JP7371769B2 - Modified risk output device, modified risk output method, and modified risk output program - Google Patents

Description

The present invention relates to a modified risk output device, a modified risk output method, and a modified risk output program that output risks when a diagram is modified.

Due to the development of mobility technology, population growth, and overcrowding in urban areas, the number of transportation infrastructure such as railways, airlines, buses, and ships, as well as the number of users thereof, will continue to increase. Currently, work related to transportation diagrams (sometimes referred to as service schedules or timetables) is mostly performed manually, and this work is becoming increasingly complex. Therefore, the use of AI (Artificial Intelligence) is expected from the perspective of labor saving and automation of operations.

For example, Patent Document 1 describes a traffic management support device that performs traffic management related to train delay reduction and the like. The device described in Patent Document 1 identifies a configuration to be corrected in order to operate a train according to the corrected timetable data, based on the difference between actual timetable data and scheduled timetable data, and configuration information.

JP2019-93906A

In the fields of railways and aviation, adjustments to operating schedules in the event of trouble are currently done manually. Since corrections are time-sensitive, it is difficult to take time to consider corrections. It is conceivable that even while we are considering what would happen if we revise the service schedule at this timing, the situation worsens and another revision of the service schedule becomes necessary. On the other hand, it is also conceivable that the rush to revise the schedule may result in not being able to select the most appropriate revision that could have been considered if more time had been taken.

For example, by using the device described in Patent Document 1, it is possible to specify a configuration to be modified and an index for solving a problem. However, the device described in Patent Document 1 does not take into account the creation of a plan for modifying the bus schedule, and the modification of the bus schedule itself is left to experts. Therefore, it is difficult to say that the functions of AI are being fully utilized from the perspective of labor saving and automation of operations.

Therefore, in order to save labor and speed up planning operations through AI, in other words, to make changes to the operating schedule appropriately and quickly, it is necessary for humans to It is desirable to be able to understand possible risks in real time.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide a modified risk output device, a modified risk output method, and a modified risk output program that can output the results of modifying a diagram and the risks that may occur due to the modification.

The corrected risk output device according to the present invention optimizes the objective function learned using the congestion degree calculation means that calculates the congestion degree of vehicles and stops, and business history data including diagram change records. a diagram output means for outputting a corrected diagram obtained by correcting a diagram; a risk calculation means for calculating a current risk, which is a risk that occurs at the current time; and a revised risk, which is a risk that occurs due to the correction of the diagram, based on the degree of congestion; and a risk output means for outputting the current risk and modified risk, and the risk calculation means calculates the risk for each cause based on a risk occurrence probability model assumed for each cause based on the congestion level of each time and each stop. The present invention is characterized in that the risk output means outputs the calculated current risk and modified risk for each cause .

The revised risk output method according to the present invention calculates the congestion level of vehicles and stops, and optimizes the objective function learned using business history data including diagram change records.The revised risk output method corrects the current diagram. The diagram is then output, and the current risk, which is the risk that occurs at the current time, and the revised risk , which is the risk that arises from modifying the diagram , are calculated by calculating the probability of occurrence of the risk assumed for each cause based on the degree of congestion and the degree of congestion at each time and each stop. It is characterized by calculating each cause based on a model and outputting the calculated current risk and corrected risk for each cause .

The modified risk output program according to the present invention uses a computer to perform a congestion degree calculation process that calculates the congestion degree of vehicles and stops, and optimizes an objective function learned using business history data including diagram change records. A diagram output process that outputs a corrected diagram by correcting the current diagram, a risk calculation process that calculates the current risk that is the risk that occurs at the current time, and the revised risk that is the risk that occurs due to the correction of the diagram based on the degree of congestion; Execute the risk output process that outputs the calculated current risk and revised risk, and in the risk calculation process, the risk for each cause is calculated based on the risk occurrence probability model assumed for each cause based on the congestion level of each time and each stop. is calculated, and in the risk output process, the current risk and modified risk for each calculated cause are output .

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

FIG. 1 is a block diagram showing a configuration example of an embodiment of a modified risk output device according to the present invention. FIG. 2 is an explanatory diagram showing an example of business history data. It is an explanatory diagram showing an example of an output risk. It is a flow chart which shows an example of operation of a revised risk output device. 1 is a block diagram showing an overview of a modified risk output device according to the present invention. FIG.

