JP7273014B2 - Estimation device, estimation method and estimation program - Google Patents

Description

The present invention relates to an estimating device, an estimating method, and an estimating program.

Conventionally, when measuring cross-sectional traffic volume, vehicle detectors (for example, traffic counters) are installed on various roads to measure traffic volume. Cross-sectional traffic volume data indicating the measurement result of such cross-sectional traffic volume is utilized in various fields such as traffic control, provision of congestion information, traffic safety measures, road maintenance, and road management. In order to obtain such cross-sectional traffic volume data, we propose a system that collects travel history information (probe information) of vehicles mounted on in-vehicle equipment via roadside detectors and optical beacons and processes it at a traffic control center, etc. It is In addition, when a company considers opening a new store, a traffic survey is requested, and the traffic surveyor may measure the traffic volume.

JP-A-2002-312886 JP 2015-212863 A

However, the conventional technology described above has a problem that cross-sectional traffic volume data cannot be acquired efficiently. For example, in the method of installing roadside sensors or the like on the road, there is a problem that the measurement points are fixed and data cannot be collected by changing the measurement points flexibly.

Also, if a traffic surveyor is hired and the traffic data is collected by a dedicated counter, it is troublesome.

An object of this application is to acquire cross-sectional traffic volume data efficiently in view of the above.

An estimation device according to the present application includes an acquisition unit that acquires position information from a terminal device mounted on a vehicle, and an estimation unit that estimates the number of vehicles that have traveled a predetermined position within a predetermined period based on the acquired position information. and a part.

ADVANTAGE OF THE INVENTION According to one aspect|mode of embodiment, it is effective in the ability to acquire cross-sectional traffic volume data efficiently.

FIG. 1 is a diagram showing an example of estimation processing for estimating traffic flow. FIG. 2 is a diagram showing an example of data for estimating cross-sectional traffic volume. FIG. 3 is a diagram showing an example of a method for setting a range from which a user terminal device acquires travel information. FIG. 4 is a diagram showing an example of travel information detected by the user terminal device. FIG. 5 is a diagram illustrating a configuration example of an estimation device according to the embodiment; FIG. 6 is a flowchart showing a processing procedure for estimating traffic flow, which is executed by the estimation device according to the embodiment. FIG. 7 is a diagram illustrating an example of a hardware configuration;

Embodiments for implementing the estimation device, estimation method, and estimation program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. Note that the estimation device, estimation method, and estimation program according to the present application are not limited by this embodiment. The details of one or more embodiments are set forth in the following description and drawings. Also, each of one or more embodiments can be appropriately combined within a range that does not contradict the processing content. Also, in one or more embodiments below, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. Estimation process]
First, an example of estimation processing according to an embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of estimation processing for estimating the number of vehicles that have traveled a predetermined position on a road within a predetermined period. In addition, in the example shown in FIG. 1, the example in which the estimation system 1 according to the embodiment performs the process of estimating the cross-sectional traffic volume at a predetermined intersection has been described.

As shown in FIG. 1, the estimation system 1 includes user terminal devices 10 ₁ to 10 _n , an estimation device 100, and an information center server 200 (n is any natural number). In this specification, the user terminals 10 ₁ to 10 _n are collectively referred to as "user terminals 10" when there is no need to distinguish between the user terminals 10 ₁ to 10 _n . Although not shown in FIG. 1 , the estimation system 1 may include multiple estimation devices 100 and multiple information center servers 200 .

The user terminal device 10 is an information processing device used by a user. The user terminal device 10 may be any type of information processing device including smart phones, desktop PCs (Personal Computers), notebook PCs, and tablet PCs.

In the example of FIG. 1, the user terminal device 10 is a client device used by a user who drives a vehicle. In this example, the user terminal device 10 is a smart phone installed with a car navigation application (called a car navigation app). A smart phone is installed in a user's vehicle, for example. Such a smart phone can be attached to an in-vehicle holder. The term "user terminal device 10 installed in the user's vehicle" may include "user terminal device 10 installed in the user's vehicle". That is, the term "installation of the user terminal 10" can encompass "permanent installation of the user terminal 10 (e.g., mounting the user terminal 10)". In addition, the user terminal device 10 can acquire probe information detected by a vehicle information acquisition device mounted on a vehicle, for example, a probe device, by wire or wirelessly, or the user terminal device 10 itself can detect travel information. can be included.

The information center server 200 is realized by a server device or a cloud system used by a traffic information provider or the like. For example, the information center server 200 is used by private organizations, private companies, etc. that promote the use of travel information from vehicles throughout society.

The estimation device 100 is an information processing device that estimates traffic flow. The estimating device 100 may be any type of information processing device, including a server. Although not shown in FIG. 1, the estimation device 100 communicates with the user terminal device 10 and the information center server 200 by wire or wirelessly via a network (for example, the Internet).

In the example of FIG. 1, the estimating device 100 estimates the traffic volume and cross-sectional traffic volume. For example, the estimating device 100 estimates cross-sectional traffic volumes for motorcycles, standard-sized vehicles, and large-sized vehicles, for example, for various moving objects such as motorcycles and automobiles within a predetermined range near an intersection.

In the example of FIG. 1, the two-wheeled vehicle is, for example, a motorcycle or a motorized bicycle. Ordinary cars are, for example, light cars, passenger cars, light freight cars, small freight cars, and rental passenger cars. Large vehicles are, for example, buses, general cargo vehicles, and special vehicles.

Here, the traffic cross section will be explained. A traffic cross-sectional volume survey is a form of inflow and outflow of moving bodies to a predetermined position or area (for example, a predetermined position of an intersection or a main road, etc.; hereinafter collectively referred to as "predetermined position"). It is information indicating Here, the manner of inflow is the manner in which what kind of moving object entered a predetermined position, from what direction, and how. Also, the outflow mode is information about what kind of moving object left a predetermined position and in which direction.

In order to estimate such cross-sectional traffic volume, the estimation device 100 determines, for example, inflow and outflow from the flow of vehicles when viewed from the center of the intersection. For example, the estimation device 100 estimates that the vehicle has left a predetermined position when the vehicle enters an intersection from each road. To give a more specific example, inflow refers to progressing from road (1) to road (4) to one of the roads in FIG. 1, and outflow refers to road (1) in FIG. ) to road (4), a vehicle that has flowed into the intersection has proceeded to any of the roads (1) to (4).

