MODIFICATION RISK OUTPUT DEVICE, MODIFICATION RISK OUTPUT METHOD, AND MODIFICATION RISK OUTPUT PROGRAM

Abstract

The congestion degree calculation means 81 calculates a congestion degree at a vehicle and a stop. The diagram output means 82 outputs a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram. The risk calculation means 83 calculates a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree. The risk output means 84 outputs the calculated current risk and the modification risk.

Description

TECHNICAL FIELD

This invention relates to a modification risk output device, a modification risk output method, and a modification risk output program that outputs a risk when a diagram is modified.

BACKGROUND ART

Due to the development of mobility technologies, population growth and urban overcrowding, the number of transportation infrastructures such as railroads, airlines, buses, and ships, as well as their users, are in a state of continuous growth. Currently, most of the work related to transportation operation diagrams (operation schedules, or diagrams) is performed manually, and this work is becoming increasingly complex. Therefore, the use of AI (Artificial Intelligence) is expected from the viewpoint of labor saving and automation.

For example, Patent literature 1 describes an operation management support device that performs operation management related to reducing train delays and the like. The device described in Patent literature 1 identifies configurations to be modified in order to operate trains according to the modified schedule data, based on the difference between the actual schedule data and the fixed schedule data, and configuration information.

CITATION LIST

Patent Literature

• PTL 1: Japanese Patent Laid-Open No. 2019-93906

SUMMARY OF INVENTION

Technical Problem

In the fields of railroads and aviation, modifications of operating schedules, such as in the event of trouble, are currently made manually. Since the modification is time-sensitive, it is difficult to take the time to consider the modification. Even while considering “what will happen if the operation schedule is modified at this time,” the situation may worsen and another operation schedule modification may become necessary. On the other hand, it is also assumed that the rush to modify the operation schedule may prevent the selection of the optimal modification that could have been considered if more time had been taken.

For example, by using the device described in Patent literature 1, it is possible to identify the configuration to be modified and the indicators to solve the problem. However, the device described in Patent literature 1 does not consider the creation of a proposal to modify the operation schedule, and the modification of the operation schedule itself is left to a skilled person. Therefore, it is difficult to say that the functions of AI are fully utilized from the viewpoint of labor saving and automation of operations.

Therefore, in order to save labor and speed up the planning work through AI, i.e., to modify the operation schedule appropriately and quickly, it is desirable for the human operator to be able to understand in real time the results of modifying the operation schedule and the risks that may occur as a result of the modification.

Therefore, it is an exemplary object of the present invention is to provide a modification risk output device, a modification risk output method, and a modification risk output program that can output a result of a modification of a diagram and a risk that may occur due to the modification.

Solution to Problem

The modification risk output device according to the present invention including: a congestion degree calculation means which calculates a congestion degree at a vehicle and a stop; a diagram output means which outputs a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; a risk calculation means which calculates a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and a risk output means which outputs the calculated current risk and the modification risk.

The modification risk output method according to the present invention including: calculating a congestion degree at a vehicle and a stop; outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and outputting the calculated current risk and the modification risk.

The modification risk output program according to the present invention causing the computer to execute: congestion degree calculation process of calculating a congestion degree at a vehicle and a stop; diagram output process of outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; risk calculation process of calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and risk output process of outputting the calculated current risk and the modification risk.

Advantageous Effects of Invention

According to the present invention, it is possible to output a result of a modification of a diagram and a risk that may occur due to the modification.

BRIEF DESCRIPTION OF DRAWINGS

FIG. 1 It depicts a block diagram showing a configuration example of an exemplary embodiment of a modification risk output device according to the present invention.

FIG. 2 It depicts an explanatory diagram showing an example of business history data.

FIG. 3 It depicts an explanatory diagram showing an example of an output risk.

FIG. 4 It depicts a flowchart showing an operation example of the modification risk output device.

FIG. 5 It depicts a block diagram showing an overview of a modification risk output device according to the present invention.

DESCRIPTION OF EMBODIMENTS

The following is a description of the exemplary embodiment of the invention with reference to the drawings.

