Operation support device, operation support method, and program

Abstract

To provide an operation support device, etc., capable of presenting a response policy according to a situation that may arise after a diagram change.SOLUTION: An operation support device according to one aspect of the present disclosure includes: simulation means for simulating the flow of people in a transportation facility using a changed diagram, which is a diagram that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; estimation means for estimating the degree of congestion of a location related to the transportation facility from results of the simulation; and determination means for determining a response policy that satisfies a condition related to the degree of congestion from results of the estimation.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to technology for supporting the operation of transportation facilities. [Background technology]

[0002] Transportation facilities such as railways operate according to a diagram that shows an operation plan. Hereinafter, a diagram will be simply referred to as a "timetable." When an accident or equipment failure occurs, the transportation facility may be interrupted or delayed. In such cases, the predetermined timetable is changed. The transportation facility then operates according to the changed timetable.

[0003] Patent Document 1 discloses a technology related to changing a train schedule. Specifically, Patent Document 1 discloses a technology for simulating the number of passengers boarding a train and updating the train schedule by using travel demand information from past data for a day that is highly similar to the current day.

[0004] As a technology related to simulation, Patent Document 2 discloses a method of performing a simulation using a cell model and number of people information data to obtain congestion within a station as congestion prediction information, and performing a simulation based on a network model modified based on the congestion prediction information to obtain congestion within a station as congestion prediction information. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2018 / 087811 [Patent Document 2] JP 2019-101860 A Summary of the Invention [Problem to be solved by the invention]

[0006] As mentioned above, when a service interruption, delay, or other abnormality occurs in a transportation facility, the timetable will be changed. However, there is no clear policy on how to deal with the abnormality, taking into consideration the situation that may occur when the transportation facility operates according to the changed timetable.

[0007] The present disclosure has been made in consideration of the above-mentioned problems, and one of its objectives is to provide an operation support device etc. that is capable of presenting a response policy in response to a situation that may arise after a timetable change. [Means for solving the problem]

[0008] An operation assistance device according to one aspect of the present disclosure includes a simulation means for simulating the flow of people in a transportation facility using a changed timetable, which is a timetable that can be changed when an abnormality occurs in the operation of the transportation facility, and information regarding the flow of users of the transportation facility, an estimation means for estimating the congestion level of a location related to the transportation facility from the results of the simulation, and a decision means for deciding a response policy that satisfies a condition related to the congestion level from the results of the estimation.

[0009] An operation support method according to one aspect of the present disclosure uses a revised timetable, which is a timetable that may be changed when an abnormality occurs in the operation of a transportation facility, and information regarding the flow of users of the transportation facility to simulate the flow of people in the transportation facility, estimates the degree of congestion in locations related to the transportation facility from the results of the simulation, and determines a response policy that satisfies conditions related to the degree of congestion from the results of the estimation.

[0010] A program according to one aspect of the present disclosure causes a computer to perform the following processes: simulating the flow of people in a transportation facility using a revised timetable, which is a timetable that can be changed when an abnormality occurs in the operation of the transportation facility, and information regarding the flow of users of the transportation facility; estimating the degree of congestion of locations related to the transportation facility from the results of the simulation; and determining a response policy that satisfies a condition related to the degree of congestion from the results of the estimation. Effect of the Invention

[0011] According to the present disclosure, it is possible to present a response policy according to a situation that may arise after a schedule change. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration including a travel assistance device according to the present disclosure. [Diagram 2] 1 is a first block diagram illustrating an example of a functional configuration of a travel assistance device according to the present disclosure. [Diagram 3] 4 is a first flowchart illustrating an example of an operation of a travel assistance device according to the present disclosure. [Figure 4] 1 is a diagram illustrating an example of a configuration of a travel assistance system according to the present disclosure. [Diagram 5] 2 is a second block diagram showing an example of a functional configuration of a travel assistance device according to the present disclosure. FIG. [Figure 6] FIG. 13 is a diagram showing an example of configuration information according to the present disclosure. [Figure 7] FIG. 2 is a diagram showing an example of content to be distributed according to the present disclosure. [Figure 8] 5 is a second flowchart illustrating an example of the operation of the travel assistance device according to the present disclosure. [Figure 9] 11 is a third block diagram illustrating an example of a functional configuration of a travel assistance device according to the present disclosure. FIG. [Figure 10] 4 is a fourth block diagram showing an example of a functional configuration of a travel assistance device according to the present disclosure. FIG. [Figure 11] 10 is a third flowchart illustrating an example of the operation of a travel assistance device according to the present disclosure. [Figure 12] 5 is a fifth block diagram illustrating an example of a functional configuration of a travel assistance device according to the present disclosure. FIG. [Figure 13] 4 is a fourth flowchart illustrating an example of the operation of a travel assistance device according to the present disclosure. [Figure 14]FIG. 2 is a block diagram showing an example of a hardware configuration of a computer device that realizes a travel assistance device according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings, in which each of the drawings is associated with one or more embodiments.

