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

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

Use is from the data estimation road traffic condition in mobile data source

The present invention is application number be 200780015916.2 the dividing an application of patented claim of (" using the data estimation road traffic conditions from the mobile data source ").

Technical field

Following open text relates generally to the technology that a kind of data of obtaining from various data sources are estimated road traffic condition, for example through infer the information of relevant traffic on these roads based on the data sample that has reflected the actual travel on the road interested.

Background technology

Because road traffic is to continue to increase than bigger ground of road capacity speed, the traffic congestion of surge is to commercial and government operation and individual happiness generation ill effect.Therefore, carried out the traffic congestion that surge is resisted in various effort in every way, offered individual and tissue such as the information through obtaining current traffic condition and with information.Can be (for example through variety of way; Via RF broadcast, internet site; Internet site has shown the map of geographic area; Wherein current traffic congestion is by the coloud coding information representation on some main roads of this geographic area, and information can send to cellular mobile phone and other portable consumer device etc.) such current traffic condition information is offered interested parties.

A kind of source that obtains relevant current traffic condition information comprises that observation that manual work provides (for example; The helibus of the relevant magnitude of traffic flow and accident general information is provided; And in some more large-scale metropolitan areas, another kind of source is the traffic sensor network report of sending via mobile phone by the driver etc.); It can measure the magnitude of traffic flow (for example, through being embedded in the sensor in the pavement of road) of different kinds of roads in the zone.Although the artificial observation that provides can provide some values under condition of limited, such information only limits to few regions usually at every turn and lacks the enough details that are enough to use usually.

In some cases, the traffic sensor network can provide the more detailed information of some road traffic conditions.But there are variety of issue in such information and the information that is provided by other similar source.For example; A lot of roads do not have path sensor (for example; Do not have the geographic area of path sensor and/or be not large enough to have path sensor and as the arterial highway of closing on a network part); Even the road with path sensor also possibly often can not offer precise data, and this has greatly weakened the data value that traffic sensor provided.Non-a kind of reason accurate and/or non-authentic data comprises that traffic sensor damages, thereby data can not be provided, or provides and be interrupted data, or correct reading of data.Non-another kind of reason accurate and/or non-authentic data is included in the problem that one or more sensors carry out the temporary transient transmission of data, causes being interrupted transmission, or postpones to transmit, or does not transmit data.In addition; A lot of sensors do not dispose or design (is for example reported relevant driver condition; Whether their function is normal); Even if the status information of having reported the driver also maybe be incorrect (for example, report driver function normally but in fact really not so), so just be difficult to maybe can not be definite whether accurate by data that traffic sensor provided.In addition, the information of relevant traffic only can obtain with original and/or discrete form, thereby uses limited.

Hide, it is very helpful providing a kind of improved technology to obtain and estimating the information of relevant traffic and various relevant additional abilities are provided.

Description of drawings

Fig. 1 illustrates the block scheme that is used at least in part estimating based on the data of being obtained from vehicle and other mobile data source the data stream between the assembly of system implementation example of road traffic condition.

Fig. 2 A-2E illustrates the instance of estimating road traffic condition at least in part based on the data of obtaining from vehicle and other mobile data source.

Fig. 3 is the block scheme that illustrates the computing system that is suitable for carrying out described data sample management system (Data Sample Manager System) embodiment.

Fig. 4 is the process flow diagram of the exemplary embodiment of data sample filtrator routine.

Fig. 5 is the process flow diagram of the exemplary embodiment of data sample exceptional value remover (Outlier Eliminator) routine.

Fig. 6 is the process flow diagram of the exemplary embodiment of data sample speed estimator routine.

Fig. 7 is the process flow diagram of the exemplary embodiment of data sample flow estimation device routine.

Fig. 8 is the process flow diagram that mobile data source information provides the exemplary embodiment of routine.

Fig. 9 A-9C illustrates the action instance that obtains and mobile data source in the relevant road traffic condition is provided.

Figure 10 A-10B illustrates the instance of the data sample that correction obtains from road traffic sensors.

Figure 11 is the process flow diagram of the exemplary embodiment of sensing data read error detector routine.

Figure 12 is the process flow diagram of the exemplary embodiment of sensing data read error corrector routine.

Figure 13 is the process flow diagram that sensing data reads the exemplary embodiment of gatherer routine.

Figure 14 is the process flow diagram of the exemplary embodiment of magnitude of traffic flow estimation device routine.

Embodiment

Based on the relevant data of the traffic of obtaining; The technology of estimation road traffic condition is described in every way; Such as the vehicle that comes comfortable travels down with other mobile data source and/or from traffic sensor (for example, being embedded in the road or near physical sensors).In addition, at least some embodiment, the data sample that comes from the mobile data source can be used from the data in one or more other sources and replenish, such as the data that read through the physical sensors that obtains in road annex or road.Based on the data sample that is obtained (for example; From road traffic sensors; From each mobile data source or collect the data that data point reads) can comprise the various filtrations and/or the adjustment of data sample and reading to the estimation of road traffic condition, and the various deductions of interested traffic correlated characteristic and probability are definite.

As said; The road traffic condition information data of being obtained in certain embodiments by the mobile data source (for example can comprise; Vehicle) a plurality of data samples that provide; From based on the data readings of the traffic sensor of road (for example being embedded in the loop sensor in the pavement of road) with from the data of other data source.Data can with such as the variety of way analysis of total vehicle total amount of estimating in the specific part of the average traffic speed of estimation and the interested road of institute etc. so that confirm interested traffic characteristic so that with in real time or the mode of (for example at reception bottom data sample and/or reading) that is bordering in real time carry out the definite of traffic.For example, the data of being obtained can be adjusted to detect and/or to proofread and correct the mistake in data in every way.If the road traffic condition information of being obtained is coarsely maybe can not represent interested actual traffic situation characteristic; Then in each embodiment, can also filter in every way to remove data; Comprise through will be at least part based on the non-interested data sample of road with according to the related data sample of other data sample and/or be regarded as identical as the data sample of adding up exceptional value; In certain embodiments, filtration can also comprise execution related with data sample and specified link.The filtered data sample (for example can also comprise other reflection vehicle location or non-interested behavior; The vehicle that berths, vehicle spins etc. in parking lot or building) data sample and/or other can not represent the data sample that actual vehicle is gone on interested road.Estimate at least some embodiment that the data of being obtained can comprise at least in part based on the data sample that is obtained and confirm to be used for traffic (for example, the magnitude of traffic flow and/or average traffic speed) in specific geographic area road network various piece.Then can use the data of being estimated to carry out and relate to analysis, prediction, forecast, and/or other function of traffic relevant information is provided.In at least some embodiment; The data sample management system uses at least some described technology to prepare by the employed data of traffic data client; Predicted traffic information such as produce a plurality of forecasts of traffic in a plurality of times in future provides system, and this will be in following detailed description.

In certain embodiments, the adjustment of fetched data sample can comprise the data sample that corrects mistakes, such as through detecting and/or proofread and correct mistake in the current data (data readings that for example, receives from road traffic sensors) in every way.Particularly; Such as the analysis based on the data sample that is provided by these data sources, the technology of " health " be used to estimate the particular source traffic sensor of road (for example based on) of describing is so that whether the specified data source is in proper working order and the precise information sample is provided reliably.For example; In certain embodiments; Whether the former data readings that the current data reading that will be provided by given traffic sensor and this traffic sensor provide (for example, the historical average certificate) compares, significantly different with in the past common data readings to confirm current traffic data reading; For example this can be caused by the other problem in this traffic sensor non-normal working and/or the data, and/or can replace and reflect unusual current traffic condition.In each embodiment, can carry out this detection and analysis in every way to possible errors in particular source and/or the current traffic data reading; This will more go through following, comprise that part is based on the sorting technique such as use neural network, Bayes classifier, decision tree etc. at least.

Detecting, can proofread and correct or revise this corrupt data sample (and data sample of losing) by this way such as behind corrupt data sample from the damaged data source of operate as normal not.For example in certain embodiments; Can (for example revise one or more data sources through using one of relevant information or other to originate; Traffic sensor) obliterated data and corrupt data; For example through from closing on or data sample is (for example the relevant traffic sensor of other operate as normal the time; Through the data readings that is provided by adjacent traffic sensor is taken the mean); Lose and the foresight information of corrupt data sample (for example, the expected data reading that foresight through using these data sources and/or the logical condition information of forecast sexual intercourse are confirmed one or more data sources) through relating to, (for example via the historical information of one or more data sources; Through using historical average according to reading), via using relevant consistent deviation or other type of error that can compensate of leading to errors is adjusted with the correction data sample etc.Relate to revise lose with other details of corrupt data sample will be in following detailed description.

In addition, the technology of description also is used for various alternate manners estimation traffic related informations, such as the situation of the correction of the data sample that allows to carry out reliably particular source (for example, special traffic sensor) in current available data.For example, the existence of the unhealthy traffic sensor of a plurality of not operate as normal possibly cause not having enough data to come in these traffic sensors each estimated traffic flow information fully credibly.In this case, traffic related information possibly estimate with various alternate manners, comprises based on relevant traffic sensor group and/or relates to the out of Memory of road network structure.For example; To more describe ground in detail as following; Each interested road can come modeling or expression through using a plurality of road segment segment, and each road segment segment can have the traffic sensor of a plurality of associations and/or the data that obtain from one or more other data sources (for example, mobile data source).The words of if so; Can be directed against particular lane highway section (or other group of a plurality of relevant traffic sensors) in every way and estimate road traffic condition information; For example through use be used to estimate the adjacent road section traffic related information, be used for the particular lane highway section information of forecasting (for example; In the Future Time section limited, produce, at least in part based on recent situation in current and the schedule time such as three hours etc.), to the forecast information in particular lane highway section (for example; In Future Time section, produce such as two weeks or longer time, so as not use current and the recent condition information that is used to predict some or whole), the historical long-run average in particular lane highway section etc.Through using such technology, even if when having only the current traffic condition data of a small amount of or neither one or a plurality of approaching sensor or other data source, also traffic related information can be provided.Other details that relates to such traffic related information estimation will be in following detailed description.

As previously mentioned, the information of relevant road traffic condition can obtain from the mobile data source in every way in various embodiments.In at least some embodiment, the mobile data source comprises the vehicle on the road, its each comprise one or more computing systems that close the vehicle mobile data that provide.For example; Every vehicle can comprise that GPS (" GPS ") equipment and/or other can confirm geographic position, speed, direction and/or other sign or relate to the geolocation device of the data of vehicle '; And the one or more equipment on the vehicle (no matter whether being geolocation device or different communication facilities) can be with such data (for example sometimes; Pass through Radio Link) (for example offer one or more systems that can use such data; The data sample management system will more be described in detail following).For example; Such vehicle by the distributed network of the vehicle of each incoherent user's operation, fleet (for example can comprise; Be used for express company (delivery company), taxi and bus company, carrier, government department or agency; The vehicle of car rental services etc.), be subordinate to and provide relevant information (for example; The vehicle of commercial network OnStar service), be operated to obtain such traffic related information the vehicle group (for example; Through the predetermined route that goes, or go on road and dynamically to change direction, to obtain the information of relevant interested road), the vehicle that is mounted with mobile telephone equipment (for example; As built-in device and/or have vehicle-mounted thing (vehicle occupant)) positional information (for example, based on the GPS ability of equipment and/or based on the geo-location ability that is provided by the mobile network) etc. can be provided.

In at least some embodiment, the mobile data source can comprise or based on other mobile device of the user of computing equipment and travels down, be the driver and/or the passenger of vehicle on the road such as the user.Such subscriber equipment can comprise equipment with GPS ability (for example, mobile phone and other handheld device), or position and/or mobile message alternatively also can otherwise produce in other embodiments.For example; Equipment in vehicle and/or subscriber equipment can (for example communicate with the external system of ability detection and tracking relevant devices information; The equipment that passes through separately through a plurality of emittor/receivers in the network of system operation); Thereby make the position of equipment and/or mobile message be determined with variety of way with various level of detail; Perhaps such external system can also the relevant vehicle of detection and tracking and/or user's information and with equipment mutual (for example, can observe and discern the camera system of driving board and/or user face).For example, such external system can comprise mobile phone tower and network, and other wireless network (for example; Wi-Fi Hotspot), use detecting device (for example, the RFID of the vehicle transducer of the various communication technologys; Or " radio frequency identification "), other detecting device of vehicle and/or user (for example, uses infrared ray; Sonar, radar or Laser Distance Measuring Equipment are to confirm the position and/or the speed of vehicle) etc.

Can use the road traffic condition information that obtains from the mobile data source in every way, no matter still be separately and use together from other road traffic condition information of one or more other sources (for example, from road traffic sensors).In certain embodiments; Use such road traffic condition information that obtains from the mobile data source, provide info class to be similar to data from path sensor, but for the road of the path sensor that not have to move (for example; For the road that lacks sensor; Such as for the geographic area that does not have networks of road sensors and/or not even as big as the arterial highway of sensor is arranged, for the path sensor that damages etc.), the Copy Info that receives from path sensor or other source with verification; Thereby identification provides the path sensor (for example, because interim or current problem) of non-precise information etc.And road traffic condition can be measured or representes no matter be based on the data sample from mobile data source and/or traffic sensor data readings with one or more modes, for example aspect absolute in (for example, average velocity; The volume of traffic in the indicated time period; The average holding time of other position on one or more traffic sensors or the road is for example to represent that vehicle passes through or the average percentage of activated sensors time; The computed rank of one or more congestion in road is for example measured based on one or more other traffics; Or the like) and/or aspect relatively (for example, the difference of expression and normal conditions or maximum case).

In certain embodiments, the form of the data sample that some road traffic condition information can be taked to be provided by various data sources, for example related with vehicle data source is with the travelling characteristic of reporting vehicle.Each data sample can comprise the quantity of information of variation.For example, the data sample that is provided by the mobile data source can comprise one or more come source identifier, speed identifier, orientation or direction indication, position indication, timestamp and status identifiers.Coming source identifier can be numeral or the string of sign as the vehicle (or people and miscellaneous equipment) of data source.In certain embodiments, the mobile data source identifier can be permanent with the mobile data source or be temporary transient related (for example, for life-span in mobile data source; For one hour; For the session of current use, for example so that unlocking vehicle or data-source device are just distributed a new identifier each time).In at least some embodiment; Come source identifier related with the mobile data source; So that the secret relation from the data in mobile data source of relating to minimizes (no matter be forever or temporary transient related), for example through to stop the mode of discerning the mobile data source related based on identifier to be created and/or the operate source identifier with this mobile data source and identifier.The speed indication can reflect the instant or average velocity (for example, mph.) in the mobile data source of expression in every way.The orientation can reflect the direction of going, and is angle or other tolerance orientation or the radian of compass (for example, based on) with " degree " expression.Position indication can reflect the physical location (for example lat/lon to or Universal Transverse Mercator coordinate) of expression in every way.Timestamp can be indicated the time of mobile data source record sample preset time, for example with local zone time or UTC (" Universal Coordinated Time ") time.Status identifier can represent the mobile data source state (for example, vehicle move, stop, engine running and stops etc.) and/or at least some states (for example, electric weight is low, signal intensity is weak etc.) of sensing, record and/or transmitter.

In certain embodiments, the road network in given geographic area can come modeling or expression through using a plurality of road segment segment.Each road segment segment can be used to represent the part of road (or a plurality of road); For example (for example, each road segment segment has particular length, such as one mile long road through given physics road being divided into a plurality of road segment segment; Or the road part of selecting to reflect similar traffic characteristic is as road segment segment); A plurality of road segment segment like this can be the continuous parts of road, or alternatively in certain embodiments, and they can overlapping or any road segment segment all have the part of phase mutual interference.In addition, road segment segment can be represented the one or more traveling lanes on the given physics road.Therefore, on each of both direction, all have the specific multilane of one or more traveling lanes can be with the two road section is related at least, wherein at least one road segment segment and the direction go related, and at least another with other direction on go related.In addition, in some cases, a plurality of tracks of the single road that on single direction, goes can be represented by a plurality of roadway segment, if for example the track has different travel conditions characteristics.For example, given freeway facility can have quick or high occupancy (" HOV ") track, it can be represented with as quick or HOV track by routine (for example, non-HOV) the far different mode in track of going on the equidirectional with expression.Roadway segment can also be connected to other adjacent road segment segment or the road segment segment adjacent with other related, thereby form the road segment segment network.

Fig. 1 illustrates the process flow diagram that is used at least in part based on the data stream between the assembly of the system implementation example of the data estimation road traffic condition that obtains from vehicle and other mobile data source.Shown data flowchart is intended to be reflected in data source, i.e. the logical expressions of the data stream between the assembly of the embodiment of data sample management system, and the traffic data client.That is to say; Actual data stream possibly take place via various mechanism; Comprise direct stream (for example, by realize or such as the network service of message) and/or via one or more Database Systems or other indirect stream such as the storage system of file system through parameter.Shown data sample management system 100 comprises data sample exceptional value removal assembly 106, data sample velocity estimation assembly 107, data sample stream estimation assembly 108 and optional sensor collection assembly 110.

In an illustrated embodiment, the assembly 104-108 of data sample management system 100 and 110 obtains data sample from various data sources, and this comprises data source 101, road traffic sensors 103 and other data source 102 based on vehicle.Can be included in a plurality of vehicles of one or more travels down based on the data source 101 of vehicle, its each can comprise one or more computing systems and/or can provide the miscellaneous equipment that closes the vehicle running data.Like the other ground of will more describing in detail, every vehicle can comprise GPS and/or can define the geolocation device of closing position, speed and/or other data that vehicle goes.Such data can (for example be passed through wireless data link by the assembly of said data sample management system; Satellite uplink and/or mobile telephone network) or alternate manner is (for example; After vehicle arrives certain physical location, for example after its base is got back to by fleet, carry out physics wired/cable connects) obtain.Road traffic sensors 102 can comprise and be installed in each street, highway or other road, go up or near a plurality of sensors, for example is embedded in loop sensor energy measurement time per unit in the road surface through the vehicle fleet size on this sensor, car speed and/or relate to other data of the magnitude of traffic flow.Data can be similarly from road traffic sensors 102 via obtaining based on wired or wireless data link.Other data source 103 can comprise the data source of various other types; Comprise Map Services and/or database that relevant road network information is provided; For example link between road and the traffic control information (for example, the existence of traffic control signal and/or position and/or speed limit zone) that relates to this road.

Though the data source 101-103 in this example directly offers each assembly 104-108 and 110 of data sample management system 100 with data sample, data sample also can be handled earlier before being provided for these assemblies in other embodiments.Such processing can comprise based on the identity in time, position, geographic area and/or individual data source (for example, vehicle, traffic sensor etc.) tissue and/or collect data sample in logical collection.In addition, such processing can comprise that merging or data splitting sample are to more senior logical data sample or other value.For example, the data sample that the road traffic sensors of colocated obtains from a plurality of geography can be integrated with single logical data sample through average or other collection mode.In addition, such processing can comprise derives based on one or more data samples that obtain or the element of generated data sample or data sample.For example; In certain embodiments; At least some can provide the data sample that only comprises coming source identifier and geographic position based on each of the data source of vehicle; If so is so with specified time interval or section and a plurality of different data sample group that periodically provides just can be related with another and as specific vehicle was provided At All Other Times.Can also further handle such data sample group and confirm other relevant information of going; For example the orientation of each data sample (for example; Through calculating the angle between the position of the position of data sample and previous and/or subsequent data sample) and/or the speed of each data sample is (for example; Through calculating the distance between the position of the position of data sample and previous and/or subsequent data sample, and will be apart from divided by the corresponding time).