FIG. 1 is a block diagram showing a configuration example of an exemplary embodiment of a modification risk output device according to the present invention. The modification risk output device 100 of this exemplary embodiment includes a storage unit 10, a situation acquisition unit 20, a congestion degree calculation unit 30, an objective function selection unit 40, a modified diagram output unit 50, a risk calculation unit 60, and a risk output unit 70. The modification risk output device 100 is connected to a display unit 200.

The storage unit 10 stores parameters and various information used by the modification risk output device 100 of this exemplary embodiment for processing. Specifically, the storage unit 10 stores an objective function that has been learned in advance using business history data. The business history data is, for example, a history of modifications made to the operation schedule for a certain condition (e.g., congestion, delay occurrence, etc.).

FIG. 2 is an explanatory diagram showing an example of business history data. The business history data D11 illustrated in FIG. 2 is an example of data that maps plans to results at each station for each train. The business history data D12 shows an example of data such as that illustrated in the business history data D11 plotted as a diagram. In D12, the dotted line represents the plan and the solid line represents the result.

The objective function of this exemplary embodiment is learned in advance using the business history data including the actual changes in the operation schedule as described above. The business history data may also include a congestion degree of a vehicle and a stop. In this exemplary embodiment, the congestion degree of the vehicle and the stop means, for example, the degree of congestion determined based on passengers present at a stop (e.g., a platform) and passengers boarding a vehicle located at that stop. The learning method of the objective function is arbitrary, for example, inverse reinforcement learning using the business history data. Since the optimization of operation schedules of trains and other vehicles can be large-scale, the objective function may be represented by an Ising model that is handled by an annealing quantum computer or the like.

In the following explanation, the case of modifying the train diagram will be used as an example. That is, a train is given as an example of the vehicle and a station is given as an example of the stop. However, the vehicle is not limited to a train, but may also be a bus or an airplane, for example. In this case, a stop is a bus stop or an airfield.

The storage unit 10 of this exemplary embodiment may store a plurality of objective functions by situation and by objective. The contents of the assumed situations and objectives are arbitrary. For example, the situations assumed in a train include time periods, the location of train accidents or transportation disruptions, the type of accident or transportation disruption, the congestion state at each station, and the full capacity of the train.

The above-mentioned time periods include, for example, morning commuting hours, night commuting hours, first departure hours, last train hours, etc. Also, the location of train accidents or transportation disruptions are for example, at stations with many passengers and connecting trains such as Tokyo Station, stations where trains can turn around, stations connected to rail yards (garages), stations with many or few available train tracks, etc. The type of accident or transportation disruption is, for example, equipment trouble (e.g., doors), personal injury, passenger trouble, etc.

Another example of a possible objective in trains is when, for example, the decision-maker's intention (purpose) to make a diagram modification differs depending on his/her inspiration, mood, or individual differences, even in the same situation. For example, it is assumed that the decision maker wants to prioritize passenger transportation at station A (i.e., increase the number of trains departing from station A). In this case, the objective function at that time can be said to be an objective function in which the weight of the term related to station A is large.

Thus, by learning the past objective functions under each assumed situation, an optimized railroad schedule can be presented to the operator under those objective functions at the time of actual operation. The presented operator can refer to multiple candidates, such as A station-oriented schedules, B station-oriented schedules, and so on, and can decide which of them seems to be the best.

In addition, the storage unit 10 of this exemplary embodiment may store entry/exit result data of ticket gates at each station that is sequentially collected in real time. The entry/exit result data may be stored in a central server (not shown) or a cloud server (not shown) that is connected to the modification risk output device 100 via communication lines. In this case, the modification risk output device 100 may periodically acquire the entry/exit result data from these servers and store them in the storage unit 10. The storage unit 10 is realized by, for example, a magnetic disk.

The situation acquisition unit 20 acquires the estimated situation at the vehicle and the stop in the current and future. The situation estimated for the vehicle is, for example, the boarding rate of the vehicle, the operation status (delay status) of the vehicle, and so on. The estimated situation at the stop is, for example, the degree of passenger stagnation at the stop, the degree of passenger density at the stop, and so on.

