030171870A1 (en) * 2002-03-05 2003-09-11 Triangle Software Llc Personalized traveler information dissemination system
WO2004021305A2 (en) * 2002-08-29 2004-03-11 Itis Holdings Plc Apparatus and method for providing traffic information
CN1645402A (en) * 2005-01-19 2005-07-27 北京交通大学 Road traffic flow data quality controlling method and apparatus

Also Published As

Publication number Publication date
EP1938296B1 (en) 2011-09-07
WO2007103180A3 (en) 2007-12-06
WO2007103180A2 (en) 2007-09-13
CN102289935A (en) 2011-12-21
EP1938296A2 (en) 2008-07-02
CN101438335A (en) 2009-05-20
AU2007224206A1 (en) 2007-09-13
CN102254434B (en) 2013-05-01
ES2373336T3 (en) 2012-02-02
CN102289935B (en) 2015-12-16
CN102289936A (en) 2011-12-21
CN102254434A (en) 2011-11-23
AT523869T (en) 2011-09-15
EP2278573A1 (en) 2011-01-26
CN102394008A (en) 2012-03-28
CN102289936B (en) 2014-08-06
CN102394008B (en) 2015-01-07
JP2009529187A (en) 2009-08-13
ES2386529T3 (en) 2012-08-22
CN102394009B (en) 2014-05-14
EP2278573B1 (en) 2012-05-16
CN101438335B (en) 2011-09-21

Similar Documents

Publication Publication Date Title
Lomax et al. Selecting travel reliability measures
US9940836B2 (en) Estimating transit queue volume using probe ratios
KR100971446B1 (en) Satellite positioning system enabled media measurement system and method
Li et al. Performance evaluation of vehicle-based mobile sensor networks for traffic monitoring
US8457880B1 (en) Telematics using personal mobile devices
CA2496870C (en) Apparatus and method for providing traffic information
US8949013B2 (en) Ranking nearby destinations based on visit likelihoods and predicting future visits to places from location history
US8190362B2 (en) Displaying road traffic condition information and user controls
JP4346472B2 (en) Traffic information prediction device
Aslam et al. City-scale traffic estimation from a roving sensor network
JP2010204089A (en) Personalized user routing and recommendation
DE102012201472A1 (en) Method for providing parking information on free parking spaces
Herrera et al. Evaluation of traffic data obtained via GPS-enabled mobile phones: The Mobile Century field experiment
CA2823827C (en) Crowd sourced traffic reporting
AU2011226623B2 (en) Learning road navigation paths based on aggregate driver behavior
US8041660B2 (en) Optimizing traffic predictions and enhancing notifications
CN102132132B (en) Local decision policies about the sharing of sensed data that enhance privacy and lower communication costs for services that aggregate data from personal devices
US20090287405A1 (en) Traffic data quality
US20140330596A1 (en) System for monitoring vehicle and operator behavior
Zhan et al. Urban link travel time estimation using large-scale taxi data with partial information
US20150292894A1 (en) Travel route
US9958280B2 (en) Assessing inter-modal passenger travel options
US20140278055A1 (en) Updating road maps
US8386157B2 (en) Universal GPS traffic monitoring system
US7948400B2 (en) Predictive models of road reliability for traffic sensor configuration and routing

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C14 Grant of patent or utility model
CF01