JP2011113362A - Traffic information estimation system, boundary traffic information estimation apparatus, traffic information estimation apparatus for divided regions, computer program, traffic information estimation method, boundary traffic information estimation method, and traffic information estimation method for divided region - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a new technology for appropriately estimating traffic information in a wide region. <P>SOLUTION: A traffic information estimation system S can estimate, in a region where a plurality of road links are included, the traffic information of the road links based on the traffic information of other road links included in the region. The system S includes an estimation unit 11 for divided regions for estimating the traffic information of road links of estimation objects included in respective divided regions obtained by dividing the region into a plurality of regions without using the traffic information of other road links included in other divided regions other than the divided regions including the road links of the estimation object, but with the traffic information of other road links included in the divided region identical to the divided regions including the road links of the estimation object. The system further includes a boundary estimation unit 11A for estimating the traffic information of boundary road links located at or near a border of the divided regions among the road links included in the region by using the traffic information of the boundary road links in other divided regions. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a traffic information estimation system, a boundary traffic information estimation device, a divided region traffic information estimation device, a computer program, a traffic information estimation method, a boundary traffic information estimation method, and a divided region traffic information estimation method. is there.

As a technology for providing road traffic information to drivers, VICS (Vehicle Information and Communication System: “VICS” is a registered trademark of the foundation) is widely known.
This VICS tabulates traffic information including traffic congestion and link travel time on each route based on fixed point observation information consisting of the number of vehicles, vehicle speed, etc. collected from various roadside sensors (vehicle detectors, loop coils, etc.). The traffic information is provided to the driver by wide-area communication such as narrow-area communication using beacons or FM broadcasting.

As another technique for providing road traffic information to a driver, a traffic information estimation system using a probe car (hereinafter referred to as a probe system) is also known.
For example, as shown in Patent Documents 1 and 2, this probe system uses a vehicle (probe vehicle) that actually travels on a road as a moving body sensor, and wirelessly communicates probe information such as the current vehicle position and time. Are collected from each probe vehicle to generate road traffic information.

Japanese Patent Laid-Open No. 5-151696 Japanese Patent Laying-Open No. 2005-4467

The VICS information can be obtained only with respect to some roads such as main trunk roads where roadside sensors are installed.
On the other hand, in the probe system, since a vehicle (probe vehicle) that actually travels on the road is used as a moving body sensor, traffic information can be acquired even on a road where no roadside sensor is installed.

  However, at present, the number of probe cars is very small, and traffic information cannot be obtained for road links for which no data is obtained from either the VICS or the probe system.

  Therefore, for road links for which data is not obtained from the (VICS and probe) system, it is conceivable to estimate the traffic information based on the traffic information of another road link. For example, the traffic information of a certain road link can be correlated with the traffic information of a road link connected to the road link or other related road links. If such a correlation is used, the traffic information of the road link to be estimated can be supplemented using the traffic information of another road link.

However, if the above estimation is performed in a very wide area, the number of road links that need to be estimated becomes very large and the calculation load of the estimation increases.
For this reason, it is conceivable to set a divided area obtained by dividing the area into a plurality of areas and estimate the traffic information for each divided area. In this case, since it is possible to perform an estimation operation for each relatively narrow divided region, it is easy to decentralize the processing.

  However, when estimating traffic information for each divided area, road links near the boundary of the divided areas may have a high correlation with road links in other divided areas, but the other divided areas A situation occurs in which traffic information of road links cannot be taken into account. For this reason, the estimation accuracy in the vicinity of the boundary of the divided areas is lowered.

  Therefore, an object of the present invention is to provide a new technique for appropriately estimating traffic information in a wide area.

(1) The present invention is a traffic information estimation system capable of estimating traffic information of the road link in an area including a plurality of road links based on traffic information of other road links included in the area, The estimation of the traffic information of the estimation target road link included in each divided area obtained by dividing the area into a plurality of areas is performed on other road links included in other divided areas other than the divided area including the estimation target road link. A divided region estimation unit that uses traffic information of other road links included in the same divided region as the divided region including the estimation target road link without using the traffic information, and a road included in the region Boundary estimation that estimates traffic information of boundary road links located at or near the boundary of the divided area of the links using traffic information of boundary road links in other divided areas When a traffic information estimating system characterized in that it comprises.

  According to the present invention, the traffic information of the road link can be estimated for each divided region, so that the processing can be distributed. Moreover, since it has a boundary estimation unit that estimates the traffic information of the boundary road link located at or near the boundary of the divided area using the traffic information of the boundary road link in the other divided areas, the boundary road link Can prevent a drop in the accuracy of traffic information estimation.

(2) It is preferable that the boundary estimation unit obtains traffic information of boundary road links in other divided regions from the divided region estimation unit. In this case, the boundary road link can be estimated using the traffic information of the boundary road link estimated by the divided region estimation unit.

(3) The boundary estimation unit determines a boundary road link for estimating traffic information using traffic information of a boundary road link included in another divided region from the road link from which the actual traffic information is obtained. It can be extracted based on the estimated distance to the road link. As a result, even when the traffic information is estimated for each divided area, the estimated accuracy near the boundary of the divided area is reduced by appropriately using the measured values of the road link traffic information included in the other divided areas. Can be suppressed.

(4) Traffic information based on actual measurement values at boundary road links that can be estimated by the boundary estimation unit, and boundary roads in the other divided areas that are used to estimate traffic information of boundary road links that can be estimated Boundary that optimizes estimation parameters for estimating traffic information of boundary road links that can be estimated using the boundary learning data that is stored as a combination of link traffic information as boundary learning data It is preferable to further include a learning unit. In this case, the estimation parameter for estimating the traffic information of the boundary road link can be optimized.

(5) Traffic information based on measured values in a road link that can be an estimation target by the division area estimation unit, and traffic information of the other road link that is used to estimate traffic information of the road link that can be the estimation target Is stored as divided region learning data, and the divided region learning unit that optimizes the estimation parameter for estimating the traffic information of the road link that can be the estimation target using the accumulated divided region learning data Is preferably further provided. In this case, the estimation parameter for estimating the road link traffic information in the divided area can be optimized.

(6) The present invention viewed from another viewpoint is a boundary used in a traffic information estimation system that estimates traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas. A traffic information estimation device for traffic information of a boundary road link located at or near a boundary of the divided area among road links included in the area, and traffic information of a boundary road link in another divided area A boundary traffic information estimation device comprising a boundary estimation unit for estimation using

(7) The present invention viewed from still another viewpoint is used in a traffic information estimation system that estimates traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas. A traffic information estimation device for a divided area that is obtained by estimating traffic information of a road link to be estimated included in one divided area without using traffic information of another road link included in another divided area, A division region estimation unit that uses traffic information of other road links included in the one division region, and the division region estimation unit is located at or near the boundary of the one division region A traffic information estimation device for a segmented area characterized in that it is configured to provide traffic information of a border road link to a boundary estimation unit for estimating traffic information of a border road link in another segmented area.

(8) The present invention viewed from still another viewpoint is a computer program for causing a computer to function as the traffic information estimation system according to any one of (1) to (5).

(9) The present invention viewed from still another aspect is a computer program for causing a computer to function as the boundary traffic information estimating device described in (6) above.

(10) The present invention viewed from still another viewpoint is a computer program for causing a computer to function as the traffic information estimation device for divided areas described in (7) above.

(11) According to another aspect of the present invention, traffic information for estimating traffic information of the road link in an area including a plurality of road links based on traffic information of other road links included in the area In the estimation method, the traffic information estimation of the estimation target road link included in each of the divided areas obtained by dividing the area into a plurality of divided areas is included in the other divided areas other than the divided area including the estimation target road link. Without using the traffic information of the other road links to be estimated, using the traffic information of the other road links included in the same divided area as the divided area including the estimation target road link, Of the road links included in the area, the traffic information of the boundary road link located at or near the boundary of the divided area, using the traffic information of the boundary road link in another divided area, A traffic information estimating method characterized by comprising the boundary for estimating step of constant, the.

