Traffic prediction system, traffic prediction method and program

Abstract

To provide a traffic prediction system which efficiently predicts change of required time required for passage of a route when traffic volume of the route changes in accordance with behavioral change.SOLUTION: A traffic volume data acquisition unit 112 acquires traffic volume data. A required time acquisition unit 118 acquires an actual value of required time. A traffic volume calculation unit 120 calculates inflow traffic volume for every route by using the traffic volume data and the actual value of the required time. A traffic condition prediction unit 150 calculates a prediction value of the required time to the calculated inflow traffic volume and a prediction value of the required time when the inflow traffic volume is varied by using a preliminarily generated traffic model for every route. A variation calculation unit 160 calculates variation of the prediction value of the required time when the inflow traffic volume is varied for every route.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a traffic prediction system, a traffic prediction method, and a program, and more particularly to a traffic prediction system, a traffic prediction method, and a program for monitoring vehicle traffic. [Background technology]

[0002] There is a technology for predicting traffic in a traffic network (road) on which vehicles travel. For example, Patent Document 1 discloses a prediction calculation device that defines a road having multiple entrances and multiple exits as being formed by multiple links having a predetermined length, and predicts the movement status of multiple vehicles moving from the entrance to the exit for each link. In the prediction calculation device according to Patent Document 1, the entrance traffic volume prediction unit calculates the number of vehicles flowing in from the entrance for each entrance as the number of flowing vehicles based on traffic volume information indicating the traffic volume of vehicles observed on the road. The unexpected incident response unit estimates exits that the vehicle may select based on the obstruction information indicating an incident that may obstruct the movement of the vehicle, and generates corrected origin / end point information by multiplying standard origin / end point information indicating the traffic volume in a standard movement state from the entrance to the exit by a conversion rate generated based on the estimated exit. In addition, the reference situation calculation unit calculates the movement speed of the vehicle for each link based on the corrected origin / end point information. The prediction calculation unit calculates a section travel time to a destination that the vehicle will travel to by a predetermined time based on the calculated number of incoming vehicles and the calculated travel speed, and predicts the traffic conditions. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5523886 Summary of the Invention [Problem to be solved by the invention]

[0004] Traffic volume on a road (route) may change with a behavioral change such as a change in the mode of transportation from the entrance to the exit of a road (route) of a vehicle. In this case, it is desirable to efficiently predict the change in the time required to pass through the road (route) (travel time). Here, Patent Document 1 uses data (infrastructure data) collected by equipment (traffic counters, etc.) managed by the road administrator. However, it is not easy to obtain such data (infrastructure data) at a desired point. Therefore, the technology of Patent Document 1 may not be able to efficiently predict the change in travel time when traffic volume on a route changes with a behavioral change.

[0005] The present invention provides a traffic prediction system, a traffic prediction method, and a program that can efficiently predict changes in the time required to travel a route when the traffic volume on the route changes due to behavioral changes. [Means for solving the problem]

[0006] The traffic prediction system of the present invention includes a traffic volume data acquisition unit that acquires traffic volume data indicating the relationship between time and traffic volume at a specified point, a required time acquisition unit that acquires, for each of at least one route leading to the specified point, an actual value of the required time for a vehicle to travel from a reference point of the route to arrive at the specified point through the route, a traffic volume calculation unit that calculates an inflow traffic volume flowing into the route from the reference point using the traffic volume data and the actual value of the required time, a traffic condition prediction unit that calculates, for the route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance, and a change calculation unit that calculates an amount of change in the predicted value of the required time when the inflow traffic volume is changed for the route.

[0007] In addition, the traffic prediction method of the present invention acquires traffic volume data indicating the relationship between time and traffic volume at a specified point, acquires, for each of at least one route leading to the specified point, an actual value of the time required for a vehicle to travel from a reference point of the route to arrive at the specified point, calculates an inflow traffic volume flowing into the route from the reference point using the traffic volume data and the actual value of the required time, calculates, for the route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed using a traffic model generated in advance, and calculates, for the route, an amount of change in the predicted value of the required time when the inflow traffic volume is changed.

[0008] In addition, the program of the present invention causes a computer to execute the following steps: acquiring traffic volume data indicating the relationship between time and traffic volume at a specified point; acquiring, for each of at least one route leading to the specified point, an actual value of the time required for a vehicle to travel from a reference point of the route to arrive at the specified point via the route; calculating an inflow traffic volume flowing into the route from the reference point using the traffic volume data and the actual value of the required time; calculating, for the route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed using a traffic model generated in advance; and calculating, for the route, an amount of change in the predicted value of the required time when the inflow traffic volume is changed.

[0009] In the present invention, by being configured as described above, it is possible to predict the change in the required time when the inflow traffic volume is changed without acquiring infrastructure data. Therefore, the present invention makes it possible to efficiently predict the change in the required time to pass through a route when the traffic volume on the route changes with a behavioral change.

[0010] In a preferred embodiment, the required travel time acquisition unit acquires the actual value of the required travel time by using actual travel data obtained from each of a plurality of specific vehicles traveling along the route. The driving history data is obtained from a specific vehicle that can be managed by the system administrator. Therefore, it is easy for the system administrator to obtain the driving history data. Therefore, the present invention makes it possible to easily obtain the actual value of the required time.

[0011] In a preferred embodiment, the required time acquisition unit acquires an actual value of the required time for each of the multiple routes leading to the specified point, the traffic volume calculation unit calculates the inflow traffic volume for each of the multiple routes using the traffic volume data and the actual value of the required time, and the traffic condition prediction unit calculates, for each of the multiple routes, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, and calculates, for each of the multiple routes, an amount of change in the predicted value of the required time when the inflow traffic volume is changed. With this configuration, it is possible to predict which route will have a large change in the required time, and therefore to determine which route will be most effective in changing the behavior of the user.

[0012] In a further embodiment, the required time acquisition unit acquires an actual value of the required time using actual driving data obtained from each of a plurality of specific vehicles traveling on each of the plurality of routes, and the traffic volume calculation unit calculates the incoming traffic volume for each of the plurality of routes using the share of each route in the traffic volume in the traffic volume data, calculated based on the number of specific vehicles traveling on each of the plurality of routes. With this configuration, it is possible to calculate the inflow traffic volume of each route without acquiring infrastructure data.

[0013] In addition, preferably, the traffic volume calculation unit uses the share rate to calculate an outflow cumulative traffic volume, which is an accumulation of outflow traffic volumes, which are traffic volumes flowing out from each of the plurality of routes, among the traffic volumes in the traffic volume data, calculates an inflow cumulative traffic volume, which is an accumulation of the inflow traffic volumes, using the outflow cumulative traffic volume and the actual value of the required time, and calculates the inflow traffic volume for each hour of the day from the inflow cumulative traffic volume. With this configuration, it is possible to calculate the inflow traffic volume of each route without acquiring infrastructure data.

[0014] In addition, preferably, the traffic model is generated by adjusting parameters of the traffic model so as to reproduce the actual value of the required travel time when the inflow traffic volume is input to the traffic model. With this configuration, it is possible to accurately calculate a predicted value of the required travel time from the incoming traffic volume.

[0015] Also, preferably, the parameters of the traffic model include a bottleneck capacity for each route at each time of day. With this configuration, it is possible to calculate a predicted value of the required time that accurately reproduces the actual value of the required time. Therefore, the present invention makes it possible to accurately predict the required time and the outflow traffic volume. Effect of the Invention

