WO2014203391A1

WO2014203391A1 - Traffic action estimation system and traffic system

Info

Publication number: WO2014203391A1
Application number: PCT/JP2013/067067
Authority: WO
Inventors: 高行秋山
Original assignee: 株式会社日立製作所
Priority date: 2013-06-21
Filing date: 2013-06-21
Publication date: 2014-12-24
Also published as: JPWO2014203391A1; JP6055916B2

Abstract

The purpose of the present invention is to interpolate a traffic action history acquired from each individual by measurement information acquired from public transportation to thereby improve the measurement accuracy of the traffic action history of the individual. This traffic action estimation system tentatively predicts a traffic volume assuming that the entire population of some site takes the same traffic action as a traffic action history acquired from each individual, compares an actual congestion degree index of a traffic route and the result of the tentative prediction, and readjusts the population that takes each traffic action such that the difference therebetween decreases.

Description

Traffic behavior estimation system, traffic system

The present invention relates to a technique for estimating behavior characteristics when an individual uses transportation.

In emerging countries, there is a rapid population concentration in urban areas due to economic development. In contrast, traffic infrastructure such as roads, railways, and buses has not been developed, and traffic congestion due to sudden increase in traffic volume has become serious. On the other hand, in developed countries, there are problems after traffic improvement, such as deterioration over time after the traffic improvement was implemented, and operators having difficulty in management due to the developed traffic network not following the actual usage situation. Yes.

In order to deal with the above problems, it is necessary to improve public transportation networks such as new roads and railways. When developing a transportation network, in general, (1) create a new city plan, (2) evaluate the proposed plan, (3) select the optimal plan based on the evaluation, and (4) follow the plan. The procedure to construct and operate the transportation network is taken.

When evaluating a traffic plan, simulation technology for predicting traffic demand is used to evaluate the impact of the newly developed traffic network on traffic volume. Non-Patent Document 1 below describes a prediction method called a four-stage estimation method. The four-stage estimation method requires various parameter settings at each step. These parameters are set based on manual traffic surveys and survey results.

The manual traffic survey takes a lot of time and effort and is only conducted once every 5 to 10 years. In view of this, probe systems that presume road congestion using GPS information mounted on public transportation such as taxis and buses and sensors installed on the roadside using IT (Information Technology) have become widespread. In addition, a person probe technology has been developed that collects traffic behavior histories of individual residents using mobile phones and smartphones.

The probe system installs a measurement terminal on an object to be measured (vehicles such as taxis and buses), and various measurement data such as time, coordinates (latitude, longitude), speed, etc. of the object to be measured are constant (for example, every 1 second) To measure the average speed of the measurement object in the measurement object section, the time when the measurement object passes a specific location (such as a bus stop or a station), and the like.

Person probe technology obtains information necessary for traffic measurement by always carrying a portable terminal equipped with a measurement function necessary for measurement to a person in charge of investigation and collecting its location information.

In order to create a city plan appropriately, it is necessary to grasp as specifically as possible how an individual uses transportation. This is because it is not effective to expand the means of transportation not used by individuals. Therefore, it is conceivable to use the person probe technique to collect the detailed history of the use of the means of transportation by the individual and use it when creating the city plan. However, in order to collect the number of data that can be used for city planning using the person probe technology, it is necessary to prepare a large number of investigators and mobile terminals, which is generally difficult. Therefore, it is difficult to conduct a survey with sufficient accuracy.

On the other hand, when using a measuring terminal installed in public transportation, it is possible to grasp a wide range of traffic conditions and the like, but it is difficult for each individual to grasp in detail the history of using transportation means. The measurement data acquired from the transportation means represents the movement history of the transportation means itself, but does not represent how each individual uses the transportation means. This is because the timing at which each individual starts or ends the use of the means of transportation is not shown.

The present invention has been made in view of the problems as described above, and the traffic behavior history acquired from each individual is interpolated by the measurement information acquired from public transportation to improve the measurement accuracy of the personal traffic behavior history. The purpose is to let you.

The traffic behavior estimation system according to the present invention tentatively predicts the traffic volume on the assumption that the entire population at a certain point takes the same traffic behavior as the traffic behavior history acquired from each individual, and the actual congestion degree of the traffic route The population that takes each traffic action is readjusted so that the difference between the index and the provisional prediction result becomes smaller.

According to the traffic behavior estimation system according to the present invention, it is possible to improve the measurement accuracy of an individual traffic behavior history without preparing a large number of investigators or mobile terminals.