(12) The present invention viewed from still another viewpoint is a boundary in a traffic information estimation system that estimates traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas. A traffic information estimation method for a road, wherein traffic information of a boundary road link located in or near a boundary of the divided area among road links included in the area is used, and traffic information of a boundary road link in another divided area is used. A boundary traffic information estimation method characterized by including a boundary estimation step for estimation.

(13) From another viewpoint, the present invention provides a divided region in a traffic information estimation system that estimates the traffic information of the road link in a region including a plurality of road links for each divided region obtained by dividing the region into a plurality of regions. A traffic information estimation method for a vehicle, wherein traffic information of an estimation target road link included in one divided region is estimated without using traffic information of another road link included in the other divided region. The step of using the traffic information of other road links included in the divided area, and the traffic information of the boundary road link located in or near the boundary of the one divided area, and the traffic of the boundary road link in the other divided area And a step of making the information usable in estimation of information.

  According to the present invention, it is possible to appropriately estimate traffic information in a wide area.

1 is an overall configuration diagram of a traffic information system. It is a figure which shows the state which divided | segmented the object area | region into the several division area. 1 is an overall configuration diagram of a traffic information estimation system. It is a flowchart which shows the procedure of the estimation / learning process of a traffic information estimation system. It is a whole block diagram of the traffic information estimation apparatus for divided areas. It is a block diagram of an input information processing part. It is a figure which shows conversion information. It is a flowchart which shows the traffic information estimation process procedure in a division area. It is a block diagram of a neural network. It is a figure which shows the example of the road link in one division area. It is a figure which shows the initial state of a division area estimation database. It is a figure which shows the initial state of a division area weight database. It is a figure which shows the VICS information and probe information which were acquired as input information. It is a figure which shows the division area estimation database after the 1st update. It is a figure which shows the division area estimation database after the 2nd update. It is a figure which shows the division area estimation database after the 3rd update. It is a figure which shows the part extracted as a snapshot. It is a figure which shows the database for division area learning. It is a flowchart which shows a learning process. It is a figure which shows the boundary road link contained in the boundary area | region among object areas. It is a figure which shows the whole structure of the traffic information estimation apparatus for boundaries. It is a figure which shows the boundary estimation database in which the speed information acquired from the traffic information estimation apparatus for division areas was set. It is a figure which shows the initial state of a boundary weight database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows a boundary estimation database. It is a figure which shows the boundary estimation database after completion of secondary estimation. It is a figure which shows the boundary weight database after learning.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.
[1. overall structure]
FIG. 1 shows a traffic information system having a traffic information estimation system 1. In addition to the traffic information estimation system 1, the traffic information system includes a probe vehicle 3 equipped with the in-vehicle device 2, a roadside communication device 4 that wirelessly communicates with the in-vehicle device 2, and a roadside sensor 5.

  The traffic information estimation system 1 has a function of acquiring traffic information (observation information) such as VICS information and probe information and generating traffic information for provision to provide to the vehicle. The traffic information estimation system 1 can also be configured as a part of a traffic control system that performs various traffic processing such as traffic signal control and traffic control based on traffic information.

  The traffic information estimation system 1 is configured by a computer having a processing device (CPU) and a storage device. The system 1 is preferably composed of a plurality of computers, but may be composed of a single computer. A computer program for causing the computer to function as a traffic information estimation system is stored in the storage device of one or more computers. The computer program is executed by the processing device, and the processing device performs functions as the traffic information estimation system 1 by inputting and outputting to the storage device and the like. The functions of the traffic information estimation system 1 described below are realized by the computer program unless otherwise specified.

  The in-vehicle device 2 generates probe information as observation information of the probe vehicle 3 and wirelessly transmits it to the roadside communication device 4. The probe information is traffic information including the position of the probe vehicle, the passing speed of the position, the passing time of the position, the vehicle ID of the probe vehicle, and the like. Further, the probe information may include other information. The position of the probe vehicle is calculated based on the GPS signal received by the GPS receiver included in the in-vehicle device 2.

  The roadside communication device 4 transmits / receives information to / from the in-vehicle device 2 by wireless communication. Specifically, the roadside communication device 4 receives probe information as observation information transmitted by the in-vehicle device 2 and transfers the probe information to the traffic information estimation device (central device) 1. Further, the roadside communication device 4 can acquire traffic information for provision to the vehicle from the traffic information estimation device (central device) 1 and transmit the traffic information to the in-vehicle device 2. The roadside communication device 4 and the traffic information estimation device 1 are connected by a communication line.

  The roadside sensor 5 is for detecting traffic information as observation information (actually measured values), for example, a vehicle detector for ultrasonically detecting a vehicle passing underneath, or a loop for detecting a vehicle by a change in inductance. It consists of an image sensor that measures the traffic volume and vehicle speed by image processing of the coil or camera video, and is used on highways and major trunk roads for the purpose of measuring the number of vehicles flowing into the intersection and the vehicle speed. is set up.

  The observation information detected by the roadside sensor 5 is transmitted to the VICS center server 6 via the communication line, and the VICS center server 6 generates VICS information based on the observation information of the roadside sensor 5. This VICS information is transmitted to the traffic information estimation device 1 via a communication line.

The VICS information is traffic information including traffic jams and link travel times on each road link. Since the VICS information is updated by obtaining observation information from the roadside sensor 5 every 5 minutes, high-density information can be obtained in time. However, the roadside sensor 5 is not installed on all roads (20% or less on main roads), and the area coverage rate is low.
On the other hand, since the probe information is acquired from the probe vehicle 3 traveling on the road, the area coverage rate can be increased. However, since the penetration rate of the in-vehicle device 2 for becoming the probe vehicle 3 is still low, only low-density data can be obtained in terms of time.

  That is, when a road link is set on a road in a predetermined area, traffic information (VICS information) is always obtained for each VICS information update unit time for a road link from which VICS information is obtained. On the other hand, as for road links for which VICS information cannot be obtained, there are road links for which probe information can be obtained as traffic information, and road links for which probe information cannot be obtained for each VICS information update unit time. become.

[2. Details of Traffic Information Estimation System]
[2.1 Introduction]
The traffic information estimation system according to the present embodiment acquires VICS information and / or probe information, and estimates traffic information of a road link for which neither VICS information nor probe information is obtained, and complements the traffic information of the road link. By doing so, traffic information of all road links in an area (target area) where generation of traffic information is required is generated.
In this way, by supplementing road link traffic information for which neither VICS information nor probe information can be obtained, more accurate traffic information can be provided to the vehicle (navigation system), or traffic control can be performed with high accuracy. Is possible.
In the following, a road link for which VICS information or probe information is not obtained and traffic information needs to be estimated and complemented is referred to as “estimation target road link”.

[2.2 Divided area and boundary area]
In the present embodiment, the entire region (target region) that includes a plurality of road links and requires generation of traffic information is regarded as being configured by a set of a plurality of divided regions. The target area here corresponds to, for example, all or a part of a certain country or region. Therefore, the number of divided areas is actually about several hundred to several tens of thousands, but in this embodiment, as shown in FIG. 2, the entire target area is divided into four divided areas (first divided area to A case where the image is divided into (fourth divided region) will be described. Hereinafter, the divided area may be referred to as “mesh”.
Further, in the present embodiment, a boundary portion where the divided areas contact each other in the target area is referred to as a “boundary area”.

[2.3 Overall configuration of traffic information estimation system]
As shown in FIG. 3, the traffic information estimation system S is a traffic information estimation device 1 for a plurality of (four) divided areas provided corresponding to each divided area of the first divided area to the fourth divided area. And a boundary traffic information estimation device 1A for the boundary region.

  Each of the plurality of divided area traffic information estimation devices 1 acquires and estimates the traffic information of the road link included in the corresponding divided area. The boundary traffic information estimation apparatus 1A acquires and estimates traffic information of road links included in the boundary area. Therefore, the traffic information of the road link included in the boundary area can be estimated by the divided area traffic information estimation apparatus 1 and can also be estimated by the boundary traffic information estimation apparatus 1A.