Embodiments of the present invention will be described below with reference to the drawings.

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

The storage unit 10 stores parameters and various information used in processing by the modified risk output device 100 of this embodiment. Specifically, the storage unit 10 stores an objective function learned in advance using business history data. The business history data is, for example, a history of changes made to the operating schedule for certain conditions (such as when congestion occurs or when delays occur).

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 associates plans and actual results at each station of each train. Further, the business history data D12 shows an example in which data as exemplified in the business history data D11 is plotted as a diagram. Note that in the work history data D12, dotted lines represent plans and solid lines represent actual results.

The objective function of this embodiment is learned in advance using business history data including the track record of changes in the operating schedule as described above. Further, the business history data may include the degree of congestion of vehicles and stops. In this embodiment, the degree of congestion of a vehicle and a stop means, for example, the degree of congestion determined based on the number of passengers present at a stop (for example, a platform) and the passengers boarding a vehicle located at that stop. do. The learning method for the objective function is arbitrary, and examples include inverse reinforcement learning using business history data. Furthermore, since optimization of train schedules and the like can be performed on a large scale, the objective function may be expressed by an Ising model handled by an annealing quantum computer or the like.

In the following explanation, a case where a train diagram is changed will be exemplified. That is, a train is taken as an example of a vehicle, and a station is taken as an example of a stop. However, the vehicle is not limited to a train, and may be, for example, a bus or an airplane. In this case, the stop is a bus stop, an airport, or the like.

Furthermore, the storage unit 10 of this embodiment may store a plurality of objective functions for each situation and purpose. The assumed situation and purpose are arbitrary. For example, possible situations for trains include the time of day, the location where a train accident or transportation failure occurs, the type of accident or transportation failure, the congestion status of each station, and the full capacity of the train.

The above-mentioned time periods include, for example, the morning commuting time, the evening return time, the first train time, and the last train time.The locations where train accidents or transportation disruptions occur include, for example, Tokyo Station. These include stations with many users and connecting trains, stations where trains can turn around, stations connected to a depot (garage), stations with many or few available tracks, etc. Further, the types of accidents or transport obstacles include, for example, problems with equipment such as doors, personal accidents, passenger problems, and the like.

In addition, as a possible purpose for trains, for example, even in the same situation, what the decision maker is trying to do (purpose) in making a timetable adjustment may differ depending on inspiration, mood, and individual differences. For example, suppose that a decision maker wants to give priority to passenger transportation at station A (that is, increase the number of trains departing from station A) and makes a schedule adjustment. In this case, it can be said that the objective function at that time is an objective function in which the term related to station A has a large weight.

In this way, by learning past objective functions under each assumed situation, a railway schedule optimized under those objective functions can be presented to the operator during actual operation. The presented operator can refer to multiple candidates, such as a timetable emphasizing station A, a timetable emphasizing station B, etc., and can therefore judge which one looks best among them.

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

The situation acquisition unit 20 acquires the estimated situation of the current and future vehicles and stops. The situation estimated for a vehicle is, for example, the occupancy rate of the vehicle, the operation status (delay status) of the vehicle, and the like. Further, the situation estimated at the stop includes, for example, the degree of stagnation of passengers at the stop, the degree of crowding of passengers at the stop, and the like.

The situation acquisition unit 20 includes a simulator execution unit 21 and a collected data acquisition unit 22. Note that 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.

The simulator execution unit 21 executes a simulator that simulates boarding and alighting of passengers at each stop, and calculates the degree of retention of passengers at at least one of each stop and vehicle in the present and future, or the currently estimated operation status of the vehicle. get. In other words, by using such a simulator, it is possible to estimate the risks of troubles and delays that may occur in the future.

The simulator execution unit 21 may simulate, for example, the degree of retention of passengers at each stop or vehicle in the present and future, and may simulate the current operation status of the vehicle (for example, the degree of delay, how many minutes later a train will arrive at each platform at each station, etc.). arrival, etc.) may be estimated. For example, by running a simulator, it is possible to estimate a situation where train delays are likely to increase because the station is overflowing with people (more people than the station can accommodate). .