The estimating device 100 indicates the traffic volume of each road at the intersection for each cross-section as the cross-sectional traffic volume, and the number of inflowing vehicles proceeding from the intersection to each road and the outflowing number of vehicles proceeding from each road to the intersection. Estimate the total. For example, in FIG. 1, the estimating apparatus 100 calculates the total number of vehicles that entered the intersection from road (1) and vehicles that entered from roads (2) to (4) and exited road (1), that is, , is the sum of incoming and outgoing vehicles on road (1). Then, the estimating device 100 obtains the total number of inflowing and outflowing vehicles on each of the roads (1) to (4) that intersect at the intersection in the example of FIG. all can be obtained.

Here, an example of the traffic cross-sectional volume survey will be described with reference to FIG. FIG. 2 is a diagram showing an example of a traffic cross-section survey according to the embodiment. For example, when an intersection becomes a four-way intersection, vehicles enter from a certain road toward the intersection to turn right, go straight, or turn left. In such a case, the estimating device 100 calculates the total number of motorcycles (total of motorcycles by direction), the total number of ordinary vehicles (total of ordinary vehicles by direction), the number of large vehicles, and The total (total of large vehicles by direction) will be estimated. The estimating apparatus 100 estimates the total of ordinary vehicles and large vehicles (total vehicle by direction) from the total motorcycle by direction, the ordinary vehicle by direction, and the large vehicle by direction, and calculates the estimated vehicle total by direction. Estimate the inflow path total by adding the total of two-wheeled vehicles.

On the other hand, all vehicles that proceeded from the intersection to the road are outflows. Therefore, the estimating device 100 estimates the number of motorcycles, standard-size vehicles, and large-sized vehicles exiting the intersection, and sets them as the exit road motorcycle total, the exit road normal-sized vehicle total, and the exit road large-sized vehicle total, respectively. Then, the estimating device 100 calculates an outflow road total by adding the outflow road motorcycle total, the outflow road normal vehicle total, and the outflow road large vehicle total. In addition, the estimating device 100 calculates the total motorcycle cross-section that is the sum of the two-wheeled vehicles that have flowed into the intersection and the two-wheeled vehicles that have flowed out of the intersection, and the vehicle cross-section that is the sum of the number of vehicles that have flowed into the intersection and the vehicles that have flowed out of the intersection. Estimate the total.

Returning to FIG. 1, the description is continued. Conventionally, in order to obtain cross-sectional traffic volume, information on cross-sectional traffic volume collected by the prefectural police nationwide using measuring equipment such as vehicle detectors is compiled by the chief of the police and collected by the Japan Road Provided by the Traffic Information Center. For example, a system has been put into practical use in which travel history information (probe information) of a vehicle mounted on an in-vehicle device is collected via a roadside sensor or an optical beacon and processed in a traffic control center or the like. In some cases, a traffic surveyor uses a dedicated counter.

However, in the former case, it is necessary to update the position information of the measurement point and install the vehicle detector as necessary, which takes time and cost. In addition, in the latter case, measurement locations are limited, and securing personnel and labor costs are required.

Therefore, in the exemplary embodiment of FIG. 1, the estimating device 100 performs the estimation process described below in order to estimate the cross-traffic volume without spending much time and money.

First, the user terminal device 10 carried by the user riding in each vehicle, that is, the user terminal device 10 mounted on each vehicle, acquires various sensing data as travel information at predetermined time intervals. For example, the user terminal device 10 acquires the own vehicle position (for example, latitude and longitude), time, etc. acquired by GPS (Global Positioning System). Note that the user terminal device 10 may acquire vibration information detected by an acceleration sensor, a gyro sensor, or the like, traveling direction, speed at a point, acceleration, etc. as travel information. In addition, the user terminal device 10 may acquire, for example, steering wheel operation, point speed, blinker information, etc. as travel information from various control devices mounted on the vehicle.

Next, the estimation device 100 acquires the travel information acquired by the user terminal device 10 (step S11). For example, each time the user terminal device 10 acquires the travel information, the estimation device 100 may set the time interval longer than the time interval for acquiring the travel information (for example, every day), or the user terminal device 10 is connected to WiFi. The history of the travel information acquired by the user terminal device 10 is acquired when the user terminal device 10 is in the vehicle.

In such a case, the estimation device 100 estimates the vehicle type, movement mode, and traffic flow based on the travel information (step S12). For example, the estimation device 100 estimates the type of vehicle traveling on the road R1 based on information such as vibration information, speed information, and acceleration information included in the travel information. For example, the vibration measured by the user terminal device 10 is considered to vary depending on the vehicle type. Therefore, the estimating device 100 estimates whether the vehicle belongs to a motorcycle, a standard-sized vehicle, or a large-sized vehicle, based on the characteristics of the vibration shape obtained from the vibration information. In addition, such processing is, for example, a machine learning model (for example, a neural network, etc.) that learns the relationship between the vehicle type and the characteristics of the vibration information acquired by the user terminal device 10 mounted on the vehicle of the vehicle type. can be expressed using Note that the estimating device 100 may, for example, acquire information on the vehicle type registered by the user from each user terminal device 10 and identify the vehicle type of each vehicle based on the acquired information.

Next, the estimation device 100 estimates the movement mode of each vehicle based on the acquired travel information. For example, the estimation device 100 estimates how each vehicle has moved on the road based on the history of position information. Based on the estimation results, the estimation device 100 estimates how each vehicle flows into and out of the investigation target intersection.

Also, for example, the estimating device 100 estimates the movement mode of each vehicle based on the winker information included in the travel information. More specifically, when a certain vehicle emits a turn signal indicating a right turn at an intersection, estimation device 100 estimates that the vehicle has turned right at the intersection. If the estimating apparatus 100 cannot acquire the turn signal information, the estimating apparatus 100 may perform estimation based on, for example, the amount of change in the numerical value of the traveling direction included in the traveling information.