In an illustrated embodiment; Data sample filter assemblies 104 obtains data sample from the data source 101 based on vehicle with other data source 102, and before they being offered data sample exceptional value removal assembly 106 and offering data sample stream estimation assembly 108 alternatively, the data sample that is obtained is filtered.As will more go through ground elsewhere; Such filtration can comprise: with data sample with related corresponding to the road segment segment of road in the geographic area, and/or identification not corresponding to interested road segment segment or reflect the data sample of uninterested vehicle location or behavior.Can comprise data sample is related with road segment segment: use reported position and/or the orientation of each data sample to confirm that this position and orientation are whether corresponding to the road segment segment of previous qualification.Identification can not comprise corresponding to the data sample of the interested road segment segment of institute: remove or discern such data sample so as not to their modelings, consider or by other assembly processing of data sample management system 100; Such data sample of removing can comprise that those corresponding to the road of the road class of uninterested specific function (for example; Residential street) data sample, those data samples (for example, ramp and collector/distribution lane/tell highway road) etc. corresponding to the part of uninterested road or zone.Whether the recognition data sample reflects that uninterested vehicle location or behavior can comprise: discern and be in idle condition (for example, engine is leaving and stopping), drive the corresponding data sample of vehicle of (for example, spinning with low-down speed) etc. in the garage parking.In addition, in certain embodiments, filtration can be included as that to appear or further analyze and discern road segment segment be that (or not being) is interested.For example; Such filtration at special time period (for example can comprise analysis; Hour, day, week) changeability of the interior magnitude of traffic flow and/or the degree of blocking up of each bar road segment segment; (for example, unavailable or their functional category of roads is represented littler or the road segment segment of travel still less for the sensing data reading) is as uninterested road and road segment segment so that from further analysis, get rid of and have (intra-time period) changeability in the low time period and/or lower of blocking up or whole road segment segment.

The sensing data adjuster 105 auxiliary data samples that correct mistakes are for example through detecting and proofread and correct from the mistake of the reading of road traffic sensors 103 acquisitions.In certain embodiments; By sensing data adjustment component detection is that insecure data sample is not forwarded to other assembly and uses and (or the non-reliable expression of particular data sample is provided; So that other assembly can be handled these data samples); For example, be not forwarded to data sample exceptional value remover 106.If so, data sample exceptional value are removed assembly can determine whether that then enough authentic data samples can use, if not, then initiate the correction behavior.Alternatively; In some embodiment and environment; Sensing data adjustment assembly can also be carried out some corrections to the data sample; Will more go through ground as following, the data after then will proofreading and correct offer sensor collection assembly 110 (also offer other assembly alternatively, for example the data sample exceptional value is removed assembly and/or data sample stream estimation assembly).The faults data sample can use various technology; Comprise statistical measurement; Will by the distribution of the current data sample of given road traffic sensors report with the corresponding time period (for example, identical week fate with one day in the identical time) in distribute by the history of the data sample of this road traffic sensors report and to compare.Difference actual and historical distribution range can be calculated by statistical measures, Kullback-Leibler divergence for example, and it provides the convex measuring of the similarity between two probability distribution, and/or the statistical information entropy.In addition, some path sensors can be reported the indication that sensor is healthy, can also use such indication to detect the mistake of the data sample that is obtained.If in the data sample that is obtained, detect mistake; Then can revise the data sample of makeing mistakes in every way; Comprise that the mean value that is used to from the data sample on adjacent (for example, the next door) of confirming error-free adjacent/next door path sensor replaces such data sample.In addition, can replace such as the value of before or simultaneously having predicted and/or having predicted that provides by predictive traffic information systems, revise the data sample of makeing mistakes through using.Other details that relating to predicted traffic information provides will provide in addition.

The data sample exceptional value is removed assembly 106 and is obtained the filtered data samples and/or obtain adjustment or revised data samples from sensing data adjustment assembly 105 from data sample filter assemblies 104, then identification and considering remove those do not represent the data sample that goes of the actual vehicle on interested road and the road segment segment.In an illustrated embodiment, for each interested road segment segment, block analysis is write down in special time period and the data sample group (for example, through data sample filter assemblies 104) related with road segment segment, if remove, which should remove to confirm.Can carry out in every way and so non-representative data sample confirmed that comprise based on following technology: with respect to other data sample in the data sample group, detecting data sample is the statistics exceptional value.Other details that relates to the removal of data sample exceptional value will provide in addition.

Data sample velocity estimation assembly 107 is removed assembly 106 from the data sample exceptional value and is obtained data samples, so as the data sample that obtains in the embodiment shown be illustrated in the actual vehicle on interested road and the road segment segment go.Data sample velocity estimation assembly 107 is then analyzed the data that obtained; With based on this road segment segment (for example; Through data sample filter assemblies 104; Or the reading that comes through sensor) the data sample group related with the time period from road segment segment part, estimate at least one in the interested time period one or more speed of interested road segment segment.In certain embodiments, the speed of being estimated can comprise this and organize the speed average of a plurality of data samples, also can (for example, the age (age) is so that give the newer bigger weighting of data sample by one or more attribute weights of data sample; And/or the source of data sample or type, so that come to the bigger weighting in the source with higher expected reliability or availability from the mobile data source or from the weighting that path sensor changes data sample).The more details that relate to the velocity estimation that carries out from data sample will provide elsewhere.

Data sample stream estimation assembly 108 is institute's interested road segment segment estimation telecommunication flow information at least one interested time period; With the estimation volume of traffic (for example; Be expressed as in such as per minute or special time amount hourly arrive or through the vehicle total amount or the average of road segment segment), the estimation traffic density (for example; Be expressed as such as every mile or kilometer etc. the vehicle average or the total amount of per unit distance) and estimation traffic occupancy (for example, be expressed as take specified point or regional average or total time quantum) etc. at for example per minute or the special time amount vehicle that per hour waits.In an illustrated embodiment; To the estimation of telecommunication flow information at least in part based on removing the information that relates to traffic speed that assembly 106 provides by data sample velocity estimation assembly 107 and data sample exceptional value, alternatively can be based on the traffic data sample information that provides by sensing data adjustment assembly 105 and data sample filter assemblies 104.Other details that relates to the estimation of traffic sample flow will provide elsewhere.

If exist; Then such as removed any insecure data sample at sensing data adjustment assembly and/or revised any lose and/or non-authentic data sample after, sensor data collection assembly 110 is collected the sensor-based traffic related information that is provided by sensing data adjustment assembly 105.Alternatively, in other embodiments, the sensor data collection assembly can alternatively be carried out this losing and/or the removal and/or the correction of corrupt data sample.In some cases, sensor data collection assembly 110 can be that each of these road segment segment provides telecommunication flow information through the information of collecting (for example, average) and being provided by a plurality of independent traffic sensor related with each road segment segment.Likewise; If exist; Sensor data collection assembly 110 can provide information; The estimation traffic that provides with the assembly that replenishes by for example data sample velocity estimation assembly 107 and/or data sample stream estimation assembly 108 etc., or can be reliable from the data sample in mobile data source or do not have the authentic data sample of q.s to allow other assembly such as data sample velocity estimation assembly 107 and data sample stream estimation assembly 108 etc. to provide under the situation of accurate estimation road traffic condition information alternatively to use.

The road traffic condition information of the estimation that one or more in an illustrated embodiment traffic data clients 109 obtain to be provided by data sample velocity estimation assembly 107 and/or data sample stream estimation assembly 108 (for example; Speed and/or flow data), and can use such data in every way.For example; Traffic data client 109 can comprise other assembly and/or by the traffic information system of the operator of data sample management system 100 operation; For example the foresight transport information provides system, uses traffic related information to be created in the traffic related information of the future transportation situation forecast of a plurality of Future Time; And/or in real time the transport information of (or being bordering in real time) presents system and obtains or provide system, and the traffic related information of (or being bordering on real-time) is provided in real time to terminal user and/or third party's client.In addition, traffic data client 109 can comprise that the computing system of being operated by the third party is to provide transport information to its client.In addition; In some environment (for example; When not carrying out accurate estimation for data sample velocity estimation assembly and/or data sample stream estimation assembly obtains enough data; And/or when from not obtaining under the data conditions based on vehicle or other data source) these one or more traffic data clients 109 obtain the road traffic condition information that provided by sensor data collection assembly 110 alternatively; Can substitute data from data sample velocity estimation assembly and/or data sample stream estimation assembly, or extra acquisition outside this.

For illustrated purpose, some embodiment wherein estimate the road traffic condition of particular type in a particular manner in following description, and use such estimation transport information with various specific modes.But; Should be understood that; Can be otherwise and use in other embodiments that the input data of other type produce such traffic estimation, described technology can used in other situation very widely, and the present invention is not limited to the exemplary details that provided.

Fig. 2 A-2E illustrates the instance based on the data estimation road traffic condition that obtains from vehicle and other mobile data source, as by described data sample management system performed.Particularly, Fig. 2 A illustrates the instance that data sample filters, and is used to have several roads 201,202,203 and 204 and have an example region 200 of indication legend indication 309 in a northerly direction.In this example, road 202, such as the limited entering road (limited access road) of the highway or the highway that crosses, be divided into the west to east orientation on the respectively different track group 202a and the 202b of driving vehicle.Track group 202a comprises HOV track 202a2 and a plurality of other conventional track 202a1, and track group 202b comprises HOV track 202b2 and a plurality of other conventional track 202b1 similarly.Road 201 is to walk road 202 (for example, via overline bridge or bridge), and road 204 is onramps, and its northern runway 201b with road 201 is connected to the eastbound carriageway group 202b of road 202.Road 203 is local frontage roads of adjacent road 202.

Can be illustrated in the road shown in Fig. 2 A in every way, to be used for described data sample management system.For example, one or more road segment segment can be related with each physics road, and are for example that the north row is related with northern runway 201a and southern runway 202b respectively with highway section, southern trade.Similarly, at least one head west road segment segment and at least one eastbound road segment segment are can be respectively related with head west track group 202a and the eastbound carriageway group 202b of road 202.For example; The part in the eastbound carriageway group 202b of road 201 east can be and the part in the track group 202b west that heads west of road 201 road segment segment independently mutually; For example (for example change between road segment segment based on general road traffic condition or through being everlasting; Because vehicle significantly flow into the track group 202b of road 201 from onramp 204 usually, so in general causes in bigger blocking up to the track group 202b of road 201 east orientations).In addition; Can one or more tracks group be decomposed in a plurality of road segment segment; If for example different tracks (for example generally or often has different road traffic condition characteristics; Based on giving certain portions as first road segment segment track group 202b in these tracks of enjoying similar traffic characteristic corresponding to track 202b1; And will owing to its have different traffic characteristics thereby as corresponding to the second lane section of HOV track 202b2)-in other this situation; Have only single road segment segment can be used for such track group, but this track group of estimation road traffic condition the time some data samples (for example, corresponding to the 202b2 in HOV track those) can from use, get rid of (for example removing assembly) through data sample filter assemblies and/or data sample exceptional value.Alternatively; Some embodiment can be expressed as the single road section with a plurality of tracks of a plurality of given roads; Even if this track is a up train in the opposite direction; When for example road traffic condition is similar usually on both direction---for example, frontage road 205a can have two opposite driving lanes, but can be represented by a road segment segment.Road segment segment can otherwise come to confirm at least in part at least some embodiment, for example related with geography information (for example, physical dimension and/or orientation and/or traffic relevant information (for example, speed limit).

A plurality of data sample 205a-k that Fig. 2 A has also described at specified time interval or a plurality of mobile datas source in zone 200 of going during the section (for example, 1 minute, 5 minutes, 10 minutes, 15 minutes etc.) At All Other Times (for example, vehicle, not shown) reported.By one of a plurality of mobile datas source report the time, each of data sample 205a-k all is illustrated as arrow, the orientation of its expression data sample.Data sample 205a-k is superimposed upon on the zone 200 so that reflect that position that each data sample reports (for example by this way; Represent with dimension and precision unit; Such as based on the GPS reading); They can be different with the physical location of vehicle when the record data sample (for example, because out of true or wrong reading, or because the intrinsic variable precision of employed position sensing mechanism).For example; Data sample 205g has shown the slightly position in north of road 202b; It can reflect the vehicle that being drawn to 202b2 north side, track (for example, because mechanical fault), or it can be reflected in the non-exact position of the vehicle of actual travel on the eastbound direction in track 202b2 or other track.In addition; Single mobile data source can be than shown in the source of data sample more data sample; If for example sample 205i and sample 205h are by in the time period, (for example reporting along single portion vehicle that road 202 east orientations go; Through comprising the single transmission of a plurality of data samples that are used for a plurality of previous time points, so that per 5 minutes or per 15 minutes report data samples).About storing and providing the more details of a plurality of fetched data samples will be included in the following content.

Described in certain embodiments data sample management system can be filtered the data sample that is obtained, so as with data sample be mapped to predetermined road segment segment and/or identification not corresponding to the data sample of interested road segment segment.In certain embodiments; If reported position with the preset distance in corresponding road of road segment segment and/or track (for example; 5 meters) in; And its orientation with the predetermined angular (for example plus or minus 15 degree) in the orientation in corresponding road of this road segment segment and/or track in, then data sample is related with road segment segment.Though can before data sample can be used for the data sample management system, carry out the association of the data sample of road segment segment in other embodiments; Road segment segment in the illustrated embodiment and enough location-based information are (for example; The orientation of road segment segment; The physical extent of road segment segment etc.) association is to make such confirming.

As directed instance, data sample 205a can be with related corresponding to the road segment segment of road 203, because its reported position drops in the scope of road 203 and at least one orientation identical (or being bordering on identical) of its orientation and related road 203.In certain embodiments, when using the single road section to be illustrated in a plurality of track of going on the opposite direction, can with two aspect ratios of the orientation of data sample and road segment segment than whether can be related with this road segment segment with determining data sample.For example, data sample 205k has roughly opposite with data sample 205a orientation, if but use road segment segment to represent two opposite carriageway of road 203, then it also can be with related corresponding to the road segment segment of road 203.

Yet; Because road 203 is approaching with track group 202a; Also possible is; Because the orientation of data sample 205k is identical with the orientation of track group 202a, then data sample 205k is reflected in the vehicle that goes on the group 202a of track, if the blank space of the reported position of the data sample 205k vehicle location mistake of in one or more tracks of track group 202a, going for example.In certain embodiments, a plurality of possible road segment segment situation of being used for a data sample can remove based on the out of Memory related with this data sample.For example; In this case; The analysis of the report speed of data sample 205k can help this removal; If for example group 202a in track is corresponding to the highway of 65mph speed limit, road 203 local frontage road for having the 30mph speed limit, and the speed reported of data sample is 75mph (cause with highway track related than big with the related possibility of local frontage road).Generally speaking; If the report speed of data sample 205k is compared the observation of track group 202a or observation or the transmission speed that transmission speed more is similar to road 203, then such information can be used for partly confirming data sample and road 203 related rather than track group 202a.Alternatively, if the report speed of data sample 205k more is similar to observation or the transmission speed of track group 202a, then its just related with track group 202a rather than road 203 than the speed of observation or the road 203 that sends.Also can be used as a part (for example, position like the info class of other type in this removal; The orientation; State; Other relates to the information of data sample, other most recent data sample that for example comes from identical mobile data source etc.), for example reflect the matching degree of data sample information type and candidate roads section as the part of weighted analysis.

For example, for data sample 205b is related with the road segment segment that is fit to, the position that it is reported appears at track 201b and the overlapping part of track group 202a, and it closes on track 201a and other road.But the orientation that data sample is reported (roughly north row) is more approaching with the orientation of track 201b (north row) than the orientation of other candidate's track/road, thus in this instance it probably with related corresponding to the road segment segment of track 201b.Similarly; Data sample 205c comprises can mate a plurality of road/tracks (track 201a for example; 201b and track group 202a) reported position, but the road segment segment that its orientation (roughly heading west) can be used to select be used for track group 202a is as being used for the only road segment segment of this data sample.

Still this instance, data sample 205d can be not related with any road segment segment, because its orientation (roughly eastbound) and corresponding to the reverse direction that is in of the track group 202a (heading west) of the reported position of this data sample.If there is not other suitable candidate roads section; The position that itself and data sample 205d are reported is enough near (for example; In predetermined distance), if it is too far away for example to have a track group 202b in similar orientation, then during filtering, get rid of this data sample from the follow-up use of the analysis of this data sample.

Data sample 205e can be related with the road segment segment such as corresponding to the road segment segment of HOV track 202a2 corresponding to track group 202a; This be because its reported position and orientation corresponding to the position and the orientation in this track; If for example being used for the location-based technology of the position of this data sample has enough resolution and (for example distinguishes the track; Different GPS, infrared ray, sonar or radar ranging equipment).Data sample can also be based on the factor except position-based information and is related with the specific track of multiple-lane road, if for example the track has different traffic characteristics.For example; In certain embodiments; Can use the report speed of data sample to come the expection of the speed (or the magnitude of traffic flow other measure) through the data sample that is used for each such candidate track is observed (for example to distribute; Usually or Gaussian distribution) modeling, and data sample is conformed to specific track or matees.For example; Because observation, deduction or the historical average speeds of the vehicle that the speed reported of this data sample more approaches than observation, deduction or historical average speeds at the vehicle that goes on the conventional track 202a1 to go on the 202a2 of HOV track; Therefore data sample 205e can be with related corresponding to the road segment segment of HOV track 202a2; For example through confirm the analysis of observation or deduction speed (for example, using the data readings that provides by one or more road traffic sensors) and/or other relevant current data based on other data sample.

In a similar fashion, data sample 205f, 205h; 205i and 205j can be respectively with corresponding to track 201a; Track 202a1, track 202b1 is related with the road segment segment on slope 204, because position that they are reported and orientation are corresponding to the position and the orientation in these roads or track.

Even if its reported position shown in outside the scope of road; Data sample 205g also can be with related (for example corresponding to the road segment segment of track group 202b; The road segment segment that is used for HOV track 202b2), this is because reported position can be in the predeterminable range (for example 5 meters) of road.Alternatively, if the reported position of data sample 205b away from road, then it can be not related with any road segment segment yet.In certain embodiments, use the different preset distance can for the data sample that provides by the different pieces of information source, so that the reflection data source is known or the accuracy level of expectation.For example; By the data sample that uses the mobile data source do not proofread and correct gps signal to provide can use high relatively (for example; 30 meters) predeterminable range, and can comparatively speaking use the predeterminable range of low (for example, 1 meter) by the data sample that usage variance is proofreaied and correct the mobile data source of GPS equipment and provided.

In addition, data sample filter can comprise identification not with the corresponding data sample of interested road segment segment and/or can not represent data sample in the actual vehicle of travels down.For example, can remove some data samples according to considering, because they are related with the irrespective road of data sample management system.For example, in certain embodiments, the data sample related with the road (for example, residential block street and/or arterial highway) of secondary function road class can be filtered.Return Fig. 2 A again; For example; Can filtering data sample 205a and/or 205k; Because road 203 is to be positioned at the local frontage road of low-down functional classification and not considered by the data sample management system, perhaps also can filtering data sample 205j, do not separate because onramp is too short with the expressway.Filtration can also be based on other factors, the for example deduction in other mobile data source or report behavior on one or more road segment segment.For example, related with road segment segment and might represent that by a series of data samples of representing same position all that single mobile data source provides this mobile data source has stopped.If other data sample of all related with the same link section is all represented the mobile data source of moving; Then the data sample corresponding to the mobile data source that stops can by filtering, be the vehicle that berths owing to the mobile data source for example owing to not being illustrated in the actual vehicle of going on this road segment segment.And; In certain embodiments; Data sample can comprise the report indication (for example, vehicle is transmitted as " parking " that engine starts, and vehicle stops sending) of vehicle traction state; If so, can use such indication to come the such data sample that can not represent the actual travel vehicle of filtering similarly.

Fig. 2 B illustrate with at specified time interval or obtain and the view of a plurality of data samples that road segment segment is related from a plurality of data sources in the section At All Other Times; Wherein data sample marks on curve 210; And x axle 210b is the time of measuring, and y axle 210a is a measured speed.In this instance; Data sample shown in obtaining from a plurality of mobile datas source and one or more road traffic sensors related with road segment segment; And shown in legend in show (promptly with different shape; Black solid diamond " ◆ " is used for from the data sample of road traffic sensors acquisition, and square hollow " " is used for from the data sample of mobile data source acquisition).As said with reference to figure 2A, the shown data sample that comes from the mobile data source can be related with road segment segment.