The situation acquisition unit 20 includes a simulator execution unit 21 and a collected data acquisition unit 22. The situation acquisition unit 20 may include only one of the simulator execution unit 21 and the collected data acquisition unit 22, or may include both of them.

The simulator execution unit 21 executes a simulator that simulates passenger boarding and alighting at each stop, and obtains the current and future degree of passenger stagnation at least one of each stop and vehicle, or the current estimated operation status of the vehicle. In other words, such a simulator can be used to estimate the risk of possible future problems or delays.

The simulator execution unit 21 may, for example, simulate the degree of passenger stagnation at each current and future stop or vehicle, estimate a current vehicle operation status (e.g., the degree of delay, how many minutes after each train arrives at each platform at each station, etc.). For example, a simulator could be run to estimate situations such as a station overflowing with people (exceeding the number of people that can be accommodated at the station), which is likely to further increase train delays.

The mode of the simulator executed by the simulator execution unit 21 in this exemplary embodiment is arbitrary. For example, the distribution p(x, t, a, b) of the number of passengers x departing from station a and arriving at station b at each time t may have been created in advance based on previously obtained data on the number of passengers entering and exiting the ticket gates at each station, or may have been created based on an appropriate model representing the flow of people.

The collected data acquisition unit 22 acquires entry/exit result data at each stop that is collected sequentially, and estimates the current degree of passenger stagnation at each stop. Specifically, the collected data acquisition unit 22 may estimate the degree of passenger stagnation at each station by acquiring the entry/exit result data of a ticket gate at each station. The collected data acquisition unit 22 may, for example, estimate the degree of passenger stagnation at each stop by calculating the number of passengers entering or exiting per hour. This data allows, for example, the amount of human outflow at a station at any given time to be determined.

The congestion degree calculation unit 30 calculates a congestion degree at a vehicle and a stop. Specifically, the congestion degree calculation unit 30 calculates the congestion degree based on the current and future estimated situation at the vehicle and the stop obtained by the situation acquisition unit 20.

In this exemplary embodiment, the congestion degree calculation unit 30 may calculate the congestion degree at the vehicle and the stop based on the degree of passenger stagnation or operation status. As the degree of passenger stagnation, the passenger count distribution p described above may be used. As the operation status, the diagram status of the vehicle at the current time and the number of passenger capacity in each vehicle may be used. Therefore, the congestion degree calculation unit 30 may, for example, use the distribution p of the number of passenger capacity, the diagram status of the vehicle at the current time, and the number of passengers in each vehicle, to calculate the distribution of the congestion degree at each stop (e.g., each platform at each station), and the distribution of the congestion degree at each vehicle with different time zones, vehicle types, and destinations.

The specific method of calculating the congestion degree is explained below, using the case of a train as an example. However, the method of calculating congestion degree is not limited to the specific examples below, and is arbitrary as long as it is consistent throughout.

For example, on a line with only stop trains at each station, if ti is the time when the last train arrives at station a, then the distribution f (x, t, a) of the number of passengers waiting for a train at station a at time T for the train bound for direction S is represented by Equation 1, illustrated below. This distribution f can be called the degree of passenger stagnation.

$\begin{array}{cc}\left[\mathrm{Math}.1\right]& \\ f\left(x,t,a\right)=\sum _{b\in Y_S}{\int }_{t_1}^{T}p\left(x,t,a,b\right)\mathrm{dt}& \left(\mathrm{Equation}1\right)\end{array}$

In Equation 1, Y_s is the set of stations in the direction S rather than station a. Also, the distribution p(x, t, a, b) is the distribution of the number of passengers x departing from station a at time t and arriving at station b. This distribution p can also be said to be a distribution that changes according to the operating status.

Developing Equation 1 above, the congestion degree calculation unit 30 may calculate the degree of passenger stagnation by considering passengers left unloaded. In other words, the congestion degree calculation unit 30 may calculate the congestion degree by considering passengers left unloaded at each station platform. Specifically, the congestion degree calculation unit 30 may calculate the number of passengers left unloaded by subtracting the number of passenger capacity of the train after calculating the number of passengers waiting on the platform at the time of train arrival using Equation 1 above. The congestion degree calculation unit 30 may also calculate the number of passengers left unloaded by subtracting the maximum number of passengers instead of the number of passenger capacity, considering the possibility that the boarding rate may exceed 100%.