In addition, the estimating apparatus 100 may estimate a left turn or a right turn when the amount of change in the numerical value of the traveling direction indicated by various types of sensor information exceeds a predetermined threshold, and may estimate the vehicle to go straight when the amount does not exceed the threshold. . For example, the estimating device 100 may estimate whether the vehicle is turning left, turning right, or going straight based on the amount of change in the acceleration sensor. In addition, the estimation device 100 refers to the map information acquired by the user terminal device 10, calculates the degree of approximation between the route acquired using the position information related to the vehicle position and the road on the map, turns left, You may estimate whether to go straight or turn right. In addition, the estimation device 100 may reflect real-time information such as traffic rules such as one-way streets and prohibition of entry, road closures due to construction work, etc. in the estimation process using the map information. Note that these processes may be realized using various known techniques for estimating the running position of the vehicle.

Next, the estimating device 100 estimates the movement mode of turning left, going straight, and turning right for each type of vehicle in which the user terminal device 10 is installed, and estimates the traffic flow (step S12). For example, the estimating device 100 identifies vehicles that have flowed into or out of an intersection subject to a traffic cross-section survey based on the mode of movement. Subsequently, the estimating device 100 identifies each model of the identified vehicle. Then, the estimating device 100 generates the result of the traffic cross-section survey for each vehicle type. After that, the estimating device 100 provides the result of the traffic cross section survey to the information center server 200 as necessary (step S13).

[2. Estimation based on actual measurements]
In the above description, the estimating device 100 estimates the cross-sectional traffic volume based on the travel information measured by each user terminal device 10 . However, if the user terminals 10 are not installed in all vehicles, the estimating device 100 may not be able to estimate an appropriate cross-sectional traffic volume.

Therefore, the estimating device 100 estimates the total cross-section of a two-wheeled vehicle and the total cross-section of a vehicle within a predetermined time using the user terminal device 10 at the measurement target point, and then the ratio of the correct data (actual value) and the user terminal device A final estimate is calculated by considering 10 utilizations. That is, the estimating device 100 may use the travel information acquired by the user terminal device 10 as the travel information of the vehicle serving as the probe to estimate the cross-sectional traffic volume at a predetermined position.

For example, the estimating device 100 acquires the result of a manually acquired traffic cross-sectional volume survey at an intersection targeted for traffic cross-sectional volume survey. Also, the estimation device 100 uses the travel information acquired by the user terminal device 10 to estimate the cross-sectional traffic volume. Then, the estimation device 100 generates a correction model for converting the traffic cross-sectional volume estimated using the travel information acquired by the user terminal device 10 into a manually acquired traffic cross-sectional volume. Such a correction model can be realized by various machine learning techniques such as various regression analysis, SVM (Support Vector Machine), and neural network. Estimation apparatus 100 may generate such a correction model for each position to be estimated, for each region including the position to be estimated, for each day of the week or time period, for each vehicle type, and the like. It may be generated for each combination of attributes.

Subsequently, the estimating device 100 uses the travel information acquired by the user terminal device 10 to estimate the traffic cross-sectional volume at the location to be estimated, which is the traffic cross-sectional volume at the primary level to be estimated. Then, the estimating device 100 may obtain a final estimation result by correcting the estimated traffic section volume using the generated correction model.

[3. Geofence settings]
Also, in the above description, the user terminal device 100 acquires travel information at predetermined time intervals, but the embodiment is not limited to this. For example, if the time interval for acquiring the travel information is long, there is a possibility that the travel information indicating how the user terminal device 100 moved at the intersection to be investigated cannot be acquired. Therefore, the estimation device 100 may acquire geofences in advance for intersections to be investigated. When such a geofence is set, the user terminal device 100 collects travel information within the geofence in more detail than outside the geofence.

For example, FIG. 3 is a diagram showing an example of a method for setting a range from which a user terminal device acquires travel information. For example, as shown in FIG. 3, the estimating device 100 surrounds a predetermined range with a virtual fence around a predetermined intersection to be measured (for example, geofencing). Geofencing is a location-based feature that allows you to set a virtual geographical boundary on a map, automatically record your entry and exit within that boundary, and use it to This is a function that can notify predetermined information. By setting up a geofence, it is possible to acquire travel information for vehicles that enter and leave the fence.

For example, the user terminal device 10 accepts delivery of information indicating pre-geofed areas. Then, when the user terminal device 10 enters the geofenced area, the user terminal device 10 acquires travel information at shorter time intervals than outside the geofenced area. For example, the user terminal device 10 acquires travel information every 30 minutes or every 2 kilometers outside the geofence, and acquires travel information every 30 seconds or every 10 m inside the geofence. may

Also, the user terminal device 10 may change the timing of transmitting the travel information depending on whether it is outside or inside the geofence. For example, the user terminal device 100 may transmit travel information every 30 minutes outside the geofence, and may transmit travel information each time it acquires travel information inside the geofence.

[4. Configuration of estimation device]
Next, a configuration example of the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram illustrating a configuration example of the estimation device 100 according to the embodiment. As shown in FIG. 5 , estimation device 100 includes communication unit 110 , storage unit 120 , and control unit 130 . Note that the estimation apparatus 100 has an input unit (for example, keyboard, mouse, etc.) that receives various operations from an administrator or the like who uses the estimation apparatus 100, and a display unit (liquid crystal display, etc.) for displaying various information. may

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information between the user device 10 and the information center server 200 via the network.

(storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 5 , storage unit 120 includes travel information storage unit 121 , vehicle estimation model storage unit 122 , movement mode estimation model storage unit 123 , and training data storage unit 124 .

(Travel information storage unit 121)
The travel information storage unit 121 stores travel information.
FIG. 4 is a diagram showing an example of data stored in the travel information storage unit 121 according to the embodiment. As described above, with respect to travel information, the user terminal device 10 may acquire the probe information detected by the probe device mounted on the vehicle by wire or wirelessly, or the user terminal device 10 itself installed on the vehicle may detect it. can also be included.

The travel information storage unit 121 stores the travel information received by the reception unit 132, for example. In the example of FIG. 4, the "travel information" is stored in the travel information storage unit 121 for each "user identifier". As an example, the "driving information" includes the item "sensor information", the item "time", and the item "vehicle position".