Exemplary data sample comprises road traffic sensors data sample 211a-c and mobile data source data sample 212a-d.Can confirm the report speed of given data sample and writing time through its position on curve map.Mobile data source data sample 212d have the report speed of (or other speed unit) 15 mph.s and with respect to some starting points at about 37 minutes (or unit) At All Other Times by record.To more describe ground in detail as following, some embodiment can shown in analyze in the special time window in the time period or handle the data that obtained, for example time window 213.In this instance, time window 213 comprises recorded data sample in 10 minutes the time interval of 30 minutes to 40 minutes time.In addition, some embodiment can also become two or more groups with the data sample component that in the special time window, produces, for example, and group 214a and group 214b.For example, the data sample shown in should be noted in the discussion above that shows as the dual model (bi-modal) that has reflected report speed and distributes, and it has the bulk data sample, is reported in the speed in 25-30 mph. scope or the 0-8 mph. scope.This dual model or other multi-model (multi-modal) that possibly produce speed distribute be because; For example bottom magnitude of traffic flow pattern is non-homogeneous; Here owing to for example make traffic to stop-the mobile traffic control signal of walking modes; Or road segment segment comprises a plurality of traffic tracks of moving with friction speed (for example, HOV track or express lane have than other high relatively speed in non-HOV track).In this multi-model that has speed data distributes; Some embodiment can be divided into two or more groups with data sample to be handled; So that processing degree of accuracy that produce to improve or resolution (for example, through calculating the average velocity that reflects each magnitude of traffic flow speed more accurately) and interested additional information the speed of HOV traffic and non-HOV traffic differences (for example); Or recognition data sample group is got rid of (for example, not comprising the part of HOV traffic as subsequent analysis).Though do not illustrate here, this different group of data sample can be discerned in every way, comprise through being the difference distribution modeling of every group of observation speed (for example normal or Gaussian distribution).

Fig. 2 C illustrates filtrator is carried out the removal of data sample exceptional value or considered the instance that the data sample that is not illustrated in the up vehicle of sailing in particular lane highway section is got rid of; It is based on the report speed that is used for data sample (though the one or more of data sample can replace with a part that performs an analysis in other embodiments, no matter and be that the speed of being reported is got rid of in replacement) in this example.Particularly, Fig. 2 C has shown table 220, and it illustrates for the example set execution data sample exceptional value of ten data samples and removes (quantity that is performed in actual use, the data sample of analysis can be bigger).Shown data sample is passable; For example; Be all data samples that in special time window (the for example time window 213 of Fig. 2 B), take place, or alternatively can comprise the subclass (for example included in the group 214a of Fig. 2 B or 214b) of the data sample of special time window or can comprise available all data samples in the longer time section.

In this example; In determined data sample group; Velocity deviation through the average velocity of other data sample from group comes each speed sample in the determining data sample group is identified as the statistics exceptional value with respect to other data sample with non-representational data sample.Can measure the deviation of each speed sample; The numerical value of the standard deviation that for example differs with respect to the average velocity of other data sample in group; The big data sample of its deviation ratio predetermined threshold (for example 2 standard deviations) is identified as exceptional value; And eliminating (for example, through abandoning) from further processing.

Table 220 comprises orientation row 222, and it has described the content of a plurality of row 221a-f.The every capable 223a-j of table 220 illustrates for the exceptional value of a different data sample in ten data samples and removes analysis; Row 221a indicates to be the data sample of every row analysis; Owing to will analyze the each row of data sample, therefore it got rid of from other sample of this group to confirm this result's difference.The data sample of row 223a can be referenced as first data sample, and the data sample of row 223b can be referenced as second data sample etc.Row 221b comprises the report speed of each data sample, and it with how many mph.s is measured.Row 221c has listed with respect to will be by other data sample data sample of relatively given row, in the group, and row 221d has listed the speed on a rough average by the data sample group of row 221c indication.Row 221e has comprised in the speed of the data sample of getting rid of from row 221b and has been listed in the roughly deviation between the average velocity of other data sample the 221d, and it is measured with standard deviation.Whether whether it is bigger than 1.5 standard deviations for this instance purpose to be based on the deviation of listing among the row 221e, be listed as 221f and indicate given data sample should be removed.In addition, the average velocity 224 that is used for all 10 data samples is shown as about 25.7 mph.s, and the standard deviation 225 of all 10 data samples is shown as about 14.2.

Like this, for example, the speed that row 223a illustrates data sample 1 is 26 mph.s.Next, the average velocity that calculates other data sample 2-10 is about 25.7 mph.s.Then the deviation of the average velocity of the speed of computational data sample 1 and other data sample 2-10 is approximately .02 standard deviation.At last, because the deviation of data sample 1 is lower than the threshold value of 1.5 standard deviations, so determining data sample 1 is not an exceptional value.In addition, the speed that row 223c illustrates data sample 3 is 0 mph., and the average velocity of other data sample 1-2 and 4-10 is calculated as about 28.6 mph.s.Then the deviation of the average velocity of the speed of computational data sample 3 and other data sample 1-2 and 4-10 is approximately 2.24 standard deviations.At last, because the deviation of data sample 3 is higher than the threshold value of 1.5 standard deviations, so determining data sample 3 is exceptional values.

More formally, given N data sample v ₀, v ₁, v ₂..., v _n, record and related with given road segment segment, current data sample v in the given time period _nTo be removed, if

$\frac{|v_i-\stackrel{\‾}{v_i}|}{{\mathrm{\σ}}_i}\≥c$

Wherein, v _iFor by the speed of the current data sample analyzed;

Be other data sample (v ₀..., v _I-1, v _I+1..., v _n) average velocity; σ _iStandard deviation for other data sample; C is constant threshold (for example, 1.5).In addition, as the special circumstances of handling the division by 0 that possibly exist, if the standard deviation sigma of other data sample _iBe zero and the speed of current data sample and be not equal to other data sample

Average velocity, then remove current sample v _i

To each v _iBe noted that other data sample (v that might not want iteration all ₀..., v _I-1, v _I+1..., v _n) calculate on average

And standard deviation sigma _iOther data sample v ₀..., v _I-1, v _I+1..., v _nAverage

Also can represent as follows:

$\stackrel{\‾}{v_i}=\frac{N\stackrel{\‾}{v}-v_i}{N-1}$

And other data sample v ₀..., v _I-1, v _I+1..., v _nStandard deviation sigma _iCan represent as follows:

${\mathrm{\σ}}_i=\sqrt{\frac{1}{N-2}[(N-1){\mathrm{\σ}}^2-\frac{N{(v_i-\stackrel{\‾}{v})}^2}{N-1}]}$

Wherein, N is the sum (comprising current data sample) of data sample;

Be all data sample v ₀, v ₁, v ₂..., v _nAverage; v _iBe the current data sample, and σ is all data sample v ₀, v ₁, v ₂..., v _nStandard deviation.Through using above-mentioned formula, calculating mean value and standard deviation efficiently, and particularly can be with constant Time Calculation.Because above-mentioned algorithm has been calculated mean value and standard deviation for each data sample on each road segment segment, thus this rule operation O (MN) time, wherein M is the road hop count, N is the data sample number of each road segment segment.

In other embodiments; Also can use other exceptional value to remove and/or data removal algorithm, can substitute or additional described exceptional value detection, for example based on neural network classifier; The nature Bayes classifier; And/or the regression model technology, and a plurality of data sample group is considered the technology of (for example, if at least some data samples are not independent with other data sample) together.

Fig. 2 D illustrates the instance that uses data sample to carry out the average velocity estimation, and has shown the instance data sample that is used for particular lane highway section and time period that is similar to described in Fig. 2 B.Data sample marks in curve map 230, its in x axle 230b Measuring Time at y axle 230a measuring speed.In certain embodiments, the average velocity of given road segment segment can calculate by periodicity benchmark (for example, per 5 minutes).Each calculating can be in such as the schedule time window (or at interval) of 10 minutes or 15 minutes a plurality of data samples of consideration.If on such time window, calculate average velocity; For example at the terminal of time window or be bordering on the end; Then when collecting the speed of data sample; The weighting in every way of data sample in time window, " age " of for example considering data sample is (for example, based on to because the change of traffic; Therefore older data sample is unlike in more and near the newer data sample that kind of current time place record the such intuition or the expection of precise information of the actual traffic situation of or other current times terminal about time window can be provided, and older data sample is given a discount).Similarly; In certain embodiments; When the weighted data sample, can consider other data sample attribute, for example the type of data source or to be used for the particular source of data sample (for example, more accurate or data source type or the particular source than the better data of other data source can be provided than other data source if data sample comes from; Then just heavier to its weighting), and one or more other weighted factor type.

Shown in instance in, the average velocity that is used for the instance road segment segment calculated once on 15 minutes time window in per five minutes.This case description the relative weighting of two illustrated data sample 231a and 231b because they have contribution to two time window 235a and each average velocity that is calculated of 235b.Time window 235a is included in data recorded sample between 30 and 45 constantly, and time window 235b is included in data recorded sample between 35 and 50 constantly.Data sample 231a and 231b drop in time window 235a and the 235b.

Shown in instance in, each data sample in the preset time window all with the proportional weighting of its age.That is to say that older data sample is than newer data sample weight less (therefore less to the contribution of average velocity).Particularly, in this instance the weight of given data sample according to the minimizing of age indication property.The weighted function of this decay is through illustrating corresponding to two weighting curve 232a and the 232b of time window 235a and 235b respectively.Each weighting curve 232a and 232b mark data sample writing time at x axle (level), mark weight at y axle (vertically).In time the sample weights of back (for example, more near time window terminal) record greater than the sample of (for example, more beginning) record early in time near time window.The weight of given data sample can through on curve 230 from data sample paint downwards perpendicular line to it with corresponding to the place of weight map curve intersection of interested time window find out.For example, weight map 232a is corresponding to time window 235a, and according to the relative age of data sample 231a (older) and 231b (newer), the weight 233a of data sample 231a is less than the weight 233b of data sample 231b.In addition, weight map 232b is corresponding to time interval 235b, and can find out the weight 234b of the weight 234a of data sample 231a less than data sample 231b similarly.In addition, clearly, for the follow-up time window, the weight of given data sample decays in time.For example; The weight 233b of data sample 231b in time window 235a is greater than the weight 234b of the identical data sample 231b in time window 235b afterwards because data sample 231b during the time window 235a than during time window 235b, upgrading relatively.

More normally, in one embodiment, can represent as follows for the weight of the moment t recorded data sample terminal with respect to the time at moment T place:

w(t)＝e ^-α(T-t)

Wherein, e is known mathematics constant, and α is variable parameter (for example, 0.2).More than given, then be N data sample v in time interval of T place end constantly ₀, v ₁, v ₂..., v _nWeighted mean velocity can explain t wherein as follows _iBe data sample v _iThe time (for example, its time of being write down) of expression:

$\mathrm{Weihgted\; average\; speed}=\frac{\underset{i}{\overset{n}{\mathrm{\Σ}}}{v}_i{e}^{-\mathrm{\α}(T-t_i)}}{\underset{i}{\overset{n}{\mathrm{\Σ}}}{e}^{-\mathrm{\α}(T-t_i)}}$

And, the mistake of the average velocity that calculated is estimated and can be calculated as follows:

$\mathrm{Errore\; stimate}=\frac{\mathrm{\σ}}{\sqrt{N}}$

Wherein, N is data sample number and the σ data sample v for coming from average velocity ₀, v ₁, v ₂..., v _nStandard deviation.Also can put the letter value similarly in other embodiments for what the average velocity that calculates or produce was confirmed other form.

As will be attentively, no matter substitute or except age of data sample, data sample can be based on the other factors weighting.For example, data sample can be as stated but is used different weighting function (for example, the weight of data sample is with linear the minimizing rather than the minimizing of index ground of age) to carry out time weight simultaneously.In addition, the data sample weighting can also be based on the sum of the data sample in the interested time interval.For example; Above-mentioned variable parameter α can depend on or based on the sum of data sample and change; So that the older more at most data sample of the quantity of data sample just (for example produces high more punishment; Lower weight), the possibility that is more postponed the increase of (for example, newer) data sample to be reflected as the purpose of calculating average velocity.And data sample can be based on the other factors that comprises the data source type and weighting.For example, can be following situation, specific data source is (for example; Specific road traffic sensors; Or whole traffic sensors of particular network) all be that known (for example, based on the status information of reporting) or expectation (for example, based on history observation) are unreliable or coarse.Under these circumstances, the data sample (for example, the data sample 211a of Fig. 2 B) that obtains from such road traffic sensors can lack than the data sample weighting that from the mobile data source (the for example data sample 212a of Fig. 2 B) obtains.

It is the instance that road segment segment is carried out magnitude of traffic flow estimation that Fig. 2 E has simplified based on data sample, and it for example can comprise infers the volume of traffic, density and/or occupancy.In this example; The volume of traffic of given road segment segment is expressed as in given time window, flowing through the vehicle total amount of road segment segment or the vehicle total amount that in time window, on road segment segment, reaches; The traffic density of given road segment segment (for example can be expressed as the per unit distance; Mile or kilometer) the vehicle total amount, the traffic occupancy can be expressed as vehicle and take particular lane highway section or the mean time area of a room of point on the road segment segment.

Given a plurality of will be by the observation different mobile data source of given road segment segment of coming during given time window, to go; With as the known of total vehicle in mobile data source or expection number percent, then can infer total volume of traffic---the vehicle fleet (comprising the vehicle that is not the mobile data source) of the road segment segment of during time window, going.Average velocity from the estimation of total volume of traffic of being inferred and the vehicle on road segment segment just can further calculate traffic density and road occupancy.

A kind of simple approach of estimation total volume of traffic in particular lane highway section during the special time window is that the number percent of using expectation will become the actual vehicle of mobile data sample source is simply removed the quantity in the mobile data source of this time window---like this; For example; If in time window, will become the mobile data sample source from 25 mobile data sources reception mobile data samples and at 10% of the total vehicle of road segment segment expection, the total amount of then estimating for the time quantum of this time window is 250 actual vehicle.But because the intrinsic changeability of vehicle arrival rate, if particularly the expectation number percent of mobile data sample source is very little, then this approach possibly cause the great variety of adjacent time window total amount estimation.As a kind of replacement, it provides more complicated analysis, and total volume of traffic of given road segment segment can be inferred as follows.The different mobile data source of given specific quantity (for example, each vehicle) n on the road segment segment of length l, in given time period τ, uses Bayesian statistics to infer the main average rate (underlying means rate) that the mobile data source arrives, λ.The mobile data source that on one section road corresponding to road segment segment, arrives can stochastic modeling, and therefore discrete processes can be described through Poisson statistics, that is: on time

$p\left(n\right|\mathrm{\λ})=\frac{{\mathrm{\λ}}^n{e}^{-\mathrm{\λ}}}{n!}$

From above formula, can calculate the possibility that n mobile data source observed, given mean arrival rate λ and the vehicle number n that is observed.For example, assumed average arrival rate λ=10 (vehicle/unit interval) and observation n=5 portion vehicle, then replacement produces:

$p\left(n\right|\mathrm{\&lambda;})=\frac{{10}^5{\mathrm{<figure-callout\; id="10"\; label="e"\; filenames="HDA0000080815930000031.png,HDA0000080815930000041.png"\; state="\{\{state\}\}">e</figure-callout>}}^{10}}{5!}\&ap;0.038$

Expression actual observation n=5 portion vehicle has 3.8% possibility.Similarly, (that is, n=10) possibility is 12.5% if mean arrival rate is λ=10 (vehicle/unit interval) then actual observation to 10 vehicle reaches.

Above formula can make the possibility of the specific arrival rate λ that is used for confirming the given n of observation with Bayes' theorem.Like what known, Bayes' theorem is:

$p\left(\mathrm{\&lambda;}\right|n)=\frac{p\left(n\right|\mathrm{\&lambda;})p\left(\mathrm{\&lambda;}\right)}{p\left(n\right)}$

Remove through replacement and constant, can obtain as follows:

$p\left(\mathrm{\&lambda;}\right|n)\&Proportional;\frac{{\mathrm{\&lambda;}}^n{e}^{-\mathrm{\&lambda;}}}{n!}$

From above, the proportional or relative possibility of arrival rate λ can be calculated in n mobile data source of given observation, and the probability distribution of the probable value of λ is provided when each observed reading of given n.For the particular value of n, the degree of confidence that the possibility on each arrival rate value distributes and allows to select a representational arrival rate value (for example, mean value or intermediate value) and allow this value of estimation.

And, give the known percentage fix on the road as total vehicle in mobile data source, also as " permeability factor ", therefore can calculate the arrival rate amount of total traffic as follows:

$\mathrm{Total\; traffic\; volume}=\frac{\mathrm{\&lambda;}}{q}$

In certain embodiments, the total volume of traffic on the road segment segment alternatively can be expressed as the total amount k of vehicle that flows through the length l of road segment segment at time τ in the time period.

Fig. 2 E illustrates given observation sample size, the probability distribution of various total volume of traffic of given sample mobile data source permeability factor q=0.014 (1.4%).Particularly, Fig. 2 E illustrates three-dimensional curve diagram 240, and it has marked the mobile data source number (n) that observes on y axle 241, on x axle 242, has indicated the traffic arrival rate amount of inferring, and on z axle 243, has indicated the possibility of the traffic value of each deduction.For example; This curve map shown given mobile data source observation count n=0, the actual traffic amount is about 0.6 (or 60%) near the possibility zero, as by shown in the hurdle 244a; And time per unit actual traffic amount is about 0.1 in the possibility of 143 left and right vehicle wheels, shown in hurdle 244b.And; Given mobile data source observation count n=28; Then the total actual traffic amount of time per unit at 2143 left and right vehicle wheels (corresponding to about 30 the mobile data sample sources of time per unit; The permeability factor of given instance) possibility is about 0.1, and shown in hurdle 244c, it has shown the intermediate value that approaches total actual traffic amount.

In addition, can use total traffic arrival rate amount (being illustrated in the vehicle number k that arrives in the time τ of road segment segment) of the deduction that is used for given road segment segment, the average velocity v that is estimated and average vehicle length d to calculate average occupancy and density, then

Vehicles?per?mile， $m=\frac{k}{\mathrm{v\&tau;}}$

Occupancy＝md

As discussed previously, the average velocity v of the vehicle on road segment segment can obtain through the operating speed estimating techniques, the description of for example being done with reference to figure 2D.

Figure 10 A-10B illustrates adjustment or revises the instance from the misdata sample of the for example unreliable and obliterated data sample of road traffic sensors etc.Particularly, Figure 10 A has shown a plurality of instance data readings that obtain from a plurality of traffic sensors in each time, and it is organized in the table 1000.Table 1000 comprises a plurality of data readings row 1004a-1004y; Its each comprise that unique identification provides traffic sensor ID (" the identifier ") 1002a of the traffic sensor of reading; Traffic sensor data read numerical value 1002b comprises the traffic flow information by the traffic sensor report; The traffic sensor reading duration, 1002c reflected the time by traffic sensor image data reading, and traffic sensor state 1002d comprises the indication of traffic sensor mode of operation.Though traffic sensor can be reported the traffic flow information (for example, the volume of traffic and occupancy) of other type in other embodiments, in this instance, has only shown velocity information, and value also can be with other form report.

Shown in instance in, data readings 1004a-1004y can each time by a plurality of traffic sensor collections and can being shown in the table 1000 by record sheet.In some cases, data readings by traffic sensor periodically (for example, per minute, per five minutes etc.) gather and/or with such cycle by this traffic sensor report.For example; Traffic sensor 123 per five minutes image data readings; Shown in data reading 1004a-1004d and 1004f-1004i, it has shown a plurality of data readings of being gathered independently two days (being 8/13/06 and 8/14/06) at 10:25AM and 10:40AM by traffic sensor 123 in this instance.

Data readings 1004a-1004y shown in each comprises data read numerical value 1002b, and it comprises the traffic flow information of being observed or being obtained by data transducer.Such traffic flow information can comprise the arrival of going, close on or pass through one or the speed of multi-section vehicle of traffic sensor.For example, data readings 1004a-1004y has shown the car speed that sensor 123 observes four different time respectively, 34 mph.s (mph), 36mph, 42mph and 38mph.In addition, traffic flow information can comprise the arrival of going, close on or vehicle total amount or counts through traffic sensor, and no matter substitutes or except speed and/or out of Memory.Total quantity can be when traffic sensor is mounted or activate, the semi-invariant of the vehicle of traffic sensor observation.Counts can be from sensor acquisition formerly during data readings, by the semi-invariant of the vehicle of traffic sensor observation.Data readings 1004w-1004x has shown at two different time sensors 166 and has added up 316 cars and 389 cars respectively.In some cases, the recorded data reading can not comprise data read numerical value, for example work as given traffic sensor and sensor fault occurred, thus can not collection or hourly observation or report observation (for example, because network failure).For example, data readings 1004k has shown that traffic sensor 129 can not provide data read numerical value at the 10:25AM of 8/13/06 this day, as indicated in data read numerical value row 1002b by "--".