1 is a configuration diagram of a traffic behavior estimation system according to Embodiment 1. FIG. It is a figure which shows the structure and data example of the model parameter. It is a figure which shows the structure of the population data 170, and a specific example. It is a figure which shows the structure and data example of the traffic capacity data. It is a figure explaining the relationship of the zone in FIG. 2A and 2C, a node, and a link. It is a figure which shows the structure of the probe person data 150, and a data example. It is a figure which shows the structure and data example of congestion degree data. 5 is a flowchart for explaining the operation of a model learning unit 110. It is a flowchart explaining the detail of step S401. It is a block diagram of the traffic system which concerns on Embodiment 2. FIG. It is a flowchart explaining operation | movement of the traffic system which concerns on Embodiment 2. FIG. It is a figure which shows the screen image at the time of a user setting a new road using the GUI program 651. FIG. It is a figure which shows the screen image which shows the result of having evaluated the new traffic route by the convenience evaluation part 620 and the traffic planning part 630. FIG. It is a figure which shows the screen image which displays the expense, convenience, and evaluation parameter | index of several new traffic plans as a list. It is a block diagram of the traffic system which concerns on Embodiment 3. FIG. It is a block diagram of the traffic system which concerns on Embodiment 4. It is a block diagram of the traffic system which concerns on Embodiment 5. FIG. It is a block diagram of the traffic system which concerns on Embodiment 6. FIG. It is a figure which shows the screen image which a user (for example, traffic plan creator) sets a charging area using the GUI program 651. FIG. It is a figure which shows the screen image which shows the result of having evaluated the new traffic route by the billing effect prediction part 1320. It is a block diagram of the traffic system which concerns on Embodiment 7. FIG.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, functionally identical elements may be denoted by the same numbers. The accompanying drawings show specific embodiments in accordance with the principle of the present invention, but these are for the understanding of the present invention and are not used for limiting the interpretation of the present invention. Absent.

<Embodiment 1>
FIG. 1 is a configuration diagram of a traffic behavior estimation system according to Embodiment 1 of the present invention. The traffic behavior estimation system according to the first embodiment is a system that estimates traffic behavior of an individual living in a city and outputs it as a model parameter 190, and includes a traffic behavior estimation device 100, a probe 200, and a personal data source 300. .

The probe 200 is a measuring terminal that measures the state of traffic congestion, such as a GPS mounted on a taxi or bus, a VICS (registered trademark) installed on a road, a camera that captures the state of the transportation, etc. It is comprised using.

The personal data source 300 is a personal traffic such as a GPS or acceleration sensor mounted on a portable terminal carried by an individual, a use history of an IC card that can be used in transportation, a person trip questionnaire result at the time of national census, etc. It is an information source for collecting action history.

The traffic behavior estimation apparatus 100 complements the traffic behavior history of each individual collected from the personal data source 300 with the measurement data of each transportation means collected from the probe 200, and generates a highly accurate traffic behavior model of each individual. Device. The generated traffic behavior model can be used, for example, when creating a city plan.

The traffic behavior estimation device 100 includes a processor 101, a memory 102, and a storage device 103. These are connected to each other by a bus. The traffic behavior estimation apparatus 100 can be configured using, for example, a large computer, but is not limited thereto, and may be configured by operating a plurality of computers in parallel, for example.

The processor 101 executes each program stored in the memory 102. The memory 102 stores a model learning unit 110, a congestion degree calculation unit 120, a personal history calculation unit 130, and a data collection unit 140.

The data collection unit 140 collects information about the measurement results obtained by the probe 200 and the traffic behavior of each individual provided by the personal data source 300. For example, each data can be collected from the probe 200 and the personal data source 300 via a communication network, or measurement data stored in a storage medium can be read and acquired.

The personal history calculation unit 130 estimates the detailed information such as the transportation means used by each individual from the information about the individual traffic behavior collected by the data collection unit 140 and stores it in the storage device 103 as the probe person data 150. In addition, the personal history calculation unit 130 may estimate the travel route based on, for example, the use history of the IC card, or may estimate the traffic behavior of the individual from the personal questionnaire result. A specific example of the probe person data 150 will be described later with reference to FIG. When the probe person data 150 is provided in advance, the personal history calculation unit 130 can be omitted.

The congestion degree calculation unit 120 calculates the congestion degree of each means of transportation from the measurement data of the means of transportation collected by the data collection unit 140 and stores it as the degree of congestion data 160 in the storage device 103. For example, the travel time on each road can be calculated from GPS information mounted on a taxi or bus, and this can be used as the degree of congestion. In addition, the traffic volume may be estimated based on the VICS traffic information camera image and used as the congestion level. When the congestion level data 160 is provided in advance, the congestion level calculation unit 120 can be omitted.

The storage device 103 stores probe person data 150, congestion data 160, population data 170, traffic capacity data 180, and model parameters 190. Specific examples of these data will be described later.

The model learning unit 110 estimates the model parameter 190 using the probe person data 150, the congestion degree data 160, the population data 170, and the traffic capacity data 180. The model learning unit 110 includes an individual behavior analysis unit 111, a usage state calculation unit 112, a congestion degree calculation unit 113, and an evaluation unit 114. Details of these parts will be described later.

The model learning unit 110, the congestion degree calculation unit 120, the personal history calculation unit 130, and the data collection unit 140 can be configured by the processor 101 executing programs describing these operations, and realize these functions. It can also be configured using hardware such as a circuit device. The following description is based on the assumption that the program is configured as shown in FIG. The processor 101 actually executes these programs. However, for the convenience of description, each function unit will be described as an operation subject.

FIG. 2A is a diagram showing a configuration of the model parameter 190 and an example of data. The model parameter 190 is data representing a tendency of an individual to use transportation means, and includes a city 191, a departure place 192, an arrival place 193, a traffic volume 194, and a selection pattern 195.