"User identifier" indicates an identifier for identifying a user who uses the user terminal device 10 installed in the vehicle. The “sensor information” is information obtained by the user terminal device 10 from information detected by a probe device installed in the vehicle or information detected by the user terminal device 10 itself. The 'sensor information' includes the item 'vibration information', the item 'traveling direction information', the item 'velocity point information', the item 'acceleration information', and the item 'blinker information'. A case where the user terminal device 10 itself detects travel information will be described below.

The “vibration information” indicates information regarding body chassis vibration and engine vibration during running detected by the user terminal device 10 . “Traveling direction information” indicates information about the traveling direction detected by the user terminal device 10 . “Point speed information” indicates information about the speed of each vehicle position detected by the user terminal device 10 . “Acceleration information” indicates information about acceleration detected by the user terminal device 10 . “Turn signal information” indicates information regarding the usage status of the turn signals detected by the user terminal device 10 . “Time” indicates information about the time acquired by the user terminal device 10 . “Vehicle position” indicates information about latitude and longitude acquired by the user terminal device 10 .

For example, FIG. 4 shows that "vibration information VI11" was collected by the user terminal device 10 used by the user identified by the user identifier "U1". The vibration information VI11 corresponds to parameters such as vibration displacement, vibration velocity, and vibration acceleration, for example.

Also, for example, FIG. 4 shows that "moving direction information TD11" is collected by the user terminal device 10 used by the user identified by the user identifier "U1". For example, it corresponds to parameters such as the direction of travel and the orientation of the vehicle body.

Also, for example, FIG. 4 shows that "velocity point information VE11" is collected by the user terminal device 10 used by the user identified by the user identifier "U1". For example, it corresponds to parameters such as speed for each vehicle position.

Also, for example, FIG. 4 shows that "acceleration information AC11" is collected by the user terminal device 10 used by the user identified by the user identifier "U1". For example, it corresponds to parameters such as longitudinal acceleration, lateral acceleration, and yaw acceleration.

Also, for example, FIG. 4 shows that "winker information WIN11" is collected by the user terminal device 10 used by the user identified by the user identifier "U1". For example, it corresponds to the parameter of the use condition of the blinker.

Also, for example, FIG. 4 shows that "time TM11" was acquired by the user terminal device 10 used by the user identified by the user identifier "U1".

Also, for example, FIG. 4 shows that the “vehicle position SP11” is acquired by the user terminal device 10 used by the user identified by the user identifier “U1”. The own vehicle position SP11 corresponds to parameters such as latitude and longitude, for example.

(Vehicle estimation model storage unit 122)
The vehicle estimation model storage unit 122 stores a vehicle estimation model (that is, machine learning model data) that is a machine learning model for estimating the vehicle type. The vehicle estimation model storage unit 122 stores, for example, vehicle estimation models received by the reception unit 132 described below. The vehicle estimation model storage unit 122 may store a vehicle estimation model generated by the vehicle estimation unit 133 described below. The vehicle estimation unit 133 can generate a vehicle estimation model from predetermined training data, as will be described later.

(Movement mode estimation model storage unit 123)
The movement manner estimation model storage unit 123 stores a movement manner estimation model (that is, machine learning model data) that is a machine learning model for estimating movement manners. The movement manner estimation model storage unit 123 stores, for example, a movement manner estimation model received by the reception unit 132 described below. The movement manner estimation model storage unit 123 may store a movement manner estimation model generated by the movement manner estimation unit 134 described below. The movement manner estimation unit 134 can generate a movement manner estimation model from predetermined training data, as will be described later.

(Training data storage unit 124)
The training data storage unit 124 stores training data datasets (that is, training datasets). The training data storage unit 124 stores, for example, training data sets received by the receiving unit 132 described below. The stored training dataset contains instances (also called feature vectors). For example, the stored training dataset contains instances with known labels. More specifically, the stored training data set includes instances that are vectors of feature values and the labels of the instances (ie, the labels associated with the instances).

For example, the training data storage unit 124 stores a training data set used for generating the vehicle estimation model described above. In this case, the instance corresponds to the above-described travel information, for example, information detected from a user terminal device (for example, the user terminal device 10) of a vehicle traveling on a predetermined road. On the other hand, the label of this instance corresponds to, for example, the type of vehicle in which this user terminal device 10 is installed (for example, vehicle type).

Also, for example, the training data storage unit 124 stores a training data set used for generating the movement state estimation model described above. In this case, the instance corresponds to the above-described travel information, for example, information detected from a user terminal device (for example, the user terminal device 10) of a vehicle traveling on a predetermined road. On the other hand, the label of this instance corresponds to, for example, the mode of movement (for example, turn right, go straight, turn left) when traveling on this predetermined road. The mode of movement is not limited to the mode of movement described above depending on the shape of the road.

(Estimated traffic volume storage unit 125)
The estimated traffic volume storage unit 125 stores the estimated traffic volume. Specifically, the data shown in FIG. 2 are stored for each road related to the set measurement points. The final cross-sectional traffic volume is the total cross-sectional area for motorcycles and the total cross-sectional area for automobiles.

(control unit 130)
The control unit 130 is a controller. For example, a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executes various programs (estimation programs) stored in a storage device inside the estimation device 100. (equivalent to one example) is implemented by executing the RAM or the like as a work area. Also, the control unit 130 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 5, the control unit 130 includes an acquisition unit 131, a reception unit 132, a vehicle estimation unit 133, a movement state estimation unit 134, and a map information provision unit 135, and obtains information described below. Realize or perform the function or action of a process. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be another configuration as long as it performs information processing described later.

(Acquisition unit 131)
The acquisition unit 131 acquires travel information detected by the user terminal devices of some of the vehicles traveling on a predetermined road. For example, the user terminal devices of some of the vehicles traveling on a predetermined road include terminal devices that move with the vehicle, terminal devices that are installed on the vehicle, terminal devices that are mounted on the vehicle, and user terminals that are connected to the vehicle. A terminal device, a terminal device held by a user driving a vehicle, a terminal device inside the vehicle, a terminal device attached to the outside of the vehicle, and other user terminal devices present in the vehicle (for example, the user terminal device 10). .