Note that the traffic information estimation system S of the present embodiment can be configured by five computers in response to the presence of the five estimation devices 1 and 1A, but is configured by fewer than five computers. May be.
In other words, the five devices 1 and 1A shown in FIG. 3 correspond to computer programs (division area traffic information estimation computer program or boundary traffic information estimation computer program) for performing the functions of the respective devices 1 and 1A. It is not necessary to support a computer as hardware.
Therefore, the functions of the plurality of estimation devices 1 and 1A may be assigned to one computer. The number of computers to be used for configuring the system S may be determined as appropriate depending on the processing speed and storage capacity of the computer, and is not limited to the number of devices shown.

Each of the estimation devices 1 and 1A has a function of estimating the traffic information of the estimation target road link and a function of learning a parameter used for estimation (estimation parameter).
In this estimation system S, each estimation device 1 for each divided region estimates the traffic information of the road link included in the divided region and learns the estimation parameters for each divided region, and also uses the estimation device for the boundary region. 1A performs traffic information estimation (re-estimation) and learning of estimation parameters for road links (boundary road links) included in the boundary region.

  FIG. 4 shows a procedure of estimation / learning processing in the traffic information estimation system S. First, at the time of starting the system, initial values are set as required for estimation databases (described later) 13 and 13A and weight databases (described later) 15 and 15 provided in each estimation device 1 and 1A.

Then, the traffic information estimation device 1 for each divided area of the traffic information estimation system S acquires VICS information and probe information, and generates speed information (traffic information) of each road link from the VICS information and probe information. However, road links from which speed information can be acquired are a part of road links in each divided area, and there are road links from which speed information cannot be obtained.
Therefore, the traffic information estimation device 1 for each divided area estimates speed information of road links for which speed information is not obtained, and learns estimation parameters (step S101).
It should be noted that, for reasons such as being connected only to road links in other divided areas, in the estimation of speed information for each divided area (step S101), road links (boundary road links) where speed information cannot be estimated may occur. is there. In addition, since it is connected to the road link of the same divided area, it is also connected to the road link of the other divided area, so the speed information of the road link of the other divided area is used for estimation of appropriate speed information. There may be a road link (boundary road link) to be considered.

  In order to estimate the speed information of these road links (boundary road links), the traffic information estimation device 1 for each divided area obtains and estimates the speed information of the road links in each divided area. Is transmitted to the boundary traffic information estimation apparatus 1A (step S102).

As a result, the boundary traffic information estimation device 1A collects speed information of all boundary road links included in the boundary region. The boundary traffic information estimation device 1A estimates the speed information of each boundary road link using the speed information of the boundary road link in different divided regions (step S103). Further, an estimation parameter for estimating the speed information of the boundary road link is also learned (step S103).
If the estimation by the traffic information estimation device for a divided area 1 is “primary estimation”, the estimation by the boundary traffic information estimation device 1A can be called “secondary estimation”.

  The speed information of the boundary road link updated by the secondary estimation is transmitted from the boundary traffic information estimation apparatus 1A to be returned to each divided area traffic information estimation apparatus 1 (step S104).

Through the processes in steps S101 to S104, speed information of each road link in the entire target area is obtained.
According to the present embodiment, even if the target area is wide and the number of road links included in the target area is very large, the speed information is estimated / learned for each divided area, so that processing is performed in units of divided areas. Can be decentralized. In addition, when estimation is performed in units of divided areas, the estimation accuracy of the speed information of the boundary road link located at or near the boundary of the divided area decreases, but by estimating / re-estimating the boundary road link by secondary estimation, Thus, it is possible to prevent a reduction in the estimation accuracy of the speed information of the boundary road link.

  Further, the processes in steps S101 to S104 described above are repeatedly executed every time the speed information is acquired / generated. In the present estimation system S, in order to acquire VICS information and probe information and generate speed information in accordance with the update period (for example, 5 minutes) of VICS information, the processing of steps S101 to S104 is performed to update VICS information. It is repeatedly executed in accordance with a cycle (for example, 5 minutes).

[2.4 Configuration of Traffic Information Estimation Device for Divided Area]
FIG. 5 shows a traffic information estimation device 1 for divided areas. The estimation device 1 performs estimation / learning processing in any one of the first to fourth divided areas.
This estimation device 1 includes a divided region estimation system (divided region estimation unit) 11 for estimating traffic information of an estimation target road link in a corresponding divided region, and parameters (estimation parameters) used for the estimation. And a divided region learning system (divided region learning unit) 12 for learning.

  Further, the traffic information estimation device 1 includes a divided region estimation database (traffic information database) 13 for accumulating traffic information and the like estimated by the divided region estimation system 11, and among the data in the estimated database 13, a divided region learning system. 12, a divided region learning database 14 for accumulating data used for learning in 12, and a divided region weight database (estimated parameter database) 15 for accumulating estimation parameters (in this embodiment, “weight”) are stored on the storage device. I have.

  Further, the divided area traffic information estimation device 1 performs input processing for the VICS information and probe information acquired by the divided area traffic information estimation device 1 (hereinafter referred to as “input information” when both information are collectively referred to). An information processing unit 16 is provided.

  The input information processing unit 16 performs processing for generating “speed information” of each link from the input information, and the generated “speed information” is given to the divided region estimation database 13, and the divided region estimation database Used for 13 updates.

As shown in FIG. 6, the input information processing unit 16 includes a VICS information processing unit 17 that generates “speed information” from the acquired VICS information, and a probe information processing unit that generates “speed information” from the acquired probe information. 18.
The VICS information processing unit 17 calculates a link travel speed calculation unit 17a that calculates the link travel speed of the road link from the link travel time included in the VICS information, and a speed that converts the link travel speed into “speed information” of the link. And an information conversion unit 17b.

  The link travel speed calculation unit 17a of the VICS information processing unit 17 divides the link length of the road link for which the link travel speed is to be calculated by the link travel time of the road link, so that the link travel speed [km / h] Is calculated. The link lengths of all road links in the target area are stored in advance in the storage device of the device 1.

  The speed information conversion unit 17b of the VICS information processing unit 17 converts the link travel speed obtained by the link travel speed calculation unit 17a into an index value (speed index information) called “speed information” (standardized speed). This conversion is performed by the speed information conversion unit 17 b referring to the “speed-speed information” conversion information 19 preset in the apparatus 1. The “speed-speed information” conversion information 19 is set as shown in FIG. 7, for example, and will be described later in detail.

  The link travel speed calculation unit 18b of the probe information processing unit 18 calculates the link travel speed of the road link for which the link travel speed is to be calculated based on the position and time included in the probe information.

  Similar to the speed information conversion unit 17b of the VICS information processing unit 17, the speed information conversion unit 18b of the probe information processing unit 18 converts the link travel speed into “speed information”. The processing content is the same as that of the speed information conversion unit 17b.

  The aforementioned “speed information” is an index value that takes a value corresponding to the magnitude of the link travel speed. In the present embodiment, as shown in FIG. 7, the speed information takes a value from 0 to 1, the link travel speed is nearly “0” near 100 [km / h], and the link travel speed is 0. A value of 1 is taken at [km / h]. The conversion information 19 shown in FIG. 7 uses a natural logarithm. Specifically, when the link travel speed (horizontal axis in FIG. 7) is x and the speed information (vertical axis in FIG. 7) is y, The function is y = exp (− (x / 20)). Note that the value “20” in this formula is a preferred example and is not limited to “20”, and any positive number a can be adopted.

In the function of y = exp (− (x / 20)), the slope seen from x is obtained by differentiating this expression by x, and is as follows.

  As described above, the conversion information in FIG. 7 is set so that the rate of change in the speed information (standardized speed) y with respect to the change in the link travel speed x (the slope seen from x) decreases as the link travel speed x increases. Has been.

この場合、ｙからみた傾きは、ｙの逆数に比例することになる。 Here, when the function of FIG. 7 is expressed as a function with respect to y, x = −20 × ln (y). In this case, the slope seen from y is obtained by differentiating this expression with y. It is.