The city 191 holds the ID of the city where the data was collected. The departure place 192 and the arrival place 193 hold the ID of each point (zone) in the city. The traffic volume 204 holds the traffic volume generated between the departure place 192 and the arrival place 193. For example, the number of vehicles passing between the departure place 192 and the arrival place 193 can be used as the traffic volume 204, but other traffic volume indicators may be used. The selection pattern 195 holds the probability that each transportation facility is selected between the points. In addition, for example, an evaluation scale such as time priority or charge priority may be used as the selection pattern 195.

FIG. 2B is a diagram showing a configuration of the population data 170 and a specific example. The population data 170 is data describing information about the population of a city targeted by the system according to the present invention, and includes a city 171, a population 172, and the number of households 173. A city 171 corresponds to the city 191. The population 172 holds the population number of the city. The number of households 173 holds the number of households in the city.

FIG. 2C is a diagram illustrating a configuration of the traffic capacity data 180 and a data example. The traffic capacity data 180 is data describing the traffic capacity of a traffic route connecting points, and includes a link 181, a node 182, a length 183, a fee 184, a traffic means 185, and a traffic capacity 186. Since the traffic capacity data 180 and the population data 170 are used as constraint conditions when the flowchart described later with reference to FIG. 4 is performed, they may be combined into one as the constraint condition data.

The link 181 holds a traffic route ID such as a road or a traffic section. The node 182 holds IDs of points that hit both ends of the link. The length 183 holds the length of the link. The fee 184 holds an amount necessary for passing through the link. The transportation means 185 holds transportation means that can pass through the link. The traffic capacity 186 holds a traffic volume that is allowed when the link is passed by the transportation means.

FIG. 2D is a diagram for explaining the relationship between zones, nodes, and links in FIGS. 2A and 2C. When an individual goes from the node N1 to the node N4, the individual may go through a plurality of nodes. Each node is connected by a link. Each node is included in a zone which is a wider regional unit.

FIG. 3A is a diagram showing a configuration of the probe person data 150 and data examples. The probe person data 150 is data describing the result of estimating the traffic behavior of each individual based on the data collected from the personal data source 300. Although this data includes the result of estimating the transportation means 155 and the purpose 156 according to the flowchart described later, the number of data is not yet interpolated. The probe person data 150 includes a city 151, a citizen 152, a date and time 153, coordinates 154, a transportation means 155, and a purpose 156.

The city 151 corresponds to the city 191. Citizen 152 holds an ID that identifies the individual who acquired the data from personal data source 300. The date and time 153 holds the date and time when data was measured in the personal data source 300. The coordinates 303 hold the GPS coordinates (or address, etc.) of the measurement location when the data is measured in the personal data source 300. The purpose 156 holds the movement purpose of the individual who acquired data from the personal data source 300 at the time of measurement.

FIG. 3B is a diagram illustrating a configuration of the congestion degree data 160 and a data example. The congestion degree data 160 is data for storing a result of calculating an index indicating the congestion degree of each link based on data collected from the probe 200, and includes a city 161, a link 162, and a congestion degree 163.

The city 161 corresponds to the city 191, and the link 162 corresponds to the link 181. The congestion degree 163 holds a congestion degree index of the link. For example, an index indicating the time required to pass the link or the degree of congestion can be used as the congestion degree 163. Furthermore, you may make it hold | maintain the some congestion degree 163 according to a season or a time slot | zone.

FIG. 4 is a flowchart for explaining the operation of the model learning unit 110. The operation of the model learning unit 110 starts this flowchart according to, for example, a user of the traffic behavior estimation apparatus 100 according to an instruction or according to a predetermined execution cycle. Hereinafter, each step of FIG. 4 will be described.

(FIG. 4: Step S401)
The personal behavior analysis unit 111 calculates a selection pattern regarding which transportation means each individual included in the probe person data 150 has a tendency to select. This corresponds to provisional calculation of the selection pattern 195 of the model parameter 190 for each individual included in the probe person 150. However, at the time of this step, the number of data is the same as the probe person data 150 and has not been interpolated yet. Details of this step will be described again with reference to FIG.

(FIG. 4: Step S402)
The usage status calculation unit 112 assigns the population 172 described by the population data 170 equally to each selection pattern provisionally calculated in step S401. For example, if the city T1 has a population of 10,000 people and 10 patterns for selecting the means of transportation by individuals in the city T1 are obtained in step S401, 1000 people are assigned to each selection pattern. Assume that all 1000 people assigned choose a mode of transportation according to their assigned selection pattern. Thereby, the usage status calculation unit 112 can calculate the status of how each transportation means is used under the assumption.

(FIG. 4: Step S403)
The congestion degree calculation unit 113 calculates the congestion degree of each link on the assumption that the population is assigned to each selection pattern in step S402. The congestion degree of each link can be calculated by obtaining the traffic volume of each link using a general traffic volume allocation method such as an equilibrium allocation method.

(FIG. 4: Step S404)
The evaluation unit 114 obtains a difference between the congestion degree calculated in step S403 and the congestion degree of the link described in the congestion degree data 160, and obtains the difference in step S401 so that the difference becomes small. Steps S402 to S403 are repeated by changing the selection pattern and the population allocation obtained in step S402. When the difference has converged (for example, when the difference is equal to or less than a predetermined threshold), the iterative process is terminated, and the selection pattern at that point is reflected in the model parameter 190.