Note that the mode of the simulator executed by the simulator execution unit 21 of this embodiment is arbitrary. For example, at each time t, the distribution p(x, t, a, b) of the number of passengers x departing from station a and reaching station b as their destination is based on previously acquired ticket gate entrance/exit record data at each station. It may be created in advance based on the flow of people, or it may be created using an appropriate model representing the flow of people.

The collected data acquisition unit 22 acquires entry/exit record data at each stop that is collected one after another, and estimates the current degree of stagnation of passengers at each stop. Specifically, the collected data acquisition unit 22 may acquire entry/exit record data of ticket gates at each station and estimate the degree of retention of passengers at each station. For example, the collected data acquisition unit 22 may estimate the degree of retention of passengers at each stop by calculating the number of people entering or leaving the station per hour. This data makes it possible, for example, to grasp the amount of people leaving a station at any given time.

The congestion degree calculation unit 30 calculates the congestion degree of vehicles and stops. Specifically, the congestion degree calculation unit 30 calculates the congestion degree based on the current and future estimated situations of the vehicles and stops acquired by the situation acquisition unit 20.

In this embodiment, the congestion degree calculation unit 30 may calculate the congestion degree of the vehicle and the stop based on the degree of retention of passengers or the operation status. The distribution p of the number of passengers described above can be used as the degree of retention of passengers. Further, the operation status includes the vehicle timetable status and the passenger capacity of each vehicle at the current time. Therefore, the congestion degree calculation unit 30 calculates the degree of congestion at each stop (for example, each platform of each station) using, for example, the distribution p of the number of passengers, the schedule status of the vehicles at the current time, the passenger capacity of each vehicle, etc. The distribution and the distribution of the degree of crowding for each vehicle with different time zones, vehicle types, destinations, etc. may be calculated.

Hereinafter, a specific method for calculating the degree of congestion will be explained using a train as an example. However, the method of calculating the degree of congestion is not limited to the specific example below, and may be any method as long as it is unified throughout.

For example, on a route where only trains that stop at each station are in operation, if the time when the last train arrived at station a is _t1 , then the distribution of the number of passengers waiting for the train on the S-bound platform at station a at time T is f( x, t, a) are expressed by Equation 1 illustrated below. This distribution f can be said to be the degree of passenger retention.

In Equation 1, _YS is a set of stations in the direction of S from station a. Moreover, the distribution p(x, t, a, b) is the distribution of the number of passengers x departing from station a and having station b as their destination at time t, as described above. Note that this distribution p can also be said to be a distribution that changes depending on the operating situation.

Further, by developing the above formula 1, the congestion degree calculation unit 30 may calculate the degree of retention of passengers in consideration of passengers left behind. That is, the congestion degree calculation unit 30 may calculate the congestion degree by taking into account passengers who are left behind on the platform of each station. Specifically, the congestion degree calculation unit 30 calculates the number of passengers waiting on the platform at the train arrival time using Equation 1 above, and then calculates the number of passengers left on board by subtracting the passenger capacity of the train. It's okay. Further, the congestion degree calculation unit 30 may calculate the number of passengers left on board by subtracting the maximum number of passengers instead of the capacity number of passengers, considering the possibility that the occupancy rate exceeds 100%.

The objective function selection unit 40 receives an instruction from the user to select an objective function used for modifying the bus schedule. For example, if objective functions are prepared for each situation and purpose, the objective function selection unit 40 may receive an instruction to select one or more objective functions to be used for optimization from among the prepared objective functions. good. Note that if all of the objective functions prepared in advance are used to modify the schedule, the revised risk output device 100 does not need to include the objective function selection unit 40.

By optimizing the modified schedule output unit 50 and the objective function, a schedule (hereinafter also referred to as a revised diagram) that is a modified version of the current schedule is output. Note that the modified diagram output unit 50 may take any form as long as optimization is possible based on the objective function used in this embodiment. The modified diagram output unit 50 may be realized, for example, by an optimization engine (optimization solver) that performs optimization processing based on the selected objective function. Further, when the objective function is expressed by an Ising model, the modified diagram output unit 50 may cause a quantum computer that solves an optimization problem using quantum annealing to execute the optimization process, for example. That is, when the objective function is expressed by an Ising model, the optimization process may be performed using a quantum computer while a general computer generates a schedule change plan.