For example, the acquisition unit 131 acquires vibration information indicating vibration detected by the user terminal device. Also, for example, the acquisition unit 131 acquires traveling direction information indicating the traveling direction detected by the user terminal device. Also, for example, the acquisition unit 131 acquires point speed information indicating the point speed detected by the user terminal device. Also, for example, the acquisition unit 131 acquires acceleration information indicating acceleration detected by the user terminal device. Also, for example, the acquisition unit 131 acquires winker information indicating the usage status of the winkers detected by the user terminal device. Also, for example, the acquisition unit 131 acquires time information indicating the time acquired by the user terminal device. Further, for example, the acquisition unit 131 acquires vehicle position information indicating the vehicle position acquired by the user terminal device.

The acquisition unit 131 may acquire travel information received by the reception unit 132 described below. For example, the acquisition unit 131 may acquire vibration information, traveling direction information, point speed information, acceleration information, blinker information, time information, or vehicle position information received by the reception unit 132 . Further, the acquisition unit 131 may acquire travel information from a predetermined storage device. For example, the acquisition unit 131 may acquire travel information from the travel information storage unit 121 described above. The acquisition unit 131 may store the acquired travel information in the travel information storage unit 121 described above.

In one example, the acquisition unit 131 acquires travel information (eg, first travel information) and other travel information (eg, second travel information).

The acquisition unit 131 may acquire the above-described vehicle estimation model (that is, machine learning model data). The obtaining unit 131 may obtain, for example, a vehicle estimation model received by the receiving unit 132 described below. The acquisition unit 131 may acquire the vehicle estimation model from a predetermined storage device. For example, the acquisition unit 131 may acquire the vehicle estimation model from the vehicle estimation model storage unit 122 described above. The acquisition unit 131 may store the acquired vehicle estimation model in the vehicle estimation model storage unit 122 described above.

The acquisition unit 131 may acquire the above-described movement mode estimation model (that is, machine learning model data). The acquisition unit 131 may acquire, for example, a movement mode estimation model received by the reception unit 132 described below. The acquisition unit 131 may acquire the movement state estimation model from a predetermined storage device. For example, the acquisition unit 131 may acquire the movement manner estimation model from the movement manner estimation model storage unit 123 described above. The acquisition unit 131 may store the acquired movement state estimation model in the movement state estimation model storage unit 123 described above.

(Receiver 132)
The receiving unit 132 receives travel information detected by the user terminal devices of some of the vehicles traveling on the predetermined road. For example, the receiving unit 132 receives travel information from a predetermined information processing device. For example, the receiving unit 132 receives travel information from a device of an entity related to the estimation device 100 (for example, a user of a car navigation application, a predetermined company, an organization that supervises operations related to road traffic). The receiving unit 132 may store the received travel information in the travel information storage unit 121 .

For example, the receiving unit 132 receives vibration information indicating vibration detected by the user terminal device. Also, for example, the receiving unit 132 receives traveling direction information indicating the traveling direction detected by the user terminal device. Also, for example, the receiving unit 132 receives point speed information indicating the point speed detected by the user terminal device 10 . Also, for example, the receiving unit 132 receives acceleration information indicating the acceleration detected by the user terminal device 10 . Also, for example, the receiving unit 132 receives winker information indicating the usage status of the winkers detected by the user terminal device 10 . Also, for example, the receiving unit 132 receives time information indicating the time acquired by the user terminal device 10 . Also, for example, the receiving unit 132 may further receive vehicle position information indicating the position acquired by the user terminal device 10 .

In one example, the receiving unit 132 receives, for example, first travel information from the first user terminal device 10 installed in a vehicle traveling on the first road. For example, the receiving unit 132 receives travel information from the first user terminal device 10 (for example, user terminal device 10 ₁ ) via a car navigation application installed in the first user terminal device 10 . Also, the receiving unit 132 receives other travel information (for example, the _second 2) is received.

The receiver 132 may receive the above-described vehicle estimation model (that is, machine learning model data). For example, the receiving unit 132 may receive a vehicle estimation model from a predetermined information processing device. For example, the receiving unit 132 may receive a vehicle estimation model from a device of an entity related to the estimation device 100 (for example, a predetermined company, a predetermined university, a predetermined research institute). The receiving unit 132 may store the received vehicle estimation model in the vehicle estimation model storage unit 122 .

The receiving unit 132 may receive the above-described movement mode estimation model (that is, machine learning model data). For example, the receiving unit 132 may receive the movement mode estimation model from a predetermined information processing device. For example, the receiving unit 132 may receive a mode estimation model from a device of an entity related to the estimation device 100 (for example, a given company, a given university, a given research institute). The receiving unit 132 may store the received mode estimation model in the movement mode estimation model storage unit 123 .

The receiver 132 may receive the dataset of training data described above. For example, the receiving unit 132 may receive a training data set such as a training data set used to generate the vehicle estimation model described above and a training data set used to generate the movement mode estimation model described above. The receiving unit 132 may receive the training data set from a predetermined information processing device. For example, the receiving unit 132 may receive training datasets from devices of entities related to the estimating device 100 (for example, users of car navigation applications, predetermined companies, and organizations that control operations related to road traffic). The receiving unit 132 may store the received training data set in the training data storage unit 126 .

(Vehicle estimation unit 133)
The vehicle estimator 133 estimates the type of some of the vehicles traveling on the predetermined road. For example, user terminals (eg, user terminals 10) are present in some of these vehicles. The vehicle estimation unit 133 estimates the type of vehicle in which the user terminal device is installed, based on the travel information. For example, the vehicle estimation unit 133 estimates the type of vehicle in which the user terminal device 10 is installed based on the travel information acquired by the acquisition unit 131 .

For example, the vehicle estimation unit 133 estimates the vehicle type based on the acceleration characteristics indicated by the acceleration information. For example, the vehicle estimation unit 133 estimates the vehicle type based on the acceleration characteristics indicated by the acceleration information acquired by the acquisition unit 131 .

Also, for example, the vehicle estimation unit 133 estimates the type of vehicle based on the vibration characteristics indicated by the vibration information. For example, the vehicle estimation unit 133 estimates the type of vehicle based on the vibration characteristics indicated by the vibration information acquired by the acquisition unit 131 .