(FIG. 4: Step S404: Supplement)
As the difference in this step, the average value of the absolute value of the difference between the congestion degree of each link read from the congestion degree data 160 and the congestion degree of each link calculated in step S403 may be used. May be used. The specific amount of change when changing the selection pattern and population allocation so that the difference is small may be determined using a search method such as a genetic algorithm, or any other method. You may decide.

FIG. 5 is a flowchart for explaining details of step S401. Hereinafter, each step of FIG. 5 will be described.

(FIG. 5: Step S501)
The personal behavior analysis unit 111 estimates a departure place (Origin) and an arrival place (Destination) from the movement history of each individual included in the probe person data 150. For example, a point staying at the same place for a certain amount of time is considered to be a destination or an arrival point, and movement between these points is extracted as one traffic action. As the estimation method in this step, for example, a method used in a four-stage estimation method can be used. With the estimation in this step, the travel route is also estimated.

(FIG. 5: Step S502)
The personal behavior analysis unit 111 searches for a route between the departure point and the arrival point of each traffic behavior extracted in step S501 by using the information regarding the link between the nodes described in the traffic capacity data 180. Any known technique can be used as the route search method. If a plurality of routes are obtained in this step, all routes are temporarily held.

(FIG. 5: Step S503)
The personal behavior analysis unit 111 calculates, as a statistical probability, a tendency for each individual to select each means of transportation by comparing the travel route estimated in step S501 with the route group obtained in step S502. Not only the tendency to select a transportation means but also the tendency to select a route may be calculated.

<Embodiment 1: Summary>
As described above, the traffic behavior estimation apparatus 100 according to the first exemplary embodiment collects the model parameters 190 estimated based on the limited data that can be collected from the personal data source 300 from the wide area collected from the probe 200. Interpolate using measured data. This makes it possible to accurately estimate the model parameter 190 representing the traffic behavior pattern of each individual without preparing a large number of investigators or mobile terminals.

The model parameter 190 generated in the first embodiment can be used as basic data in installation planning of public facilities and commercial facilities, value calculation of real estate properties, and the like. For example, the traffic behavior estimation apparatus 100 may be provided with a data output function for each application.

In the first embodiment, data is collected from a mobile terminal carried by an individual such as a smartphone. The data collection unit 140 or the personal history calculation unit 130 may have a function of distributing an application for the smartphone to collect GPS information and acceleration sensor measurement data. The application may be configured to provide a function of displaying traffic volume information and an action history of each individual in order to encourage each individual to use the application. Further, the application may be configured to provide a function for inputting at least one item of the probe person data 150.

In the first embodiment, the person probe data 150 differs in the number of samples sufficient to estimate the traffic behavior according to the number of zones and the population in the city. Moreover, the case where the diversity of an individual's action differs according to a season is assumed. For example, when using the person probe data 150 as basic data when a city planner makes a traffic plan, the goal may be to minimize the number of samples collected from the personal data source 300. Therefore, the traffic behavior estimation apparatus 100 may provide a function of calculating the number of samples of the personal data source 300 sufficient to calculate the model parameter 190.

<Embodiment 2>
In the second embodiment of the present invention, a configuration example in which the effect of a new city traffic plan is evaluated by simulation using the model parameter 190 obtained by the traffic behavior estimation system according to the first embodiment will be described. The configuration of the traffic behavior estimation system is the same as that of the first embodiment except that a function is added to the traffic behavior estimation device 100.

FIG. 6 is a configuration diagram of the traffic system according to the second embodiment. The traffic system includes a traffic behavior estimation apparatus 100 and a server 640. The traffic behavior estimation apparatus 100 includes a convenience evaluation unit 620 and a traffic planning unit 630 in addition to the configuration described in the first embodiment. These functional units can also be provided in the server 640 described later.

The traffic planning unit 630 is a functional unit that creates a plan for adding new traffic facilities such as roads, intersections, and railway networks to an existing traffic network. As a specific method, any known technique for creating a traffic plan can be used.

The convenience evaluation unit 620 estimates the degree of congestion of the virtual traffic network temporarily created by the model parameter 190 and the traffic planning unit 630, and thereby increases the degree of convenience improvement by the newly created traffic plan and the benefit from traffic demand. presume.

The server 640 is a terminal for making a traffic plan using the functions provided by the traffic behavior estimation apparatus 100, and includes a processor 641, a memory 650, a storage device 660, and a display unit 642. These are connected to each other by a bus.

The processor 641 executes each program stored in the memory 650. Hereinafter, for convenience of description, each program will be described as an operation subject. The memory 650 stores a GUI (Graphical User Interface) program 651 and a data communication program 652.

The data communication program 652 acquires the traffic capacity data 180 held by the traffic behavior estimation apparatus 100 and stores it in the storage device 660 as the traffic capacity data 661. Moreover, the process result by the convenience evaluation part 620 and the traffic planning part 630 is received. The GUI program 651 displays traffic capacity data 661 and map data 662 on the display unit 642, and provides a function of editing or newly registering a traffic network on the screen.

The storage device 660 stores traffic capacity data 661 and map data 662 acquired from the traffic behavior estimation device 100. The display unit 642 visually displays data on a monitor, a display, or the like.