In this case, the slope seen from y is proportional to the reciprocal of y.

As shown in FIG. 7, even if the speed information (standardized speed) changes by the same value by setting the conversion information, the effect on the actual link travel speed depends on the magnitude of the speed information (standardized speed). Different.
For example, consider cases where the speed information is 0.1 and 0.5. In this case, since the slope seen from y is proportional to the reciprocal of y, dx / dy = −20 / 0.1 = −200 and dx / dy = −20 / 0.5 = −40.

  Therefore, when the speed information changes by about 0.01, and when the speed information is higher than 0.1, the change in the link travel speed is −0.01 (dx / dy) = 2 [km / h. ], The speed information of the link travel speed is −0.01 (dx / dy) = 0.4 [km / h]. Becomes relatively small.

  That is, even if the speed information (standardized speed) changes by the same value, the influence on the actual link travel speed is determined by the reciprocal of the speed information (standardized speed). Since the reciprocal of the speed information, which is an inclination, is proportional to the link travel time for moving a unit distance (for example, 1 km), it is effective to use conversion information as shown in FIG. 7 when evaluating the travel time.

  According to the conversion information 19 set as described above, in addition to an element of simply “speed”, the road information is busy and traffic jams, or the road is empty and the vehicle is in good condition. It is also possible to have an element of the degree of traffic congestion (the degree of traffic flow). Note that the conversion information is not limited to that shown in FIG. Further, it is not necessary to use an index value as speed information, and “speed information” may be “speed” itself.

  FIG. 8 shows a traffic information estimation process in the divided area (estimated process in step S101) performed by the divided area traffic information estimation apparatus 1. First, when the traffic information estimation device for a divided area 1 acquires VICS information and probe information for the corresponding divided area, the input information processing unit 16 generates speed information of each road link from the VICS information and the probe information (step) S1). However, the road links from which speed information can be acquired in step S1 are a part of all road links in the target area, and there are road links for which speed information cannot be obtained in step S1.

  Subsequently, the speed information obtained in step S1 is set in the divided region estimation database 13, and the divided region estimation database DB4 is updated (step S2). Then, based on the content of the divided region estimation database 13 updated in step S2, the divided region estimation system 11 estimates speed information about road links for which speed information is not obtained, and the estimated speed information is The divided region estimation database 13 is set, and the divided region estimation database 13 is updated (step S3). By this step S4, speed information (a mixture of speed information based on measured values and speed information that is estimated values) is obtained for all road links in the divided areas in charge of the divided area traffic information estimation device 1. .

The speed information for all road links obtained in step S3 is output to the outside of the apparatus 1 (step S4). Specifically, it is displayed on the display of the estimation system S or output as information provided to the in-vehicle device 2.
A part of the content of the divided region estimation database 13 updated in step S3 is stored as a snapshot in the divided region learning database 14 and used as learning data by the divided region learning system 12 (step S5). .

FIG. 9 shows a neural network for the estimation system 11 to estimate speed information of the estimation target road link. The illustrated neural network generates an output value y by multiplying each of N input signals x _i (i: 1 to N) having values of 0 to 1 by weights w _i (w _i : 0 to 1). It is configured as a simple perceptron.
Here, the input signal x _i is speed information of a road link other than the estimation target road link (a road link connected to the estimation target road link), and the output value y is speed information of the estimation target road link. .

Further, the weight w _i is a value indicating how much the speed information of each of the plurality of road links other than the estimation target road link is reflected, and the road link having a high correlation with the estimation target road link (for example, A road link that constitutes the same road as the estimation target road link and is adjacent to the estimation target road link) should be set to a larger value, and a road link having a lower correlation should be set to a smaller value.

However, in the case of FIG. 9, unlike the general simple perceptron, an independent parameter w ₀ that is added to the node without being multiplied by the input signal x _i is provided. This independent parameter w ₀ expresses a factor (for example, a difference in speed limit between road links) that a factor other than speed information in a road link other than the estimation target road link gives to the speed information of the estimation target road link. Speed information can be estimated with high accuracy. Further, when learning the estimation parameter (weight), the estimation parameter is easily converged to the optimum value, and the learning process can be performed easily or at high speed.

  As described above, in order for the estimation system 11 to obtain the speed information of a certain estimation target road link, the speed information of the other road link that is slightly correlated with the estimation target road link and the other road It is only necessary to obtain a weight indicating how much the link speed information is reflected in the speed information of the estimation target road link. The speed information of such other road links is accumulated in the estimation database (traffic information database) 13, the weights are accumulated in the weight database 15, and the estimation system 11 obtains necessary information from both the databases 13 and 15. get.

  Since the above-described neural network is provided for each road link, the estimation system 11 uses speed information about each of the plurality of road links, speed information about other road links, and an estimation parameter ( It is configured to be able to be estimated using (weight).

  Note that the neural network for estimating the velocity information is not limited to a single-layer perceptron as shown in FIG. 9, but may be a multilayer perceptron having an input layer, an intermediate layer, and an output layer. When configured as a multilayer perceptron, the speed information of the estimation target road link can be appropriately obtained even when the speed information has a non-linear relationship between the estimation target road link and another road.

In the present embodiment, regarding the estimation of the speed information in the divided area, a road link connected as shown in FIG. 10 is assumed. FIG. 10 shows all road links in a certain divided area.
In FIG. 10, Vx indicates road link speed information (value of 0 to 1). The subscript x in Vx indicates the link number of the road link and takes a value of 1 to 24. That is, in FIG. 7, there are 24 road links with link numbers 1 to 24. Moreover, the arrow direction of each link shows the traveling direction of the vehicle.

In FIG. 10, road links (link numbers x = 1 to 10) indicated by solid arrows are links from which VICS information can be acquired, for example, road links corresponding to expressways and main trunk roads. Moreover, the road link (link number x = 11-24) shown by the dotted line arrow is a link from which VICS information cannot be acquired, and is, for example, a general road other than a highway or a main trunk road. A road link indicated by a dotted arrow may be an estimation target road link of speed information. That is, the road link indicated by the dotted arrow does not become the estimation target road link when the probe information which is the sample information is obtained, and when the probe information is not obtained, the estimation target road link Thus, the speed information estimation process is executed.
Even if the VICS information can be acquired, if the VICS information cannot be acquired for some reason, it is treated as an estimation target road link.

Hereinafter, on the premise of the road link in FIG. 10, the speed information estimation procedure will be described in detail with reference to FIGS. 4 and 8 again.
First, initial values are input to the divided region estimation database (traffic information database) 13 and the divided region weight database 15 by the device administrator (step S101).

  As shown in FIG. 11, the divided region estimation database 13 has data items of “check” 31, “speed information” 32, “related road link information” 33, “link length” 34, and “learning?”. Thus, the value of each data item can be stored for each road link (link number).

Among the data items, “check” 31 is an item indicating whether or not the speed information of each road link is updated and the order of update (update order; estimated order). “Speed information” 32 is an item in which speed information of each road link is set.
The “related road link information” 33 indicates a road link (related road link) correlated with each road link, and here indicates a road link (link number) connected to each road link. . The related road links in the divided area estimation database 13 are limited to the same divided area, and road links in other divided areas are not related road links here even if there is a correlation.

The “related road link information” 33 is divided into five types of “reverse”, “A order”, “A reverse”, “B order”, and “B reverse”.
“Reverse” indicates a link number of a road link opposite to an arbitrary road link. For example, for a road link with link number 1, the road link with link number 8 becomes a “reverse” road link.
“A order” is a road link connected in the forward direction behind a certain road link. For example, for the road link with link number 1, the road links with link numbers 12, 7, and 15 are “A order”. It becomes the road link.
“A reverse” is a road link connected in the reverse direction behind a certain road link. For example, for the road link with link number 1, the road links with link numbers 11, 15, and 13 are “A reverse”. It becomes the road link.