Also, for example, the vehicle estimation unit 133 estimates the type of vehicle based on the speed characteristics indicated by the speed information. For example, the vehicle estimation unit 133 estimates the vehicle type based on the speed characteristics indicated by the speed information acquired by the acquisition unit 131 .

The vehicle estimation unit 133 may estimate the type of vehicle by estimating the driving type of the vehicle.

In one example, the vehicle estimation unit 133 estimates the vehicle type of each vehicle traveling on the first road based on the travel information acquired by the acquisition unit 131 . For example, the travel information acquired by the acquisition unit 131 includes sensor information. The sensor information includes, for example, information such as vibration information and acceleration information. The vehicle estimation unit 133 can estimate the vehicle type of each vehicle traveling on the first road and the mode of movement when traveling on the first road, based on information such as vibration information and acceleration information.

For example, travel information received from a first user device 10 (eg, user device 10 ₁ ) includes first sensor information. For example, the vibration information included in the first sensor information is "the magnitude of pitching of the vehicle in which the first user device 10 is installed satisfies a predetermined condition (eg, a first threshold). It is assumed that the In this example, the vehicle estimation unit 133 estimates that the vehicle type of the vehicle in which the first user device 10 is installed is a "normal vehicle". In other words, the vehicle estimation unit 133 estimates the vehicle type of the vehicle in which the first user device 10 is installed based on how the vehicle in which the first user device 10 is installed is shaken.

Also, for example, travel information received from a second user device 10 (eg, user device 10 ₂ ) includes second sensor information. For example, the vibration information included in the second sensor information is defined as "the magnitude of pitching of the vehicle in which the second user device 10 is installed satisfies a predetermined condition (e.g., first threshold). It is assumed that the In this example, the vehicle estimation unit 133 estimates that the type of vehicle in which the second user device 10 is installed is a "large vehicle".

In another example, the vehicle estimation unit 133 may estimate the vehicle type of the vehicle in which the user device 10 is installed using the vehicle estimation model described above. Also, the vehicle estimation unit 133 may generate a vehicle estimation model from predetermined training data (for example, a training data set stored in the training data storage unit 124). For example, the vehicle estimation unit 133 converts an instance corresponding to the travel information acquired by the acquisition unit 131 (for example, a vector of feature values corresponding to the travel information) into a vehicle estimation model (for example, a decision tree, SVM (Support Vector Machine), naive Bayesian classifier) may be used to output the vehicle type. The vehicle estimation unit 133 may estimate the vehicle type of the vehicle in which the first user device 10 is installed as the “output vehicle type”. Further, for example, the vehicle estimation unit 133 inputs an instance corresponding to the travel information acquired by the acquisition unit 131 to a vehicle estimation model (for example, a neural network), thereby obtaining a “vehicle in which the user device 10 is installed. The probability that the vehicle type is a predetermined vehicle type" may be output. The vehicle estimation unit 133 may estimate the model of the vehicle in which the user device 10 is installed based on the output probabilities.

In some embodiments, the vehicle estimation unit 133 may receive from the user device 10 information indicating the type of vehicle (for example, vehicle type) driven by the user of the user terminal device 10 . Accordingly, the vehicle estimation unit 133 labels the instances included in the training data set used to generate the vehicle estimation model based on the received information indicating the type of vehicle driven by the user of the user device 10. can decide.

(Movement mode estimation unit 134)
The travel mode estimation unit 134 estimates the travel mode when some of the vehicles traveling on the predetermined road travel on the predetermined road, based on the travel information. For example, a user terminal device 10 is present in this part of the vehicle. The travel mode estimation unit 134 estimates the travel mode when the vehicle in which the user terminal device 10 is installed travels on a predetermined road, based on the travel information. For example, based on the travel information acquired by the acquisition unit 131, the movement mode when the vehicle in which the user terminal device 10 is installed travels on a predetermined road is estimated.

For example, the movement mode estimation unit 134 estimates the movement mode of the vehicle when traveling on a predetermined road based on the acceleration characteristics indicated by the acceleration information. For example, the movement mode estimation unit 134 estimates the movement mode of the vehicle when traveling on a predetermined road based on the acceleration characteristics indicated by the acceleration information acquired by the acquisition unit 131 .

Further, for example, the movement mode estimation unit 134 estimates, as the movement mode of the vehicle, at least one of right turn, straight ahead, and left turn movement modes when the vehicle travels on a predetermined road.

The movement mode estimation unit 134 may estimate the movement mode of the vehicle when traveling on the predetermined road based on the characteristics of the acceleration detected by the user terminal device 10 when the position information indicates the predetermined road. good. For example, when the position information acquired by the acquisition unit 131 indicates a predetermined road, the movement mode estimation unit 134 may drive on the predetermined road based on the acceleration characteristics indicated by the acceleration information acquired by the acquisition unit 131. You may estimate the movement mode of the vehicle at the time of doing.

In one example, the travel mode estimation unit 134 estimates the travel mode when traveling on the first road based on the travel information acquired by the acquisition unit 131 . For example, the travel information acquired by the acquisition unit 131 includes sensor information. The sensor information includes, for example, information such as vibration information and acceleration information. The movement mode estimation unit 134 can estimate the movement mode when traveling on the first road based on information such as vibration information and acceleration information.

In another example, the movement manner estimation unit 134 may use the movement manner estimation model described above to estimate the movement manner when traveling on the first road. Further, the movement manner estimation unit 134 may generate a movement manner estimation model from predetermined training data (for example, a training data set stored in the training data storage unit 126). For example, the movement state estimation unit 134 converts an instance corresponding to the travel information acquired by the acquisition unit 131 (e.g., a vector of feature values corresponding to the travel information) into a movement state estimation model (e.g., decision tree, SVM). , a naive Bayes classifier) may output the movement behavior. The movement manner estimation unit 134 may estimate the movement manner when traveling on the first road as the “output movement manner”. Further, for example, the movement mode estimation unit 134 inputs an instance corresponding to the travel information acquired by the acquisition unit 131 to a movement mode estimation model (for example, a neural network), so that "traveling on the first road The probability that the current movement mode is the predetermined movement mode" may be output. The travel mode estimation unit 134 may estimate the travel mode when traveling on the first road based on the output probabilities.