The objective function selection unit 40 accepts a selection instruction from a user for the objective function used to modify the operation schedule. For example, if objective functions are prepared by situation and by objective, the objective function selection unit 40 may accept the selection instruction for one or more objective functions to be used for optimization from among the prepared objective functions. If all the prepared objective functions are used to modify the operation schedule, the modification risk output device 100 does not need to include the objective function selection unit 40.

The modified diagram output unit 50 outputs the operation schedule modified from the current operation schedule (hereinafter also referred to as modified diagram) by optimizing the objective function. The form of the modified diagram output unit 50 is arbitrary, as long as optimization is possible based on the objective function used in this exemplary embodiment. For example, the modified diagram output unit 50 may be realized by an optimization engine (optimization solver) that performs optimization processing based on the selected objective function. When the objective function is represented by an Ising model, the modified diagram output unit 50 may, for example, cause a quantum computer that solves the optimization problem using quantum annealing to perform the optimization process. In other words, if the objective function is represented by an Ising model, the optimization process may be performed using a quantum computer while a general computer generates the change proposal to the operation schedule.

The risk calculation unit 60 calculates a risk that occurs at the present time and a risk caused by modifying the diagram, based on the calculated congestion degree above. The risk calculated in this exemplary embodiment is information that indexes the various effects of the diagram modification, and is not limited to information indicating hazards. In the following explanations, when distinguishing between risks that occur (or can occur) at the present time and risks that occur (or can occur) as a result of a diagram modification, the risk that occurs at the present time is referred to as “current risk” and the risk that occurs as a result of a diagram modification is referred to as “modification risk.”

The risk calculation unit 60 may, for example, calculate a score of the objective function as the risk. Here, the score of the objective function means the value of the objective function that the optimal solution calculated by the modified diagram output unit 50 achieves.

The risk calculation unit 60 may also calculate the risk for each possible cause based on the calculated congestion degree (e.g., the number of passengers waiting for trains at each station). The possible cause includes delays and transportation disruptions related to train operation schedules, such as the occurrence of passenger problems and delays in train arrival and departure times.

Note that because the size and structure of platforms differ from stop to stop (e.g., from station to station), the risk generally differs even for the same congestion degree. Therefore, an occurrence probability model q(t, d, a, e) of the assumed risk for each cause e is prepared in advance according to the congestion degree d at each time t and at each stop a, and the risk calculation unit 60 may calculate the risk for each cause based on that occurrence probability model q.

Here, when the congestion degree d is expressed as d=f(x, t, a) described above, the risk calculation unit 60 may, for example, calculate the risk R(t, e, a) for each cause e based on Equation 2 illustrated below. The occurrence probability model q of the risk may, for example, have been learned in advance based on result data, or may have been created with an arbitrary model indicating the probability of occurrence.

[Math.2]

R(t,e,a)=∫q(t,f(x,t,a),a,e)dx  (Equation 2)

In addition, the risk calculation unit 60 may calculate an optimization index for the objective function. The optimization index includes, for example, passenger boarding time, number of transfers, number of passengers left unloaded, passenger waiting time at stations, boarding rate, and number of service interruptions occurring.

The risk output unit 70 outputs the calculated current risk and the modification risk. If the risk is calculated for each cause, the risk output unit 70 may output the calculated risk for each cause. If an optimization index for the objective function has been calculated, the risk output unit 70 may output the amount of change in the predetermined index in the modified diagram from the fixed time schedule. For example, if the vehicle is a train, the risk output unit 70 may output the amount of change in passenger boarding time, the amount of change in the number of transfers, the amount of change in the number of passengers left unloaded, the amount of change in the boarding passenger waiting time at a station, the change in the passenger boarding rate, and number of service interruptions occurring as the amount of change.

FIG. 3 is an explanatory diagram showing an example of an output risk. The example shown in FIG. 3 shows an example in which the modified diagram output unit 50 outputs the modified diagram D13 to the display device 200, and the risk output unit 70 outputs to the display device 200 the current risk and the modification risk relating to the modified diagram D13 in association with each other.