FIG. 7 is a flowchart for explaining the operation of the traffic system according to the second embodiment. It is assumed that the process for calculating the model parameter 190 described in the first embodiment has been performed. Hereinafter, each step shown in FIG. 7 will be described.

(FIG. 7: Step S701)
The GUI program 651 displays the traffic network in the city as a map with reference to the traffic capacity data 661 and the map data 662. The congestion degree data 160 of the traffic behavior estimation apparatus 100 may be referred to via a network and displayed together with the traffic network.

(FIG. 7: Step S702)
A user such as a traffic planner uses the GUI program 651 to edit a map on the screen so as to reflect a traffic plan such as a new road or a railroad. The GUI program 651 temporarily stores a traffic network reflecting the edited result.

(FIG. 7: Step S703)
The data communication program 652 transmits the traffic network reflecting the edited result to the traffic behavior estimation apparatus 100. The convenience evaluation unit 620 uses the edited traffic network and the model parameter 190 to calculate the traffic volume on each link and the convenience of the transportation facility. As a convenience evaluation method, a commonly used four-stage estimation method may be used, or other methods for estimating traffic volume may be used.

(FIG. 7: Step S704)
The traffic planning unit 630 calculates the cost required to change from the traffic network before editing to the traffic network after editing. For example, the cost can be calculated systematically based on past construction record data, etc., or each contractor can be automatically requested for an estimate and calculated based on the result.

(FIG. 7: Step S705)
As the processing results of the convenience evaluation unit 620 and the traffic planning unit 630, the cost related to the traffic plan input by the user and the convenience of city traffic when the plan is implemented can be obtained. The convenience evaluation unit 620 or the traffic planning unit 630 may further calculate an index for evaluating the traffic plan from the calculation result of the cost and the convenience. An example of the evaluation index will be described later. The convenience evaluation unit 620 and the traffic planning unit 630 output these processing results to the server 640. The data communication program 652 receives this and displays it on the display unit 642.

FIG. 8A is a diagram showing a screen image when the user sets a new road using the GUI program 651. When the user creates a new traffic plan (project), the traffic capacity data 661, the map data 662, and the congestion degree data 160 (obtained from the traffic behavior estimation apparatus 100) are displayed on the screen. The dotted line on the screen is the link where the traffic jam occurs. The user temporarily sets a new road in consideration of such a current situation (thick line). When the editing is finished, the user presses the execution button at the lower right. The data communication program 652 transmits the traffic network data reflecting the edited result to the traffic behavior estimation apparatus 100. The traffic behavior estimation apparatus 100 implements the functions of the convenience evaluation unit 620 and the traffic planning unit 630.

FIG. 8B is a diagram showing a screen image showing a result of evaluating a new traffic route by the convenience evaluation unit 620 and the traffic planning unit 630. By adding a new road, the congestion link has disappeared. On the right side of the screen, the cost required to construct the transportation plan and the convenience of transportation after construction are displayed. Furthermore, the evaluation index calculated by the convenience evaluation unit 620 based on these costs and convenience is displayed. The user can evaluate the usefulness of the new traffic plan based on these indices.

Examples of traffic plan evaluation indexes include NPV (Net Present Value), CBR (Cost Benefit Ratio), IRR (Internal Rate of Return: Internal Rate of Return), and the like. NPV is used when it is intended to adopt a traffic plan that is as effective as possible without considering the constraints of financial resources. CBR is used when considering the limitation of financial resources and trying to adopt as efficient a traffic plan as possible. IRR is used when business profitability is important.

FIG. 9 is a diagram showing a screen image displaying a list of expenses, convenience, and evaluation indexes of a plurality of new traffic plans. The convenience evaluation unit 620 and the traffic plan unit 630 store the calculation results of these indexes in the storage device 103, and the GUI program 651 can call them. Thus, each traffic plan can be finely adjusted by the traffic behavior estimation apparatus 100 holding the calculation result and the edit result of each traffic plan.

<Embodiment 2: Summary>
As described above, the transportation system according to the second embodiment can evaluate the cost convenience of the transportation plan using the model parameter 190 calculated by the model learning unit 110. This makes it possible to evaluate traffic plans at intervals of about one week to one month. In other words, it is possible to carry out evaluation and design of urban traffic plans that have been carried out every 5 to 10 years more frequently.

<Embodiment 3>
In the third embodiment of the present invention, a configuration example will be described in which traffic regulation is performed according to the actual state of traffic behavior using the model parameter 190 obtained by the traffic behavior estimation system according to the first embodiment. The configuration of the traffic behavior estimation system is the same as that of the first embodiment.

FIG. 10 is a configuration diagram of a traffic system according to the third embodiment. The traffic system includes a traffic behavior estimation apparatus 100 and a server 1000. The server 1000 is a device that instructs the traffic regulation unit 1050 to implement traffic regulation, and includes a processor 1010, a memory 1020, a storage device 1030, and a display unit 1040. These are connected to each other by a bus. The display unit 1040 visually displays data using a monitor, a display, or the like.

The processor 1010 executes each program stored in the memory 1020. Hereinafter, for convenience of description, each program will be described as an operation subject. The memory 1020 stores a traffic condition display program 1021, a restriction information editing program 1022, a traffic volume prediction program 1023, and a restriction information distribution program 1024. The traffic volume prediction program 1023 and the regulation information distribution program 1024 can also be arranged on the traffic behavior estimation apparatus 100.