In addition, traffic sensor state 1002d can be related with at least some data readings, if for example traffic sensor and/or corresponding communication network provide the indication of the mode of operation of this traffic sensor.In an illustrated embodiment, mode of operation comprises that sensor function indicates (for example, OK) normally; The sensor off-position (for example, OFF) indication, sensor (is for example handled the single value of report; STUCK) indication, and/or break off (COM_DOWN) indication with the communication link of network is as respectively at data readings 1004m; 1004k is shown in 1004o and the 1004s.In other embodiments, other and/or different information of the mode of operation that relates to traffic sensor can also be provided, perhaps can mustn't go to this operational status information.Other traffic sensor, for example traffic sensor 123 and 166 is not configured to provide traffic sensor state indication in this embodiment, as among the traffic sensor status Bar 1002d shown in "--".

Row 1004e, 1004j, 1004n, 1004q, 1004v and 1004y be listed as 1002e point out to write down additional traffic sensor data readings in certain embodiments and/or can provide additional information also/or it is recorded as the part of each data readings.Similarly, in certain embodiments, information is lacking of showing than using described technology here.

Figure 10 B illustrates the instance of the mistake in the traffic sensor data readings that detects the unsound traffic sensor that expression can not correctly work.Particularly; Because a lot of traffic sensors can not provide the indication of traffic sensor state; And since in some cases the indication of such traffic sensor state possibly be insecure (for example; The indication sensor function is undesired but in fact it is normal, or the indication sensor function normally but in fact it is undesired), therefore possibly need to use statistics and/or other technology to detect unsound traffic sensor based on the data read numerical value of being reported.

For example; In certain embodiments; Unsound traffic sensor can through will by the time period of given traffic sensor in certain day (for example; At 4:00PM and 7:29PM) in the history of the data readings reported in same time period of (for example, 120 of the past days) in the past several days of current distribution and this sensor of the data readings reported distribute and compare and detect.Such distribution can be through for example handling from producing such as a plurality of data readings that obtain at the traffic sensor shown in Figure 10 A.

Figure 10 B has shown three histograms 1020,1030 and 1040, its each expression be based on the data readings of the data readings that obtained from traffic sensor 123 in the interested time period distribute.At histogram 1020; The interval that the data of expression are dispersed to 5 mph.s in 1030 and 1040 (for example; 0 to 4 mph., 5 to 9 mph.s, 10 to 14 mph.s etc.) and standardization; So that every hurdle (for example the hurdle 1024) representative occurs in the probability of inherent 0 and 1 of this time period (for example, being based on the number percent of data readings in the time period that falls in this barrel) for the car speed of this hurdle car speed in 5 mph. buckets (bucket).For example; Hurdle 1024 is illustrated in car speed between 50 and 54 mph.s by 123 observations of traffic sensor; About 0.23 probability is arranged, for example based on having about 23% (containing) of the data readings that obtains from traffic sensor 123 the report speed between 50 and 54 mph.s.In other embodiments, can use one or more other barrel sizes, and no matter or the bucket of replacement 5mph.For example, the 1mph bucket can provide thinner processing at interval, if but in the time period, can not obtain sufficient data readings, ++ then also possibly cause the great variety between adjacent bucket, and the 10mph bucket can provide less variation but details is also few.In addition, though current instance uses average velocity as the measuring of data readings analysis and comparison, other embodiment also can use one or more replacements or except that average velocity other to measure.For example, at least some embodiment, can use the volume of traffic and/or occupancy similarly.

In this instance, histogram 1020 has represented that in the past the history of the data readings that by traffic sensor 123 gathered between 9:00AM to 12:29PM 120 days Monday distributes.The distribution of the data readings that histogram 1030 expression is just often gathered by sensor 123 between the 9:00AM to 12:29PM of specific Monday when sensor 123 functions.Can find out clearly that the shape of histogram 1030 and histogram 1020 are similar, suppose in the expection of the travel pattern of specific Monday similarly, then as following will the discussion, can calculate similar degree in every way with the travel pattern of general Monday.The distribution of the data readings that histogram 1040 expressions are gathered by traffic sensor 123 between the 9:00AM to 12:29PM of specific Monday when sensor 123 functions are undesired, and export the data readings that can not reflect the actual traffic flow on the contrary.As obviously find out ground, the shape of histogram 1040 is different with histogram 1020 significantly, and it has reflected the data readings by the mistake of traffic sensor 123 reports.For example, projection huge in this distribution can find out in hurdle 1048, and sensor 123 had been stuck and has reported a large amount of constant reading that can not reflect the actual traffic flow when it possibly be illustrated at least some between 9:00AM to 12:29PM.

In certain embodiments; Confirm the similarity between two distributions though can use in the Kullback-Leibler divergence (divergence) between two traffic sensor DATA DISTRIBUTION, similarity or the difference between distributing also can otherwise be calculated in other embodiments.The Kullback-Leibler divergence is that the convexity of the similarity of two probability distribution P and Q is measured.It can be represented as follows:

$D_{\mathrm{KL}}\left(P\right|\left|Q\right)=\underset{i}{\mathrm{\&Sigma;}}{P}_i\log \left(\frac{P_i}{Q_i}\right)$

Wherein Pi and Qi are the value (for example, each Pi and Qi are that speed appears at i the probability in the bucket) of discrete probability distribution P and Q.Shown in instance in; The data readings shown in the histogram 1020 distribute and the Kullback-Leibler divergence (" DKL ") 1036 that between the data readings shown in the histogram 1030 distributes, is used for healthy traffic sensor for about 0.076, and distribute and the Kullback-Leibler divergence 1046 that between the data readings shown in the histogram 1040 distributes, is used for unsound traffic sensor is about 0.568 in the data readings shown in the histogram 1020.As possibility is desired; DKL 1036 is significantly less than DKL 1046 (in this case; Be approximately DKL 1046 13%), it similar in appearance to histogram 1020 (has for example reflected histogram 1030 (for example, being illustrated in the output of traffic sensor 123 just often of its function); The average behavior of expression traffic sensor 123) is far more than that more histogram 1040 (traffic sensor 123 when for example, being illustrated in its fault) is similar in appearance to histogram 1020.

In addition, substitute such as the similarity of coming and measure or in addition, some embodiment can use other statistics to measure and detect the misdata reading that is provided by traffic sensor, for example statistical information entropy from the Kullback-Leibler divergence.The statistical entropy of probability distribution is the measuring of otherness of probability distribution.The statistical entropy of probability distribution P can be represented as follows:

$H\left(P\right)=-\underset{i}{\mathrm{\&Sigma;}}{P}_i\log P_i$

Wherein, Pi is the value (for example, each Pi is the interior probability of i bucket that speed drops on the P histogram) of discrete probability distribution P.In an illustrated embodiment; Statistical entropy 1022 in the distribution shown in the histogram 1020 is approximately 2.17; Statistical entropy 1032 in the distribution shown in the histogram 1030 is approximately 2.14, and is approximately 2.22 in the statistical entropy 1042 of the distribution shown in the histogram 1040.As maybe be expectedly, statistical entropy 1042 be all bigger than statistical entropy 1032 and statistical entropy 1022, and this has reflected that traffic sensor 123 has been showed chaotic more output mode when its fault.

In addition, the difference between two statistical entropies are measured can be measured through calculating the entropy difference measurement.Entropy difference measure between two probability distribution P and Q can be represented as follows:

EM＝||H(P)-H(Q)|| ²

Wherein H (P) and H (Q) are respectively the entropy of probability distribution P and Q as stated.Shown in instance in; Be approximately 0.0010 in distribution shown in the histogram 1020 and the entropy difference measure between the distribution shown in the histogram 1030 (" EM ") 1034, and be approximately 0.0023 in distribution shown in the histogram 1020 and the entropy difference measure 1044 between the distribution shown in the histogram 1040.As can be expectedly; That the obvious specific entropy difference measure 1034 of entropy difference measure 1044 are wanted is big (in this situation big twice), and this has reflected the statistical entropy of the distribution shown in the histogram 1040 and has wanted big in the difference between the statistical entropy of the distribution shown in the histogram 1020 than statistical entropy and the difference between the statistical entropy of the distribution shown in the histogram 1020 in the distribution shown in the histogram 1030.

Can use above-mentioned statistics to measure in every way and detect unsound traffic sensor.In certain embodiments, the various information that relevant current data reading distributes can be provided as the input to healthy (or the data readings reliability) sorter of sensor, for example based on neural network, Bayes classifier, decision tree etc.For example, the sorter input information can comprise, for example, and the statistical entropy that Kullback-Leibler divergence between the historical data reading that is used for this traffic sensor distributes and the current data reading that is used for this path sensor distributes and current data reading distribute.Then, sorter is estimated the health of this traffic sensor based on the input that is provided, and the output of expression health or unhealthy sensor is provided.In some cases, the input that also provides additional information to be used as sorter, for example the indication of the time in one day is (for example; Time period from 5:00AM to 9:00AM); The indication of in one week certain day or a few days (for example, from the Monday to the Thursday, Friday; Saturday or Sunday) and/or distribute corresponding to current and historical data reading one day in time or certain day in the week, the size of mph group etc.Sorter can be trained through using actual past data reading, such as the expression that comprises the traffic sensor state, as shown in Figure 10 A.

In other embodiments, unsound traffic sensor need not to use sorter just can be identified.For example, if one or more statistics is measured greater than predetermined threshold value, can confirm that then traffic sensor is unsound.For example; If the historical data reading that is used for traffic sensor distribute and the current data reading that is used for this path sensor Kullback-Leibler divergence between distributing greater than first threshold; If the statistical entropy that the current data reading distributes is greater than second threshold value; If and/or the entropy difference measure between distribution of current data reading and the distribution of historical data reading can confirm then that greater than the 3rd threshold value this traffic sensor is unsound.In addition, also can use other non-statistical information, whether report such as traffic sensor to be considered to healthy or unsound sensor states.

Will be attentively like previous institute, though above-mentioned technology mainly is described in the context of the traffic sensor of reporting vehicle velocity information, same technology also can be used other traffic flow information, comprise the volume of traffic, density and occupation rate.

Fig. 3 is some the structural drawing of embodiment of computing system 300 that diagram is suitable for carrying out said at least technology, for example through carrying out data sample management system implementation example.Computing system 300 comprises CPU (" CPU ") 335; Each I/O (" I/O ") assembly 305; Storer 340 and internal memory 345, and shown I/O assembly comprises display 310, network connection 315; Computer-readable medium drive 320 and other I/O equipment 330 (for example, keyboard, mouse or other optional equipment, microphone, loudspeaker etc.).

In an illustrated embodiment; In internal memory 345, carry out some that various systems carry out said at least technology; Comprise that data sample management system 350, predicted traffic information provide system 360, key road identifier system 361, road segment segment to confirm system 362, RT information providing system 363 and other the optional system that is provided by program 369, these various executive systems all are referred to as traffic information system usually here.Computing system 300 and its executive system can be via network 380 (for example; Internet, one or more mobile telephone networks etc.) communicate by letter with other computing system, for example each client device 382, based on client and/or data source 384, road traffic sensors 386, other data source 388 and third party's computing system 390 of vehicle.

Particularly; Data sample management system 350 obtains the information of the situation data of various relevant current traffic condition and/or previous observation from each source, for example from road traffic sensors 386, based on the mobile data source 384 of vehicle and/or other moves or non-moving data source 388 obtains.Then data sample management system 350 is through (for example filtering; Consider to remove data sample) and/or adjustment is (for example; Error recovery) data are come the data preparing to obtain for the use of other assembly and/or system; Then use the data of being prepared to estimate the road traffic condition of each bar road segment segment, the for example magnitude of traffic flow and/or speed.Among the embodiment shown in this; Data sample management system 350 comprises data sample filter assemblies 352, sensing data adjustment assembly 353, data sample exceptional value removal assembly 354, data sample velocity estimation assembly 356, data sample flow estimation assembly 358 and optional sensor data collection assembly 355; Wherein assembly 352-358 carries out and is similar to the described function of the corresponding assembly of front in Fig. 1 (for example, data sample filter assemblies 104, sensing data adjustment assembly 105, data sample exceptional value are removed assembly 106, data sample velocity estimation assembly 107, data sample flow estimation assembly 108 and optional sensor data collection assembly 110).In addition, at least some embodiment, the data sample management system with basic in real time or the mode of near real time carry out the estimation of road traffic condition, for example in a few minutes, obtain bottom data (himself can obtain with real-time basically mode from data source).

Other traffic information system 360-363 and 369 and/or third party's computing system 390 then can use the data that provide by the data sample management system in every way.For example; Predicted traffic information provides system 360 can obtain (directly; Or indirectly via database or memory device) this data of preparing to be producing further traffic condition predictions in a plurality of Future Time, and information of forecasting is offered one or more other receiving ends, for example one or more other traffic information systems; Client device 382 is based on client 384 and/or third party's computing system 390 of vehicle.In addition; RT information providing system 363 can obtain the information of the relevant road traffic condition of being estimated from the data sample management system; And with road traffic condition information with in real time or be bordering on real-time mode and (for example offer its side; Client device 382; Client 384 and/or third party's computing system 390 based on vehicle)---when the data sample management system also with this in real time or when being bordering on real-time mode and carrying out estimation; The actual vehicle travel conditions of the same period that the take over party of the data from the RT information providing system can be based on one or more road segment segment is browsed and the information of using relevant current traffic condition on these road segment segment (like what reported by mobile data source of going in these road segment segment and/or sensor, and other data source provides the information of relevant actual vehicle travel conditions on these road segment segment).

Client device 382 can adopt various forms in each embodiment, and can comprise that usually any communication facilities and other request of producing receives any computing equipment of information to traffic information system and/or from traffic information system.In some cases; Client device (for example can be carried out the operable mutual controlling application program of user; Web browser) with produce request to the information that relates to traffic (for example, the future transportation condition information of prediction, in real time or be bordering on real-time current traffic condition information etc.); And in other situation; The information that relates to traffic that at least some are such can automatically be sent to client device (for example, text message, the new Web page, specific routine data renewal etc.) from one or more traffic information systems.

Road traffic sensors 386 comprises in a plurality of each street, expressway or other roads that are installed in such as one or more geographic areas, goes up or near sensor.These sensors can comprise loop sensor, the speed of the quantity of energy measurement time per unit through the vehicle of these sensors, vehicle and/or relate to other data of the magnitude of traffic flow.In addition, such sensor can comprise camera, motion sensor, radar ranging equipment, based on the equipment of RFID be positioned at the next-door neighbour or near the sensor of other type of road.Road traffic sensors 386 can be periodically or continuously through based on wired or through the network 380 that uses one or more data exchange mechanisms (for example, push away, draw, token, request-reply, point-to-point etc.) the data measured reading is offered data sample management system 350 based on wireless data link.In addition; Though do not illustrate here; But in certain embodiments; One or more gatherers of such road traffic sensors information (for example, the traffic department of government of operation sensor) can replace and obtain raw data and make data is available (no matter be original form or be processed back at it) to traffic information system.

Other data source 388 comprises polytype other data source, and it can be made by one or more traffic information systems and be used for providing the information of relevant traffic to user, consumer and/or other computing system.Such data source comprises Map Services and/or the database that relevant road network information can be provided; For example each other connective of each bar road and the traffic control signal (for example, the existence and the position in traffic control signal and/or speed limit district) that relates to such road.Other data source can also comprise the source about the information of the incident of influence and/or reflection traffic and/or situation; Arrange for example short-term and long-range weather forecasting, school's schedule and/or calendar, schedule of events and/or calendar, the traffic accident report that provides by manual operation person (for example, first present members, law enfrocement official, expressway employee, news media, tourist etc.), road job information, holiday etc.

In this embodiment each can be to be positioned at vehicle data are offered one or more traffic information systems and/or receive data computing system and/or communication systems from one or more these systems based on the clients/data sources of vehicle 384.In certain embodiments, data sample management system 350 can be used for the use of traffic information system and mobile data source and/or other distributed network based on user's mobile data source (not shown) based on vehicle of the information that relates to current traffic condition are provided.For example; Every vehicle or other mobile data source can have GPS (" GPS "), and equipment (for example; Have the mobile phone of GPS function, GPS equipment etc. independently) and/or other can confirm the geolocation device in geographic position; And possibly also have out of Memory; For example speed, direction, height above sea level and/or other relate to the data of vehicle ', and geolocation device or other different communication facilities obtain sometimes and provide such data to one or more traffic information systems (for example, through Radio Link).Such mobile data source will discuss in more detail elsewhere.

Alternatively, based on some of the clients/data sources 384 of vehicle or all each can have the computing system that is positioned at vehicle and/or communication system with from one or more traffic information system acquired informations, for example for vehicle user's use.For example; Vehicle can comprise the Web browser with installation or embedded panel board (in-dash) navigational system of other controlling application program; The user can use this system to come from one of traffic information system (for example predicted traffic information provides system and/or RT information providing system) request traffic relevant information, and perhaps these requests can be sent by the user's in the vehicle portable set.In addition, one or more traffic information systems can be based on the reception of lastest imformation or produce automatically will be referred to traffic information transmission to such client device based on vehicle.

Third party's computing system 390 comprises one or more optional computing systems, and it is by operator's operation of a side's who uses data such as a side of the data that receive relevant traffic from one or more traffic information systems with certain mode etc. other people rather than traffic information system.For example; Third party's computing system 390 can be such system; It is from one or more traffic information system receiving traffic informations; And related information (no matter being the out of Memory that the information that received also is based on the information that is received) offered user or other people (for example, through Web inlet or subscription service).Alternatively; Third party's computing system 390 can be operated by a side of other type; For example collect and report the media organization of traffic, or provide the information of relevant traffic to be used as the Online Map company of an itinerary service part for their user to the consumer.

Will be attentively as front institute, the data that predicted traffic information provides system 360 to use to be prepared by data sample management system 350 and other assembly in the embodiment shown are to produce the traffic condition predictions in future of a plurality of future times.In certain embodiments; The probability technology has been used in the generation of forecast; Its merged that various types of input data think many road segment segment each produce a series of future times forecasts repeatedly, for example be based on the road network in the given geographic area changing the present situation and with real-time mode.And; In at least some embodiment; Automatically creating one or more predictability Bayes or other model (for example, decision tree) in giving the future transportation condition predicting of each interested geographic area, using, for example based on the historical traffic of being observed of these geographic areas.The future transportation condition information of predictability can use helping travelling or other purpose in every way, so that based on the prediction plan of the traffic of the road of a plurality of Future Time optimal route through road network.

And, road segment segment confirm system 362 can use provide the Map Services that relates to the information of road network in one or more geographic areas and/or database with confirm automatically and management relate to maybe be by the information of the employed relevant road of other traffic information system.The information of relevant road like this can comprise (for example the confirming of specific part of the road that will be used as interested road segment segment; Traffic based on these road parts and other adjacent road part); And (for example in the road segment segment of given road network and institute interested out of Memory indication; The physical location of road traffic sensors, case point, terrestrial reference; Information about function road class and other relevant traffic characteristic; Deng) between the related or relation that automatically produces.In certain embodiments, road segment segment confirm that system 362 can periodically carry out and for the use of other traffic information system in storer 340 or database (not shown) its information of producing of storage.