“B order” is a road link connected in the forward direction in front of a certain road link. For example, for the road link with link number 1, the road links with link numbers 4 and 9 are “B order”. It becomes a link.
“B reverse” is a road link connected in the reverse direction in front of a certain road link. For example, for the road link with link number 1, the road links with link numbers 3 and 6 are “B reverse”. It becomes a link.

  Of the data items, “link length” 34 indicates the link length of each road link. “Learning?” 35 indicates whether or not the speed information of each road link is data (learning data) for learning by the divided region learning unit 20 (learning system 12). Here, it takes a value of 0 or 1. “0” indicates that the speed information of the road link is not the divided area learning data, and “1” indicates that the road link speed information is the divided area learning data. .

  The initial value input in step S101 is performed when the operation of the system S is started or reset. For the divided region estimation database 11, among the above data items, “speed information” 32, “related road link information” 33, “link” An initial value is set for “length” 34. As an initial value of the “speed information” 32, for example, 0 may be set for all road links. The initial values of “related road link information” 33 and “link length” 34 are set according to the road configuration of the target area. The initial values of “related road link information” 33 and “link length” 34 are not updated even if traffic information (speed information) including VICS information and probe information is acquired.

On the other hand, the value of “speed information” 34 is updated for all road links every time traffic information (speed information) including VICS information and probe information is acquired (steps S2 and S3).
The “check” 31 is initialized to 0 each time traffic information (speed information) is acquired (step S1). The “learning?” 35 is also set to 0 or 1 depending on whether or not the speed information of each road link should be used as learning data every time traffic information (speed information) is acquired (step S1).

As shown in FIG. 12, in the divided region weight database 15, a weight wi used when an estimated value of speed information in each road link in the divided region is obtained from speed information of other road links is set as an initial value. . The weight wi is set to “number of related road links + 1” for each road link. In FIG. 12, w ₀ is an independent parameter, and w _{1 and} subsequent weights are weights to be multiplied by the related road link speed information.

  Since the weight wi that is an estimation parameter is automatically updated to a more appropriate value by learning by the divided region learning system 12, an appropriate value may be set as an initial value. Therefore, initial setting is easy.

Now, after performing the above initialization for the divided region estimation database and the divided region weight database, the VICS information and the probe information (traffic information) as shown in FIG. Shall be.
In FIG. 13, VICS information (link travel time) for the road links with link numbers 1 to 10 is obtained, and probe information for the road link with link numbers 20 is obtained. Neither VICS information nor probe information is obtained for other road links. In FIG. 13, probe information about the road link with the link number 20 is shown as “link travel time” in the same manner as the VICS information in order to facilitate the notation.

  In the information of FIG. 13, a value “1” indicating that the road link (link number 20) in which the probe information exists is a learning target is set, and the road link (link number) in which the VICS information exists. As for 1 to 10), a value “0” indicating that it is not a learning target is set.

  When the input information as shown in FIG. 13 is acquired, the “travel time” in this information is converted into “speed information” by the input information processing unit 16 (step S1), and the response of the estimation database 13 is determined by the speed information. The “speed information” 32 of the road link to be updated is updated (first update; step S2). For the updated road link, “1” indicating that the speed information has been updated in the first update is set in “check” 31. For the road link whose “learning target” in the input information of FIG. 13 is “1” (here, the road link with the link number 20), the learning flag “learning?” 35 is set to “1”. The

  FIG. 14 shows the contents of the estimation database 13 after the first update (set of input information) is performed as described above.

Subsequently, the speed information for the road links (link numbers 11 to 19 and 21 to 24) whose speed information is not updated is estimated, and the estimation database 13 is updated with the estimated value (step S3).
Specifically, first, among the related road links (adjacent road links) of road links (link numbers 1 to 10, 20) in which “1” indicating the previous update is set in the “check” 31 item, A road link (check = 0) for which speed information has not yet been updated based on the current input information (FIG. 13) is extracted. Here, 11 road links of link numbers 12, 15, 11, 13, 19, 18, 17, 21, 21, 24, 14 and 16 are extracted (see FIG. 15). These 11 road links serve as estimation target road links here.

  Then, the divided region estimation system 11 reads the related road links for each of the eleven estimation target road links from the divided region estimation database 13 and sets the weights (for estimation) set for each of the eleven estimation target road links. Parameter) is read from the divided area weight database 15, and using these, the estimated value of the speed information of each estimation target road link is calculated. The calculated estimated value of the speed information is set in “speed information” of the divided region estimation database 13, and the second update of the speed information is performed. For the updated road link, “2” indicating that the speed information has been updated in the second update is set in “check” 31.

Among the estimation target road links, for example, an arithmetic expression for obtaining an estimated value (V ₁₂ , V ₁₅ , V ₁₁ , V ₁₃ ) of speed information of road links of link numbers ₁₂ , ₁₅ , ₁₁ , and ₁₃ is as follows. It is as follows.
V ₁₂ = w ₀ + w ₁ V ₁₁ + w ₂ V ₁ + w ₃ V ₅ + w ₄ V ₁₃ + w ₅ V ₈ + w ₆ V ₇ + w ₇ V ₁₅
V ₁₅ = w ₀ + w ₁ V ₁₃ + w ₂ V ₂₀ + w ₃ V ₁₆ + w ₄ V ₁₇ + w ₅ V ₁₄ + w ₆ V ₁ + w ₇ V ₁₁
+ W ₈ V ₅ + w ₉ V ₈ + w ₁₀ V ₁₂ + w ₁₁ V ₅
V ₁₁ = w ₀ + w ₁ V ₁₂ + w ₂ V ₈ + w ₃ V ₁₅ + w ₄ V ₇ + w ₅ V ₁ + w ₆ V ₁₁ + w ₇ V ₅
V ₁₃ = w ₀ + w ₁ V ₁₅ + w ₂ V ₈ + w ₃ V ₁₂ + w ₄ V ₇ + w ₅ V ₁ + w ₆ V ₁₁ + w ₇ V ₅
+ W ₈ V ₁₄ + w ₉ V ₁₇ + w ₁₀ V ₁₆ + w ₁₁ V ₂₀

  And among the related road links (adjacent road links) of the road links (link numbers 11 to 19, 21, 24) in which “2” indicating the previous update is set in the “check” 31 item, this input A road link (check = 0) for which speed information has not yet been updated based on the information (FIG. 13) is extracted. Here, two road links with link numbers 22 and 23 are extracted (see FIG. 16). These two road links become the next estimation target road links.

  Then, the divided region estimation system 11 reads the related road links for the two estimation target road links from the estimation database 13 and sets the weights (estimation parameters) set for the two estimation target road links. Are read from the weight database 15, and using these, the estimated value of the speed information of each estimation target road link is calculated. The calculated estimated value of the speed information is set in “speed information” of the estimation database 13, and the third update of the speed information is performed. As for the updated road link, “3” indicating that the speed information has been updated in the third update is set in “check” 31.

  The above process is repeated until the speed information for all road links is estimated (step S3). Here, since all speed information has been complemented by three updates, the estimation process is terminated.

Then, the contents of the estimation database are output (step S4).
Further, of the road link data of the estimation database 13 for which the estimation process has been completed based on the current input information (FIG. 13), the road link of the link number 20 with “1” set to “Learning?” 35. A snapshot (see FIG. 17) is added to the learning database 14. Here, the snapshot stores a combination of “speed information” of the road link of the link number for which “1” is set to “learn?” 35 and “speed information” of the related road link of the road link. It is what. Here, the speed information of the road link having the link number for which “1” is set in “Learning?” 35 is the speed information (traffic information) based on the actual measurement value because it is a value obtained from the probe information. In addition, in the “speed information” of the related road link of the road link, an actual measurement value and an estimated value obtained from VICS information are mixed.

A snapshot occurs whenever input information is acquired and all road links in the estimation database are updated (steps S2 and S3). This snapshot is generated for a road link for which probe information has been acquired.
Therefore, in the above example, the snapshot is generated only for the road link with the link number 20, but if all the road links in the estimation database are updated (steps S2 and S3) many times, the other road links are also snapped. Shots are accumulated. In addition, when a sufficient time has passed so that the input information is repeatedly generated, a plurality of snapshots are accumulated for one road link.