The traffic condition display program 1021 acquires the traffic capacity data 1032 and the congestion degree data 160 from the traffic behavior estimation apparatus 100, integrates these with the map data 1033, and displays the screen on the display unit 1040. Thereby, the user can grasp | ascertain the congestion condition of a traffic route. Video information from a camera and traffic accident information may be superimposed and displayed.

The regulation information editing program 1022 temporarily sets a new traffic regulation section on the display unit 1040 and reflects it on the traffic network. For example, when a traffic accident occurs and a traffic jam occurs, a new traffic regulation such as prohibiting traffic on a certain road so as not to occur in a more serious wide-area traffic jam is temporarily set.

The traffic volume prediction program 1023 uses the model parameters 1031 downloaded from the traffic behavior estimation apparatus 100 to predict the traffic volume of each traffic road when the traffic information temporarily set by the restriction information editing program 1022 is implemented. The user can determine the usefulness of the temporarily set traffic regulation based on the prediction result.

The restriction information distribution program 1024 distributes the traffic restriction information temporarily set by the restriction information editing program 1022 to the traffic restriction unit 1050. The traffic regulation unit 1050 performs traffic regulation based on the received traffic regulation information, and further distributes the traffic regulation information to an information bulletin board or a website. As a mode of actually implementing the traffic regulation, for example, a mode in which a detour sign is displayed on an information display board on the road, or a manual regulation is performed according to information distributed by the regulation information distribution program 1024 can be considered.

<Embodiment 3: Summary>
As described above, the traffic system according to the third embodiment can evaluate the usefulness of traffic regulation by simulation based on the model parameter 190 generated by the traffic behavior estimation apparatus 100. Thereby, the traffic regulation according to the actual condition of each individual's traffic behavior can be implemented.

In the third embodiment, when the restriction information editing program 1022 sets a new traffic restriction, a function of referring to information related to traffic restrictions implemented in the past may be provided. Further, a function may be provided in which a past traffic situation that is most similar to the current traffic situation is searched, and information relating to traffic regulation implemented at that time is referred to.

<Embodiment 4>
FIG. 11 is a configuration diagram of a traffic system according to Embodiment 4 of the present invention. The traffic system according to the fourth embodiment includes an accident detection program 1025 in addition to the configuration described in the third embodiment. Other configurations are the same as those of the third embodiment. The accident detection program 1025 can also be arranged on the traffic behavior estimation apparatus 100.

The accident detection program 1025 uses the traffic capacity data 1032 downloaded from the traffic behavior estimation apparatus 100 to detect the occurrence of a sudden traffic jam. The accident detection program 1025 assumes that the occurrence of the traffic jam is caused by a traffic accident, and assumes that the outflow of traffic volume is reduced at the point. The traffic volume prediction program 1023 estimates the future traffic volume based on the assumption.

The user refers to the traffic volume estimated by the traffic volume prediction program 1023 on the display unit 1040 and sets the traffic regulation using the regulation information editing program 1022. Subsequent operations are the same as those in the third embodiment.

According to the traffic system according to the fourth embodiment, by detecting the occurrence of a traffic accident based on the traffic volume data 180 acquired from the probe 200, it is possible to quickly implement traffic regulation before serious traffic congestion occurs. .

<Embodiment 5>
In the fifth embodiment of the present invention, a configuration example in which the signal switching interval is set in accordance with the actual traffic behavior using the model parameter 190 obtained by the traffic behavior estimation system according to the first embodiment will be described. The configuration of the traffic behavior estimation system is the same as that of the first embodiment.

FIG. 12 is a configuration diagram of a traffic system according to the fifth embodiment. The traffic system includes a traffic behavior estimation apparatus 100 and a server 1000. The server 1000 includes a signal interval setting program 1221, a traffic volume prediction program 1222, a signal control program 1223, and an information distribution program 1224 in place of or in addition to the programs described in the third to fourth embodiments. These programs can also be arranged on the traffic behavior estimation apparatus 100.

The signal interval setting program 1221 sets a signal switching interval. The switching interval may be manually input by the user, or the user may select any one from a plurality of parameters set in advance.

Based on the signal interval set by the signal interval setting program 1221 and the model parameters 1031 and the traffic capacity data 1032 acquired from the traffic behavior estimation apparatus 100, the traffic volume prediction program 1222 calculates the traffic volume in the future, for example, about one hour ahead. Predict.

The user adopts a signal interval that can eliminate the current traffic jam based on the traffic volume estimated by the traffic volume prediction program 1222. The signal control program 1223 transmits a control signal for reflecting the signal interval set by the signal interval setting program 1221 to the signal system 1230.

The information distribution program 1224 distributes information on the current traffic situation to the information bulletin system 1240. The information bulletin system 1240 distributes information related to traffic conditions received from the information distribution program 1224 to an information bulletin board on the road, an information bulletin board website on the Internet, and the like. At this time, it may be converted into a format that is easy for the user to understand.

The signal system 1230 controls the traffic light using the control signal received from the signal control program 1223 and transmits control information to the signal control program 1223.