[0016] According to the present invention, a traffic prediction system, a traffic prediction method, and a program can be provided that can efficiently predict changes in the time required to travel a route when the traffic volume on the route changes due to a change in behavior. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a diagram illustrating a traffic prediction system according to a first embodiment. [Diagram 2] FIG. 1 is a diagram illustrating a configuration of a traffic prediction device according to a first embodiment. [Diagram 3] 4 is a flowchart showing a traffic prediction method executed by the traffic prediction system according to the first embodiment. [Figure 4] 4 is a flowchart showing a traffic prediction method executed by the traffic prediction system according to the first embodiment. [Diagram 5] 4 is a flowchart showing a traffic prediction method executed by the traffic prediction system according to the first embodiment. [Figure 6] FIG. 2 is a diagram illustrating an example of a route according to the first embodiment. [Figure 7] FIG. 2 is a diagram illustrating traffic volume data according to the first embodiment. [Figure 8] FIG. 4 is a diagram for explaining a method for acquiring a required time according to the first embodiment; [Figure 9] FIG. 4 is a diagram for explaining the processing of a traffic volume calculation unit according to the first embodiment. [Figure 10] FIG. 2 is a diagram for explaining a bottleneck on a route in the traffic model according to the first embodiment. [Figure 11] 10 is a diagram illustrating an example of a bottleneck capacity adjusted when generating a traffic model according to the first embodiment. FIG. [Figure 12] FIG. 4 is a diagram illustrating a predicted value of a required travel time calculated by the traffic model according to the first embodiment. [Figure 13] FIG. 11 is a diagram comparing predicted values ​​of required time before and during execution of a measure according to the first embodiment. [Figure 14] FIG. 11 is a diagram comparing predicted values ​​of required time before and during execution of a measure according to the first embodiment. [Figure 15] FIG. 11 is a diagram comparing predicted values ​​of required time before and during execution of a measure according to the first embodiment. [Figure 16] FIG. 11 is a diagram comparing predicted values ​​of required time before and during execution of a measure according to the first embodiment. [Figure 17] FIG. 11 is a diagram illustrating a configuration of a traffic prediction device according to a second embodiment. [Figure 18] 11 is a flowchart showing a traffic prediction method executed by the traffic prediction system according to the second embodiment. [Figure 19] 11 is a flowchart showing a traffic prediction method executed by the traffic prediction system according to the second embodiment. [Figure 20] 13 is a diagram illustrating an example of a mixture rate and a total traffic volume according to the second embodiment. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] (Embodiment 1) Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that substantially the same components are given the same reference numerals. Note that in the following drawings, data such as graphs are shown as examples for use in explaining the embodiment, and therefore may not strictly correspond to each other.

[0019] 1 is a diagram showing a traffic prediction system 1 according to the first embodiment. The traffic prediction system 1 according to the first embodiment includes a traffic prediction device 100, a plurality of probe cars 20, and at least one traffic volume data detection device 50. The traffic prediction device 100 is communicatively connected to the probe cars 20 and the traffic volume data detection device 50 via a wired or wireless network 2.

[0020] The probe car 20 is a vehicle configured to transmit probe data to the traffic prediction device 100. The probe data is operation history data (driving history data) of the probe car 20. When the probe car 20 travels, an information processing device 22 mounted on the probe car 20 acquires the probe data by a sensor or the like mounted on the probe car 20. The information processing device 22 transmits the probe data to the traffic prediction device 100 via the network 2. Note that the probe data may be transmitted to a device other than the traffic prediction device 100. In this case, the traffic prediction device 100 receives (acquires) the probe data from the other device.

[0021] The probe data includes, for example, the identification information of the corresponding probe car 20, time, location information, section information (link information), speed information, traffic congestion information, etc. Section information (link information) is information about a section between certain points. Traffic congestion information can be detected, for example, by a car navigation system. The probe data makes it possible to know the time when the probe car 20 passed a certain point and the speed at that time. Alternatively, the probe data makes it possible to know the time (travel time) required for the probe car 20 to pass through a certain section in a certain time period. The probe data will be described in detail later.

[0022] The traffic volume data detection device 50 is configured to detect traffic volume at a certain fixed point (predetermined point). Here, the traffic volume data detection device 50 is managed by an administrator (system administrator) of the traffic prediction system 1. The "predetermined point" is, for example, an entrance to a facility that can be managed by the system administrator. The "predetermined point" may be, for example, an entrance to a parking lot of a facility that can be managed by the system administrator (facility administrator). In this case, the traffic volume data detection device 50 is installed near the entrance gate of the parking lot. The traffic volume data detection device 50 counts the number of vehicles entering the parking lot in association with the time. In this way, the traffic volume data detection device 50 detects the traffic volume at the entrance gate of the parking lot. The traffic volume data will be described in detail later.

[0023] The traffic prediction device 100 is, for example, a computer such as a server. The traffic prediction device 100 may be realized by cloud computing. As described later, the traffic prediction device 100 calculates the traffic volume of each of a plurality of routes ending at a predetermined point by using traffic volume data and probe data. Here, each of the plurality of routes starts from a predetermined reference point. Then, the traffic prediction device 100 predicts the change in the required time (travel time) required for a vehicle to pass through the route from the reference point to the predetermined point when the traffic volume is changed for each of the plurality of routes by using a traffic model generated in advance. Hereinafter, the required time (travel time) required for a vehicle to pass through the route from the reference point to arrive at the predetermined point may be simply referred to as the "required time of the route". The traffic prediction device 100 will be described in detail later. The above-mentioned "traffic model" is used to predict the required time of each route. This will be described in detail later.

[0024] FIG. 2 is a diagram showing a configuration of the traffic prediction device 100 according to the first embodiment. Also, FIGS. 3 to 5 are flowcharts showing a traffic prediction method executed by the traffic prediction system 1 according to the first embodiment. The traffic prediction device 100 according to the first embodiment has, as main hardware components, a CPU (Central Processing Unit) 102, a ROM (Read Only Memory) 104, a RAM (Random Access Memory) 106, and an interface unit 108 (IF; Interface). The CPU 102, the ROM 104, the RAM 106, and the interface unit 108 are connected to each other via a data bus or the like. Note that the information processing device 22 may also have a substantially similar configuration to the hardware configuration of the traffic prediction device 100.

[0025] The CPU 102 functions as a calculation device that performs control processing and calculation processing. The ROM 104 has a function for storing control programs and calculation programs executed by the CPU 102. The RAM 106 has a function for temporarily storing processing data and the like. The RAM 106 may have a database. In this way, the traffic prediction device 100 may realize a database. The interface unit 108 inputs and outputs signals to and from the outside via wired or wireless communication. The interface unit 108 also accepts data input operations by the user and displays information to the user.

[0026] As components showing functions, the traffic prediction device 100 according to the first embodiment has a route information storage unit 110, a traffic volume data acquisition unit 112, a probe data acquisition unit 114, a route share ratio calculation unit 116, and a required time acquisition unit 118. The traffic prediction device 100 according to the first embodiment has a traffic volume calculation unit 120, a parameter setting unit 128, and a traffic model generation unit 130. The traffic prediction device 100 according to the first embodiment has a change amount setting unit 140, a traffic state prediction unit 150, and a change amount calculation unit 160. The traffic volume calculation unit 120 according to the first embodiment has an outflow traffic volume calculation unit 122 and an inflow traffic volume calculation unit 124.

[0027] These components can be realized, for example, by the CPU 102 executing a program stored in the ROM 104. Also, each component may be realized by recording a necessary program in an arbitrary non-volatile recording medium and installing it as necessary. Note that each component is not limited to being realized by software as described above, but may be realized by hardware such as some kind of circuit element. Also, one or more of the above components may be realized by physically separate hardware. The same applies to other embodiments described later.

[0028] The route information storage unit 110 is configured to store route information, which is information about a plurality of routes that end at a predetermined point. The route information includes identification information (route identification information) of the route managed by the traffic prediction system 1, position information of a reference point (start point of the route) of the route, position information of an intermediate point (section) of the route, and position information of a predetermined point (end point of the route). The route information may also include identification information of the probe car 20 that is to travel along the route.

[0029] FIG. 6 is a diagram illustrating routes according to the first embodiment. Two routes R1 and R2 are shown in FIG. 6. Route R1 is a route from a reference point S1 to a predetermined point P as indicated by an arrow A1. Route R2 is a route from a reference point S2 to a predetermined point P as indicated by an arrow A2. For example, the predetermined point P is a predetermined facility. More specifically, the predetermined point P is a parking lot of a company. For example, routes R1 and R2 are routes that are used by the commuting vehicles (employee vehicles) of many employees of the company during their commute to work. The employee vehicles may be referred to as entering vehicles that are scheduled to enter the parking lot. The employee vehicles may also be referred to as target vehicles that are subject to monitoring in this embodiment.

[0030] Here, some of the many employee vehicles traveling on route R1 and route R2 are probe cars 20 (specific vehicles). The number of probe cars 20 traveling on route R1 and route R2 is determined according to the ratio of the number of many employee vehicles traveling on route R1 and route R2, respectively. In other words, the route is set so that the more employee vehicles (target vehicles) traveling on the route, the more probe cars 20 (specific vehicles) traveling on that route.

[0031] Hereinafter, the functions of the above-mentioned components will be described with reference to the flowcharts shown in Figs. 3 to 5. Fig. 3 is a flowchart showing a process for generating a traffic model according to the first embodiment. The traffic volume data acquisition unit 112 acquires traffic volume data from the traffic volume data detection device 50 (step S102). That is, the traffic volume data acquisition unit 112 is configured to acquire traffic volume data indicating the relationship between time and traffic volume at a predetermined point. The traffic volume data acquisition unit 112 may store the acquired traffic volume data in a database configured by the RAM 106.