FIG. 18 shows the contents of the divided region learning database 14 in which a plurality of snapshots are accumulated for a plurality of road links.
Based on the divided region learning database 14 in which a large number of snapshots are accumulated in this way, the divided region learning system 12 learns the weights (estimation parameters) stored in the divided region weight database 15 (optimum). The contents of the divided area weight database 15 are updated.

FIG. 19 shows the procedure of the learning process (step S101) by the divided region learning system 12. First, the divided region learning system 12 sets learning parameters such as an allowable error for error determination, the number of intermediate layers constituting the neural network (FIG. 9), and a learning count (step S11).
The divided region learning system 12 is configured as a neuro engine that optimizes (learns) a neural network as shown in FIG. That is, the divided region learning system 12 uses the speed information that is an actual measurement value among the snapshots stored in the divided region learning database 14 as a teacher signal, and the related road of the road link having the speed information that becomes the teacher signal. An appropriate neural network for outputting the teacher signal is reconstructed from the speed information about the link. That is, the divided region learning system 12 calculates the optimum value of the weight from the learning data including the speed information based on the actually measured value and the speed information about the related road link of the road link having the speed information. The optimum weight value can be calculated by, for example, the least square method.

  The optimum weight value is calculated until the speed information calculated from the speed information about the related road link approaches the teacher signal and the error from the teacher signal is less than the set allowable error (step S13). ).

  When the weights converge and the learning process in the divided area ends, the obtained weight is reflected in the divided area weight database 15 and the divided area weight database 15 is updated.

  When the input information including the VICS information and the probe information is generated after the divided region weight database 15 is updated, the speed information estimation by the divided region estimation system 11 is performed with higher accuracy using the new weight. Thus, in the traffic information estimation system S of this embodiment, the estimation accuracy of traffic information (speed information) is naturally improved by continuing operation.

  As described above, when the traffic information estimation device 1 for each divided region completes the estimation of the speed information in the corresponding divided region, each traffic information estimation device 1 is stored in the divided region estimation database 13. Of the speed information of each road link, the speed information of the road link set as the boundary road link is transmitted to the boundary traffic information estimation device 1A.

[2.5 Configuration of Traffic Information Estimator for Boundary]
In the present embodiment, it is assumed that the boundary road links in the first divided area to the fourth divided area exist as shown in FIG. FIG. 20 shows only road links set as boundary road links among all road links in the first to fourth divided areas. The boundary road link here means that the connection point with another road link exists on the boundary line between adjacent divided areas.

As shown in FIG. 20, the number of the boundary road link is indicated by a combination of [area number] indicating the area number (mesh number; value of 1 to 4) of the divided area and the road link number. In FIG. 20, the number in parentheses after the boundary road link number indicates the estimated rank (estimated rank (update rank) stored in the “check” 31 column of the divided area estimation database 13) in each divided area. .
The area numbers (mesh numbers) and the estimated ranks of the divided areas are transmitted from the divided area traffic information estimating apparatus 1 to the boundary traffic information estimating apparatus 1A together with the speed information of the boundary road links.

  FIG. 21 shows a boundary traffic information estimation device 1A that performs estimation (secondary estimation) of road link speed information in a boundary region. The boundary traffic information estimation apparatus 1A uses the boundary road link speed information in the segment area estimation database 13 updated (primary estimation) by each segment area traffic information estimation apparatus 1, and the boundary road link speeds of other segment areas. Update (secondary estimation) using information is performed. The boundary traffic information estimation apparatus 1A also performs estimation parameter learning processing for secondary estimation.

  This estimation device 1A is used for learning a boundary estimation system (boundary estimation unit) 11A for estimating traffic information of an estimation target road link in a boundary region, and a parameter (estimation parameter) used for the estimation. A boundary learning system (boundary learning unit) 12A.

  Further, the estimation device 1 accumulates data used for learning in the boundary learning system 12A among the data in the boundary estimation database 13A and the boundary estimation database 13A for accumulating speed information estimated by the boundary estimation system 11A. And a boundary weight database (estimated parameter database) 15A for accumulating estimated parameters (in this embodiment, “weight”) on a storage device.

  The “speed information” and “estimation rank” of each boundary road link given from the traffic information estimation device 1 for each divided area are given to the boundary estimation database 13A and set. Of the boundary road links, for the road links for which the speed information could not be estimated by the primary estimation, the speed information = 0.00 is set and the estimation rank = 0 is set.

  As shown in FIG. 22, the boundary estimation database 13 includes “estimation rank” 31A, “secondary estimation” 36A, “speed information” 32A, “link length” 34A, “learning flag” 35A, “related road link information”. It has 33 A data items, and for each boundary road link indicated by “mesh number−link number”, the value of each data item can be stored.

Among the data items, “estimated rank” 31A corresponds to “check” 31 in the divided region estimation database 13, and information indicating the estimated rank transmitted from the database 13 is “ Estimated rank "31A is set.
The item of “secondary estimation” 36A is an item in which information used to determine whether or not to perform secondary estimation by the boundary estimation system 11A is set, and its value is obtained as an actual measurement value of speed information. The estimated distance (number of links) from the road link to the boundary road link. Details of the item of “secondary estimation” 36A will be described later.
The item of “speed information” 32A is an item in which speed information transmitted from the divided region estimation database 13 is set, and indicates speed information in each boundary link.

The item “link length” 34A indicates the link length of each boundary road link.
The item “learning flag” 35A indicates whether or not the speed information of each boundary road link is data for learning by the boundary learning unit 20A (learning data). Or takes the value of 1. “0” indicates that the speed information of the road link is not the boundary learning data, and “1” indicates that the speed information of the road link is the boundary learning data. The “learning flag” 35A corresponds to “learning?” 35 in the divided region estimation database 13, and the flag information transmitted from the divided region estimation database 13 is set in this “learning flag” 35A.

  The “related road link information” 33A indicates boundary road links (related road links) of other divided areas correlated with the respective boundary road links. Here, other related road links are connected to the respective boundary road links. A boundary road link (mesh number-link number) is shown.

  The “related road link information” 33A is divided into five types of “reverse”, “A order”, “A reverse”, “B reverse”, and “B reverse” similarly to the divided region estimation database 13. In the road link structure of FIG. 20, there are only four types of “A order”, “B order”, “A reverse”, and “B reverse”, and therefore “reverse” is omitted in FIG. .

  The content of the boundary estimation database 13A shown in FIG. 22 is that information such as speed information of boundary road links is given from the traffic information estimation device 1 for each divided area to the traffic information estimation device 1 for boundary, and the boundary estimation database The state set to 13A is shown. That is, the information of “estimation rank” 31, “speed information” 32A, and “learning flag” 35 transmitted from the traffic information estimation device 1 for divided areas is set in the database 13A. Each time the “estimation rank” 31, “speed information” 32A, and “learning flag” 35 are set, the values of the “secondary estimation” 36A are reset to “0”.

The “link length” 34A and the “related road link information” 33A use preset values, and each information of “estimated rank” 31, “speed information” 32A, and “learning flag” 35 is set. Will not be updated.

As shown in FIG. 23, in the boundary weight database 15A, the weight wi used when the estimated value of the speed information of each boundary road link in the boundary area is obtained from the speed information of other boundary road links (related road links). Set. The weight wi is set to be “the number of related road links + 1” for each boundary road link. In FIG. 23, w ₀ is an independent parameter, and w _{1 and} subsequent weights are weights to be multiplied by the related road link speed information.

  The value of the weight wi in the boundary weight database 15A in FIG. 23 is an initial state that is initially set when the system S is started up. The value of the weight wi is the same as the learning in the divided region learning system 12, but the learning for the boundary is performed. Since it is automatically updated to a more appropriate value by learning by the system 12A, an appropriate value may be set as the initial value. Therefore, initial setting is easy.