The risk calculation unit 60 calculates the risk that occurs at the current time and the risk that occurs due to diagram correction based on the calculated congestion degree. Note that the risk calculated in this embodiment is information that indexes various effects of diagram correction, and is not limited to information that indicates danger. In the following explanation, when we distinguish between risks that occur at the present time (risks that may occur) and risks that occur (may occur) due to diagram modifications, we will refer to the risks that occur at the present time as current risks, and The risks that arise are referred to as modification risks.

For example, the risk calculation unit 60 may calculate the score of the objective function as the risk. Here, the objective function score means the value of the objective function achieved by the optimal solution calculated by the modified diagram output unit 50.

Further, the risk calculation unit 60 may calculate the risk for each assumed cause based on the calculated degree of congestion (for example, the number of passengers waiting for a train at each station). Possible causes include passenger troubles, delays in train operation schedules such as delays in train departure and arrival times, and transportation disruptions.

Note that the size and structure of the platform differs from stop to stop (for example, from station to station), so even if the level of congestion is the same, the risk generally differs. Therefore, a risk occurrence probability model q(t, d, a, e) is prepared in advance for each cause e based on the congestion degree d of each time t and each stop a, and the risk calculation unit 60 calculates the probability model q(t, d, a, e). The risk for each cause may be calculated based on the 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 calculates the risk R(t, e, a) may be calculated. Note that the risk occurrence probability model q may be learned in advance based on performance data, for example, or may be created using an arbitrary model indicating the occurrence probability.

Furthermore, the risk calculation unit 60 may calculate an optimization index for the objective function. Optimization indicators include, for example, passenger boarding time, number of transfers, number of passengers left on board, passenger waiting time at stations, occupancy rate, and number of canceled trains.

The risk output unit 70 outputs the calculated current risk and modified risk. Furthermore, when risks are calculated for each cause, the risk output unit 70 may output the calculated risks for each cause. Furthermore, when the optimization index of the objective function has been calculated, the risk output unit 70 may output the amount of change in the predetermined index from the scheduled timetable in the revised timetable. For example, when the vehicle is a train, the risk output unit 70 outputs information such as 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 on board, and the amount of change in passenger waiting time at the station. , the amount of change in occupancy rate, the number of canceled trains, etc. may be output as the amount of change.

FIG. 3 is an explanatory diagram showing an example of output risks. In the example shown in FIG. 3, the revised timetable output unit 50 outputs the revised timetable D13 to the display device 200, and the risk output unit 70 also displays the current risk and revised risk regarding the revised timetable D13 in association with each other. An example of output to the device 200 is shown.

In this way, the risk output unit 70 outputs the calculated current risk and revised risk. Therefore, the user can quantitatively judge whether or not it is better to make corrections immediately in the current situation.

The situation acquisition 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 timetable output unit 50, and the risk calculation unit 60 The risk output unit 70 may be realized by a processor (for example, a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit)) of a computer that operates according to a program (modified risk output program).

In this case, for example, the program is stored in the storage unit 10, and the processor reads the program and executes the situation acquisition unit 20 (more specifically, the simulator execution unit 21 and the collected data acquisition unit 22) according to the program. It may operate as the congestion degree calculation section 30, the objective function selection section 40, the modified timetable output section 50, the risk calculation section 60, and the risk output section 70. Further, even if the functions of the situation acquisition section 20, congestion degree calculation section 30, objective function selection section 40, modified timetable output section 50, risk calculation section 60, and risk output section 70 are provided in the form of SaaS (Software as a Service), good.

Also, the situation acquisition section 20 (more specifically, the simulator execution section 21 and the collected data acquisition section 22), the congestion degree calculation section 30, the objective function selection section 40, the modified timetable output section 50, and the risk calculation section The unit 60 and the risk output unit 70 may each be realized by dedicated hardware. For example, as described above, when the objective function is expressed by an Ising model, a part of the modified diamond output unit 50 may be realized by a quantum computer. Further, some or all of the components of each device may be realized by a general-purpose or dedicated circuit, a processor, etc., or a combination thereof. These may be configured by a single chip or multiple chips connected via a bus. A part or all of each component of each device may be realized by a combination of the circuits and the like described above and a program.