[0032] Here, the traffic volume data is data indicating the relationship between time and the number of vehicles passing through a given point P per unit time at that time. Here, in this embodiment, the "time" does not need to indicate an exact time, but may be a time period within a predetermined period (for example, a time period every 5 minutes). Also, in the example of FIG. 6, the "traffic volume" in the traffic volume data is, for example, the number of vehicles entering a parking lot (number of vehicles entering a facility) per unit time.

[0033] FIG. 7 is a diagram illustrating traffic volume data according to the first embodiment. The rectangular dots in FIG. 7 indicate the time transition of the number of cars entering the parking lot per 5 minutes as traffic volume. The circular dots in FIG. 7 indicate the time transition of the accumulated traffic volume. The accumulated traffic volume corresponds to the accumulation of traffic volume per hour. In FIG. 7, the horizontal axis indicates time, the vertical axis on the left indicates traffic volume (traffic volume per unit time), and the vertical axis on the right indicates the accumulated traffic volume.

[0034] Here, the traffic volume data indicates the traffic volume at a predetermined point P, which is the end point of each route. Therefore, the traffic volume indicated by the traffic volume data corresponds to the total number of vehicles (employee vehicles) traveling on each route. Here, if Fig. 6 and Fig. 7 correspond to each other, the traffic volume data in Fig. 7 corresponds to the total number of vehicles that have traveled along route R1 and arrived at the predetermined point P and the number of vehicles that have traveled along route R2 and arrived at the predetermined point P.

[0035] The probe data acquisition unit 114 acquires probe data from the probe cars 20 traveling along each route (step S104). That is, the probe data acquisition unit 114 is configured to acquire probe data from each of the multiple probe cars 20 (specific vehicles) traveling along the route. The probe data acquisition unit 114 may store the acquired probe data in a database configured by the RAM 106. As described above, the probe data includes identification information of the corresponding probe car 20, time, position information, section information (link information), speed information, traffic congestion information, and the like. Furthermore, the probe data may include route identification information of the route traveled by the corresponding probe car 20.

[0036] The route share rate calculation unit 116 calculates the route share rate by using the probe data (step S106). That is, the route share rate calculation unit 116 is configured to calculate the route share rate by using the probe data. Here, the route share rate indicates the ratio of the traffic volume in the traffic volume data acquired in S102 that is allocated to each route.

[0037] Specifically, the route share rate calculation unit 116 calculates the share rate of each route in the traffic volume data based on the number of specific vehicles traveling on each of the multiple routes. More specifically, the route share rate calculation unit 116 calculates the ratio of the number of probe cars 20 traveling on each route to the total number of probe cars 20 arriving at the specified point P as the share rate of each route. For example, it is assumed that the total number of probe cars 20 arriving at the specified point P is 10, the number of probe cars 20 traveling on route R1 is 7, and the number of probe cars 20 traveling on route R2 is 3. In this case, the route share rate calculation unit 116 calculates the route share rate of route R1 to be 70%, and the route share rate of route R2 to be 30%.

[0038] The required time acquisition unit 118 acquires the actual value of the required time (step S108). That is, the required time acquisition unit 118 is configured to acquire, for each route, the actual value (actual travel time) of the required time for the vehicle to arrive at the specified point P from a reference point S of at least one route heading to the specified point P along the route (for each time period). Specifically, the required time acquisition unit 118 acquires (calculates) the required time using multiple pieces of probe data. More specifically, the required time acquisition unit 118 calculates the required time for each route for each time period using probe data acquired from a probe car 20 traveling along the route.

[0039] FIG. 8 is a diagram for explaining a method of acquiring a required time according to the first embodiment. The upper diagram in FIG. 8 is a contour diagram showing the average speed in each time period for each section on the route. The lower diagram in FIG. 8 is a graph showing the actual value of the required time (travel time) in each time period corresponding to the contour diagram. Here, it is assumed that FIG. 8 shows the contour diagram and required time for route R1. Note that in the following explanation, the processing for route R1 will be described, but the same processing is performed for route R2.

[0040] The horizontal direction of the contour diagram and graph shown in FIG. 8 indicates time (time period). The vertical direction of the contour diagram indicates each section (link) of the route. In the vertical direction, the lower side is the reference point S1 and the upper side is the specified point P. Therefore, in the contour diagram, the traveling direction of route R1 is upward. In the example of FIG. 8, route R1 has 13 predetermined sections #1 to #13 from reference point S1 to specified point P. Here, the position of each section is predetermined, and therefore the distance of each section is also predetermined.

[0041] The hatching of each section in each time period corresponds to the average (harmonic mean) of the speed of the probe cars 20 that entered that section in that time period. For example, in "Section #1" in time period "6:00", it is shown that the average speed of the probe cars 20 that entered Section #1 from 6:00 to 6:15 was 30 km / h or more. Also, in "Section #13" in time period "7:30", it is shown that the average speed of the probe cars 20 that entered Section #13 from 7:30 to 7:45 was 15.0 km / h to 19.9 km / h.

[0042] The required time acquisition unit 118 calculates the average speed of the probe car 20 in each section in each time period for the route R1. Then, the required time acquisition unit 118 calculates the average travel time (average required time) of the probe car 20 in each section in each time period from the distance and average speed of each section. For example, if the average speed of "Section #13" in the time period "7:30" is V1 [km / h] and the distance of Section #13 is L1 [km], the average travel time of "Section #13" in the time period "7:30" is L1 / V1 [h].

[0043] Then, the required time acquisition unit 118 calculates the required time (travel time) of the route R1 in each time period by summing up the average travel times of the sections #1 to #13. As a result, a graph showing the actual value of the required time in each time period is obtained, as shown in the lower diagram of FIG. 8. In the lower diagram of FIG. 8, the solid line indicates the time change of the actual value of the required time of the route R1. For example, the required time of the route R1 in the time period "6:00" is about 5.5 minutes. In addition, the required time of the route R1 in the time period "7:30" is about 11 minutes. In addition, the required time of the route R1 in the time period "9:45" is about 7 minutes. Therefore, since the required time of the route R1 in the time period "7:30" is longer than the required time in other time periods, it can be estimated that there is a possibility that congestion occurs on the route R1 in the time period "7:30". In addition, in the lower diagram of FIG. 8, the dashed line indicates the time change of the free flow travel time (the required time when there is no congestion) of the route R1. The method for calculating the free flow travel time will be described later.

[0044] The traffic volume calculation unit 120 calculates the inflow traffic volume for each route using the traffic volume data and the actual value of the required time (step S110). Here, the inflow traffic volume (generated traffic volume) for each route is the traffic volume (inflow traffic volume) that flows into the route from the reference point S for each route. In other words, the traffic volume calculation unit 120 calculates the inflow traffic volume for each time (for each time period) that flows into the route from the reference point using the traffic volume data and the actual value of the required time.

[0045] FIG. 4 is a flowchart showing the processing of the traffic volume calculation unit 120 according to the first embodiment. FIG. 9 is a diagram for explaining the processing of the traffic volume calculation unit 120 according to the first embodiment. FIG. 9 is a graph showing the traffic volume of the route R1 for each time (for each time period). In FIG. 9, the horizontal axis shows the time, the vertical axis on the left shows the traffic volume (unit time traffic volume), and the vertical axis on the right shows the cumulative traffic volume. The dots shown as squares in FIG. 9 show the time transition of the outflow traffic volume (unit time traffic volume) of the route R1. The dots shown as circles in FIG. 9 show the time transition of the inflow traffic volume (unit time traffic volume) of the route R1. The solid line in FIG. 9 shows the time transition of the outflow cumulative traffic volume (cumulative outflow traffic volume) of the route R1. The dashed line in FIG. 9 shows the time transition of the inflow cumulative traffic volume (cumulative inflow traffic volume) of the route R1.

[0046] The outflow traffic volume of route R1 indicates the traffic volume of vehicles passing through route R1 and exiting from a specified point P (i.e., entering the parking lot from the specified point P). In other words, the outflow traffic volume of route R1 indicates the traffic volume of vehicles passing through route R1 and entering the parking lot from the specified point P. Furthermore, the outflow cumulative traffic volume indicates the hourly accumulation of the outflow traffic volume. Furthermore, the inflow cumulative traffic volume indicates the hourly accumulation of the inflow traffic volume. The graph illustrated in FIG. 9 can be obtained by processing of the traffic volume calculation unit 120.