<Embodiment 5: Summary>
As described above, the traffic system according to the fifth embodiment can evaluate the effect of changing the signal switching interval based on the model parameter 190 generated by the traffic behavior estimation apparatus 100 by simulation. Thereby, signal control based on the actual state of traffic behavior can be implemented. The fifth embodiment can be used in combination with the third to fourth embodiments.

<Embodiment 6>
In the sixth embodiment of the present invention, a configuration example in which the billing amount is set according to the actual state of traffic behavior using the model parameter 190 obtained by the traffic behavior estimation system according to the first embodiment will be described. The configuration of the traffic behavior estimation system is the same as that of the first embodiment.

FIG. 13 is a configuration diagram of a traffic system according to the sixth embodiment. The traffic system includes a traffic behavior estimation apparatus 100 and a server 640. The traffic behavior estimation apparatus 100 includes a billing effect prediction unit 1320 in addition to the configurations described in the first and second embodiments. The charging effect prediction unit 1320 can also be provided on the server 640.

The charging effect prediction unit 1320 estimates the traffic volume in the charging section using the charging section and the charging amount described in the traffic capacity data 180 and the model parameter 190. The billing effect prediction unit 1320 estimates the traffic volume using as a parameter which of the fee and time required to reach the destination is more important when selecting a transportation facility. Thereby, the traffic demand in the billing area can be correctly estimated.

FIG. 14A is a diagram showing a screen image in which a user (for example, a traffic plan creator) uses the GUI program 651 to set a billing area. When the user creates a new road billing plan (project), the GUI program 651 displays the traffic capacity data 661, the map data 662, and the congestion degree data 160 on the screen. The dotted line represents a traffic jam link. The user sets a new road billing area in consideration of the current situation (rectangle in the figure). The user presses the execution button at the lower right after setting the charging time zone and the fee for the charging area. The data communication program 652 transmits the traffic network data reflecting the edited result to the traffic behavior estimation apparatus 100. The traffic behavior estimation apparatus 100 executes the function of the charging effect prediction unit 1320.

FIG. 14B is a diagram showing a screen image showing a result of evaluating a new traffic route by the charging effect prediction unit 1320. By setting a new billing area, the congestion link has disappeared. On the right-hand side of the screen, the convenience required for transportation, taking into account the expenses required to construct the traffic plan and the revenue from billing after construction, is displayed. Furthermore, the evaluation index calculated by the convenience evaluation unit 620 based on these costs and convenience is displayed. The user can evaluate the usefulness of the new billing area based on these indices.

<Embodiment 6: Summary>
As described above, the traffic system according to the sixth embodiment can predict the effect of road billing using the model parameter 190 calculated by the model learning unit 110. Thereby, the road billing plan can be evaluated in accordance with the actual traffic behavior in the city. The sixth embodiment can be used in combination with the second embodiment to evaluate a traffic plan combining a billing area and a new traffic route.

<Embodiment 7>
FIG. 15 is a configuration diagram of a traffic system according to Embodiment 7 of the present invention. The traffic system according to the seventh embodiment includes a billing server 1500 in addition to the configuration described in the sixth embodiment. The charging server 1500 is a device that dynamically charges a vehicle that has passed through the charging area, and includes a processor 1510, a memory 1520, and an auxiliary storage device 1530. These are connected to each other by a bus.

The processor 1510 executes each program stored in the memory 1520. Hereinafter, for convenience of description, each program will be described as an operation subject. The memory 1520 stores a charging program 1521 and a charging vehicle detection program 1522.

The charging vehicle detection program 1522 detects that the vehicle is traveling in the charging area. For example, a vehicle traveling in a charging area is detected by collecting GPS information mounted on a car navigation system or a smartphone. In addition, for example, the vehicle may be detected using a camera image, or may be detected using short-range wireless communication.

The billing program 1521 identifies the user of the vehicle detected by the billing vehicle detection program 1522 by referring to the customer data 1532 stored in the storage device 1530, and bills from the financial institution account held by the user. The fee specified by the program 1531 is collected.

Storage device 1530 stores billing area data 1531, traffic capacity data 1533, and customer data 1532 downloaded from server 640. The billing area data 1531 holds data extracted from the data described by the traffic capacity data 180, such as a link to be billed, a billing amount, a billing time zone, and the like. The customer data 1532 holds an ID that uniquely identifies a customer and information necessary for collecting a fee such as an account number of a financial institution in association with each other.

<Embodiment 7: Summary>
As described above, in the traffic system according to the seventh embodiment, the optimal charging area is transmitted to the charging server 1500 from the charging areas evaluated by the charging effect prediction unit 1320. The charging server 1500 Collect an appropriate fee for the vehicle you are driving. Thereby, it is possible to dynamically change the billing area in accordance with the actual situation of traffic usage.

The present invention is not limited to the above-described embodiment, and includes various modifications. The above embodiment has been described in detail for easy understanding of the present invention, and is not necessarily limited to the one having all the configurations described. A part of the configuration of one embodiment can be replaced with the configuration of another embodiment. The configuration of another embodiment can be added to the configuration of a certain embodiment. Further, with respect to a part of the configuration of each embodiment, another configuration can be added, deleted, or replaced.