Regarding the estimation of the movement mode of the vehicle, for example, the acquisition unit 131, based on the position information included in the acquired travel information, is a plurality of vehicles in which the user device 10 installed with the car navigation application is installed, The number of vehicles that have traveled on the first road during a given period of time (eg, "one day") is determined. Furthermore, the movement mode estimation unit 134 acquires the usage rate of the car navigation application installed in the user device 10 from a predetermined storage device. Based on the determined number of vehicles and the acquired utilization rate of the car navigation application, the travel mode estimation unit 134 determines that "a first It is possible to estimate the number of multiple vehicles traveling on the road of For example, a plurality of vehicles in which the user device 10 installed with the car navigation application is installed, which correspond to the vehicle type "ordinary car" and the mode of movement "right turn", and the first road on the "1st" Assume that the number of vehicles traveling on the road is "5". Furthermore, it is assumed that the usage rate of the car navigation application installed in the user device 10 is "10%". In this example, the movement mode estimating unit 134 calculates the number of vehicles that correspond to the vehicle type "ordinary car" and the movement mode "right turn" and travel on the first road in "one day". The product of the number of "5" and "10 (that is, 1/(10%=0.1))" is estimated to be "50".

(Map information providing unit 135)
The map information providing unit 135 may provide not only basic map information but also map information to which conditions such as congestion information, traffic regulation, and construction information are added.

[5. Estimation process flow]
Next, a procedure of estimation processing by the estimation device 100 according to the embodiment will be described.

FIG. 6 is a flowchart showing a processing procedure for estimating traffic flow, which is executed by the estimation device 100 according to the embodiment.

As shown in FIG. 6, in one embodiment, the estimation device first sets the measurement points (step S101).

Next, the estimating device sets a geofence (step S102).

Next, the acquisition unit 131 acquires the travel information detected by the user terminal devices of some of the vehicles traveling on the predetermined road (step S103). For example, the acquisition unit 131 acquires vibration information indicating vibration of the vehicle body detected by the user terminal device. Also, for example, the acquisition unit 131 acquires traveling direction information indicating the traveling direction of the vehicle detected by the user terminal device. Also, for example, the acquisition unit 131 acquires point speed information indicating the point speed of the vehicle detected by the user terminal device. Further, for example, the acquisition unit 131 acquires acceleration information indicating acceleration of the vehicle detected by the user terminal device. Also, for example, the acquisition unit 131 acquires winker information indicating the usage status of the winkers of the vehicle detected by the user terminal device. Also, for example, the acquisition unit 131 acquires the time acquired by the user terminal device. Also, for example, the acquisition unit 1313 acquires the vehicle position acquired by the user terminal device.

Next, the vehicle estimation unit 133 estimates the vehicle type (step S104).

Next, the movement mode estimation unit 134 estimates the movement mode of the vehicle based on the travel information detected by the user terminal device (step S105).

Next, the movement mode estimation unit 134 estimates the traffic volume based on the movement mode estimated in step S104, and estimates the cross-sectional traffic volume (step S106).

[6. others〕
Also, among the processes described in the above embodiments, some of the processes described as being automatically performed can also be performed manually. Alternatively, all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

For example, part or all of the storage unit 120 shown in FIG. 4 may be held in a storage server or the like instead of being held by the estimation device 100 . In this case, the estimation device 100 acquires various information such as travel information by accessing the storage server.

[7. Hardware configuration]
Also, the estimation apparatus 100 according to the above-described embodiments is implemented by a computer 1000 configured as shown in FIG. 7, for example. FIG. 7 is a diagram illustrating an example of a hardware configuration; A computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. have

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used for various calculations by the arithmetic device 1030 and various databases are registered, and is implemented by a ROM (Read Only Memory), HDD, flash memory, or the like.

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various types of information such as a monitor and a printer. It is realized by a connector conforming to a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Also, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, scanner, etc., and is realized by, for example, USB.

Note that the input device 1020 includes, for example, optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase change rewritable discs), magneto-optical recording media such as MOs (Magneto-Optical discs), and tapes. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Also, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends the data to arithmetic device 1030, and also transmits data generated by arithmetic device 1030 via network N to other devices.

The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070 . For example, arithmetic device 1030 loads a program from input device 1020 or secondary storage device 1050 onto primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the estimation device 100 , the arithmetic device 1030 of the computer 1000 implements the functions of the control unit 130 by executing a program loaded on the primary storage device 1040 .

[8. effect〕
As described above, the estimation device 100 according to the embodiment has the acquisition unit 131, the vehicle estimation unit 133, and the movement mode estimation unit .

In the estimation device 100 according to the embodiment, the acquisition unit 131 acquires travel information detected by the user terminal device 10 of some of the vehicles traveling on a predetermined road. In addition, in the estimation device 100 according to the embodiment, the vehicle estimation unit 133 estimates the type of some of the vehicles traveling on a predetermined road based on the travel information. In addition, in the estimation device 100 according to the embodiment, the movement mode estimation unit 134 estimates the movement mode of the vehicle based on the acquired travel information.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires acceleration information indicating acceleration detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the vehicle estimation unit 133 estimates the vehicle type based on the acceleration characteristics indicated by the acceleration information.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires vibration information indicating vibration detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the vehicle estimation unit 133 estimates the type of vehicle based on the vibration characteristics indicated by the vibration information.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires speed information indicating the speed detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the vehicle estimation unit 133 estimates the vehicle type based on the speed characteristics indicated by the speed information.

Further, the estimation apparatus 100 according to the embodiment includes a movement mode estimation unit 134 that estimates movement modes when some of the vehicles traveling on the predetermined road travel on the predetermined road, based on the travel information. have.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires traveling direction information indicating the traveling direction detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the moving manner estimation unit 134 estimates the moving manner of the vehicle when traveling on a predetermined road based on the characteristics of the traveling direction indicated by the traveling direction information.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires point speed information indicating the point speed detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the movement mode estimation unit 134 estimates the movement mode of the vehicle when traveling on a predetermined road, based on the characteristics of the point speed indicated by the point speed information.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires acceleration information indicating acceleration detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the movement mode estimation unit 134 estimates the movement mode of the vehicle when traveling on a predetermined road, based on the acceleration characteristics indicated by the acceleration information.