FIG. 24 shows a traffic information estimation process in the boundary area (estimation process in step S103; secondary estimation) performed by the boundary traffic information estimation apparatus 1A.
First, the speed information of the boundary road link is acquired from each of the divided area traffic information estimation devices 1 and set in the boundary estimation database 13A (step S21). As shown in FIG. 22, “0.00” is set as the speed information for the boundary road link for which the speed information could not be estimated by the primary estimation.

  Then, the boundary road link used as the object of secondary estimation is determined among all the boundary road links (step S22). In order to determine the boundary road link to be subjected to the secondary estimation, the values of “estimation rank” 31A and “secondary estimation” 36A in the boundary estimation database 13A are used.

25 to 32 show a procedure for the boundary estimation system 11A to determine the value of “secondary estimation” 36A.
First, a boundary road link whose “estimated rank” 31A is “1”, that is, a road link from which speed information based on actual measurement values such as probe information or VICS information is obtained is searched in the boundary estimation database 13A. As shown in FIG. 25, the value of “secondary estimation” 36A of the boundary road links 1-4 and 4-5 hit by the search is set to “1”.

  Further, a boundary road link (related road link) connected to the boundary road link whose “estimated rank” 31A is “1” is searched, and as shown in FIG. 26, the boundary road link 2-4 hit by the search is searched. , 3-4 and 4-3, the value of the “secondary estimation” 36A is set to “2”.

Subsequently, the boundary road links (related road links) connected to the boundary road links 2-4, 3-4, and 4-3 in which the value of the “secondary estimation” 36A is “2” are searched. The value of “secondary estimation” 36A of the boundary road link hit by the search is set to “3”.
However, boundary road links 1-4, 3-1, 4-5, 3-1 and 1-4 exist as boundary road links connected to the boundary road links 2-4, 3-4 and 4-3. However, for the four boundary road links 1-4, 4-5, 3-1 and 1-4, since secondary estimation values of 1 to 3 are already set, these road links 1 For -4, 4-5, 3-1 and 1-4, the value of the "secondary estimation" 36A is not changed. Therefore, as shown in FIG. 27, only the value of “secondary estimation” 36A of the boundary road link 3-1 is set to “3”.

Further, the boundary road link (related road link) connected to the boundary road link 3-1 having the value of “secondary estimation” 36A of “3” is subsequently searched. The value of “secondary estimation” 36A of the boundary road link hit by the search is set to “4”.
However, there are boundary road links 2-4 and 4-3 as boundary road links connected to the boundary road link 3-1, but these boundary road links 2-4 and 4-3 are already 1 Since the secondary estimation values of 4 or less are set, the value of “secondary estimation” 36A is not changed for these road links 2-4 and 4-3 as shown in FIG. This completes the setting of the value of “secondary estimation” 36A for the boundary road link directly or indirectly connected to the boundary road link whose value of “estimation rank” 36A is “1”.

  As described above, for the boundary road links directly or indirectly connected to the boundary road links 1-4 and 4-5 whose “estimated rank” 31A is “1”, the value of the “estimated rank” 31A is “ In order to sequentially propagate the speed information of the boundary road links 1-4 and 4-5 that are “1” (speed information based on actual measurement values and the most reliable speed information) to other related boundary road links, A value equal to or greater than “1” is set in the “estimate” 36A.

  Subsequently, the value of “secondary estimation” 36A is set for the boundary road link directly connected to the boundary road link whose value of “estimation rank” 36A is “2”. In the present embodiment, for the boundary road link whose “estimation rank” 36A is “2” or more, only the secondary estimation of the boundary road link directly connected to the boundary road link is performed to simplify the processing. The boundary road link indirectly connected to the boundary road link is not subject to secondary estimation. Thereby, it can avoid performing secondary estimation again from secondary estimation.

  Specifically, as shown in FIG. 29, the boundary road links connected to the boundary road links 1-1, 1-2, 4-1, 4-4 whose “estimated rank” 31A value is “2”. Search is performed. The value of “secondary estimation” 36A of the boundary road links 2-1, 2-2, 2-3, 1-3, 1-5, 3-3 hit by the search is set to “3”.

  Next, as shown in FIG. 30, the boundary connected to the boundary road links 1-3, 2-1, 2-2, 3-4, 4-2 where the value of the “estimated rank” 31A is “3”. A search for road links is performed. Of the boundary road links 1-1, 1-2, 1-3, 1-5, 2-1-2, 2-3, 4-5 hit by the search, the value of the secondary estimation is 1 or more. The value of “secondary estimation” 36 </ b> A of the boundary road links 1-1 and 1-2 not having a value of 4 or less is set to “4”.

  Subsequently, the boundary road link connected to the boundary road link whose “estimated rank” 36A is “4” is searched. The boundary road whose “estimated rank” 36A is “4” is searched. Since no link exists, this processing is not performed.

  Subsequently, a search is performed for a boundary road link connected to the boundary road link 2-5 whose value of the “estimated rank” 31A is “5”. As shown in FIG. 31, the value of “secondary estimation” 36A of the boundary road link 3-2 hit by the search is set to “6”.

  With the above processing, the setting of the value of “secondary estimation” 36A is completed. The boundary estimation system 12A extracts boundary road links to be subjected to secondary estimation based on these “secondary estimation” 36A values and “estimation rank” 31A values, and boundary roads to perform secondary estimation. Determine the link order.

  Specifically, the boundary road link whose “secondary estimation” 36A value is “0” or “1” is excluded from the target of the secondary estimation. When the value of the “secondary estimation” 36A is “0”, it indicates that there is no reliable speed information in the other boundary road links that are related road links, and it is better not to perform the secondary estimation. It is. This is because when the value of the “secondary estimation” 36A is “1”, the speed information of the boundary road link is based on the actual measurement value, and is highly reliable, and it is not necessary to perform the secondary estimation.

Then, the boundary estimation system 12A performs the secondary estimation for the boundary road links that are not excluded from the target of the secondary estimation in ascending order of the value of the “secondary estimation” 36A. The estimation method is the same as in the primary estimation, and the speed information of the boundary road link that is the estimation target is calculated from the speed information and the weight of the related road link.
Here, the secondary estimation is not performed for the boundary road link in which the value of “estimation rank” 31A <the value of “secondary estimation” 36A. That is, the estimated distance from the road link from which the actual measurement value included in the other divided area is obtained to the boundary road link is from the road link obtained from the actual measurement value included in the same divided area to the boundary road link. If the distance is larger than the estimated distance, secondary estimation is not performed. This is because if the second-order estimation is performed, the reliability of the speed information is decreased. However, even if the value of “estimated rank” 31A <the value of “secondary estimate” 36A, the estimation is always performed in the case of a boundary road link where the value of “estimated rank” 31A = 0. This is because the speed information is not yet obtained for the boundary road link where the value of the “estimated rank” 31A = 0, and it should be estimated.

  Specifically, as shown in FIG. 32, for the boundary road links 1-4, 2-5, 4-1, 4-2, 4-4, 4-5, the value of “secondary estimation” 36A is Since it is “0” or “1”, it is excluded from the target of secondary estimation. Further, the boundary road links 1-1 and 1-2 are excluded from the targets of secondary estimation because the value of “estimation rank” 31A <the value of “secondary estimation” 36A.

  For the remaining boundary road links, as shown in FIG. 32, the value of “speed information” 32A is updated to the estimated value.

  The snapshots of the boundary road links 1-4 and 4-5 in which “1” is set in the “learning flag” 35A among the data of the boundary road links in the boundary estimation database 13A for which the secondary estimation has been completed are as follows: It is added to the boundary learning database 14A as boundary learning data. This snapshot also stores a combination of “speed information” of the boundary road link in which “1” is set in the “learning flag” 35A and “speed information” of the related road link of the boundary road link. .

  The snapshot is accumulated in the boundary learning database 14A and used for weight learning processing (learning processing in step S103). The boundary region learning system 12A learns (optimizes) the weights (estimation parameters) stored in the boundary weight database 15A in the same manner as the divided region learning system system 12, and performs the boundary weight database 15A. Update the contents of.