Thus, the risk output unit 70 outputs the calculated current risk and modification risk. This allows the user to quantitatively determine whether or not a modification should be made immediately in the current situation.

The output unit 20 (more specifically, the simulator execution unit 21 and the collected data acquisition unit 22), the congestion degree calculation unit 30, the objective function selection unit 40, the modified diagram output unit 50, the risk calculation unit 60, and the risk output unit 70 are realized by a processor (for example, CPU (Central Processing Unit), GPU (Graphics Processing Unit)) of a computer that operates according to a program (a modification risk output program).

In this case, for example, a program may be stored in a storage unit 10, and the processor may read the program and operate as the output unit 20 (more specifically, the simulator execution unit 21 and the collected data acquisition unit 22), the congestion degree calculation unit 30, the objective function selection unit 40, the modified diagram output unit 50, the risk calculation unit 60, and the risk output unit 70 according to the program. In addition, the functions of the output unit 20 (more specifically, the simulator execution unit 21 and the collected data acquisition unit 22), the congestion degree calculation unit 30, the objective function selection unit 40, the modified diagram output unit 50, the risk calculation unit 60, and the risk output unit 70 may be provided in the form of SaaS (Software as a Service).

The output unit 20 (more specifically, the simulator execution unit 21 and the collected data acquisition unit 22), the congestion degree calculation unit 30, the objective function selection unit 40, the modified diagram output unit 50, the risk calculation unit 60, and the risk output unit 70 may each be realized by dedicated hardware. For example, when the objective function is represented by an Ising model, as described above, part of the modified diagram output unit 50 may be realized by a quantum computer. Some or all of the components of each device may be realized by general-purpose or dedicated circuit, a processor, or combinations thereof. These may be configured by a single chip or by multiple chips connected through a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuit, etc., and a program.

When some or all of the components of the output unit 20 (more specifically, the simulator execution unit 21 and the collected data acquisition unit 22), the congestion degree calculation unit 30, the objective function selection unit 40, the modified diagram output unit 50, the risk calculation unit 60, and the risk output unit 70 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally located or distributed. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, etc., each of which is connected through a communication network.

Next, the operation example of this exemplary embodiment of the modification risk output device 100 will be described. FIG. 4 is a flowchart showing an operation example of the modification risk output device 100. The congestion degree calculation unit 30 calculates the congestion degree at a vehicle and a stop (step S11). The modified diagram output unit 50 outputs a modified diagram by optimizing the objective function (step S12). The risk calculation unit 60 calculates the current risk and the modification risk based on the congestion degree (Step S13). The risk output unit 70 outputs the calculated current risk and modification risk (step S14).

As described above, in this exemplary embodiment, the congestion degree calculation unit 30 calculates the congestion degree at a vehicle and a stop, and the modified diagram output unit 50 outputs a modified diagram by optimizing the objective function. The risk calculation unit 60 calculates the current risk and the modification risk based on the congestion degree, and the risk output unit 70 outputs the calculated current risk and modification risk. Thus, it is possible to output a result of a modification of a diagram and a risk that may occur due to the modification.

Next, an overview of the present invention will be described. FIG. 5 is a block diagram showing an overview of a modification risk output device according to the present invention. The modification risk output device 80 (e.g., modification risk output device 100) according to the present invention includes a congestion degree calculation means 81 (e.g., congestion degree calculation unit 30) which calculates a congestion degree at a vehicle (e.g., train) and a stop (e.g., station); a diagram output means 82 (e.g., modified diagram output unit 50) which outputs a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; a risk calculation means 83 (e.g., risk calculation unit 60) which calculates a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and a risk output means 84 (e.g., risk output unit 70) which outputs the calculated current risk and the modification risk.

Such a configuration allows output of a result of a modification of a diagram and a risk that may occur due to the modification.

The risk calculation means 83 may calculate a risk for each cause based on an occurrence probability model of the risk assumed (occurrence probability model q(t, d, a, e) of the risk) for each cause according to the congestion degree at each time and each stop, and the risk output means 84 may output the calculated (e.g., calculated according to the Equation 2 above) current risk and modification risk for each cause.