The above components, functions, processing units, processing means, etc. may be realized in hardware by designing some or all of them, for example, with an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files for realizing each function can be stored in a recording device such as a memory, a hard disk, an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

100: Traffic behavior estimation device, 110: Model learning unit, 120: Congestion degree calculation unit, 130: Personal history calculation unit, 140: Data collection unit, 150: Probe person data, 160: Congestion degree data, 170: Population data, 180: Traffic capacity data, 190: Model parameters, 200: Probe, 300: Personal data source.

Claims

A traffic condition acquisition unit that acquires a congestion degree index of a traffic route connecting points;
An individual history acquisition unit for an individual to acquire a history of using transportation,
A storage unit for storing constraint data describing the population at the point and the traffic capacity of the traffic road;
A personal behavior analysis unit that estimates a selection pattern of transportation means used by the individual to move between the points by statistically processing the history acquired by the personal history acquisition unit;
Usage of the transportation means when it is assumed that the population at the point is temporarily allocated for each selection pattern, and the transportation means is used according to the selection pattern to which all the populations assigned to the selection patterns are assigned. Usage calculation unit for calculating
A congestion degree calculation unit that calculates a congestion degree index of each traffic route by allocating the use state of the transportation means calculated by the use state calculation unit to each traffic route;
The population to be temporarily allocated to each of the selection patterns or the selection patterns until the difference between the congestion degree index calculated by the congestion degree calculation unit and the congestion degree index acquired by the traffic condition acquisition unit is equal to or less than a predetermined reference value. By interpolating the history acquired by the personal history acquisition unit according to the congestion index acquired by the traffic status acquisition unit, by repeating the processing of the usage status calculation unit and the congestion level calculation unit, An evaluation unit for storing the result in the storage unit;
A traffic behavior estimation system comprising:
In claim 1,
The traffic condition acquisition unit acquires a congestion degree index of the traffic path using a GPS mounted on public transportation,
The personal history acquisition unit includes: the history is acquired using a GPS or an acceleration sensor mounted on a portable terminal held by the individual.
In claim 2,
The personal history acquisition unit distributes an application program for collecting information acquired by the GPS or the acceleration sensor to a mobile terminal held by the individual,
The application program is configured to provide an interface for inputting at least one of the date and time when the individual uses the transportation means, coordinates, the type of transportation means, and the purpose of use. Estimation system.
The traffic behavior estimation system according to claim 1,
Changes in the congestion degree index of the traffic route when it is assumed that a new traffic route is added in addition to the traffic route described in the constraint data, and the traffic after the new traffic route is added A convenience evaluation unit that evaluates the convenience of the road based on the result of the interpolation by the evaluation unit;
A traffic planning unit that estimates the cost and time required to add the new traffic route based on the evaluation result by the convenience evaluation unit;
An output unit for outputting the result of the estimation by the traffic planning unit;
A transportation system characterized by comprising:
The traffic behavior estimation system according to claim 1,
A traffic volume predicting unit that calculates the traffic volume of the traffic path based on the result of the interpolation by the evaluation unit when it is assumed that traffic on the traffic path is regulated;
An output unit for outputting a calculation result by the traffic volume prediction unit;
A traffic regulation unit that regulates traffic on the traffic route according to the regulation assumed by the traffic volume prediction unit;
A transportation system characterized by comprising:
In claim 5,
The storage unit stores data describing a traffic regulation plan implemented by the traffic regulation unit in the past and the traffic volume of the traffic road at that time,
The traffic volume prediction unit calculates a similarity between the traffic volume of the traffic road calculated by the traffic volume prediction unit and the traffic volume of the traffic road in the past stored in the storage unit,
The output unit outputs the past traffic regulation plan corresponding to the highest similarity calculated by the traffic volume prediction unit.
In claim 5,
The traffic system includes an accident detection unit that detects that a traffic accident has occurred in the traffic road based on the congestion index of the traffic road acquired by the traffic situation acquisition unit,
The said output part outputs the information about the traffic accident which the said accident detection part detected. The traffic system characterized by the above-mentioned.
The traffic behavior estimation system according to claim 1,
A traffic volume prediction unit that calculates the traffic volume of the traffic road based on the result of the interpolation by the evaluation unit when it is assumed that the signal switching interval in the traffic road is changed;
An output unit for outputting a calculation result by the traffic volume prediction unit;
A signal control unit for changing between signal switching in the traffic route according to the signal switching interval assumed by the traffic volume prediction unit;
A transportation system characterized by comprising:
In claim 8,
The said traffic system is provided with the information delivery part which delivers the information which shows the traffic volume of the said traffic route. The traffic system characterized by the above-mentioned.
The traffic behavior estimation system according to claim 1,
A charging effect prediction unit that calculates the traffic volume of the traffic road based on the result of the interpolation by the evaluation unit when it is assumed that the charging amount in the traffic road has been changed;
An output unit for outputting a calculation result by the charging effect prediction unit;
A billing unit for changing a billing amount in the traffic route according to the billing amount assumed by the billing effect prediction unit;
A transportation system characterized by comprising:
In claim 10,
The transportation system includes a charging vehicle detection unit that detects that a vehicle has traveled in a charging area where the charging unit performs charging.
The storage unit stores account identification information of a target person to be charged by the charging unit,
When the charging vehicle detection unit detects that the vehicle has traveled in the charging area, the charging unit specifies an account of the owner of the vehicle according to the course identification information, and charges the account A characteristic transportation system.