  FIG. 33 shows the contents of the boundary weight database 15 </ b> A updated by learning through the snapshots of the boundary road links 1-4 and 4-5. As shown in FIG. 33, the weights for the boundary road links 1-4 and 4-5 are updated. Since the weight is updated every time the boundary region is estimated, when the system S is continuously operated, a weight having an appropriate value can be obtained naturally.

  When the above processing is completed, each speed information in the boundary estimation database 13A is returned to each divided region estimation database 13. As a result, the speed information in each divided area estimation database 13 takes into consideration the speed information of road links in other divided areas.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the meanings described above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

  For example, other road links (related road links) used for estimating speed information of the estimation target road link are not limited to those connected to the estimation target road link, but are separated from the estimation target road link. However, it may be a road link (for example, a road link parallel to the estimation target road link) whose speed information changes in time.

  In addition, when you want to reflect the time component in the speed information estimation, you can use road links that change characteristic in time (for example, road links that are crowded only in the morning, road links that are mixed only in the night, etc.) It can also be included in a road link (related road link). In this case, the speed information of the road link that changes temporally is commonly used for all the estimation target road links.

  Furthermore, in this embodiment, only the speed information in the same time zone is used as the speed information of other road links used for estimating the speed information of the estimation target road link. The speed information may be used. For example, in the case of a road link far away from the estimation target road link, there is a time delay until the traffic situation on the road link is reflected on the estimation target road link. Therefore, in the case of a road link far away, for example, more appropriate estimation can be performed by using the speed information of one hour ago for estimation.

  Furthermore, the traffic information to be estimated is not limited to the speed information, but may be other traffic information such as traffic jam information instead of / in addition to the speed information. In this case, the degree of traffic congestion can be calculated by assigning 1 in the speed information to a busy binary value and 0 as a smooth binary value. Further, when the traffic congestion degree is handled as the traffic information to be estimated, the neural network also requires a threshold value for determining one of the two values as the estimation parameter. In this case, the threshold value is also a learning target by the learning unit.

  Furthermore, the speed information is not limited to the standardized information, and the link travel speed itself may be used.

Furthermore, in this embodiment, the boundary road link is located at the boundary of the divided area and is directly connected to the road link of the other divided area, that is, the connection point with the other road link is divided. Although what was located on the boundary of an area | region was demonstrated as an example, it is not restricted to this.
As the boundary road link, a certain correlation regarding the traffic information may be recognized between the boundary road link and the road link of another divided region by being located near the boundary.

For example, when two parallel main roads are assumed, the boundary road link does not necessarily have to be connected to the road link of another divided area.
Furthermore, the boundary road link is located near the boundary of the divided area, but is not directly connected to the road link of the other divided area, and is connected to one or several road links included in the same divided area. It may be connected to road links in other divided areas.

S: Traffic information estimation system, 1: Traffic information estimation device for divided area, 2: In-vehicle device, 3: Probe vehicle, 4: Roadside communication device, 5: Roadside sensor, 6: VICS center computer, 11: Estimation for divided area System (divided region estimation unit), 12: divided region learning system, 13: divided region estimation database, 14: divided region learning database, 15: divided region weight database, 16: input information processing unit, 17: VICS information Processing unit, 17a: Link travel speed calculation unit, 17b: Speed information conversion unit, 18: Probe information processing unit, 18a: Link travel speed calculation unit, 18b: Speed information conversion unit, 19: Conversion information, 20: For divided area Learning unit, 1A: Traffic information estimation device for boundary, 11A: Estimation system for boundary (estimation unit for boundary), 12A: Learning system for boundary, 13A: Boundary Estimation database, 14A: boundary learning database, 15A: boundary weighting database,

Claims (13)

A traffic information estimation system capable of estimating traffic information of the road link in an area including a plurality of road links based on traffic information of other road links included in the area,
The estimation of the traffic information of the estimation target road link included in each divided area obtained by dividing the area into a plurality of areas is performed on other road links included in other divided areas other than the divided area including the estimation target road link. A segmented region estimation unit that uses traffic information of other road links included in the same segmented region as the segmented region including the estimation target road link without using traffic information;
Boundary estimation for estimating traffic information of boundary road links located at or near the boundary of the divided area among road links included in the area using traffic information of boundary road links in other divided areas And
A traffic information estimation system characterized by comprising: The traffic information estimation system according to claim 1, wherein the boundary estimation unit acquires traffic information of a boundary road link in another division region from the division region estimation unit.   The boundary estimation unit is configured to obtain a boundary road link for which traffic information is estimated using traffic information of a boundary road link included in another divided region from the road link from which traffic information based on an actual measurement value is obtained. The traffic information estimation system according to claim 1, wherein the traffic information is extracted based on an estimated distance to the boundary road link. Traffic information based on the actual measurement value of the boundary road link that can be estimated by the boundary estimation unit, and traffic of the boundary road link in the other divided region that is used to estimate the traffic information of the boundary road link that can be the estimation target A boundary learning unit that accumulates a combination with information as boundary learning data, and uses the accumulated boundary learning data to optimize estimation parameters for estimating traffic information of boundary road links that can be estimated The traffic information estimation system according to any one of claims 1 to 3, further comprising: A combination of traffic information based on measured values in a road link that can be an estimation target by the division area estimation unit and traffic information of the other road link that is used to estimate traffic information of the road link that can be the estimation target. A division region learning unit that optimizes estimation parameters for estimating traffic information of road links that can be estimated using the divided region learning data accumulated as division region learning data; The traffic information estimation system according to any one of claims 1 to 4. A traffic information estimation device for a boundary used in a traffic information estimation system that estimates traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas,
Boundary estimation for estimating traffic information of boundary road links located at or near the boundary of the divided area among road links included in the area using traffic information of boundary road links in other divided areas A traffic information estimation device for a boundary characterized by comprising a section. A traffic information estimation device for a divided area used in a traffic information estimation system that estimates traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas,
Estimating the traffic information of the target road link included in one segmented area without using the traffic information of the other road link included in the other segmented area, other road links included in the one segmented area A segmented area estimation unit that uses the traffic information of
The segmented area estimation unit is configured to estimate traffic information of a boundary road link located at or near a boundary of the one segmented area, and boundary estimation for estimating traffic information of a boundary road link in another segmented area. A traffic information estimation device for divided areas, characterized in that it is configured to be provided to a part.   A computer program for causing a computer to function as the traffic information estimation system according to any one of claims 1 to 5.   A computer program for causing a computer to function as the boundary traffic information estimating apparatus according to claim 6.   A computer program for causing a computer to function as the traffic information estimation device for divided areas according to claim 7. A traffic information estimation method for estimating traffic information of the road link in an area including a plurality of road links based on traffic information of other road links included in the area,
The estimation of the traffic information of the estimation target road link included in each divided area obtained by dividing the area into a plurality of areas is performed on other road links included in other divided areas other than the divided area including the estimation target road link. An estimation step for a divided area that is performed using traffic information of other road links included in the same divided area as the divided area including the road link to be estimated without using the traffic information;
A boundary estimation step for estimating traffic information of a boundary road link located at or near a boundary of the divided region among road links included in the region, using traffic information of the boundary road link in another divided region; ,
A traffic information estimation method comprising: A traffic information estimation method for a boundary in a traffic information estimation system for estimating traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas,
A boundary estimation step for estimating traffic information of a boundary road link located at or near a boundary of the divided area among road links included in the area, using traffic information of the boundary road link in another divided area; A traffic information estimation method for borders, comprising: A traffic information estimation method for a divided area in a traffic information estimation system for estimating traffic information of the road link in an area including a plurality of road links for each divided area obtained by dividing the area into a plurality of areas,
Estimating the traffic information of the target road link included in one segmented area without using the traffic information of the other road link included in the other segmented area, other road links included in the one segmented area Using the traffic information of
Making the traffic information of the boundary road link located at or near the boundary of the one divided area available in the estimation of the traffic information of the boundary road link in another divided area;
A traffic information estimation method for divided areas, comprising:

Images