Also, the situation acquisition section 20 (more specifically, the simulator execution section 21 and the collected data acquisition section 22), the congestion degree calculation section 30, the objective function selection section 40, the modified timetable output section 50, the risk calculation section 60, and the risk When some or all of the components of the output unit 70 are realized by a plurality of information processing devices, circuits, etc., the plurality of information processing devices, circuits, etc. may be centrally arranged or distributed. It's okay. For example, information processing devices, circuits, etc. may be realized as a client server system, a cloud computing system, or the like, in which each is connected via a communication network.

Next, the operation of the modified risk output device 100 of this embodiment will be explained. FIG. 4 is a flowchart showing an example of the operation of the modified risk output device 100 of this embodiment. The congestion degree calculation unit 30 calculates the congestion degree of the vehicle and the 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 revised risk based on the degree of congestion (step S13). Then, the risk output unit 70 outputs the calculated current risk and modified risk (step S14).

As described above, in the present embodiment, the congestion level calculation unit 30 calculates the congestion levels of vehicles and stops, and the revised diagram output unit 50 outputs a revised diagram by optimizing the objective function. Then, the risk calculation unit 60 calculates the current risk and the revised risk based on the degree of congestion, and the risk output unit 70 outputs the calculated current risk and revised risk. Therefore, it is possible to output the results of modifying the diagram and the risks that may occur due to the modification.

Next, an outline of the present invention will be explained. FIG. 5 is a block diagram showing an overview of the modified risk output device according to the present invention. The modified risk output device 80 (for example, the modified risk output device 100) according to the present invention includes a congestion degree calculation unit 81 (for example, a congestion degree calculation unit) that calculates the congestion degree of a vehicle (for example, a train) and a stop (for example, a station). 30) and a diagram output means 82 (for example, modified diagram output 50), a risk calculation means 83 (e.g., risk calculation unit 60) that calculates the current risk, which is the risk that occurs at the present time, and the revised risk, which is the risk that occurs due to the modification of the diagram, based on the degree of congestion; The risk output unit 84 (for example, the risk output unit 70) outputs the current risk and the modified risk.

With such a configuration, it is possible to output the results of modifying the diagram and the risks that may occur due to the modification.

In addition, the risk calculation means 83 calculates the probability of occurrence of risk based on a probability model of risk occurrence (for example, a probability model of risk occurrence q(t, d, a, e)) assumed for each cause based on the congestion degree of each time and each stop. The risk for each cause may be calculated, and the risk output means 84 may output the calculated current risk and modified risk for each cause (for example, by calculating using the above equation 2).

Further, the modified risk output device 80 may include a situation acquisition unit (for example, the situation acquisition unit 20) that acquires the estimated situation of the current and future vehicles and stops. Then, the congestion degree calculation means 81 may calculate the congestion degree based on the estimated situation at the vehicle and the stop.

Specifically, the situation acquisition means may include a simulator execution means (for example, the simulator execution unit 21) that executes a simulator that simulates boarding and alighting of passengers at each stop. Then, the simulator execution means estimates the current and future stagnation degree of passengers at each stop and at least one of the vehicles, or the operation status of the vehicle, and the congestion degree calculation means 81 estimates the stagnation degree of passengers or the operation status of the vehicle, based on the stagnation degree of passengers or the operation status. The congestion degree of the vehicle and the stop may be calculated based on the above.

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

Further, the situation acquisition means may include a collected data acquisition means (for example, the collected data acquisition unit 22) that acquires entry/exit record data at each stop that is sequentially collected. The collected data acquisition means may estimate the current degree of stagnation of passengers at each stop, and the congestion degree calculation means 81 may calculate the degree of congestion of the vehicle and the stop based on the degree of stagnation of passengers.

The modified risk output device 80 also includes an objective function selection unit (for example, an objective function selection unit 40 ). The diagram output means 82 may then output the corrected diagram by optimizing the selected objective function.

Part or all of the above embodiments may be described as in the following additional notes, but are not limited to the following.