In addition; Key road identifier system 361 uses given geographic area of expression and the road network that is used for the traffic related information of that geographic area; Thinking tracking and estimation road traffic condition and discern interested road automatically, for example is the use of other traffic information system and/or traffic data client.In certain embodiments; The automatic identification of interested road (or one or more road segment segment of road) can be at least in part based on following factor, the value of the peak value volume of traffic or other flow for example, the value of peak value traffic congestion; Changed the same day of the volume of traffic or other flow; Changed the same day of congestion in road, and (inter-day) in the daytime of the volume of traffic or other flow changes, and/or the variation in the daytime of congestion in road.Such factor can be analyzed through for example primary clustering (principal component); For example, then calculate the eigen decomposition of covariance matrix S through at first calculating the covariance matrix S of the traffic related information that in given geographic area, is used for all roads (or road segment segment).Then in the descending of eigenwert, the eigenvector of S representes that independently the variation to the traffic of being observed has the combination of the road (or road segment segment) of the strongest contribution.

In addition, Real-time Traffic Information provides or presents system can perhaps alternatively be provided by one or more other programs 369 by the RT information providing system.Information providing system can use by data sample management system 350 and/or other assembly (for example predicted traffic information provides system 360) and analyze and the data that provide are come for operation or used client device 382, based on the consumer and/or the commercial entity of the client 384 of vehicle, third party's computing system 390 etc. traffic-information service are provided, so as at least in part based on the data sample that obtains from vehicle and other mobile data source with in real time or be bordering on real-time mode data are provided.

Can predict, shown computing system only is schematically and not to attempt to limit scope of the present invention.Computing system 300 can be connected with other unshowned equipment, comprises through the network of one or more for example internets or via Web.Generally speaking; " client " or " server " computing system or equipment; Or traffic information system and/or assembly; Can comprise can be mutual and the combination in any of the hardware and software of carrying out said type of functionality; Include but not limited to desktop or other computing machine, database server, the network storage equipment and other network equipment, PDA, cellular mobile phone, wireless telephone, beeper, communicator, internet application, based on system's (for example, using STB and/or individual/digital video recorder) of TV with comprise various other consumer products with suitable interactive communication ability.In addition, in certain embodiments by shown in the function that provides of system component can be integrated in the assembly still less or be distributed in the additional assembly.Similarly, the function of some in the assembly shown in certain embodiments can not be provided and/or can obtain other additional function.

In addition, can be stored in storer or the memory storage though various projects are as directed when using, for the purpose of memory management and/or data integrity, these projects or their part can be transmitted between storer and other memory device.Alternatively, in other embodiments component software and/or module some or all can in the storer on another equipment, carry out and through the communication of intercomputer with shown in computing system communicate by letter.Some of system component or data structure or all also (for example can be stored in computer-readable medium; As software instruction or structural data), for example by suitable driver or the hard disk that reads through suitable connection, storer, network or portable media medium.System component and data structure (for example also can be transmitted as the data-signal that produced on various computer-readable transmission mediums; Part as carrier wave or other analog or digital transmitting signal); Comprise based on wireless and based on the medium of wired/cable; And can adopt various forms (for example, as the part of single or multiplexing simulating signal, or as a plurality of discrete digital packets or frame).In other embodiments, such computer program can also adopt other form.Therefore, the present invention also can realize with other Computer Systems Organization.

Fig. 4 is the process flow diagram of the exemplary embodiment of data sample filtrator routine 400.This routine can be provided by the execution of the embodiment of the data sample filter assemblies 104 of the data sample filter assemblies 352 of for example Fig. 3 and/or Fig. 1; So that receive data sample, and filter out uninterested data sample for the estimation of back corresponding to road in the geographic area.The data sample that filters then can use in every way subsequently, for example uses the data sample that filters to calculate the average velocity in institute interested particular lane highway section and calculates other characteristic about the magnitude of traffic flow for such road segment segment.

Routine is that the geographic area of special time period receives the data sample group in step 405 beginning here.In step 410, routine is some of these data samples based on other relevant data sample alternatively then or all produces additional information.For example; Lack institute's information of interest (the for example speed in mobile data source and/or orientation or direction) if be used for the particular data sample in vehicle or other mobile data source, then such information can combine previous and subsequent data sample to identical mobile data source one or both of and confirm.In addition; In at least some embodiment; Can collect from the next information that is used for specific mobile data source of a plurality of data samples and estimate additional information type about this data source; So that estimation is across the behavior of the data source in the time period of a plurality of data samples (for example, determining whether that vehicle has stopped a few minutes rather than stop to be used as in one or two minute the normal wagon flow of traffic, for example meets stop sign or stop light) temporarily.

After step 410; Though it is related with the particular lane highway section of road in this geographic area and this road to attempt each data sample that routine proceeds to step 415; But this step can not be performed or otherwise carry out in other embodiments; If for example the initial association of data sample and road and/or road segment segment receives in step 405 at least; If or alternatively whole routine is next corresponding to a road segment segment thereby all data samples that in step 405, receive are organized as one to a road segment segment execution one time.In an illustrated embodiment, data sample can be carried out with the related of road and road segment segment in every way, for example carries out initial association (for example, that data sample is related with nearest road and road segment segment) based on the geographic position related with this data sample separately.And; This association can comprise alternatively that additional analysis is with concise or revision initial association---for example; (for example many road segment segment are used for a specific road if location-based analysis indication has a plurality of possible road segment segment for data sample; Or alternatively many road segment segment are used to close on but incoherent road); Then such analyzing adjuncts can use the out of Memory such as speed and direction to influence related (for example, merging positional information and one or more other such factor through the mode with weighting).Like this; For example; If the reported position of data sample is between expressway and adjacent frontage road; Then just can use the information of the speed of reporting of relevant data sample to help with this data sample related with suitable road (for example, through confirming to come from frontage road) with 25 mph. speed limits with the data sample of the velocity correlation of 70 mph.s.In addition; In the certain extension of road or other road part and many different road segment segment (for example; Road for two-way traffic; Going and be modeled as first road segment segment and going on another direction is modeled as the second different road segment segment in one direction wherein; Or alternatively for the expressway of multilane, the HOV track is modeled as and one or more adjacent non-HOV track road segment segment independently) under the situation about being associated, can use the road segment segment of selecting most possible road for this data sample such as the additional information of relevant data samples such as speed and/or direction.

After step 415, routine proceed to step 420 think follow-up processing filter out not with the related any data sample of interested road segment segment, comprise not related data sample (if having) with any road segment segment.For example; The part of specified link or road possibly not be that subsequent analysis institute is interested; The road of for example getting rid of specific function road class (for example; Can be interested to some extent if the size of road and/or the volume of traffic are not large enough to), or because such as ramp, expressway or special-purpose road or cross/traffic characteristic of such road part such as minute cross road can not reflect expressway as a whole, therefore get rid of such road part.Similarly; Under many road segment segment situation related with the specific part on road; Some road segment segment are maybe some purpose institute interested; If for example having only the behavior in non-HOV track is that specific purpose institute is interested, if or to have only a direction be interested in the track of both direction, then be eliminating HOV track, expressway.Though after step 420, routine proceeds to step 425 to determine whether the behavior filtering data sample based on data source, so in other embodiments filtration also can not be performed or also can carry out always.In an illustrated embodiment; If filtration is carried out in the behavior based on the source; Then routine proceeds to step 430 to carry out such filtration; For example remove corresponding to its behavior can not reflect the data source of the interested magnitude of traffic flow behavior of institute of wanting measured data sample (for example, get rid of that engine is starting the vehicle that stops in the time expand section, get rid of in the time period that prolongs stop or parking lot or other zonule in the vehicle that spins etc.).After step 430; If or alternatively in step 425, confirm not filter based on the behavior of data source; Then routine proceeds to the data that step 490 is thought follow-up use stored filter, but the data of filtering in other embodiments alternatively can directly offer one or more clients.Then routine proceeds to step 495 to determine whether continuation.If continue, then routine turns back to step 405, if do not continue, then arrives step 499 and end.

Fig. 5 is the process flow diagram of the exemplary embodiment of data sample exceptional value remover routine 500.This routine can be removed the embodiment of assembly 106 and provided by the data sample exceptional value that the data sample exceptional value of for example execution graph 3 is removed assembly 354 and/or Fig. 1, is the data sample of exceptional value thereby remove for this road segment segment with respect to other data sample of road segment segment.

This routine receives the one group of data sample that is used for road segment segment and time period therein in step 505 beginning.The data sample that is received can be, the data sample of the filtration that for example obtains from the output of data sample filtrator routine.In step 510, routine then is divided into a plurality of groups with reflection different part of road segment segment and/or different behavior with data sample alternatively.For example; If a part and these many tracks that track, many expressways is included in together as the single road section comprise at least one HOV track and one or more non-HOV track; If the magnitude of traffic flow then in the time period is significantly different between HOV and non-HOV track, then can separate with the vehicle on other track at the vehicle on the HOV track.Can carry out such grouping in every way, for example data sample fitted to many curves, every curve is represented the typical data sample changed (for example, normal state or Gaussian curve) in the particular data sample group.In other embodiments; Also can not carry out such grouping; All reflect similar behavior (for example, alternatively being split into many road segment segment) if for example alternatively cut apart road segment segment for use in all data samples of this road segment segment if having the expressway in HOV track and other non-HOV track.

Routine proceeds to step 515, is each (if there is not the separation of the data sample of execution in step 510, then all data samples are regarded as a group) of one or more data sample groups, calculates the average traffic characteristic of all data samples.This average traffic characteristic can comprise, for example, and average velocity, and such as the corresponding statistical informations such as standard deviation with respect to intermediate value.Routine then proceeds to step 520; To each of this one or more data sample groups, carry out continuously and remove one (leave-one-out) and analyze so that select and specific will and confirm average traffic characteristic by the target data sample of temporary transient removal for remaining traffic characteristic.Difference between average traffic characteristic that is used for the remaining data sample and the average traffic characteristic that is used for all data samples from step 515 is big more, and then removed target data sample is to reflect that the possibility of exceptional value of public characteristic of other remaining data sample is just big more.In step 525; Routine is then carried out the exceptional value analysis of one or more addition type alternatively; Thereby thereby the group of removing two or more target data samples is continuously estimated their joint effect, but also can not carry out so additional exceptional value analysis in certain embodiments.After step 522, routine proceeds to step 590 removing the data sample in step 520 and/or 525, be identified as exceptional value, and stores remaining data sample for follow-up use.In other embodiments, routine alternatively can be transmitted to one or more client with remaining data sample and uses.Routine is followed step 595 to determine whether continuation.If continue, then routine turns back to step 505, if do not continue, then routine proceeds to step 599 and finishes.

Fig. 6 is the process flow diagram of the exemplary embodiment of data sample speed estimator routine 600.This routine can provide through for example carrying out the data sample velocity estimation assembly 356 of Fig. 3 and/or the data sample velocity estimation assembly 107 of Fig. 1, for example in the time period, estimates the current average velocity of this road segment segment based on each data sample that is used for road segment segment.In this exemplary embodiment; Routine is the continuous calculating of each execution road segment segment average velocity of a plurality of time intervals or time window in the time period; But to call alternatively can be (for example, the estimating a plurality of time intervals via a plurality of routine call) that is used for the single time interval for each of routine in other embodiments.For example; If the time period is 30 minutes; Then can carry out new average velocity in per five minutes calculates; For example with time interval of 5 minutes (and therefore each time interval not overlapping) with the previous or follow-up time interval, or with time interval (so overlapping with the adjacent time interval) of 10 minutes.

This routine begins in step 605; Receive indication; The data sample of its indication road segment segment in the time period (for example; From the next data sample of the data readings of mobile data source and physical sensors), or the insufficient data of indication road segment segment in the time period, but can only from mobile data source and sensing data reading, receive a data sample in certain embodiments.The data sample that is received can be, for example, obtains from the output of data sample exceptional value remover routine.Similarly, can obtain the indication of inadequate data from data sample exceptional value remover routine.In some cases; The indication of inadequate data can be based on having data sample in shortage; Be wrong (for example, adjusting assembly 105) for example through the sensing data of Fig. 1 when in the time period, not coming data sample and/or losing or be detected as when some or total data reading of road segment segment from the mobile data source related with road segment segment.In this instance, routine continues to determine whether to have received the not enough indication of data in step 610.If then routine proceeds to step 615, if not, then routine proceeds to step 625.

In step 615, routine is carried out the embodiment (describing with reference to Figure 14) of magnitude of traffic flow estimation device routine to obtain the average traffic speed of the estimation of road segment segment in the time period.In step 620, routine then provides the indication of the average velocity of estimation.In step 625, routine starts from first time interval and the next time interval of average velocity selection or time window for being estimated.In step 630, routine then is the average traffic speed of data sample calculating weighting in this time interval, and based on one or more factors to the data sample weighting.For example; In an illustrated embodiment; To the weighting of each data sample based on stand-by period of data sample and change (for example, with linearity, index; Or step-by-step movement mode), for example give near the bigger weight of terminal data sample of the time interval (because they more can be reflected in terminal actual average speed of the time interval).In addition, in an illustrated embodiment data sample can also be further based on the source of data and weighting, for example no matter lay particular stress on or on the low side, the data readings weighting that comes from physical sensors is different from the data sample weighting that comes from vehicle and other mobile data source.In addition; In other embodiments; In weighting, can use various other factorses; Comprise based on each sample---for example; Can be different from data readings weighting data readings weighting from another physical sensors from a physical sensors; Thereby reflect relevant sensor available information (for example, in the physical sensors one be intermittent error or have more coarse data readings resolution than another sensor), and the data sample that comes from a vehicle or other mobile data source can be similarly based on the information in relevant mobile data source with the data sample different ground weighting that comes from another such vehicle or mobile data source.Other type of the factor that can in weighting, use in certain embodiments comprises puts the letter value or other estimation of possible errors in the particular data sample, particular data should with degree of relevance such as particular lane highway section.

After step 630, routine proceeds to step 635 so that the indication of average computation traffic speed in the time interval to be provided, and for example stores this information and/or will offer client to information for follow-up use.In step 640, routine obtains inherent step 605 reception of time period information obtainable additional data sample afterwards subsequently alternatively.In step 645, then determine whether in the time period, will calculate more time at interval, and if like this, then routine turns back to step 625.If alternatively there is not more time at interval, or after step 620, then routine proceeds to step 695 to determine whether continuation.If continue, then routine turns back to step 605, and if not, then proceed to step 699 and end.

Fig. 7 is the process flow diagram of the exemplary embodiment of data sample flow estimation device routine 700.Routine can be passed through; For example; The embodiment of the data sample flow estimation assembly 108 of the data sample flow of execution graph 3 estimation assembly 358 and/or Fig. 1 and providing is so that estimation traffic traffic characteristic rather than the average velocity in particular lane highway section in special time period.In this exemplary embodiment; The traffic characteristic that will be estimated be included in the vehicle total amount (or other mobile data source) that arrives on the time period inherent particular lane highway section or exist and in the time period percentage occupancy of road segment segment with the point of reflection road segment segment or zone by percentage of time that vehicle covered.

Routine receives indication therein in step 705 beginning, its instruction time section road segment segment data sample and in the time period average velocity of road segment segment, or not enough data of road segment segment in the time period.Data sample can from, for example, the output of data sample exceptional value remover routine obtains, and average velocity can from, for example the output of data sample speed estimator routine obtains.The indication of not enough data can from, for example the output of data sample exceptional value remover routine obtains.In some cases; The indication of not enough data can be based on having data sample in shortage; For example losing or be detected as when some or all sensors data readings of in the time period, not coming data sample maybe ought be used for road segment segment from the mobile data source related with road segment segment is wrong (for example, adjusting assembly 105 through the sensing data of Fig. 1).Routine then continues in step 706 to determine whether to have received not enough data indication.If then routine proceeds to step 750, if not, then routine proceeds to step 710.

In step 750, routine is carried out the embodiment of magnitude of traffic flow estimation device routine (describing with reference to Figure 14) to obtain the total amount and the occupancy of the estimation of road segment segment in the time period.In step 755, routine then provides the indication of the total amount and the occupancy of estimation.

In step 710, routine confirms to provide the vehicle number (or other mobile data source) of data sample, for example through each data sample is related with specific mobile data source.In step 720, routine then confirms to provide the most possible arrival rate of road segment segment of the vehicle of this data sample based on determined vehicle number on probability top.In certain embodiments, probability confirms also further to use the information about the prior probability of the prior probability of such vehicle fleet size and specific arrival rate.In step 730, the number percent that routine then for example accounts for vehicle fleet based on determined quantity of vehicle and the relevant vehicle that data sample is provided is inferred in the time period sum through all vehicles of road segment segment, and the further fiducial interval of the total amount of estimation deduction.In step 740, routine is then inferred the number percent occupancy of road segment segment in the time period based on the total amount of being inferred, average velocity and average vehicle length.Also can estimate similarly in other embodiments the magnitude of traffic flow characteristic of interested other type.In an illustrated embodiment, routine then proceeds to the indication of step 790 with the number percent occupancy of total amount that deduction is provided and deduction.Behind step 755 or 790, continue if in step 795, confirm; Then routine turns back to step 705; If do not continue, then proceed to step 799 and end.

Figure 11 is the exemplary embodiment of sensing data error in reading detector routine 1100.Routine can by, for example, the sensing data of execution graph 3 adjustment assembly 353 and/or Fig. 1 sensing data adjustment assembly 105 provide, thereby confirm the health of one or more traffic sensors.In this exemplary embodiment, be based on the traffic sensor reading that obtains recently in the indicated time period, carry out this routine to confirm the health of one or more traffic sensors each time of one day.In addition, in various embodiments, the traffic that is used for one or more each types is measured and can be by this routine analyses by the data of traffic sensor output, for example traffic speed, quantity, occupancy etc.And; Some data that are used for traffic at least can be measured and/or collect in every way; For example (for example with various intervals level; The 5mph bucket that is used for the data set of velocity information), and in certain embodiments this routine can be analyzed data for specific traffic sensor with the interval level of one or more each that are used for that one or more traffics measure each (or other combined horizontal).

This routine begins in step 1105; And receive one or more traffic sensors and selected time classification (time classification recently for example; If routine is carried out to be bordering on real-time mode the result to be provided after each time classification; Or one or more previous time classifications of selecting for analysis) indication, but alternatively can be indicated a plurality of chronological classifications in other embodiments.In certain embodiments, the time can each all comprise time point classification (for example, 12:00AM-5:29AM and 7:30PM-11:59PM through it; 5:30AM-8:59AM, 9:00AM-12:29PM, 12:30PM-3:59PM; 4:00PM-7:29PM, and 12:00AM-11:59PM) and/or date category (for example, Monday is to Thursday; Friday, Saturday and Sunday, or alternatively have Saturday and Sunday together in groups) time classification and modeling.In each embodiment, can select specific chronological classification in every way; Comprise and (for example be reflected in time period that traffic during it expects to have similar characteristics; Based on call duration time and pattern; Or the consistent behavior of other reflection traffic), if for example traffic is rare relatively with early morning between the lights, then they are formed one group together.In addition; In certain embodiments; Can confirm to have the time period of similar magnitude of traffic flow characteristic through the analysis of history data; Thereby still be that automatic mode select time classification is distinguished different traffic sensor (for example, through geographic area, road, single-sensor etc.) no matter with manual work.

Step 1110 to 1150 in; Routine is then carried out circulation, and its analyzes each traffic sensor data readings of coming from indicated one or more traffic sensors of being used for indicated time classification to confirm the traffic sensor health status of each traffic sensor during this time classification therein.In step 1110; Begin from first traffic sensor; Routine is selected the next traffic sensor in indicated one or more traffic sensors; And select indicated time classification (or,, then be the next one combination of traffic sensor and indicated time classification) if alternatively indicated a plurality of time classifications in step 1105.In step 1115, routine is retrieved the averaged historical data readings that is used for traffic sensor and is distributed in selected time classification.In certain embodiments; The historical data reading distributes can be based on the data readings that in selected time classification, is provided by traffic sensor (for example, having striden across between the 4:00PM and 7:29PM on the date that time period such as the prolongation in nearest 120 days or recent 120 day cycle etc. comprised Monday to Thursday).

In step 1120, routine continues as selected traffic sensor and confirms target traffic sensor DATA DISTRIBUTION with selected time classification.In step 1125, routine is then confirmed the similarity that target traffic sensor data readings distributes and historical traffic sensor data readings distributes.Like the other places more detailed description, in certain embodiments, can confirm through the Kullback-Leibler divergence of calculating between distribution of target traffic sensor data readings and the distribution of historical traffic sensor data readings in the tolerance of such similarity.In step 1130, as more going through ground elsewhere, routine is then confirmed the information entropy that target traffic sensor data readings distributes.