The modification risk output device 80 may further include a situation acquisition means (e.g., situation acquisition unit 20) which acquires a situation estimated at current and future at the vehicle and the stop. The congestion degree calculation means 81 may calculate the congestion degree based on the situation estimated at the vehicle and the stop.

Specifically, the situation acquisition means may include a simulator execution means (e.g., simulator execution unit 21) which executes a simulator that simulates passenger boarding and alighting at each stop. The simulator execution means may estimate a degree of passenger stagnation at least one of the current and future at the stop and vehicle, or operation status of the vehicle, and the congestion degree calculation means 81 may calculate the congestion degree at the vehicle and the stop based on the degree of passenger stagnation or the operation status.

In that case, the simulator execution means may use the distribution of the number of passengers from a first stop to a second stop at each time to estimate the degree of passenger stagnation or the operation status in the simulator.

The situation acquisition means may include a collected data acquisition means (e.g., collected data acquisition unit 22) which acquires entry/exit result data at each stop that is collected sequentially. The collected data acquisition means may estimate the current degree of passenger stagnation at each stop, and the congestion degree calculation means may calculate the congestion degree at the vehicle and the stop based on the degree of passenger stagnation.

The modification risk output device 80 may further include an objective function selection means (e.g., objective function selection unit 40) which accepts a selection instruction for an objective function to be used for optimization from among the objective functions prepared for each situation and each objective to modify the diagram. The diagram output means may output the modified diagram by optimizing the selected objective function.

Although some or all of the above exemplary embodiments may also be described as in the following Supplementary notes, the present invention is not limited to the following.

(Supplementary note 1) A modification risk output device comprising: a congestion degree calculation means which calculates a congestion degree at a vehicle and a stop; a diagram output means which outputs a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; a risk calculation means which calculate a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and a risk output means which outputs the calculated current risk and the modification risk.

(Supplementary note 2) The modification risk output device according to Supplementary note 1, wherein the risk calculation means calculates a risk for each cause based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop, and the risk output means outputs the calculated current risk and modification risk for each cause.

(Supplementary note 3) The modification risk output device according to Supplementary note 1 or 2, further comprising a situation acquisition means which acquires a situation estimated at current and future at the vehicle and the stop, wherein the congestion degree calculation means calculates the congestion degree based on the situation estimated at the vehicle and the stop.

(Supplementary note 4) The modification risk output device according to Supplementary note 3, wherein the situation acquisition means includes a simulator execution means which executes a simulator that simulates passenger boarding and alighting at each stop, the simulator execution means estimates a degree of passenger stagnation at least one of the current and future at the stop and vehicle, or operation status of the vehicle, and the congestion degree calculation means calculates the congestion degree at the vehicle and the stop based on the degree of passenger stagnation or the operation status.

(Supplementary note 5) The modification risk output device according to Supplementary note 4, wherein the simulator execution means uses the distribution of the number of passengers from a first stop to a second stop at each time to estimate the degree of passenger stagnation or the operation status in the simulator.

(Supplementary note 6) The modification risk output device according to any one of Supplementary notes 3 to 5, wherein the situation acquisition means includes a collected data acquisition means which acquires entry/exit result data at each stop that is collected sequentially, the collected data acquisition means estimates the current degree of passenger stagnation at each stop, and the congestion degree calculation means calculates the congestion degree at the vehicle and the stop based on the degree of passenger stagnation.

(Supplementary note 7) The modification risk output device according to any one of Supplementary notes 1 to 6, further comprising an objective function selection means which accepts a selection instruction for an objective function to be used for optimization from among the objective functions prepared for each situation and each objective to modify the diagram, wherein the diagram output means outputs the modified diagram by optimizing the selected objective function.

(Supplementary note 8) A modification risk output method comprising: calculating a congestion degree at a vehicle and a stop; outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and outputting the calculated current risk and the modification risk.

(Supplementary note 9) A modification risk output method according to Supplementary note 8, further comprising: calculating a risk for each cause based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop; and outputting the calculated current risk and modification risk for each cause.