[0047] The outflow traffic volume calculation unit 122 calculates the outflow cumulative traffic volume for each route (step S112). Specifically, the outflow traffic volume calculation unit 122 calculates the outflow cumulative traffic volume for each route using the route share rate calculated in the process of S106 and the traffic volume data. More specifically, the outflow traffic volume calculation unit 122 calculates the outflow traffic volume for each route by multiplying the traffic volume in the traffic volume data by the route share rate of the route. For example, when the route share rate of route R1 is 70%, the outflow traffic volume for route R1 is calculated by multiplying the traffic volume in FIG. 7 by 0.7. As a result, the outflow traffic volume as shown by the square dots in FIG. 9 is obtained.

[0048] Then, the outflow traffic volume calculation unit 122 calculates the outflow cumulative traffic volume for each route by accumulating this outflow traffic volume for each route. As a result, the outflow cumulative traffic volume is obtained as shown by the solid line in Fig. 9. Note that, when the cumulative traffic volume of the traffic volume data at the predetermined point P (Fig. 7) is obtained, the outflow traffic volume calculation unit 122 may calculate the outflow cumulative traffic volume for each route by multiplying the cumulative traffic volume of the traffic volume data by the route share rate of the route.

[0049] The inflow traffic volume calculation unit 124 calculates the inflow cumulative traffic volume for each route (step S114). Specifically, the inflow traffic volume calculation unit 124 calculates the inflow cumulative traffic volume for each route using the outflow cumulative traffic volume and the actual value of the required time for that route. More specifically, the inflow traffic volume calculation unit 124 moves the outflow cumulative traffic volume in the past direction (leftward in FIG. 9) on the time axis for each time period by the actual value of the required time corresponding to that time period. In this way, the inflow traffic volume calculation unit 124 calculates the inflow cumulative traffic volume.

[0050] For example, in the example of FIG. 8, the position of the inflow cumulative traffic volume relative to the outflow cumulative traffic volume shifts to the left by about 5.5 minutes in the time slot of "6:00", by about 6 minutes in the time slot of "6:15", and by about 6.5 minutes in the time slot of "6:30". Similarly, the position of the inflow cumulative traffic volume relative to the outflow cumulative traffic volume shifts to the left by about 7.5 minutes in the time slot of "6:45" to "7:00", and by about 11 minutes in the time slot of "7:15" to "8:00". Similarly, the position of the inflow cumulative traffic volume relative to the outflow cumulative traffic volume shifts to the left by about 8.5 minutes in the time slot of "8:15", and by about 7 minutes in the time slot of "8:30" to "9:45".

[0051] The inflow traffic volume calculation unit 124 calculates the inflow traffic volume (unit time traffic volume) for each route from the inflow cumulative traffic volume (step S116). Specifically, the inflow traffic volume calculation unit 124 calculates the inflow traffic volume by replotting the inflow cumulative traffic volume to values ​​for each unit time (for example, every 5 minutes). In other words, the inflow traffic volume calculation unit 124 calculates the inflow traffic volume for each time (for each time slot) by breaking down the inflow cumulative traffic volume into values ​​for each unit time. More specifically, the inflow traffic volume calculation unit 124 calculates the inflow traffic volume for each time slot by calculating the difference between the value of the inflow cumulative traffic volume for a certain time slot and the value for the previous time slot.

[0052] The traffic model generation unit 130 generates a traffic model for each route (step S120 in FIG. 3). The traffic model is generated by adjusting the parameters of the traffic model so that the actual value of the required time obtained in the process of S108 is reproduced when the inflow traffic volume calculated in the process of S110 is input to the traffic model. Here, the traffic model is generated for each route. The traffic model is configured to output a predicted value of the outflow traffic volume and a predicted value of the required time for a route when the inflow traffic volume of the corresponding route is input. Furthermore, the traffic model is a model that takes into account vehicle queues at bottlenecks of the route.

[0053] The parameter setting unit 128 sets parameters of the traffic model. Here, the parameters of the traffic model are, for example, a free flow travel time and a bottleneck capacity. The parameter setting unit 128 sets the free flow travel time and the bottleneck capacity. The bottleneck capacity will be described later. Here, the free flow travel time and the bottleneck capacity are not constant on the time axis. That is, the free flow travel time can be a different value for each time (time period). Similarly, the bottleneck capacity can be a different value for each time (time period). The free flow travel time and the bottleneck capacity differ for each time (time period), for example, because the interval between lights on the traffic lights differs for each time period, the number of vehicles turning right or left changes due to an increase or decrease in the number of pedestrians, and the proportion of large vehicles entering the route changes.

[0054] A method for setting the free flow travel time will be described with reference to FIG. 8. The free flow travel time for a certain route is the required time (travel time) when no congestion occurs on that route. Here, for example, if a predetermined number of sections in which the average speed is less than a predetermined speed continue, it may be determined that congestion occurs on that route. In FIG. 8, in the time period after "8:00" (the time period surrounded by the two-dot chain line in the figure below), there are not three or more consecutive sections in which the speed is less than 30 km / h. Therefore, it may be determined that no congestion occurs in this time period. Therefore, the parameter setting unit 128 sets the free flow travel time for the time period after "8:00" in FIG. 8 to the average required time (travel time) for this time period (about 7 minutes).

[0055] Also, in the time period from "7:00" to "8:30" (the time period surrounded by the dashed line in the figure below), there are three or more consecutive sections where the speed is less than 30 km / h. Therefore, it may be determined that congestion occurs in this time period. Therefore, the parameter setting unit 128 sets the free flow travel time in the time period from "7:00" to "8:30" in FIG. 8 to the free flow travel time when no congestion occurs, that is, the free flow travel time in the time period after "8:00" (about 7 minutes). Furthermore, in the time period before "7:00" (the time period surrounded by the dashed line in the figure below), the traffic volume is gradually approaching a critical state from a low traffic volume state, and the free flow travel time is increasing. Therefore, the parameter setting unit 128 sets the free flow travel time in the time period before "7:00" in FIG. 8 to the average required time (travel time) in this time period.

[0056] FIG. 10 is a diagram for explaining a bottleneck in a route in the traffic model according to the first embodiment. Generally, in traffic, a bottleneck is a point that impedes traffic flow. That is, a bottleneck is a point with a small traffic capacity. And the bottleneck capacity is the traffic capacity at the bottleneck. For example, a bottleneck may occur at an intersection, a railroad crossing, a junction / lane reduction point, a curve, a narrow road, an uphill grade, a road construction / traffic regulation point, a site entrance, a parking entrance, and inside a parking lot. Here, the traffic capacity of a route is determined by a bottleneck with a relatively small capacity. That is, if the bottleneck capacity upstream is smaller than that downstream, congestion will occur at the upstream bottleneck, but it is highly likely that congestion will not occur at the downstream bottleneck. Therefore, in the traffic model according to the present embodiment, it is assumed that the bottleneck in the route is set at the most downstream as shown in FIG. 10. Therefore, in the traffic model, the distance between the bottleneck and the specified point P is ignored. In addition, the traffic model assumes that a vehicle travels from a reference point S to just before a predetermined point P (bottleneck) with a free flow travel time, and remains at the predetermined point P (bottleneck).

[0057] Here, an example of the traffic model is shown below. The required time for route k at each time t is T k (t), and the outflow traffic volume is d k(t). In this case, the required time is T k (t) is expressed by the following formula 1. In the following explanation of the formula, for the formula with a bar "-" above the letter X, it will be written as "X - " is sometimes written.

number

[0058] Here, q - k,t is the bottleneck capacity of route k at time t. As described above with reference to Fig. 10, in the traffic model according to this embodiment, a bottleneck is set at the most downstream position (predetermined point P) of route k.

[0059] Also, T - k,t is the free-stream travel time for route k at time t. T - k,t As described above, A can be set in advance by the parameter setting unit 128. k (t) is the cumulative inflow traffic volume of route k at time t, as shown in the following formula 2. Note that t' indicates the processing time before time t. For example, if the required time T k (t) and outflow traffic volume d k When calculating (t), t' = t-5 [minutes].

number

[0060] In addition, in Equation 2, the boundary condition is A k (-T - k,0 )=0. Also, a k (t) is the inflow traffic volume of route k at time t. k (t) corresponds to the inflow traffic volume calculated in the process of S110 (S116). k (t) is input into the traffic model.