In step 1135; Routine is that the health of the selected traffic sensor of selected time classification estimation is to carry out healthy classification (for example, indication " health " or " unhealthy ", or the value on " health " yardstick through using various information then; For example from 1 to 100); It comprises determined similarity, determined entropy and selected time classification in this embodiment, and (for example, the selected hour is classification constantly, and for example 4:00PM is to 7:29PM; And/or selected date category, such as Monday to Thursday).In other embodiments, can use the out of Memory type, for example want the indication 5mph bucket of the data set of velocity information (for example, for) of the interval degree of measured data.In one embodiment, can use neural network to classify, and in other embodiments, can use other sorting technique, comprise decision tree, Bayes classifier etc.

In step 1140, routine is that selected traffic sensor and selected time classification confirmed traffic sensor health status (in this example for healthy or unhealthy) based on the traffic sensor health and/or the other factors of estimation then.In certain embodiments, the health that no matter when is used for the traffic sensor of selected time classification is estimated as health in step 1135, and it is healthy that the health status that then is used for traffic sensor can be considered to.In addition; The health that no matter when is used for the traffic sensor of selected time classification be estimated as unhealthy (for example; In step 1135); And selected time classification has the moment at the hour classification of enough big time period (for example at least 12 or 24 hours) of related covering, and the health status that then is used for traffic sensor can be thought unsound.And, in certain embodiments, can retrieve and use the relevant information (for example being used for one or more previous and/or follow-up time periods) that relates to the time classification, thus in the long time period (for example, one day) to the health classification of traffic sensor.Such logic has reduced the interim unusual travel pattern of accurately reporting based on sensor and the sensor health status has been carried out the wrong negative risk of confirming (for example when in fact traffic sensor is health, confirming that the health status of traffic sensor is unsound).

For example, possibly produce the negative definite of mistake owing in data readings, changing the same day significantly because of external factor (for example, traffic hazard, weather accident etc.).For example, the traffic accident of special traffic sensor place or near generation it possibly cause traffic sensor in the short relatively time period (for example, one to two hour), unusual and irregular data readings to be provided.If the sensor health status is definite only based on the data readings that mainly in the caused distribution time by traffic hazard, is obtained, what then just might lead to errors is negative definite.Through confirming unsound sensor status, can reduce so wrong negative definite risk based on the data readings that is obtained from the relatively large time period (for example, 12 or 24 hours).On the other hand; In general possibility is very low for negative definite (for example when in fact traffic sensor is healthy, the confirming that the health status of traffic sensor is unsound) of mistake; Because the traffic sensor of fault can not provide the data readings that is similar to historical data reading (for example, the general travel pattern of reflection).Likewise, can confirm that suitably the health status of traffic sensor is healthy based on the relatively short time period.

Some embodiment can be through with the routine of time classification shown in repeatedly carry out every day of reflection short period section (for example; Prolonged the chronological classification of the moment at the hour classification of first three hour earlier to have; Routine of execution in per three hours) and with the time classification that reflects the whole previous date (for example carry out a routine at least in every day; To prolong the time classification of the previous 24 hours moment at hour classification, at the executive routine at midnight) and realize this different logical.

In addition; Confirming of sensor states can be based on other factors; For example whether be selected time classification obtain sufficient amount data readings (for example; Because sensor is the report data reading off and on) and/or based on the indication (for example, traffic sensor is stuck) of the sensor states that provides by traffic sensor.

In step 1145, routine provides the health status of determined traffic sensor.In certain embodiments; Can serve as reasons other assembly (for example; The sensor data collection assembly 110 of Fig. 1) follow-up use and (for example store the traffic sensor health status; Be stored in database or the file system) and/or it is directly offered other assembly (for example, data sample exceptional value remove assembly).In step 1150, routine determines whether to exist more a plurality of sensors (or combination of traffic sensor and time classification) to handle.If then routine proceeds to step 1110 continuation, if not, then proceed to step 1155 to carry out other suitable action.This other action can comprise, for example, and for each each of one or more time classifications that is used for a plurality of traffic sensors come periodically (for example, once a day, inferior on every Mondays) repeated calculation historical data reading distribute (for example, at least 120 days).Distribute through periodicity repeated calculation historical data reading, in the face of the traffic that gradually changes, routine can continue to provide confirming of accurate traffic sensor health status.After step 1155, routine proceeds to step 1199 and returns.

Figure 12 is the process flow diagram of the exemplary embodiment of data readings error recovery device routine 1200.This routine can be through for example, the sensing data adjustment assembly 105 of the sensing data of execution graph 3 adjustment assembly 353 and/or Fig. 1 and providing, thus confirm to be used for the data readings after the correction of one or more traffic sensors related with road segment segment.Shown in exemplary embodiment in, this routine can periodically be carried out (for example per five minutes) be used for being identified as by sensing data error in reading corrector routine unsound traffic sensor with correction data readings.In other embodiments, can carry out this routine as required,,, or alternatively in various environment, can not be used with the data readings after the correction that obtains to be used for the particular lane highway section for example through sensor data collection device routine.For example; In general all data samples through confirming to be used for the particular lane highway section (for example; Come from a plurality of data sources; The polytype that for example can comprise the mobile data source of traffic sensor and one or more dissimilar types) traffic flow conditions that whether provides enough data to analyze this road segment segment is carried out the analysis and the correction of data, if not, then do not carry out from the correction of the next data of each traffic sensor.

This routine begins in step 1205; Wherein its receive the road segment segment related with one or more traffic sensors indication (for example; Be classified as unsound result through that come from sensing data error in reading detector routine, one or more related traffic sensor); And receive the indication of the one or more time classifications that will be processed (for example, wherein be classified as be unsound time classification at least potentially) alternatively at least one of the traffic sensor of association.In other embodiments, interested one or more traffic sensors can otherwise be indicated, for example through directly receiving the indication of one or more traffic sensors.In step 1210 to 1235; Routine is carried out a circulation; Wherein it handles unsound traffic sensor on indicated road segment segment, with (for example in step 1205 indicated time classification) during one or more time classifications for these traffic sensors definite and correction is provided after data readings.

In step 1210, begin from first, routine is chosen in the next unsound traffic sensor in the indicated road segment segment.This routine also through select one or more during it traffic sensor before be designated as unsound time classification and wait and select the time classification that will use, for example one or more time classifications indicated in step 1205.In step 1215, routine confirms whether have other enough traffic sensor healthy and that can be used to assist the unhealthy sensor readings correction that is used for selected time classification in indicated road segment segment.Whether this confirms to be based on and exists at least predetermined amount of data (for example in the indication road segment segment during the selected time classification; At least two) and/or predetermined percentage is (for example; At least 30%) healthy traffic sensor; And it is also conceivable that near the relative position (for example, adjacent or traffic sensor can be superior to sensor) of healthy traffic sensor in the road segment segment of indication away from unhealthy traffic sensor.If in step 1215, confirm to exist enough healthy traffic sensors; Then routine proceeds to step 1220, here based on the correction data reading of confirming to be used for unhealthy traffic sensor from the data readings of coming at other healthy traffic sensor of the road segment segment that is used for selected time classification.Can confirm the correction data reading in every way, for example through calculating from the average of two or more data readings of the healthy traffic sensor acquisition the indication road segment segment of selected time classification.In certain embodiments, all healthy traffic sensors may be used to averaging, but can only use selected healthy traffic sensor in other embodiments.For example; If the predetermined percentage of the traffic sensor in indicated road segment segment (for example; At least 30%) during selected time classification, be healthy; Then can use all healthy traffic sensors to come averaging, otherwise can only use nearest predetermined quantity (for example, at least two s') healthy traffic sensor.

There are not enough healthy traffic sensors if alternatively in step 1215, confirm in the indication road segment segment that is used for classification seclected time; Then routine proceeds to step 1225, here it attempt based on relate to this traffic sensor/or the out of Memory of road segment segment confirm to be used for the correction data reading of unhealthy traffic sensor.For example; Such information can comprise the predict traffic conditions information that is used for road segment segment and/or unhealthy traffic sensor; Be used for the forecast traffic related information of road segment segment and/or unhealthy traffic sensor, and/or be used for the historical average traffic related information of road segment segment and/or unhealthy traffic sensor.Can carry out the relative reliability that various logic reflects various information types.For example, in certain embodiments, use predict traffic conditions information (for example) can have precedence over the forecast traffic related information, use the forecast traffic related information can have precedence over historical average traffic related information again as long as can obtain.The additional detail that relates to prediction and forecast future transportation traffic conditions can be submitted on March 3rd, 2006; And the U.S. Patent application No.11/367 that is entitled as " Dynamic Time Series Prediction Of Future Traffic Conditions "; Obtain in 463, its full content is incorporated in this as a reference.In other embodiments; Execution in step 1215 and 1225 is not carried out if the data readings for example in step 1220 is always proofreaied and correct based on the best data that obtain from other healthy traffic sensor during selected time classification and/or relevant time classification.For example; If the predetermined percentage at least of all healthy traffic sensors (for example in the indication road segment segment of selected time classification; At least 30%) be healthy; Then proofread and correct can be based on these all traffic sensors for data readings, otherwise are based on the healthy traffic sensor that closes on most in the indicated and/or road segment segment of closing on during selected time classification and/or the relevant time classification.

Behind step 1220 or 1225, routine proceeds to step 1230 and provides determined traffic sensor data readings as the correction reading that is used for the traffic sensor during selected time classification.In certain embodiments, determined traffic sensor data readings can be stored (for example, being stored in database or the file system) for the follow-up use of other assembly (for example, the sensor data collection assembly 110 of Fig. 1).In step 1235, the traffic sensor that routine determines whether to be processed and the additional combinations of time classification.If have, then routine turns back to step 1210, if not then proceed to step 1299 and finish.

Figure 13 is the process flow diagram of the exemplary embodiment of sensing data reading gatherer routine 1300.This routine can be passed through; For example; The sensing data reading collection assembly 355 of execution graph 3 and/or Fig. 1 sensing data reading collection assembly 110 provide, and for example confirm and are provided at special time classification or the traffic related information of a plurality of traffic sensors (for example related with the particular lane highway section a plurality of traffic sensors) in the section At All Other Times.Shown in exemplary embodiment in, this routine is that carry out in the particular lane highway section, but in other embodiments can be from a plurality of traffic sensor group acquisition of informations of other type.In addition; This routine can provide by other routine of the estimation of carrying out traffic related information (for example replenishes; The traffic related information of the information that data sample flow estimation device routine) provides provides traffic related information thereby can not provide in other routine under the situation of accurate estimation (for example because data deficiencies).

This routine is in step 1305 beginning and receive one or more section and one or more time classifications or the indication of section At All Other Times.In step 1310, routine begins to select next bar road segment segment of one or more indicated road segment segment from first.In step 1315, some that routine obtains to be gathered in the indicated time period by all traffic sensors related with this road or the traffic sensor data readings that all can get.Such information for example can obtain from the sensing data adjustment assembly 105 of Fig. 1 and/or the sensing data adjustment assembly 353 of Fig. 3.Particularly; Routine can obtain the traffic sensor data readings and/or obtain the traffic sensor data readings of proofreading and correct from being confirmed as unsound traffic sensor for being confirmed as healthy traffic sensor in some cases, and for example those sensing data error in reading corrector routines by Figure 12 provide or confirm.

In step 1320, routine is then collected the data readings that is obtained with one or more modes, thereby confirms in the indicated time period, to be used for average velocity, amount and/or the occupancy of road segment segment.Average velocity can be for example through confirming through the data readings averaging of the car speed of one or more traffic sensors reflection.The volume of traffic can be confirmed according to reporting vehicle quantity data reading.For example; Given report is activated from sensor and begins the loop sensor through the vehicle cumulative amount of sensor, then the volume of traffic two data readings that can obtain through deducting in the indicated time period and removed the result and inferred simply by the time interval between data readings.In addition, density can be confirmed based on determined average velocity, amount and average vehicle length, as describing in more detail elsewhere.In some cases, data readings weighting in every way (for example, through the age) is so that near more data readings has the influence bigger than old more data readings in average discharge is confirmed.

In step 1325, routine determines whether that then many road segment segment (or other group of a plurality of traffic sensors) will handle.If have, then routine turns back to step 1310, otherwise proceeds to step 1330 so that determined traffic flow information to be provided.In certain embodiments, can store determined flow information (for example, being stored in database or the file system) so that the RT information providing system 363 of the traffic data client 109 of the follow-up Fig. 1 of offering and/or Fig. 3.Next, routine proceeds to step 1339 and returns.

Figure 14 is the process flow diagram of the exemplary embodiment of magnitude of traffic flow estimation device routine 1400.This routine can provide through for example carrying out magnitude of traffic flow estimation assembly (not shown), thereby estimation in every way is used for various types of traffic flow informations of road segment segment.In this exemplary embodiment; For example can not obtain in enough data conditions for accurately carrying out their estimations separately when these routines, routine can be estimated the estimation of device routine call with acquisition amount and/or occupancy with the estimation of acquisition average velocity and/or by the data sample flow of Fig. 7 by the data sample speed estimator routine call of Fig. 6.

This routine in step 1405 beginning and reception channel highway section, one or more time classification or the indication of section and one or more traffic flow informations such as one or more types such as speed, amount, density, occupancies At All Other Times.In step 1410; Routine determines whether to estimate based on one or more relevant road segment segment the traffic flow information of indication type; For example, the precise information that whether has the traffic flow information that is used for one or more types based on such road segment segment in the time period shown in one or more.Relevant road segment segment can be discerned in every way.For example; In some cases; The information of relevant road segment segment can comprise the relevant information that between road segment segment, concerns; For example first road segment segment has the travel pattern of the road segment segment that is similar to second (for example, adjacent) usually, thereby the traffic flow information that is used for second road segment segment can be used for estimating the magnitude of traffic flow on first road segment segment.In some cases; No matter analysis is to carry out in advance and/or dynamically; Can confirm such relation automatically; For example be based on the section of two road the statistical study (for example, be similar to distributing in the different time similar data of previous discussion, but alternatively analyze in two or more different sensors such as the similarity between the same time) of magnitude of traffic flow pattern separately about discerning given traffic sensor.Alternatively, can select one or more adjacent road segment segment to come related indicated road segment segment and need not that any of particular kind of relationship confirms between the road segment segment of having carried out.If confirm based on relevant road segment segment estimation traffic flow information, then routine proceeds to step 1415 and is used for the value of the traffic flow information of indicated type based on the same type traffic flow information that is used for one or more relevant road segment segment estimation.For example, confirm the average velocity (for example, through using the traffic speed that comes from an adjacent road section, or traffic speed averaging) of this road segment segment to coming from two or more adjacent road sections based on the average traffic speed of one or more adjacent road sections.

If alternatively in step 1410, confirm not to be used for the traffic flow information of indicated road segment segment based on relevant road segment segment estimation, then routine proceed to step 1420 and determine whether in one or more indicated time periods based on be used for this indication road segment segment and instruction time section information of forecasting be that indicated road segment segment is estimated traffic flow information.In certain embodiments, such information of forecasting possibly only obtain under specific situation, obtains accurate current data simultaneously if for example repeat prediction (for example to ensuing 3 hours per 15 minutes once) to a plurality of following moment.Likewise, if the accurate input data that (for example, above three hours) is used to produce prediction in time expand are available, then can need not to obtain prediction by the employed future transportation condition information of this routine.Alternatively, in certain embodiments, the future transportation condition information of such prediction is owing to some other former thereby non-availability, for example owing to do not use in this embodiment.If in step 1420, confirm based on information of forecasting estimation traffic flow information; Then routine proceeds to step 1425, and the information of forecasting that system 360 obtains is provided and is the indication type of estimating time period of road segment segment and the indication of indication traffic flow information based on the information of forecasting from for example Fig. 3.The additional detail that relates to prediction and forecast future transportation traffic conditions is the U.S. Patent application No.11/367 that is entitled as " Dynamic Time Series Prediction Of Traffic Conditions " that on March 3rd, 2006 submitted to; Can obtain in 463, its full content is incorporated in this as a reference.

If alternatively in step 1420, confirm is not that indicated road segment segment (is for example estimated traffic flow information based on information of forecasting; Because this information can not get), then routine proceeds to step 1430 and determines whether and in the time period of one or more indications, is indicated road segment segment estimation traffic flow information based on the forecast information that is used for this road segment segment and time period.In certain embodiments, can be for exceeding the Future Time forecast traffic of ability predict traffic conditions, for example in the mode of not using at least some the present situation information.Likewise, if can not obtain information of forecasting (for example, having surpassed three hours with regard to non-availability), then still can use forecast information, the information that for example obviously produces in advance owing to be used to produce the accurate input data of prediction.If in step 1430, confirm based on forecast information estimation traffic flow information, then routine proceeds to step 1435 and is the traffic flow information that type is indicated in indicated road segment segment and time period estimation based on the forecast information that provides system 360 to obtain from for example predicted traffic information.

If alternatively be not that indicated road segment segment (is for example estimated traffic flow information in step 1430 based on forecast information; Because this information non-availability); Then routine proceed to step 1440 and based on the historical average discharge information that is used for indicated road segment segment be indicated road segment segment and time period estimation indication type traffic flow information (for example; For the identical or corresponding time period, for example based on the time classification that comprises the moment at hour classification and/or date category).For example; If forecast information be unavailable (for example; Because the input data of the time longer than the cycle that produces nearest prediction and forecast are unavailable; Therefore can not produce new prediction can not produce new forecast), then routine can be used the historical average discharge information that is used for indicated road segment segment.Relate in the U.S. Patent application (application attorney docket is 480234.410P1) that is entitled as " Generating Repre sentative Road Traffic Flow Information From Historical Data " that the additional detail that produces historical average discharge information can submit at the same time and obtaining, its full content is incorporated in this as a reference.

After step 1415,1425,1435 or 1440, the estimation traffic flow information that routine proceeds to step 1445 and indicated type is provided for indicated road segment segment and indicated time period.The information that is provided can for example be returned the routine of calling this routine (for example, data sample flow estimation device routine) and/or be stored (for example, being stored in database or the file system) for follow-up use.After step 1445, routine proceeds to step 1499 and returns.

Fig. 9 A-9C illustrate obtain with relevant road traffic condition information is provided in the action instance in mobile data source.The information of relevant road traffic condition can be in every way obtains from the mobile device equipment or the subscriber equipment of vehicle (no matter based on); For example through (for example using Radio Link; Satellite uplink, cellular network, WI-FI, packet radio etc.) transmission and/or when equipment reaches suitable butt joint (docking) or other tie point physics download (for example, in case the main base of return or other purpose with the suitable equipment that can carry out download of information just from fleet's download message).Though the information of the relevant road traffic condition of the very first time that obtains in second time that obviously was later than (for example provides various benefits; Revise the prediction of the very first time; For the data of using institute's observed case have subsequently been improved prediction processing etc.); For example can be the situation of slave unit physics download message, when with in real time or when being bordering on real-time mode and obtaining, such road traffic condition information provides additional benefits.Therefore; In at least some embodiment, the mobile device with wireless communication ability can provide the information of at least some required relevant road traffic conditions continually, for example periodically (for example; Per 30 minutes; 1 minute, 5 minutes etc.) but and/or when information needed time spent that can q.s (for example, for each data point relevant with road traffic condition information; For every N such data, for example wherein N is configurable number; Reach specific memory and/or transmission size etc. when fetched data).In certain embodiments; This frequent radio communication of the road traffic condition information of being obtained can also (for example replenished through the additional road traffic condition information that obtains At All Other Times; The continuous physical of slave unit is downloaded; Via few frequency (less-frequency) radio communication that comprises the greater amount data), for example comprise additional data corresponding to each data point, comprise the acquisition of information of relevant a plurality of data points etc.