(Supplementary note 10) A program recording medium in which a modification risk output program is recorded, the modification risk output program causing a computer to execute: congestion degree calculation process of calculating a congestion degree at a vehicle and a stop; diagram output process of outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; risk calculation process of calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and risk output process of outputting the calculated current risk and the modification risk.

(Supplementary note 11) The program recording medium in which the modification risk output program is recorded according to Supplementary note 10, wherein a risk for each cause is calculated based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop, in the risk calculation process, and the calculated current risk and modification risk for each cause is output, in the risk output process.

(Supplementary note 12) A modification risk output program causing a computer to execute: congestion degree calculation process of calculating a congestion degree at a vehicle and a stop; diagram output process of outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram; risk calculation process of calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and risk output process of outputting the calculated current risk and the modification risk.

(Supplementary note 13) The modification risk output program according to Supplementary note 12, wherein a risk for each cause is calculated based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop, in the risk calculation process, and the calculated current risk and modification risk for each cause is output, in the risk output process.

Although the present invention has been described with reference to the exemplary embodiments and examples, the present invention is not limited to the foregoing exemplary embodiments and examples. Various changes understandable by those skilled in the art can be made to the structures and details of the present invention within the scope of the present invention.

REFERENCE SIGNS LIST

• 10 Storage unit
• 20 Situation acquisition unit
• 21 Simulator execution unit
• 22 Collected data acquisition unit
• 30 Congestion degree calculation unit
• 40 Objective function selection unit
• 50 Modified diagram output unit
• 60 Risk calculation unit
• 70 Risk output unit
• 100 Modification risk output device
• 200 Display device

Claims

1. A modification risk output device comprising:

a memory storing instructions; and

one or more processors configured to execute the instructions to:

calculate a congestion degree at a vehicle and a stop;

output a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram;

calculate a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and

output the calculated current risk and the modification risk.

2. The modification risk output device according to claim 1, wherein the processor is configured to execute the instructions to:

calculate a risk for each cause based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop; and

output the calculated current risk and modification risk for each cause.

3. The modification risk output device according to claim 1, wherein the processor is configured to execute the instructions to:

acquire a situation estimated at current and future at the vehicle and the stop; and

calculate the congestion degree based on the situation estimated at the vehicle and the stop.

4. The modification risk output device according to claim 3, wherein the processor is configured to execute the instructions to:

execute a simulator that simulates passenger boarding and alighting at each stop;

estimate a degree of passenger stagnation at least one of the current and future at the stop and vehicle, or operation status of the vehicle; and

calculate the congestion degree at the vehicle and the stop based on the degree of passenger stagnation or the operation status.

5. The modification risk output device according to claim 4, wherein the processor is configured to execute the instructions to:

use the distribution of the number of passengers from a first stop to a second stop at each time to estimate the degree of passenger stagnation or the operation status in the simulator.

6. The modification risk output device according to claim 3, wherein the processor is configured to execute the instructions to:

acquire entry/exit result data at each stop that is collected sequentially;

estimate the current degree of passenger stagnation at each stop; and

calculate the congestion degree at the vehicle and the stop based on the degree of passenger stagnation.

7. The modification risk output device according to claim 1, wherein the processor is configured to execute the instructions to:

accept a selection instruction for an objective function to be used for optimization from among the objective functions prepared for each situation and each objective to change the diagram; and

output the modified diagram by optimizing the selected objective function.

8. A modification risk output method comprising:

calculating a congestion degree at a vehicle and a stop;

outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram;

calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and

outputting the calculated current risk and the modification risk.

9. A modification risk output method according to claim 8, further comprising:

calculating a risk for each cause based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop; and

outputting the calculated current risk and modification risk for each cause.

10. A non-transitory computer readable information recording medium storing a modification risk output program when executed by a processor, that performs a method for:

calculating a congestion degree at a vehicle and a stop;

outputting a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram;

calculating a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree; and

outputting the calculated current risk and the modification risk.

11. The non-transitory computer readable information recording medium according to claim 10, wherein

a risk for each cause is calculated based on an occurrence probability model of the risk assumed for each cause according to the congestion degree at each time and each stop, and

the calculated current risk and modification risk for each cause is output.