In addition, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires winker information indicating the winker usage status detected by the user terminal device 10 . Further, in the estimation device 100 according to the embodiment, the movement manner estimation unit 134 estimates the movement manner of the vehicle when traveling on a predetermined road based on the characteristics of the turn signal usage indicated by the turn signal information.

Further, in the estimation apparatus 100 according to the embodiment, the movement manner estimation unit 134 selects at least one of right turn, straight ahead, and left turn movement manners when the vehicle travels on a predetermined road as the movement manner of the vehicle. presume.

Also, in the estimation device 100 according to the embodiment, the acquisition unit 131 further acquires position information indicating the position of the user terminal device 10 detected by the user terminal device 10 . In addition, in the estimation device 100 according to the embodiment, the movement mode estimation unit 134 drives on a predetermined road based on the acceleration characteristics detected by the user terminal device 10 when the position information indicates the predetermined road. Estimate the mode of movement of the vehicle at the time.

Also, the estimation device 100 according to the embodiment may be a terminal device having the user terminal device 10 and installed in a vehicle.

In addition, in the estimation device 100 according to the embodiment, the acquisition unit 131 acquires travel information detected by the terminal device of the vehicle using the user terminal device 10 of the terminal device via a predetermined network.

Further, when the estimating apparatus 100 according to the embodiment estimates that a plurality of users are riding in the same vehicle and that the plurality of user identifiers correspond to the same travel information, the estimation apparatus 100 determines that a plurality of user terminal apparatuses are in the same vehicle. is installed, and the number of vehicles that have traveled a given location within a given period of time is estimated.

Also, the estimation apparatus 100 according to the embodiment estimates the number of vehicles that have traveled a plurality of predetermined positions within a predetermined period by setting a plurality of geofences.

Also, the estimation apparatus 100 according to the embodiment acquires attributes of a user from a user terminal device installed in a vehicle, is a vehicle boarded by a user who satisfies a predetermined condition, and stays at a predetermined position for a predetermined period of time. Estimate the number of vehicles that have traveled within For example, the number of vehicles that have traveled a predetermined location within a predetermined period is estimated for each region, gender, age, etc., which are the living areas of the user.

By each processing mentioned above, estimating device 100 can acquire cross-sectional traffic volume data efficiently.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

In addition, the above-described estimating apparatus 100 may be implemented by a plurality of server computers, and depending on the function, may be implemented by calling an external platform or the like using an API (Application Programming Interface), network computing, or the like. Flexible to change.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

Note that the vehicle estimation unit 133 and the movement mode estimation unit 134 can collectively be read as an estimation unit.

1 estimation system 10 user terminal device 100 estimation device 200 information center server 110 communication unit 120 storage unit 121 traveling information storage unit 122 vehicle estimation model storage unit 123 movement mode estimation model storage unit 124 training data storage unit 125 estimated traffic volume storage unit 130 Control unit 131 Acquisition unit 132 Reception unit 133 Vehicle estimation unit 134 Movement mode estimation unit 135 Map information provision unit

Claims (10)

an acquisition unit that acquires running information of the vehicle, including control information from a control device of the vehicle, from a terminal device mounted on the vehicle;
A vehicle that estimates the number of terminal devices installed in the vehicle based on the acquired driving information and the history of the driving information , and drives a predetermined location within a predetermined period based on the estimated result. and an estimating unit for estimating the number of . The acquisition unit acquires vehicle type information indicating the vehicle type of the vehicle from the terminal device,
2. The estimator according to claim 1, wherein the estimating unit estimates the number of vehicles that have traveled the predetermined position within a predetermined period for each vehicle type, based on the vehicle type information and the travel information. estimation device. The estimating unit generates a model for estimating a movement mode of the vehicle corresponding to the traveling information based on the traveling information acquired by the acquiring unit, and uses the model to locate a predetermined position at a predetermined location. 3. The estimating device according to claim 1 or 2, estimating the mode of movement of a vehicle that has traveled within a period of time. 4. Any one of claims 1 to 3, wherein the acquisition unit acquires the travel information of the vehicle transmitted from the terminal device when the vehicle enters a predetermined range from the predetermined position. The estimating device described in . The estimating unit calculates the number of terminal devices that have traveled the predetermined position within a predetermined period based on the ratio between the vehicle equipped with the terminal device capable of acquiring the travel information and the other vehicle. The estimating device according to any one of claims 1 to 4, wherein the number of vehicles that have traveled a predetermined position within the predetermined period is estimated. The acquisition unit acquires attributes of the user from a terminal device of the user riding in the vehicle,
The estimating unit is the number of vehicles that have traveled a predetermined position within a predetermined period based on the traveling information acquired from the terminal device in which the attribute of the user satisfies a predetermined condition among the acquired traveling information. 6. The estimating device according to any one of claims 1 to 5, wherein the estimating device according to any one of claims 1 to 5 estimates the number of vehicles boarded by the user who satisfies the predetermined condition. The acquisition unit acquires map information corresponding to travel information,
The estimating device according to any one of claims 1 to 6, wherein the estimating unit estimates the movement mode of the vehicle from the map information acquired by the acquiring unit. The estimating device according to any one of claims 1 to 7 , wherein the estimating unit estimates the number of vehicles that have traveled a plurality of predetermined positions within a predetermined period. A computer implemented estimation method comprising:
an acquisition step of acquiring travel information of the vehicle, including control information from a control device of the vehicle, from a terminal device mounted on the vehicle;
A vehicle that estimates the number of terminal devices installed in the vehicle based on the acquired driving information and the history of the driving information , and drives a predetermined location within a predetermined period based on the estimated result. and an estimation step of estimating the number of . an acquisition procedure for acquiring driving information of the vehicle, including control information from the control device of the vehicle, from a terminal device mounted on the vehicle;
A vehicle that estimates the number of terminal devices installed in the vehicle based on the acquired driving information and the history of the driving information , and drives a predetermined location within a predetermined period based on the estimated result. An estimation program characterized by causing a computer to execute an estimation procedure for estimating the number of and .

Images