Though through with the road traffic condition information that real-time or other frequent mode obtain to be obtained various benefits being provided from mobile device, the radio communication of so in certain embodiments road traffic condition information that obtains can retrain in every way.For example; In some cases, the cost structure of transmitting data from mobile device via specific radio link (for example, satellite is uploaded) with few interval frequently (for example can be; Per 15 minutes) transmission that takes place, perhaps mobile device can be come with such interval transmission by programming in advance.In some other situation; Mobile device possibly temporarily lost the ability through the transmission of radio links data; For example owing to (for example lack wireless coverage in the zone at mobile device place; Because the cellular radio receiver base station do not closed on), because other action of carrying out by the user of mobile device or equipment, or because the temporary transient problem of mobile device or associated transmitter.

Therefore; At least some such mobile devices can be assigned or be configured to store a plurality of data samples (or making so a plurality of data samples be stored in other associate device) in certain embodiments, can in a wireless transmission, be transmitted together for use at least some information of a plurality of data samples.For example; At least some mobile devices are configured to can not (for example pass through the transmission of radio links data at mobile device in certain embodiments; Mobile device transmits each data sample usually separately; For example per 30 seconds or 1 minute) time the cycle memory storage road traffic condition information data sample that obtains, and then these data samples of storing are transmitted together at the time durations of the next wireless transmission of appearance.Some mobile devices can also be configured to performance period property (for example per 15 minutes; Or when the data of specified amount can be used for transmitting) wireless transmission; And at least some embodiment, can also be configured to during the time interval between the wireless transmission to obtain and a plurality of data samples of storage road traffic related information (for example with predetermined sampling rate; For example 30 seconds or one minute), and then during next wireless transmission, these data samples of storing are transmitted (or the subclass of these samples and/or set) together similarly.Like an embodiment; If nearly the wireless transmission cost Shi $0.25 of 1000 information units and the size of each data sample are 50 units, then per minute sampling and transmission in per 20 minutes comprise that the data set (rather than per minute sends each sample individually) of 20 samples is very helpful.In such embodiment; Though data sample possibility slight delay is (in the instance of cyclical transmission; Postponed time period average half the between the transmission, supposed regular acquisition data sample), the road traffic condition information that then obtains from transmission still provides the real-time information that is bordering on.And, can produce and provide additional information based on a plurality of data samples of storing by mobile device in certain embodiments.For example; If specific mobile device only can obtain the information of relevant current present position during each data sample; But can not obtain the additional correlation information such as speed and/or direction, then such additional correlation information can be calculated based on a plurality of follow-up data samples or confirmed.

Particularly, Fig. 9 A has described and has had several interconnective roads 925,930,935 and 940 and the exemplary area 955 ( road 925 and 935 north-souths are walked, and road 930 and 940 East and West directions are walked) of the legend indication 950 of indication road north orientation direction.Though only shown the road of limited quantity, they can represent vast geographic area, for example across several miles interconnective expressways, or have striden the subclass of the avenue in several districts.In this instance, the mobile data source (for example, vehicle, not shown) 945a goes to 945c from the position in 30 minutes cycle, and be configured to obtain and transmitted in per 15 minutes the data sample of expression current traffic condition.Therefore; When the mobile data source begins to go; It position 945a obtain and transmit first data sample (as in this instance with shown in the asterisk " ★ "); 945b obtains and transmits second data sample in the position after 15 minutes, and in that 945c obtains and transmits the 3rd data sample in the position after 30 minutes altogether.In this instance; Indication (for example, in gps coordinate), current direction (for example, north orientation), present speed that each data sample comprises current location are (for example; 30 minutes are per hour) and the current time; As use the transmission of 945a of data value Pa, Da, Sa and Ta represented, and also can comprise out of Memory (for example, the identifier in indication mobile data source) alternatively.Acquisition although it is so and the current traffic condition information that provides provide more benefit, but are not sure of a plurality of details from such data, comprise from position 945b to the route of 945c whether partly along road 930 or 940.And such sample data does not allow, for example will be in the part of the road between position 945a and the 945b 925 different road segment segment as the different traffic that can report and predict.

With with mode like Fig. 9 category-A; Fig. 9 B has described instance 905; Its in 30 minutes cycle the mobile data source from the position went interconnective road 925,930,935 and 940 and the per information (as represented) of sending relevant traffic in 15 minutes in mobile data source of 945a to 945c at the asterisk shown in position 945a, 945b and the 945c.But in this instance, the mobile data source is configured to per minute and obtains and store data sample, and subsequent transmission is included in the preceding 15 minutes data from each data sample.Therefore; When go between position 945a and 945b in the mobile data source; The mobile data source obtains the group 910b of 15 data sample 910b1 to 910b15, and in this instance, and the arrow that utilizes time of data sample to sentence the direction indication in mobile data source is indicated each data sample.In this instance, each data sample comprises current location, current direction, present speed and the indication of current time similarly, and the continuous transmission of 945b comprises each these data values that are used for data sample 910b in the position.Similarly, go between position 945b and 945c like the mobile data source, then the mobile data source obtains 15 data sample 910c1-910c15, and the subsequent transmission of 945c comprises each the fetched data value that is used for 15 data samples in the position.Through such additional data sample is provided, can obtain various additional information.For example, the route that is easy to confirm the 945b to 945c from the position now is partly along road 930 rather than road 940, and allows corresponding traffic related information is used for road 930.In addition; The data sample that specific data sample is adjacent with them can provide the various information of relevant road smaller portions; For example allow the road 925 between position 945a and 945b to be expressed as for example (for example reaching 15 different road segment segment; Through each data sample is related with different road segment segment), its each all have the different road traffic condition of possibility.For example; Can observe out intuitively; The average velocity that is used for data sample 910b1-910b6 is roughly static (because approximate equality ground interval data sample); And the average velocity that is used for data sample 9101-910b8 increases (becoming big because data sample, has reflected the distance of between the data sample of this instance of user, going in the interval at given 1 minute corresponding to each position that gradually is far apart out), and the average velocity of data sample 910b1-910b15 descends.Though the data sample in this instance directly provides the information of relevant such speed, data message such among other embodiment can obtain from the data sample information that only comprises current location.

Fig. 9 C has described the 3rd instance 990; Wherein the mobile data source in 30 minutes cycle from the position 965a to the 965c interconnective road part of going, and the per information of transmitting relevant traffic in 15 minutes in mobile data source (as among position 965a, 965b and the 965c shown in the asterisk).As shown in Fig. 9 C, the mobile data source is configured to that per minute obtains and the storage data sample in this instance, and subsequent transmission comprises in preceding 15 minutes the data from each of at least some data samples.Therefore, go between position 965a and 965b like the mobile data source, then the mobile data source obtains the group 960b of 15 data sample 960b1-960b15.But; Data sample 960b5-b13 as through co (does not detect mobile owing to be not directed against these data samples; Therefore employed in this instance is annular rather than arrow; But for the sake of clarity with its independent demonstration rather than in the top of one another), about 9 minutes (for example, stopping at cafe) stopped in a side of road 925 in the mobile data source in this embodiment.Therefore; When 965b produces next transmission in the position; Transmission in certain embodiments can comprise all information that are used for all data samples, or alternatively can omit at least some information (for example, information of omitted data sample 960b6-960b12; Know that if this is the mobile data source is still mobile between data sample 960b5 and 960b13, then they do not provide additional useful information in this situation).And; Though do not illustrate here; But can omit the information of one or more such data samples in other embodiments; And can to postpone follow-up transmission all be available (for example, if based on data volume that will be sent out rather than the property transmission of performance period time) up to 15 data samples that will be transmitted.And, go between position 965b and 965c like the mobile data source, then the mobile data source is obtaining data sample 960c13 and 960c14 (as in this embodiment with opening shown in circle rather than the arrow) in the current disabled zone of radio communication.In other embodiments, wherein each data sample all is independent transmission when obtaining but when not storing, and these data samples can be lost, but in this instance, and 965c is storage and transmits with other data sample 960c1 to 960c12 in the position on the contrary.Though do not illustrate here; But the mobile data source (for example can also temporarily lose ability that the basic device that uses data to obtain obtains one or more data samples in some cases; If the mobile data source loses the ability a few minutes of obtaining the GPS reading) if---like this; Then the mobile data source can be reported the data sample that other obtains and (for example need not further reaction in certain embodiments; Then allow the take over party to insert if desired or estimate these data samples), though can attempt otherwise to obtain data sample in other embodiments (for example, through using accurate inadequately mechanism to confirm the position; For example the cellular mobile telephone tower triangular is measured; Or, for example pass through dead reckoning through estimating current location with the orientation based on the position of previously known and follow-up average velocity), even if these data samples (for example have lower accuracy or degree of accuracy; Can be through comprising degree to the low credibility of these data samples or higher possible errors, or through comprising how indication these and/or other data sample produces).

Though in each of Fig. 9 B and 9C; The example data sample only illustrates a vehicle or other mobile data source for brevity, but in other embodiments, can not use a plurality of data samples that are used for specific mobile data source to confirm the particular course of being gathered by this mobile data source; And more specifically; Even can be not other is related with each (for example, if the source of each mobile data sample is anonymous, or having nothing different with other source).For example; If a plurality of data samples that come from specific mobile data source and can't help the take over party be used in produce relate to these data samples collective data (for example; Continuous data sample based on positional information only is provided produces speed and/or directional information); For example when such collection data comprise each data sample or are not used; Can not provide such take over party to discern in certain embodiments and relate to mobile data sample source and/or indicate a plurality of data samples from identical mobile data source (for example, increasing the privacy that relates to the mobile data source) based on design decision.

Alternatively; In at least some such embodiment; A plurality of mobile datas source is used for confirming interested road condition information together, for example uses a plurality of data samples that come from all mobile data sources to confirm the acquisition of information of this road segment segment to particular lane highway section (or other part of road).Like this; For example; The interested time period (for example; 1 minute, 5 minutes, 15 minutes etc.) in, each of a plurality of incoherent mobile datas source can provide one or more its data samples that oneself go on the particular lane highway section that relate in this time period, and if each such data sample comprise speed and directional information (for example); Then can confirm average gathering speed, for example to be similar to mode for the road traffic sensors of a plurality of vehicle acquisition of informations through sensors for this time period and the road segment segment that usually on equidirectional, moves that is used for all data sources.Specific data sample can be related with the particular lane highway section in every way; For example through the data sample position is related with the road with proximal most position (or road segment segment) (no matter for any road; Or only to satisfying the road of specific criteria; The category of roads that for example belongs to one or more indicated functions) and then select suitable road segment segment for this road, or through use by the mobile data source with the indication that provides together of the data sample of related road (or road segment segment).In addition; In at least some embodiment, for the purpose of assigning data sample to road and other purpose (for example, with north orientation track, expressway as the different track different) with the south orientation track of expressway; Road that will be except one-way road is as different road; And if like this, the direction that then is used for the mobile data sample can also be used to confirm the suitable road related with data sample---but, in other embodiments; Otherwise modeling; For example with two-way avenue as a road (for example) according to the average traffic of reporting and predicting for the vehicle that on both direction, moves, with each track of the expressway of multilane or other road as different logic road etc.

In certain embodiments, confirm interested road condition information for the ease of using a plurality of mobile datas source, fleet can be configured to provide employed road sample in every way.For example; If identical starting point is all left in the similar time of every day by each large-scale fleet; Then each vehicle can be configured to relate to how soon and how long to begin to provide data sample by difference, for example minimizes to be near the mass data all single starting point and/or to be provided to obtain and the variation during the transmission data sample.More specifically; The mobile data source device can be configured to carry out how and when obtaining data sample in every way; Comprise the total distance that begins to cover based on from the starting point starting point of fleet's group (for example for); Obtain and/or transmit the distance that begins to cover from last data sample, from the outset between T.T. of (for example vehicle is from time that starting point is left) experience, the time of obtaining and/or transmitting experience from last data sample; Produce the indexical relation of relevant one or more indicated positions (for example, through, arrive, leave etc.) etc.Similarly; The mobile data source device can be configured to carry out how and when transmitting or providing one or more data samples that obtain in every way, for example when the statistics predetermined condition, comprises based on the total distance from the starting point covering; Obtain and/or transmit the distance of covering from last data sample; Play the T.T. of experience from the outset,, produce the indexical relation of relevant one or more indicated positions from the time that last data sample obtained and/or transmitted experience; The indication number of a plurality of data samples of having collected; The indicated data volume of having collected (for example, fill up or be filled in fact on the mobile device quantity of the buffer of storage data sample, or for example fill up or fill up in fact be used to transmit instruction time amount quantity) etc.

Fig. 8 is the process flow diagram that mobile data source information provides the exemplary embodiment of routine 800; Each the mobile data source device based on other data source 102 of the data source 101 of vehicle and/or Fig. 1 of one or more data source 384 and/or other data source 388 (for example, subscriber equipment) and/or Fig. 1 based on vehicle that for example can be used for Fig. 3 through operation provides.In this instance, this routine is that specific mobile data source acquisition data sample is indicated current traffic, and suitably stores data sample so that subsequent transmission can comprise the information that is used for a plurality of data sources.

This routine begins in step 805; Wherein retrieval will be used in as data sample and obtain and the parameter of the part that provides, and for example configuration parameter is used to indicate and when should obtains data sample and when should produce the transmission of Information corresponding to one or more data samples.Routine proceeds to step 810 and waits for; Up to obtaining data sample in time; For example (for example based on the parameter of being retrieved and/or out of Memory; Passed through the indicated time quantum of past data sample acquiring, distance shown in the past data sample acquiring of having gone, indication is obtained data sample etc. with continuous in fact mode).Routine then proceeds to step 815 with the mobile data sample that obtains based on current location and mobile data source, and in step 820, stores data sample.If in step 825, confirm also not arrive the time of transmission data; For example (for example measure the instruction time of the previous transmission of process based on parameter of being retrieved and/or out of Memory; The indication distance of having gone and before having transmitted; Indication is as long as it is available or transmit data sample etc. with continuous in fact mode), then routine is returned step 810.

Otherwise routine proceeds to step 830 to retrieve and to select any data sample of being stored owing to previous transmission (or from beginning, transmitting from the first time).Routine then alternatively in step 835 based on a plurality of selected data samples (for example; The whole average velocitys that are used for all data samples; If the information of being obtained only provides positional information, then be the average velocity that is used for each data sample and direction etc.) the collected data of generation.But also can not carry out in other embodiments, the generation of the data of such collection.In step 840; Routine then from selected data sample group, removes some that are used for some or total data sample alternatively or all institute's information that obtain are (for example; Only transmission is used for the selected type of each data sample, removes those and exceptional value or wrong data sample occur, removes those data samples that do not move corresponding to the reality in mobile data source etc.); In other embodiments, also can not carry out such information removes.In step 845, routine then is transmitted in current information and the information of any collection that will use by rights in the data sample present group to the take over party.In step 895, routine determines whether to continue (for example whether the mobile data source is continued to use and be movably), and if then turn back to step 810.Otherwise routine proceeds to step 899 and finishes.Can not transmit among the embodiment and situation of data in the mobile data source; No matter whether because temporary transient situation has still alternatively reflected the configuration at first of mobile data source; Step 830-845 can not be performed can transmit data up to the mobile data source or (for example, downloading via physics) is provided because previous transmission and obtained and the data sample of storage some or all.

As the previous ground of noticing; In case and the information that has obtained relevant road traffic condition; For example from one or more mobile datas source and/or one or more other source; Then can use road traffic condition information in every way, for example report current road traffic condition, or use past and current road traffic condition information to come each prediction future transportation situation in a plurality of Future Time with real-time basically mode.In certain embodiments; The input type of data that is used to produce the future transportation condition predicting can comprise the following situation of various current, past and expection; And from the output that prediction processing is come can comprise for a plurality of Future Time in (for example, three hours, or a day) at the fixed time at interval each (for example; Following per 5,15 or 60 minutes) prediction of the expection traffic that on each of institute interested a plurality of target track highway section, produced, like institute's description in more detail elsewhere.For example, the input type of data can comprise following: relevant be used in the geographic area interested each target track highway section current and pass by the information of the volume of traffic, the for example network of selected road in the geographic area; Information about current and recent traffic hazard; Information about current, recent and future trajectory engineering; About current, past with expect the information (for example, precipitation, temperature, wind direction, wind speed etc.) of external weather condition; The information of, past current about at least some and following incident of arranging (for example; The type of incident, the start and end time of time expection, and/or the place of time or other position etc.; For example be used for all incidents; The incident of indication type, very great incident, for example have be expected on the indicated threshold value attending etc. of (the for example attendant of 1000 or 5000 expections)); Information (for example, whether school gives a lesson and/or the position of one or more schools) with the arrangement of relevant school.In addition; Though in certain embodiments; A plurality of Future Time of prediction future transportation situation are every points on time; But so in other embodiments prediction alternatively can be represented a plurality of time points (for example, the time period), for example through being illustrated in the average of future transportation situation during these a plurality of time points or collecting tolerance.And, some of input data or all can be known and represent (for example, the weather of expection) with the degree of change confirming, and can produce additional information and be illustrated in the prediction that is used for being produced and/or the credibility of other metadata.In addition, for a variety of causes and each time can initialization future transportation situation prediction, for example in periodic manner (for example, per 5 minutes), when receiving any or enough new input data, response is from the request that is used for coming etc.

Can use in certain embodiments some of same type of input data come to produce similarly the future transportation situation the longer-term limit forecast (for example; A following week; Or following one month); But the input data of some types also can not be used in the forecast of such longer-term limit, for example relevant information at the present situation (for example, current traffic, weather or other situation) that forecasts the time that produces.In addition, the forecast of such longer-term limit can with the forecast of short-term limit relatively more the lowland frequency produce, and can be produced the forecast of comparison short-term limit more can reflect different Future Time section (for example, per hour rather than per 15 minutes).

Can also select to be used to produce the road and/or the road segment segment of future transportation condition predicting and/or forecast in every way.In certain embodiments; For a plurality of geographic areas (for example; The urban district) each produces future transportation condition predicting and/or forecast; Wherein each geographic area has the road network of a plurality of interconnection---and can select such geographic area in every way, be a prominent question based on current traffic condition information available easily (for example, being based on the road traffic sensors network of at least some roads in this zone) and/or traffic congestion wherein for example.In some such embodiment; The road that is used to produce future transportation condition predicting and/or forecast comprises that those are easy to obtain the road of current traffic condition information; And in other embodiments; The selection of such road can (for example, size or capacity based on road for example comprise expressway and primary highway based on one or more other factorses at least in part; Road traffic regulation based on carrying traffic for example comprises mainly being substituted into Class I highway and the blocked road such as the road of larger capacities such as expressway and primary highway; Based on the functional category of road, for example specified etc.) by federal expressway management board.In other embodiments, can be that a road produces future transportation condition predicting and/or forecast, and no matter its size and/or with the mutual relationship of other road.In addition, can select to be used to produce the road segment segment of future transportation condition predicting and/or forecast in every way, for example with each road traffic sensors as different section; For each road segment segment with a plurality of road traffic sensors composition group (for example, reduce producing the quantity of independent prediction and/or forecast) of putting together for example through composition group that the road traffic sensors of specific quantity is put together; Select road segment segment so that the logic relevant portion of the road of reflection traffic identical or fully similar (for example, strong related); For example based on the traffic related information of (for example, from vehicle and/or the data that produce the user of travels down, like institute's discussions more in detail elsewhere) from traffic sensor and/or other source; Deng.

In addition; In each embodiment, can use future transportation condition predicting and/or forecast information in a different manner; Like institute discussions more in detail elsewhere, be included in each time in every way (for example, through with information transmission to cellular mobile telephone and/or other portable consumer device; Through giving user's display message, for example through Web browser and/or application program; Through information being offered other tissue and/or the entity of at least some information being provided to the user; For example analyze and modification information after the third party that provides of execution information etc.) such information (is for example offered user and/or tissue; Response request is through periodicity transmission information etc.).For example; In certain embodiments; Use prediction and/or forecast information to confirm the travel route and/or the time of suggestion; For example between starting position and final position the optimal route through road net and/or carry out shown in the optimal time that goes, and such confirming is based upon each prediction and/or forecast information of a plurality of Future Time of one or more roads and/or road segment segment.