(Additional note 1) Modification of the current diagram by optimizing the objective function learned using a congestion degree calculation means that calculates the congestion degree of vehicles and stops, and business history data including diagram change records. a diagram output means for outputting a rear diagram; a risk calculation means for calculating a current risk that is a risk that occurs at the present time; and a revised risk that is a risk that is caused by modifying the diagram based on the congestion degree; A modified risk output device comprising: risk output means for outputting a risk and the modified risk.

(Additional note 2) The risk calculation means calculates the risk for each cause based on the probability model of risk occurrence assumed for each cause based on the congestion degree of each time and each stop, and the risk output means calculates the risk for each calculated cause. The revised risk output device according to supplementary note 1, which outputs the current risk and the revised risk.

(Supplementary note 3) The congestion degree calculation means is provided with a situation acquisition means for acquiring the estimated situation of the vehicle and the stop in the present and future, and the congestion degree calculation means calculates the congestion degree based on the situation calculated for the vehicle and the stop. Or the modified risk output device described in Appendix 2.

(Additional Note 4) The situation acquisition means includes a simulator execution means that executes a simulator that simulates boarding and alighting of passengers at each stop, and the simulator execution means is configured to execute a simulator that executes a simulator that simulates boarding and alighting of passengers at each stop, and the simulator execution means includes a simulator that executes a simulator that simulates boarding and alighting of passengers at each stop, and the simulator execution means includes a simulator that executes a simulator that simulates boarding and alighting of passengers at each stop and a vehicle. The corrected risk output device according to appendix 3, wherein the congestion degree calculation means estimates the congestion degree of the passenger or the operation status of the vehicle, and the congestion degree calculation means calculates the congestion degree of the vehicle and the stop based on the retention degree of the passengers or the operation status. .

(Additional note 5) The simulator execution means uses the distribution of the number of passengers from the first stop to the second stop at each time in the simulator to estimate the degree of passenger retention or operation status, and outputs the corrected risk described in Appendix 4. Device.

(Supplementary Note 6) The situation acquisition means includes a collected data acquisition means that acquires entry/exit record data at each stop that is sequentially collected, and the collected data acquisition means estimates the current degree of stagnation of passengers at each stop; The corrected risk output device according to any one of appendices 3 to 5, wherein the congestion degree calculation means calculates the congestion degree of the vehicle and the stop based on the degree of retention of passengers.

(Additional note 7) The diagram output means is equipped with an objective function selection means that accepts an instruction to select an objective function to be used for optimization from among objective functions prepared for each situation and purpose in which the diagram is changed, and the diagram output means selects the selected objective function. The modified risk output device according to any one of Supplementary Notes 1 to 6, which outputs a corrected diagram by optimizing.

(Additional note 8) By calculating the congestion level of vehicles and stops and optimizing the objective function learned using business history data including diagram change records, a corrected diagram is output by correcting the current diagram. , a current risk that is a risk that occurs at the present time and a revised risk that is a risk that occurs due to modification of the diagram are calculated based on the congestion degree, and the calculated current risk and the revised risk are output. Modified risk output method.

(Appendix 9) Calculate the risk for each cause based on the risk occurrence probability model assumed for each cause based on the congestion degree of each time and each stop, and output the calculated current risk and revised risk for each cause.Appendix 8 Modified risk output method described.

(Additional Note 10) The current diagram is corrected by optimizing the objective function learned by the computer using the congestion degree calculation process that calculates the congestion degree of vehicles and stops, and business history data including diagram change records. a diagram output process that outputs a diagram after the correction, a risk calculation process that calculates the current risk that is the risk that occurs at the current time, and the revised risk that is the risk that occurs due to the correction of the diagram based on the congestion degree; A program storage medium that stores a modified risk output program for executing a risk output process for outputting the current risk and the modified risk.

(Additional Note 11) In the risk calculation process, the computer calculates the risk for each cause based on a probability model of risk occurrence assumed for each cause based on the congestion level of each time and each stop, and in the risk output process, the risk is calculated. The program storage medium according to appendix 10, which stores a modified risk output program that outputs the current risk and modified risk for each cause.