[0061] Also, Dk (t) is the cumulative outflow traffic volume of route k at time t, as shown in Equation 3 below.

number

[0062] In addition, in Equation 3, the boundary condition is D k (0) = 0. Also, d k (t) is the outflow traffic volume of route k at time t, as shown in Equation 4 below.

number

[0063] Also, a k (tT - k,t ) is the free-stream travel time T - k,t This shows the traffic volume that flowed into route k from the reference point S when going back only a few meters. In this traffic model, it is assumed that the travel time from the reference point S to the specified point P (bottleneck) is free flow. Therefore, a k (tT - k,t ) corresponds to the traffic volume of vehicles arriving at the bottleneck (predetermined point P) at time t. Similarly, A k (tT - k,t ) is the free-stream travel time T - k,t The cumulative traffic volume that flowed from the reference point S to the route k when going back by 100 km is shown. k (tT - k,t ) corresponds to the cumulative traffic volume of vehicles arriving at the bottleneck (predetermined point P) at time t.

[0064] In addition, the upper part of the right side of Equation 4 is A k (tT - k,t )=D k If (t), then d k (t)=a k (tT -k,t ) and A k (tT - k,t )=D k When the time (t) is reached, it means that there is no congestion (queue) at the bottleneck (predetermined point P). Therefore, at time (tT - k,t ) the inflow traffic volume a k (tT - k,t ) all flow out of path k at time t. Therefore, d k (t)=a k (tT - k,t In this case, the time (tT - k,t ) the inflow traffic volume a k (tT - k,t ) is the bottleneck capacity q at time t. - k,t Therefore, the inflow traffic volume a k (tT - k,t ) all flow out of path k at time t.

[0065] In addition, the lower part of Equation 4 is A k (tT - k,t )>D k If (t), then d k (t)=q - k,t And, A k (tT - k,t )>D k When the time (t) is reached, it means that a queue is occurring at the bottleneck (a specific point P). - k,t ) the inflow traffic volume a k (tT - k,t) does not flow out of route k at time t, but some (or all of them if the queue is already large) are stuck at the bottleneck. Then, the traffic volume corresponding to the stuck queue is equal to the bottleneck capacity q - k,t If it exceeds d, the outflow traffic volume k (t) is the bottleneck capacity q - k,t It becomes.

[0066] In addition, in the above formula 1, "A k (tT - k,t )-D k "(t)" means the amount of vehicles in the queue (number of vehicles). Therefore, the second term on the right side means the time spent in the queue (stay time). Therefore, Equation 1 expresses the time required for route k at time t, T k (t) is the free flow travel time T - k,t and residence time.

[0067] The traffic model generation unit 130 inputs the inflow traffic volume calculated in the process of S110 into the traffic model represented by the above-mentioned formulas 1 to 4 for each route. Then, the traffic model generation unit 130 performs the calculations of formulas 1 to 4 in order from t=0, thereby obtaining a predicted value T k Then, the traffic model generation unit 130 calculates the predicted value T k Then, the curve fitting is performed between (t) and the actual value of the required time (lower graph of Fig. 8). Then, the predicted value of the required time T k The bottleneck capacity q is fitted so that (t) fits the actual travel time. - k,t (Bottleneck capacity parameter) is adjusted. For example, the estimated time required at a certain time t is T k If (t) is significantly different from the actual required time, the bottleneck capacity q corresponding to that time t - k,t Just adjust the following.

[0068] FIG. 11 is a diagram illustrating a bottleneck capacity adjusted when generating a traffic model according to the first embodiment. FIG. 12 is a diagram illustrating a predicted value of a required time calculated by the traffic model according to the first embodiment. FIG. 11 and FIG. 12 respectively show a bottleneck capacity and a required time of route R1. In FIG. 11, the horizontal axis shows time, and the vertical axis shows a value of the bottleneck capacity. The dashed line in FIG. 11 shows a time-dependent change in the bottleneck capacity. In FIG. 12, the horizontal axis shows time, and the vertical axis shows the required time (travel time). In FIG. 12, the solid line shows a time-dependent change in the predicted value of the required time, and the dashed line shows a time-dependent change in the actual value of the required time. The dashed line shows a time-dependent change in the free flow travel time.

[0069] For example, the traffic model in FIG. 12 may use the bottleneck capacity illustrated in FIG. 11 as a parameter. As illustrated in FIG. 12, the predicted value of the required time calculated by the traffic model generated by the traffic model generation unit 130 generally reproduces the actual value of the required time well. As illustrated in FIG. 11, the bottleneck capacity is not constant for all time, but is a different value for each time. In other words, the bottleneck capacity is a parameter for each route for each time. In this way, by configuring the bottleneck capacity to differ for each time, the traffic model can calculate a predicted value of the required time that reproduces the actual value of the required time well. Therefore, in this embodiment, the traffic model defined by the above formula is used to calculate the required time T for route k. k (t) and outflow traffic volume d k (t) can be predicted with high accuracy.

[0070] Furthermore, in this embodiment, the traffic model is used to calculate the required time T k Since it is possible to accurately predict (t), it is possible to accurately calculate the predicted value of the required time when the inflow traffic volume is changed. Therefore, in this embodiment, it is possible to accurately calculate the change in the predicted value of the required time when the inflow traffic volume is changed. This will be described in detail below.

[0071] 5 is a flowchart showing a process of calculating the change in the predicted value of the required time when the inflow traffic volume is changed, using the traffic model according to the first embodiment. Here, "changing the inflow traffic volume" is performed in order to evaluate the implementation of a measure (behavioral change) for reducing traffic congestion. In other words, the traffic prediction device 100 calculates the change in the required time when a certain measure is implemented, using the inflow traffic volume that takes into account the change in the inflow traffic volume when the measure is implemented.

[0072] Steps S132 to S140 are substantially the same as steps S102 to S110 in Fig. 3, and therefore will not be described here. If the inflow traffic volumes for each route generated in the traffic model generation process (Fig. 3) are also used in the process in Fig. 5, steps S132 to S140 may be omitted.

[0073] The change amount setting unit 140 sets the change amount of the inflow traffic volume (step S142). Specifically, the change amount setting unit 140 sets the change amount of the inflow traffic volume corresponding to the assumed measure. An example of the measure is to convert X% of employee vehicles (target vehicles) traveling on the route to be evaluated to bus commuting such as a shuttle bus (transportation means conversion). Another example of the measure is to convert X% of employee vehicles (target vehicles) traveling during a time period with high traffic volume (peak time period) to a time period outside the peak time period (off-peak commuting). For example, in the case of the measure "convert 30% of employee vehicles to bus commuting", the change amount setting unit 140 may reduce the inflow traffic volume by 30% throughout all time periods. That is, the change amount setting unit 140 multiplies the inflow traffic volume by 0.7 throughout all time periods. Also, for example, in the case of the measure "convert 30% of employee vehicles to bus commuting", the change amount setting unit 140 may reduce the inflow traffic volume during a congestion time period (described later) by 30%. Also, for example, in the case of a policy of "diverting 30% of employee vehicles traveling during peak hours to times outside of peak hours," the change amount setting unit 140 may move 30% of the incoming traffic volume during peak hours to times outside of peak hours.

[0074] The traffic condition prediction unit 150 calculates the predicted value of the required time (step S150). That is, the traffic condition prediction unit 150 calculates the predicted value of the required time for the inflow traffic volume calculated in S140 and the predicted value of the required time when the inflow traffic volume is changed for each route by using the traffic model generated in advance in S120. Specifically, in the process of S120, the parameters of the traffic model (free flow travel time and bottleneck capacity) are determined. Then, the traffic condition prediction unit 150 calculates the predicted value of the required time for each time period before the implementation of the measure by inputting the inflow traffic volume for each time period calculated in the process of S140 into the traffic model whose parameters have been determined. Similarly, the traffic condition prediction unit 150 calculates the predicted value of the required time for each time period when the inflow traffic volume is changed (i.e., when the measure is implemented) by inputting the inflow traffic volume for each time period that takes into account the change amount set in the process of S142 into the traffic model whose parameters have been determined.