In addition, various embodiment are mutual for user and other client provide various mechanism to come with one or more traffic information systems (for example, the data sample management system 350 of Fig. 3, RT information providing system 363, and/or information of forecasting provides system 360 etc.).For example; Some embodiment can and receive the corresponding client that responds for the request of producing and mutual control are provided (for example; Client-side program provides mutual user interface; Based on the Web browser interface etc.), for example request relates to information and/or requirement analysis, the selection of current and/or predict traffic conditions, and/or the information that relates to travel route is provided.In addition, some embodiment provide API (" application programming interfaces "), and it allows the client computing system to carry out some able to programmely or all asks, for example through internet message agreement (for example, Web service) and/or other communication mechanism.

Those skilled in the art also can understand, and can be provided with mode alternatively by function that routine provided in certain embodiments as discussed abovely, for example can be divided in a plurality of routines or focuses on several routines.Similarly, the routine shown in certain embodiments can provide than described more function, for example when the routine shown in other alternatively lacks respectively or comprises such function, or works as the function quantity optional time that is provided.In addition, though various operation can be as shown carried out with ad hoc fashion (for example serial or parallel) and/or particular order, it will be understood by those skilled in the art among other embodiment these operations and also can carry out with other order and mode.Those skilled in the art can also be understood that the data structure of above-mentioned discussion can make up by different way, for example the individual data segmentation of structures is concentrated in a data structure in a plurality of data structures or with a plurality of data structures.Similarly, the data structure shown in certain embodiments can be stored than said more or less information, for example when the data structure shown in other alternatively lacks respectively or comprises such information, or when the quantity or the type optional time of institute's canned data.

It is understandable that from above-mentioned,, under the situation that does not deviate from the spirit and scope of the present invention, can carry out various modifications although described certain embodiments at this for the purpose of example.Therefore, the present invention is except that accompanying claims and all not limited this quotes element as proof.In addition, although particular aspects of the present invention is discussed with the form of given claim, inventor's imagination contains various aspects of the present invention with any available claim form.For example, though current only can being stated as in aspects more of the present invention is embedded in the computer-readable medium, similarly others also can comprise.

Claims (56)

1. a computer-executed method is used to estimate the data sample of having represented at the vehicle of travels down, and said method comprises:

Receive the indication of one or more road segment segment of one or more roads, each road segment segment all has the data sample of a plurality of associations, and each data sample is all by one in multi-section vehicle report and indicated the reported position with the corresponding vehicle of said road segment segment; With

For at least one each of said road segment segment,

Automatically analyze a plurality of associated data samples of this road segment segment; Confirm not represent in those data samples the one or more of on said road segment segment actual vehicle travel conditions; Each of at least one of determined data sample indicated the reported position of the vehicle of report data sample; And this report position is corresponding to the actual vehicle travel conditions on said road segment segment, and at least one each of determined data sample all have the said data sample of report vehicle related orientation and should the association orientation not corresponding to the actual vehicle travel conditions on said road segment segment; With

Other data sample provide one or more indications from follow-up use, to remove determined data sample, so that can be used for assisting going on said road segment segment.

2. according to the method for claim 1; Wherein, One or more each at least one road segment segment; Provide indication to remove determined data sample for follow-up use and comprise the associated data sample except determined data sample of analyzing the highway section,, and comprise that the determined average velocity of indication is to be used for assisting going of on road segment segment other vehicle with the average velocity of the vehicle confirming on road segment segment, to go.

3. according to the method for claim 2; Wherein, For each of one or more road segment segment; Provide indication to remove determined data sample for follow-up use and comprise: to analyze the associated data sample except determined data sample in highway section,, and indicate the determined magnitude of traffic flow to be used for assisting going of on road segment segment other vehicle with the magnitude of traffic flow of the vehicle confirming on road segment segment, to go.

4. according to the method for claim 1; Wherein, For one or more road segment segment each, confirm that the one or more data samples at the actual vehicle travel conditions on the road segment segment of not representing of road segment segment comprise: the reporting vehicle position of confirming those data samples is corresponding to the uninterested segment path of representing the actual vehicle travel conditions on the road segment segment.

5. according to the method for claim 4, wherein, at least one each of one or more road segment segment, said road part is to go to and/or from the part of the low capacity road of said road segment segment at least.

6. according to the method for claim 4, wherein, at least one each of said one or more road segment segment, said road partly is near the part of the different road said road segment segment.

7. according to the method for claim 4, wherein, at least one each of said one or more road segment segment, said road partly is the subclass as a plurality of tracks of a said road segment segment part.

8. according to the method for claim 4; Wherein, For at least one each of said one or more road segment segment, said road partly be said road segment segment upwards and/or downward ramp, with related the crossing of the road of said road segment segment/bifurcated road, and related the crossing and/or bifurcated track, and the curb of the road of the related branch line track of the road of said road segment segment, said road segment segment and be used for one or more at least a portion of fault zone of the road of said road segment segment of the road of said road segment segment.

9. according to the method for claim 4, wherein, for one of said one or more road segment segment, said uninterested segment path is the part of a said road segment segment.

10. according to the method for claim 4, wherein, for one of said one or more road segment segment, said uninterested segment path is at least a portion with different another road segment segment of a said road segment segment.

11. method according to claim 1; Wherein, For of said at least one road segment segment; Some of a plurality of data samples related with a said road segment segment are also related with one or more other different road segment segment, and the determined one or more data samples that are used for a said road segment segment are from said at least some data samples.

12. method according to claim 1; Also comprise one for said road segment segment; At least in part based on and a uninterested road segment segment; Automatically confirm to be used for the data sample of a plurality of associations of a said uninterested road segment segment, and provide one or more indications to come to remove the data sample of said a plurality of associations for follow-up use.

13. according to the method for claim 12, wherein, at least in part based on confirming that as uninterested function road class a said road segment segment is uninterested.

14. according to the method for claim 12, wherein, the actual vehicle volume of traffic that is based at least in part on the said road segment segment confirms that a said road segment segment is uninterested.

15. method according to claim 12; Wherein, At least in part based on to confirming and/or, confirm that a said road segment segment is uninterested at (intra-day) variable quantity on the same day of vehicular traffic on the said road segment segment to the confirming of (inter-day) in the daytime variable quantity of vehicular traffic on a said road segment segment.

16. according to the method for claim 12, wherein, at least in part based on the actual traffic amount of blocking up on a said road segment segment is confirmed that a said road segment segment is uninterested.

17. method according to claim 12; Wherein, at least in part based on to traffic congestion on the said road segment segment when daily variation confirm and/or to the variable quantity in the daytime of traffic congestion on a said road segment segment confirm a said road segment segment is uninterested.

18., also comprise and confirm not related one or more data samples automatically, and provide one or more indications to come to remove said one or more data sample for follow-up use with uninterested any road segment segment according to the method for claim 1.

19. method according to claim 1; Wherein, For one or more each of said at least one road segment segment, to one or more data samples of not representing the actual vehicle travel conditions on said road segment segment of road segment segment confirm comprise: confirm under-represented one or more data samples based on the reported position of one or more data samples at least in part.

20. method according to claim 19; Wherein, For each of said one or more road segment segment; Each of a plurality of associated data samples of said road segment segment all indicated the speed of the vehicle of report data sample, and confirming also at least in part based on by the indicated speed of said one or more data samples under-represented one or more data samples of said road segment segment.

21. method according to claim 20; Also be included as at least one each of said one or more road segment segment; Be at least some each of a plurality of associated data samples of said road segment segment, through using the indication speed of estimating said data sample by the reported position of a plurality of data samples indications of the vehicle report of the said data sample of report.

22. method according to claim 19; Wherein, For each of said one or more road segment segment; Be used for said road segment segment a plurality of associated data samples each all have the related orientation of vehicle of the said data sample of report, and one or more data samples of wherein confirming said road be not representative also at least in part based on the related orientation of said one or more data samples.

23. method according to claim 22; Also comprise at least one each for said one or more road segment segment; And, estimate the orientation related with said data sample through using by the reported position of a plurality of data samples indications of the vehicle report of the said data sample of report at least some each of a plurality of associated data samples that are used for said road segment segment.

24. method according to claim 22; Wherein, One of said one or more road segment segment is a part that is included in the road of the vehicle that goes on two reverse directions; A wherein said road segment segment is corresponding to the vehicle that on the said both direction, goes, at least in part based on confirming that with the related orientation of said one or more data samples not representative one or more data samples of said road segment segment comprise: confirm that its related orientation is not representative to a said road segment segment with the corresponding data sample that goes on another of said both direction.

25. method according to claim 22; Wherein, One of said one or more road segment segment is a part that comprises the road in a plurality of tracks with the vehicle that on a plurality of directions, goes; A said road segment segment is corresponding to the subclass in a plurality of tracks with the vehicle that on said a plurality of directions one or more, goes, at least in part based on confirming that with the related orientation of said one or more data samples not representative one or more data samples of a said road segment segment comprise: confirm that its related orientation is not representative to a said road segment segment corresponding to the data sample of said one or more directions.

26. method according to claim 22; Wherein, One or more other road segment segment with one or more other roads of said one or more road segment segment are overlapping; In the vehicle ' of going on the said road segment segment with on the different one or more directions of one or more other directions of the vehicle that goes on said other road segment segment, and at least in part based on confirming not representative the comprising of one or more data samples of a said road segment segment with the related orientation of said one or more data samples: confirm that its related orientation is not representative to a said road segment segment corresponding to the data sample of said one or more directions of a said road segment segment.

27. method according to claim 1; Wherein, For one or more each of said at least one road segment segment, with other data sample of said one or more data samples and said road segment segment at least some of confirming to comprise of one or more data samples of not representing actual vehicle travel conditions on said road segment segment of said road segment segment are compared.

28. method according to claim 1; Wherein, One or more each for said at least one road segment segment; To said road segment segment do not represent one or more data samples of actual vehicle travel conditions on the said road segment segment confirm comprise: be identified in the subclass of the actual vehicle travel conditions on the road segment segment interested or uninterested, and confirm that whether said one or more data samples are corresponding to the subclass of being discerned.

29. method according to claim 1; Each all indicates one or more indications of a plurality of data samples of the reported position of vehicle to it also to comprise reception; At least in part based on the reported position of at least one road segment segment corresponding data sample in related one or more positions separately, in said a plurality of data samples at least some each is related with at least one of said road segment segment.

30. method according to claim 29; Wherein, Each all has the related orientation of the vehicle of said data sample said a plurality of data sample, with data sample related with road segment segment also at least in part based on the related orientation of the vehicle of the corresponding said data sample in related one or more orientation of said road segment segment.

31. according to the method for claim 30, also be included as at least some each of a plurality of data samples, use by the indicated reported position estimation orientation related of a plurality of data samples with said data sample corresponding to the vehicle of data sample.

32. it is, wherein, that data sample is related with road segment segment also at least in part based on one or more vehicle ' characteristics of the vehicle of said data sample except reported position according to the method for claim 29.

33. method according to claim 29; Wherein, Data sample is related with road segment segment also at least in part based on will extending one or more distances with the related one or more positions of said road segment segment, and said one or more distances are at least in part based on the accuracy of reported position and confirm.

34. according to the method for claim 33, wherein, to data sample will be related with road segment segment one or more preset distances of extending of one or more positions at least in part based on the type in data sample source.

35. method according to claim 1; Wherein, One or more each at least some road segment segment; A plurality of associated data samples of said road segment segment also comprise a plurality of data samples, its each all by the traffic sensor report of keeping watch on said road segment segment, and each has all reflected the one or more positions corresponding to said traffic sensor on the said road segment segment.

36. method according to claim 35; Also comprise the one or more indications of reception to a plurality of data samples; Each data sample is all by a plurality of traffic sensor reports of keeping watch on a plurality of road segment segment; Adjust at least some traffic sensors of said a plurality of data samples with these data samples of statistical report; And be at least some each of said a plurality of data samples, at least in part based on by the one or more positions that data sample reflected of coupling, that in said data sample and the said road segment segment at least one is related with each related one or more position of said at least one road segment segment.

37. method according to claim 1; Wherein, One or more each at least one road segment segment; The definite of one or more data samples who does not represent at actual vehicle travel conditions on the said road segment segment to said road segment segment also comprises a plurality of data samples that identification is reported by the single portion vehicle that on said road segment segment, goes, and based on confirming that from the pooling information of a plurality of data samples of being discerned a plurality of data samples that identify are under-represented.

38. method according to claim 1; Wherein, One or more each at least one road segment segment; Each has also reflected the report time of the vehicle of data sample at its reported position place a plurality of associated data samples of said road segment segment, to the automatic analysis of said a plurality of associated data samples of said road also corresponding to predetermined amount of time, so that the actual vehicle travel conditions on said road segment segment is the travel conditions in the section at the fixed time.

39. method according to claim 1; Also comprise; For a plurality of different time periods each, receive a plurality of associated data samples of one in the said road segment segment, each associated data sample has all reflected the reported position of the vehicle at the report time place on said road segment segment in the said time period; And wherein be used for the automatic analysis of a described road segment segment for each execution of said time period, this is analyzed based on the data sample of its report time in the said time period automatically.

40. method according to claim 1; Wherein, For one or more each of at least one road segment segment, carry out confirming to one or more data samples of not representing actual vehicle travel conditions on said road segment segment of said road segment segment with real-time basically mode.

41. method according to claim 40; Wherein, Before by vehicle report data sample; Obtain and at least some of at least some related a plurality of data samples of said road the reports that produce at least some data samples with real-time basically mode in the one or more backs that obtaining at least one data sample through the vehicle on said road segment segment of going.

42. a computing system that is configured to estimate the data sample of representing driving vehicle comprises:

First assembly, it is configured to receive the indication to a plurality of data samples of road, near the vehicle location each data sample reflection road into a plurality of roads each; With

The data sample filter assemblies, it is configured to into a plurality of roads at least some,

Automatically confirm in a plurality of data samples of said road the vehicle location that it reflected not corresponding on said road one or more data samples of interested traveling state of vehicle; With

Indicated data sample one or more indications to a plurality of data samples of the said road except determined data sample is provided, so that can be used for assisting going on road.

43. computing system according to claim 42; Wherein, For one or more each of a plurality of roads, to the vehicle location that it reflected of said road not corresponding on said road interested traveling state of vehicle data sample confirm comprise: confirmed to reflect not the vehicle location that the precalculated position with road is complementary.

44. computing system according to claim 42; Wherein, Said data sample filter assemblies also is configured to one or more each at least one a plurality of road; At least in part based on one or more preset bearings of said road, confirm automatically said road the one or more vehicle ' orientation that is reflected and with on said road one or more data samples in interested vehicle ' orientation corresponding.

45. according to the computing system of claim 42, wherein, each all is included in the instruction of carrying out in the storer of said computing system said first assembly and said data sample filter assemblies.

46. computing system according to claim 42; Wherein, Said first assembly comprises receiving trap, is used for to a plurality of roads each, receives the indication to a plurality of data samples of said road; Each data sample is reflected near the position of the vehicle the said road; And wherein said data sample filter assemblies comprises device, and it is at least some each of said a plurality of roads, confirm automatically in a plurality of data samples of said road the vehicle location that it reflected not corresponding on said road one or more data samples of interested traveling state of vehicle; And the one or more indications to a plurality of data samples of the said road except determined data sample are provided, so that indicated data sample can be used for assisting going on road.

47. a computer-executed method is used to estimate the data sample of reporting by at the vehicle of travels down, this data sample includes the information of closing the vehicle travel conditions, and said method comprises:

Reception is to the indication of a plurality of road segment segment of one or more roads;

Receive the information of the current traffic condition of relevant a plurality of road segment segment; The information that is received comprises a plurality of data samples; Each data sample is all by a report in a plurality of vehicles, and reflects the report speed of this vehicle in the report geographical location, the report that also reflects this vehicle orientation of going; With

For each of a plurality of road segment segment,, based on being identified the data sample of representing the travel conditions on the said road segment segment, and be said road segment segment estimation traffic through following steps:

One group of multidata sample of identification from a plurality of data samples; The geographic position that this group data sample is reported in preset distance with respect to one or more predetermined geographic localities of said road segment segment, and this group data sample reported go the orientation in target offset with respect to one or more preset bearings of said road segment segment;

At least in part based on determined not with the report geographic position of the corresponding data sample of predetermined portions of the road segment segment at interested traveling state of vehicle place, confirm that automatically one or more data samples of this group are not represented the actual vehicle travel conditions on the said road segment segment;

Remove the determined data sample of not representing the actual vehicle travel conditions on the said road segment segment from said group; With

After removal, use the traffic of all vehicles that remaining data sample deduction is gone in group on said road segment segment,

Make so that can obtain the traffic of inferring based on data sample and to be used for assisting going on said road segment segment.

48. method according to claim 47; Wherein, A road segment segment of a plurality of road segment segment is corresponding to the first of the expressway with a plurality of tracks; The predetermined geographic locality that wherein is used for a said road segment segment comprises the geographic area in a plurality of tracks that cover the expressway that is used for said first; The preset distance that extend said geographic area is at least in part based on the precision of the sort of location determining device in the report geographic position of at least some data samples that are used to confirm as the group that a said road segment segment identifies; The preset bearing that wherein is used for a said road segment segment comprises the corresponding one or more orientation of direction of the vehicle that goes on a plurality of tracks with the first of said expressway; And at least in part based on the degree of accuracy of position determining device, at least some data samples of the group that said position determining device is used for identifying to a said road segment segment confirm to report the orientation of going with respect to the target offset of one or more preset bearings of a said road segment segment.

49. method according to claim 48; Wherein, The predetermined portions of a said road segment segment at interested traveling state of vehicle place comprise one or more tracks of expressway, its report geographic position in the data sample that is confirmed as the group that can not represent the actual vehicle travel conditions on a said road segment segment that identifies for a said road segment segment is confirmed as and the corresponding data sample in ramp above and/or under the expressway.

50. method according to claim 48; Wherein, The predetermined portions of a said road segment segment at said interested traveling state of vehicle place comprises one or more tracks of said expressway, and in the data sample that is confirmed as the group that can not represent the actual vehicle travel conditions on a said road segment segment that wherein identifies for a said road segment segment one is that it reports that geographic position is confirmed as and cross/near bifurcated road or the expressway the corresponding data sample in track.

51. method according to claim 48; Wherein, The predetermined portions of a said road segment segment at said interested traveling state of vehicle place comprises the subclass in the track of said expressway, and in the data sample that is confirmed as the group that can not represent the actual vehicle travel conditions on a said road segment segment that wherein identifies one for a said road segment segment be its report geographic position be confirmed as with subclass not in the track in the corresponding data sample in track of expressway.

52. method according to claim 48; Wherein, in the data sample that is confirmed as the group that can not represent the actual vehicle travel conditions on a said road segment segment that identifies for a said road segment segment one be from go with corresponding another road segment segment of the different second portion of said expressway on vehicle and be confirmed as and a said data sample that road segment segment is related improperly.

53. method according to claim 48; Wherein, The type of said location determining device is GPS (GPS) device type, and the preset distance that extend said geographic area is corresponding to such distance, is accurate at the reading of the interior GPS equipment from said type of this distance.

54. method according to claim 47; Wherein, One or more each for said a plurality of road segment segment; Automatically confirm one or more data in the group do not represent the actual vehicle travel conditions on the said road segment segment also at least in part based on: report the one or more ride characteristics except the report geographic position of the vehicle of those data samples, said one or more ride characteristics comprise the car speed that the report speed of those data samples is reflected.

55. method according to claim 47; Wherein, Each of a plurality of data samples also indicated and the report speed of data sample, report geographic position and the report report time that the orientation is associated that goes; Wherein carry out each the estimation of traffic of a plurality of road segment segment, also carry out in the time period identification, have report time corresponding to the said time period with the data of the group of toilet identification to the group of the data sample of road segment segment in each of a plurality of different time periods.

56. method according to claim 47; Wherein, Receive the data sample relevant repeatedly to reflect changing traffic with the current traffic condition of said a plurality of road segment segment; Serve as that the data sample that recently receives is carried out the estimation of traffic to each of said a plurality of road segment segment wherein with real-time mode; Use in said group remaining data sample to infer that the traffic of all vehicles that on said road segment segment, go comprises: the average velocity of confirming remaining data sample; Infer the average velocity of all vehicles that on said road segment segment, go based on determined average velocity, and the information of relevant average velocity of inferring is offered the people that one or more considerations will be gone on said road segment segment.

Images