(Additional note 12) The current diagram is corrected by optimizing the objective function learned by the computer using the congestion degree calculation process that calculates the congestion degree of vehicles and stops, and business history data including diagram change records. a diagram output process that outputs a diagram after the correction, a risk calculation process that calculates the current risk that is the risk that occurs at the current time, and the revised risk that is the risk that occurs due to the correction of the diagram based on the congestion degree; A modified risk output program for executing a risk output process for outputting the current risk and the modified risk.

(Additional Note 13) In the risk calculation process, the computer calculates the risk for each cause based on the risk occurrence probability model assumed for each cause based on the congestion level of each time and each stop, and the risk is calculated in the risk output process. The corrected risk output program according to supplementary note 12, which outputs the current risk and corrected risk for each cause.

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. The configuration and details of the present invention can be modified in various ways that can be understood by those skilled in the art within the scope of the present invention.

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

Claims (8)

a congestion degree calculation means for calculating the congestion degree of the vehicle and the stop;
a diagram outputting means for outputting a modified diagram that is a modified current diagram by optimizing an objective function learned using business history data including diagram change records;
risk calculation means for calculating a current risk, which is a risk that occurs at the current time, and a revised risk, which is a risk that occurs due to modification of the diagram, based on the congestion degree;
comprising a risk output means for outputting the calculated current risk and the revised risk ,
The risk calculation means calculates the risk for each cause based on a risk occurrence probability model assumed for each cause based on the congestion degree of each time and each stop,
The risk output means outputs the current risk and the corrected risk for each calculated cause.
A modified risk output device characterized by: comprising a situation acquisition means for acquiring the estimated situation of the current and future vehicles and stops;
The corrected risk output device according to claim 1 , wherein the congestion degree calculation means calculates the congestion degree based on the estimated situation at the vehicle and the stop. The situation acquisition means includes a simulator execution means for executing a simulator that simulates boarding and alighting of passengers at each stop;
The simulator execution means estimates the degree of retention of passengers at at least one of each stop and vehicle, or the operation status of the vehicle, in the present and future;
The corrected risk output device according to claim 2 , wherein the congestion degree calculation means calculates the congestion degree of the vehicle and the stop based on the degree of retention of passengers or the operation status. 4. The corrected risk output device according to claim 3 , wherein the simulator execution means uses the distribution of the number of passengers from the first stop to the second stop in the simulator at each time to estimate the degree of retention of passengers or the operation status. The status acquisition means includes a collected data acquisition means for acquiring entry/exit record data at each stop that is sequentially collected;
The collected data acquisition means estimates the current degree of stagnation of passengers at each stop;
The corrected risk output device according to any one of claims 2 to 4 , wherein the congestion degree calculation means calculates the congestion degree of the vehicle and the stop based on the degree of retention of the passengers. comprising objective function selection means that accepts an instruction to select an objective function to be used for optimization from among objective functions prepared for each situation and purpose for changing the diagram;
The modified risk output device according to any one of claims 1 to 5 , wherein the diagram output means outputs the modified diagram by optimizing the selected objective function. Calculate the congestion level of vehicles and stops,
By optimizing the objective function learned using business history data including diagram change records, the system outputs a modified diagram that is a modified version of the current diagram.
The current risk, which is the risk that occurs at the present moment, and the revised risk , which is the risk that occurs due to the modification of the diagram, are calculated based on the probability of risk occurrence model that is assumed for each cause based on the congestion level and the congestion level of each time and each stop. Calculated for each cause ,
A modified risk output method characterized by outputting the current risk and the modified risk for each calculated cause . to the computer,
Congestion degree calculation processing that calculates the congestion degree of vehicles and stops;
Diagram output processing that outputs a corrected diagram by correcting the current diagram by optimizing an objective function learned using business history data including diagram change records;
a risk calculation process that calculates a current risk that is a risk that occurs at the current time and a revised risk that is a risk that occurs due to modification of the diagram based on the congestion degree;
Executing a risk output process that outputs the calculated current risk and modified risk ;
In the risk calculation process, the risk for each cause is calculated based on a risk occurrence probability model assumed for each cause based on the congestion degree of each time and each stop,
A corrected risk output program for outputting the current risk and the corrected risk for each calculated cause in the risk output process .

Images