[0075] The change amount calculation unit 160 calculates the change amount of the required time (step S160). That is, the change amount calculation unit 160 calculates the change amount of the predicted value of the required time when the inflow traffic volume is changed for each route. Specifically, the change amount calculation unit 160 calculates the difference between the predicted value of the required time for the inflow traffic volume before the change (before the implementation of the measure) and the predicted value of the required time when the inflow traffic volume is changed (when the measure is implemented). For example, the change amount (difference) may be the difference between the peak of the predicted value of the required time before the implementation of the measure and the peak of the predicted value of the required time when the measure is implemented. Also, for example, the change amount (difference) may be the difference between the average of the predicted value of the required time before the implementation of the measure and the average of the predicted value of the required time when the measure is implemented. Also, for example, the change amount (difference) may be the difference between the length of the congestion time period in the predicted value of the required time before the implementation of the measure and the length of the congestion time period in the predicted value of the required time when the measure is implemented. Here, the congestion time period may be a time period in which the predicted value of the required time exceeds the free flow travel time.

[0076] Also, for example, the amount of change (difference) may be the difference between the area of ​​the region defined by the curve of the predicted value of the required time before the implementation of the measure and the area of ​​the region defined by the curve of the predicted value of the required time when the measure is implemented. Here, the "area of ​​the region defined by the curve of the predicted value of the required time" may be the value obtained by integrating the predicted value of the required time over all time periods (i.e., the area between the curve of the predicted value of the required time and the horizontal axis). Alternatively, the "area of ​​the region defined by the curve of the predicted value of the required time" may be the area between the curve of the predicted value of the required time and the curve of the free flow travel time.

[0077] If the traffic prediction device 100 has not completed the processes of S142 to S160 for all measures (NO in step S170), the process returns to S142. The traffic prediction device 100 then performs the processes of S142 to S160 for other measures for which the processes have not been completed. On the other hand, if the traffic prediction device 100 has completed the processes of S142 to S160 for all measures (YES in S170), the process ends.

[0078] 13 to 16 are diagrams comparing the predicted travel time before and after a measure is implemented according to the first embodiment. In Figs. 13 to 16, the dashed lines indicate the time progression of the predicted travel time when no measure is implemented (i.e., when the conversion rate is 0%). The solid lines indicate the time progression of the predicted travel time when a measure is implemented. The dashed and dotted lines indicate the time progression of the free flow travel time. The horizontal axis indicates time, and the vertical axis on the left indicates travel time (required time) [seconds].

[0079] 13 to 14 show the predicted travel time when the measure "transportation mode change" is implemented for route R1. In FIG. 13 to 14, the square dots show the hourly change in the number of vehicles that were changed from private cars to buses at each time, and the vertical axis on the right shows the number of vehicles changed. FIG. 13 shows a comparison of the travel time when the measure "change 5% of employee vehicles to buses for commuting" is implemented and the travel time before the measure is implemented. FIG. 14 shows a comparison of the travel time when the measure "change 30% of employee vehicles to buses for commuting" is implemented and the travel time before the measure is implemented. As illustrated in FIG. 13, with a change rate of 5%, the change in the travel time (travel time) during peak hours is -0.4 minutes. On the other hand, as illustrated in FIG. 14, with a change rate of 30%, the change in the travel time (travel time) during peak hours is -2.1 minutes. Therefore, the manager can effectively evaluate the measures "convert 5% of employee vehicles to bus commuting" and "convert 30% of employee vehicles to bus commuting".

[0080] 15 and 16 show predictions of the required time when the measure "off-peak commuting" is implemented for route R1. FIG. 15 shows a comparison between the required time when the measure "divert 5% of employee vehicles traveling during peak hours to times outside the peak hours" is implemented and the required time before the measure is implemented. FIG. 16 shows a comparison between the required time when the measure "divert 30% of employee vehicles traveling during peak hours to times outside the peak hours" is implemented and the required time before the measure is implemented. Here, in the examples of FIG. 15 and FIG. 16, the peak hours are set to one hour from 6:40 to 7:40. Employee vehicles corresponding to the first half of the peak hours (6:40 to 7:10) are set to depart 15 minutes earlier, and employee vehicles corresponding to the second half of the peak hours (7:10 to 7:40) are set to depart 15 minutes later.

[0081] As illustrated in FIG. 15, with a diversion rate of 5%, the change in required time (travel time) during peak hours is -0.4 minutes. On the other hand, as illustrated in FIG. 16, with a diversion rate of 30%, the change in required time (travel time) during peak hours is -2.4 minutes. Therefore, the manager can effectively evaluate the measures "divert 5% of employee vehicles traveling during peak hours to times outside of peak hours" and "divert 30% of employee vehicles traveling during peak hours to times outside of peak hours."

[0082] When a manager (system manager) of a facility corresponding to a given point P predicts the traffic of target vehicles around the facility, he or she may want to predict how much congestion will be alleviated and how much travel time will be shortened due to changes in the behavior of the target vehicles. Here, traffic volume data is required to predict the traffic state, but generally, it is often difficult to obtain infrastructure data such as traffic counter information.

[0083] The traffic prediction system 1 according to the present embodiment is configured to calculate the inflow traffic volume of each route from the traffic volume data at a predetermined point P and the actual value of the required time. The traffic prediction system 1 according to the present embodiment is configured to calculate, for each route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance. The traffic prediction system 1 according to the present embodiment is configured to calculate, for each route, a change in the predicted value of the required time when the inflow traffic volume is changed. With this configuration, it is possible to predict the change in the required time when the inflow traffic volume is changed without acquiring infrastructure data. Therefore, the traffic prediction system 1 according to the present embodiment can efficiently predict the change in the required time required to pass through the route when the traffic volume of the route changes due to behavioral change.

[0084] Moreover, the traffic prediction system 1 according to the present embodiment is configured to acquire the actual value of the required time by using probe data (traveling record data) acquired from each of a plurality of probe cars passing through the route. Here, the probe data is acquired from the probe cars 20 that can be managed by the system administrator. Therefore, it is easy for the system administrator to acquire the probe data. Therefore, the traffic prediction system 1 according to the present embodiment can easily acquire the actual value of the required time.

[0085] Moreover, the traffic prediction system 1 according to the present embodiment is configured to acquire the actual value of the required time for each of a plurality of routes, calculate the inflow traffic volume, and calculate the predicted value of the required time and the predicted value of the required time when the inflow traffic volume is changed. The traffic prediction system 1 according to the present embodiment is configured to calculate the amount of change in the predicted value of the required time when the inflow traffic volume is changed for each of a plurality of routes. With this configuration, it is possible to predict which route has the largest change in the required time. Therefore, it is possible to determine the route on which behavioral modification is highly effective. This makes it possible to proactively implement behavioral modification measures for routes on which behavioral modification is highly effective.

[0086] Moreover, the traffic prediction system 1 according to the present embodiment is configured to calculate the inflow traffic volume of each of the multiple routes using the share of each route in the traffic volume data, which is calculated based on the number of probe cars traveling on each of the multiple routes. With this configuration, it is possible to calculate the inflow traffic volume of each route without acquiring infrastructure data such as traffic counter information.

[0087] Moreover, the traffic prediction system 1 according to the present embodiment is configured to calculate the outflow cumulative traffic volume of each of a plurality of routes using the share rate, calculate the inflow cumulative traffic volume using the outflow cumulative traffic volume and the actual value of the required time, and calculate the inflow traffic volume from the inflow cumulative traffic volume. With this configuration, it becomes possible to calculate the inflow traffic volume of each route without acquiring infrastructure data such as traffic counter information.

[0088] In addition, in the traffic prediction system 1 according to the present embodiment, the traffic model is configured to be generated by adjusting the parameters of the traffic model so that the actual value of the required time is reproduced when the inflow traffic volume is input to the traffic model. With this configuration, it becomes possible to accurately calculate the predicted value of the required time from the inflow traffic volume.

[0089] In addition, in the traffic prediction system 1 according to the present embodiment, the parameters of the traffic model are configured to include the bottleneck capacity of each route at each time. With this configuration, it is possible to calculate a predicted value of the required time that accurately reproduces the actual value of the required time. Therefore, in this embodiment, it is possible to accurately predict the required time and outflow traffic volume.

[0090] (Embodiment 2) Next, the second embodiment will be described with reference to the drawings. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In addition, in each drawing, the same elements are given the same symbols, and repeated explanations are omitted as necessary. Note that the system configuration according to the second embodiment is substantially the same as that shown in FIG. 1, so explanations are omitted. The second embodiment differs from the first embodiment in terms of the cases where infrastructure data can be acquired.

[0091] Fig. 17 is a diagram showing a configuration of a traffic prediction device 100 according to the embodiment 2. Figs. 18 and 19 are flowcharts showing a traffic prediction method executed by the traffic prediction system 1 according to the embodiment 2. As in the embodiment 1, the traffic prediction device 100 according to the embodiment 2 has a CPU 102, a ROM 104, a RAM 106, and an interface unit 108 as main hardware components.

[0092] Similarly to the first embodiment, the traffic prediction device 100 according to the second embodiment includes a route information storage unit 110, a traffic volume data acquisition unit 112, a probe data acquisition unit 114, a route share calculation unit 116, and a required time acquisition unit 118 as components indicating functions. The traffic prediction device 100 according to the second embodiment includes a traffic volume calculation unit 120, a parameter setting unit 128, and a traffic model generation unit 130. The traffic prediction device 100 according to the second embodiment includes a change amount setting unit 140, a traffic state prediction unit 150, and a change amount calculation unit 160. The traffic prediction device 100 according to the second embodiment further includes an infrastructure data acquisition unit 210, a mixture rate calculation unit 212, and a total traffic volume calculation unit 220.

[0093] In addition, in the flowchart shown in Fig. 18, the processes of S202 to S210 are substantially similar to the processes of S102 to S110 shown in Fig. 3, respectively, and therefore description thereof will be omitted. The infrastructure data acquisition unit 210 acquires infrastructure data (step S212). Specifically, the infrastructure data acquisition unit 210 acquires infrastructure data collected from facilities, etc. managed by a road administrator (e.g., an administrative agency, etc.) different from the system administrator. The infrastructure data is, for example, data collected by a traffic counter, etc. (traffic counter data).

[0094] More specifically, the infrastructure data acquisition unit 210 acquires infrastructure data indicating traffic volume before and after a predetermined point P in the same direction as the traveling direction of the vehicle on each route. For example, for route R1 illustrated in Fig. 6, the infrastructure data acquisition unit 210 acquires infrastructure data (traffic counter data) from a traffic counter that is installed on the side of a reference point S1 with respect to the predetermined point P and measures traffic volume in the same direction as the traveling direction of route R1. In addition, the infrastructure data acquisition unit 210 acquires infrastructure data (traffic counter data) from a traffic counter that is installed on the opposite side of the reference point S1 with respect to the predetermined point P and measures traffic volume in the same direction as the traveling direction of route R1.

[0095] The inclusion rate calculation unit 212 calculates the inclusion rate of the target vehicle with respect to the total traffic volume (step S214). Here, the "total traffic volume" indicates the total traffic volume of each route. In other words, the total traffic volume indicates the traffic volume of vehicles related to the target vehicle and general vehicles other than the target vehicle for each route. The inclusion rate indicates the traffic volume of the target vehicle (the number of vehicles entering the parking lot per unit time) with respect to the total traffic volume. Specifically, for each route, the inclusion rate calculation unit 212 calculates, as the inclusion rate, the ratio of the number of vehicles entering the parking lot per unit time indicated by the traffic volume data to the traffic volume indicated by the infrastructure data acquired in S212 for each time. Here, as will be described later with reference to FIG. 20, the inclusion rate changes with the passage of time.

[0096] The total traffic volume calculation unit 220 calculates the total traffic volume (step S216). Specifically, the total traffic volume calculation unit 220 calculates the total traffic volume using the mixing rate calculated in S214 and the inflow traffic volume calculated in S210. More specifically, the total traffic volume calculation unit 220 calculates the total traffic volume that has flowed into each route by dividing the inflow traffic volume by the mixing rate for each time.

[0097] FIG. 20 is a diagram illustrating the inclusion rate and the total traffic volume according to the second embodiment. FIG. 20 illustrates a graph showing the traffic volume and inclusion rate of route R1. In the graph shown in FIG. 20, the horizontal axis indicates time, the left vertical axis indicates the traffic volume (number of vehicles per 5 minutes), and the right vertical axis indicates the inclusion rate of employee vehicles. Moreover, the rectangular dots in FIG. 20 indicate the time-to-time transition of the inflow traffic volume of route R1. Note that the rectangular dots in FIG. 20 correspond to the inflow traffic volume (shown by circular dots) shown in FIG. 9. Moreover, the circular dots in FIG. 20 indicate the time-to-time transition of the total traffic volume of route R1. Moreover, the dashed line in FIG. 20 indicates the time-to-time transition of the inclusion rate of employee vehicles.

[0098] In the example of FIG. 20, the employee vehicle inclusion rate of route R1 increases from approximately 5% to 30% in the time period "6:00-7:00". The employee vehicle inclusion rate of route R1 remains at approximately 30% in the time period "7:00-8:45", and reaches a peak value of approximately 35% in the time period "8:15". The employee vehicle inclusion rate of route R1 decreases from approximately 30% to 5% in the time period "8:45-9:15". The inclusion rate calculation unit 212 calculates the total traffic volume indicated by the circular dots by dividing the inflow traffic volume indicated by the square dots by the inclusion rate indicated by the dashed line for each time.

[0099] The traffic model generating unit 130 according to the second embodiment generates a traffic model for each route (step S220). Here, in the second embodiment, the traffic model generating unit 130 generates a traffic model using the total traffic volume calculated in S216. In the second embodiment, the traffic model is generated by adjusting the parameters of the traffic model so that the actual value of the required time acquired in the process of S208 is reproduced when the total traffic volume flowing into the route, calculated in the process of S216, is input to the traffic model. This allows the parameter setting unit 128 to set the bottleneck capacity for the total traffic volume. Also, the traffic model generating unit 130 can generate a traffic model with the bottleneck capacity corresponding to the total traffic volume as a parameter.

[0100] Fig. 19 is a flowchart showing a process of calculating the amount of change in the predicted value of the required time when the inflow traffic volume is changed, using the traffic model according to the second embodiment. As in S132 to S140 in the first embodiment, the traffic prediction device 100 according to the second embodiment performs substantially the same process as the processes of S202 to S216 (step S230). Note that, when the inflow traffic volume (total traffic volume) for each route generated in the traffic model generation process (Fig. 18) is also used in the process of Fig. 19, the process of S230 may be omitted.

[0101] The change amount setting unit 140 according to the second embodiment sets the change amount of the total traffic volume flowing into the route (step S242). Specifically, the change amount setting unit 140 sets the change amount of the total traffic volume corresponding to the assumed measure. Here, the target of the measure is employee vehicles (target vehicles). Therefore, the change amount setting unit 140 according to the second embodiment sets the change amount in consideration of the ratio of the number of vehicles entering the parking lot (number of vehicles entering the facility) per unit time to the total traffic volume. Specifically, the change amount setting unit 140 according to the second embodiment sets the change amount by multiplying the total traffic volume flowing into each route at each time (time period) by the mixing rate and the conversion rate.

[0102] The traffic condition prediction unit 150 according to the second embodiment calculates a predicted value of the required time (step S250). That is, the traffic condition prediction unit 150 calculates, for each route, a predicted value of the required time for the total traffic volume calculated in S216 and a predicted value of the required time when the total traffic volume is changed, using a traffic model generated in advance in S220. Specifically, in the process of S220, parameters of the traffic model (free flow travel time and bottleneck capacity) are determined. Then, the traffic condition prediction unit 150 calculates a predicted value of the required time for each time period before the implementation of the measure by inputting the total traffic volume for each time period calculated in the process of S216 into the traffic model whose parameters have been determined. Similarly, the traffic condition prediction unit 150 calculates a predicted value of the required time for each time period when the total traffic volume is changed (i.e., when the measure is implemented) by inputting the total traffic volume for each time period that takes into account the change amount set in the process of S242 into the traffic model whose parameters have been determined.

[0103] The change amount calculation unit 160 according to the second embodiment calculates the amount of change in the required time (step S260). That is, the change amount calculation unit 160 calculates the amount of change in the predicted value of the required time for each route when the total traffic volume flowing into the route is changed. The method of calculating the amount of change is substantially the same as that of the first embodiment, and therefore the description is omitted. Then, if the traffic prediction device 100 according to the second embodiment has not completed the processing of S242 to S260 for all measures (NO in step S270), the processing returns to S242. Then, the traffic prediction device 100 performs the processing of S242 to S260 for other measures for which the processing has not been completed. On the other hand, if the traffic prediction device 100 has completed the processing of S242 to S260 for all measures (YES in S270), the processing ends.

[0104] The traffic prediction device 100 according to the second embodiment can predict the change in the required time when a measure is implemented, taking into account the overall traffic volume. Therefore, it is possible to perform a prediction that is more in line with the actual state of the route. On the other hand, in this embodiment, as described in the first embodiment, it is possible to predict the traffic when a behavioral change is performed even without acquiring infrastructure data. In other words, in the present invention, it is possible to predict the change in the required time when a behavioral change is performed even without acquiring infrastructure data.

[0105] (Modification) The present invention is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit and scope of the present invention. For example, the order of the steps in the flowcharts shown in Figures 3 to 5 and 17 to 19 can be modified as appropriate. Also, one or more steps in the flowcharts shown in Figures 3 to 5 and 17 to 19 may be omitted.

[0106] In the above embodiment, the process is performed for each of the multiple routes, but the present invention is not limited to this configuration. That is, the process may be performed for one route. However, by performing the process for each of the multiple routes as described above, it is possible to determine which route has the greatest effect of behavioral modification.

[0107] In the second embodiment, the total traffic volume is calculated by dividing the inflow traffic volume by the mixing rate, but the present invention is not limited to this configuration. The total traffic volume of the outflow traffic volume may be calculated by dividing the outflow traffic volume by the mixing rate, and the total traffic volume of the outflow traffic volume may be calculated by performing the process shown in FIG.

[0108] In the above example, the program can be stored and provided to the computer using various types of non-transitory computer readable media. The non-transitory computer readable medium includes various types of tangible storage media. Examples of the non-transitory computer readable medium include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs, CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable medium include electrical signals, optical signals, and electromagnetic waves. The transitory computer readable medium can provide the program to the computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path. [Explanation of symbols]

[0109] 1 ··· Traffic prediction system, 2 ··· Network, 20 ··· Probe car, 22 ··· Information processing device, 50 ··· Traffic volume data detection device, 100 ··· Traffic prediction device, 110 ··· Route information storage unit, 112 ··· Traffic volume data acquisition unit, 114 ··· Probe data acquisition unit, 116 ··· Route share rate calculation unit, 118 ··· Travel time acquisition unit, 120 ··· Traffic volume calculation unit, 122 ··· Outflow traffic volume calculation unit, 124 ··· Inflow traffic volume calculation unit, 128 ··· Parameter setting unit, 130 ··· Traffic model generation unit, 140 ··· Change amount setting unit, 150 ··· Traffic state prediction unit, 160 ··· Change amount calculation unit, 210 ··· Infrastructure data acquisition unit, 212 ··· Mixture rate calculation unit, 220 ··· Total traffic volume calculation unit

Claims

1. a traffic volume data acquisition unit for acquiring traffic volume data indicating a relationship between time and traffic volume at a predetermined point; a required time acquisition unit that acquires, for each of a plurality of routes toward the predetermined point, a performance value of a required time for a vehicle to travel from a reference point along the route to arrive at the predetermined point, using driving performance data obtained from each of a plurality of specific vehicles traveling along the plurality of routes; a traffic volume calculation unit that calculates an inflow traffic volume from the reference point to the route for each of the plurality of routes, using the traffic volume data, the actual value of the required time, and a share of each route in the traffic volume in the traffic volume data, the share being calculated based on the number of specific vehicles traveling on each of the plurality of routes; a traffic condition prediction unit that calculates, for each of the plurality of routes, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance; a change amount calculation unit that calculates a change amount of the predicted value of the required time when the inflow traffic volume is changed for each of the plurality of routes; having The traffic volume calculation unit, Using the share rate, calculate an outflow cumulative traffic volume, which is an accumulation of outflow traffic volumes, which are traffic volumes outflowing from each of the plurality of routes, among the traffic volumes in the traffic volume data; Calculating an inflow cumulative traffic volume, which is a cumulative total of the inflow traffic volumes, using the outflow cumulative traffic volume and the actual value of the required time; Calculating the inflow traffic volume for each hour from the inflow cumulative traffic volume; Traffic prediction system.

2. the required time acquisition unit acquires a performance value of the required time by using actual driving data obtained from each of a plurality of specific vehicles traveling along the route; The traffic forecasting system of claim 1 .

3. A traffic volume data acquisition unit that acquires traffic volume data indicating a relationship between time and traffic volume at a specified point; a required time acquisition unit that acquires, for each of at least one route leading to the predetermined point, a performance value of a required time for a vehicle to travel from a reference point of the route to arrive at the predetermined point along the route; a traffic volume calculation unit that calculates an inflow traffic volume from the reference point to the route by using the traffic volume data and the actual value of the required time; a traffic condition prediction unit that calculates, for the route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance; a change amount calculation unit that calculates a change amount of the predicted value of the required time when the inflow traffic volume is changed for the route; having the traffic model is generated by adjusting parameters of the traffic model so as to reproduce the actual value of the required travel time when the inflow traffic volume is input to the traffic model; The parameters of the traffic model include a bottleneck capacity for each route at each time of day; Traffic prediction system.

4. Acquire traffic volume data showing the relationship between time and traffic volume at a specified point; obtaining, for each of a plurality of routes toward the predetermined point, a performance value of a required time for a vehicle to travel from a reference point along the route to the predetermined point by using driving performance data obtained from each of a plurality of specific vehicles traveling along the plurality of routes; Using the traffic volume data, the actual value of the required time, and the share of each route in the traffic volume data, which is calculated based on the number of specific vehicles traveling on each of the multiple routes, calculate an inflow traffic volume from the reference point to the route for each of the multiple routes, Using the share rate, calculate an outflow cumulative traffic volume, which is an accumulation of outflow traffic volumes, which are traffic volumes outflowing from each of the plurality of routes, among the traffic volumes in the traffic volume data; Calculating an inflow cumulative traffic volume, which is a cumulative total of the inflow traffic volumes, using the outflow cumulative traffic volume and the actual value of the required time; Calculating the inflow traffic volume for each hour from the inflow cumulative traffic volume; It is calculated by Calculating, for each of the plurality of routes, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance; Calculating a change in the predicted value of the required time when the inflow traffic volume is changed for each of the plurality of routes; Traffic prediction methods.

5. Acquiring traffic volume data showing the relationship between time and traffic volume at a specified point, acquiring, for each of at least one route, a performance value of a required time for a vehicle to travel from a reference point of the at least one route leading to the predetermined point to the predetermined point along the route; Calculating an inflow traffic volume from the reference point to the route using the traffic volume data and the actual value of the required time; Calculating, for the route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance; Calculating a change in the predicted value of the required time when the inflow traffic volume is changed for the route; the traffic model is generated by adjusting parameters of the traffic model so as to reproduce the actual value of the required travel time when the inflow traffic volume is input to the traffic model; The parameters of the traffic model include a bottleneck capacity for each route at each time of day; Traffic prediction methods.

6. acquiring traffic volume data indicating a relationship between time and traffic volume at a predetermined point; acquiring, for each of a plurality of routes toward the predetermined point, a performance value of a required time for a vehicle to travel from a reference point along the route to the predetermined point, by using driving performance data obtained from each of a plurality of specific vehicles traveling along the plurality of routes; Using the traffic volume data, the actual value of the required time, and the share of each route in the traffic volume data, which is calculated based on the number of specific vehicles traveling on each of the multiple routes, calculate an inflow traffic volume from the reference point to the route for each of the multiple routes, Using the share rate, calculate an outflow cumulative traffic volume, which is an accumulation of outflow traffic volumes, which are traffic volumes outflowing from each of the plurality of routes, among the traffic volumes in the traffic volume data; Calculating an inflow cumulative traffic volume, which is a cumulative total of the inflow traffic volumes, using the outflow cumulative traffic volume and the actual value of the required time; Calculating the inflow traffic volume for each hour from the inflow cumulative traffic volume; and calculating the value by calculating, for each of the plurality of routes, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance; A step of calculating a change in the predicted value of the required time when the inflow traffic volume is changed for each of the plurality of routes; A program that causes a computer to execute the following.

7. A step of acquiring traffic volume data indicating a relationship between time and traffic volume at a specified point; acquiring, for each of at least one route, a performance value of a required time for a vehicle to travel from a reference point of the at least one route leading to the predetermined point to the predetermined point along the route; calculating an inflow traffic volume from the reference point to the route by using the traffic volume data and the actual travel time; calculating, for the route, a predicted value of the required time for the calculated inflow traffic volume and a predicted value of the required time when the inflow traffic volume is changed, using a traffic model generated in advance; A step of calculating a change amount of the predicted value of the required time when the inflow traffic volume is changed for the route; Run the following on your computer: the traffic model is generated by adjusting parameters of the traffic model so as to reproduce the actual value of the required travel time when the inflow traffic volume is input to the traffic model; The parameters of the traffic model include a bottleneck capacity for each route at each time of day; program.

Images