[0014] <First embodiment> An overview of a travel assistance device according to a first embodiment will be described.

[0015] Fig. 1 is a diagram illustrating an example of a configuration including a travel assistance device 100. The travel assistance system 1000 includes at least the travel assistance device 100. In the example of Fig. 1, the travel assistance system 1000 includes the travel assistance device 100 and a management terminal 200. The travel assistance device 100 is communicatively connected to the management terminal 200 via a wireless or wired network.

[0016] The operation support device 100 may be applied in the operation of transportation. An example of a transportation is a railway. For example, the operation support device 100 may perform a simulation based on timetable information and present various information according to the simulation results when operating a railway. The operation support device 100 may be, for example, a server device, but is not limited to this example. The operation support device 100 may be realized as a cloud server. Note that in this disclosure, an example in which the operation support device 100 is applied in the operation of a railway will be mainly described. However, a situation in which the operation support device 100 may be applied is not limited to this example. For example, the operation support device 100 may be applied in the operation of various transportation facilities that transport users by getting on and off at stations or stops.

[0017] The control terminal 200 is a terminal used by employees of a transportation facility. For example, the control terminal may be a terminal used by a commander who issues various commands during the operation of a railway. The control terminal 200 is, for example, a personal computer.

[0018] Next, an example of the functional configuration of the travel assistance device 100 will be described.

[0019] 2 is a block diagram showing an example of a functional configuration of the travel assistance device 100. The travel assistance device 100 includes a simulation unit 110, an estimation unit 120, and a determination unit .

[0020] The simulation unit 110 performs a simulation of people flow in a transportation facility. Specifically, when the transportation facility schedule is changed, the simulation unit 110 performs a simulation of people flow using information on a changed schedule, which is a schedule that may be changed. For example, assume that an abnormality occurs in the operation of the transportation facility due to an accident or the like. In this case, the simulation unit 110 performs a simulation of a change in the time series of people flow when the transportation facility operates according to the changed schedule, for example, based on the changed schedule and information on the flow of users of the transportation facility. Here, the information on the flow of users of the transportation facility is, for example, information indicating the number of inflows and outflows of users for each station, but is not limited to this example.

[0021] In this way, the simulation unit 110 performs a simulation of people flow in the transportation facility by using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users. The simulation unit 110 is an example of a simulation means.

[0022] The estimation unit 120 estimates the congestion degree according to the result of the simulation. The congestion degree is a degree indicating the congestion state. For example, the congestion degree may be an index based on the number of people per unit area, but is not limited to this example. The estimation unit 120 may estimate the congestion degree of a place related to the transportation facility. The place related to the transportation facility is, for example, a train, a station, a platform, etc. Note that the place related to the transportation facility may be a place used by users of the transportation facility, and is not limited to this example. For example, the estimation unit 120 may estimate the congestion degree in time series for each train, station, and platform when the transportation facility operates according to a changed timetable.

[0023] In this way, the estimation unit 120 estimates the degree of congestion in a place related to transportation facilities from the result of the simulation. The estimation unit 120 is an example of an estimation means.

[0024] The determination unit 130 determines a response policy based on the result of the estimation. More specifically, the determination unit 130 determines a response policy for a situation that may occur when a transportation facility operates according to a changed timetable. For example, assume that the estimation unit 120 estimates the congestion degree for each station and platform of a railway. At this time, the determination unit 130 may determine, for example, to allocate station staff to a location where the congestion degree is higher than a threshold value. In addition, the determination unit 130 may determine, for example, to display information indicating that a transfer to a subsequent train is encouraged on a display installed on a platform when the congestion degree of a subsequent train is lower than that of a preceding train. In addition, the determination unit 130 may determine, for example, to notify a taxi company around the station of information indicating that the congestion degree is high when the congestion degree of a station is equal to or higher than a predetermined threshold value. That is, the determination unit 130 may determine a response policy that satisfies a condition related to the congestion degree. Note that the algorithm for determining a response policy is not limited to this example.

[0025] In this manner, the determination unit 130 determines a response policy that satisfies the condition regarding the congestion degree from the result of the estimation. The determination unit 130 is an example of a determination means.

[0026] The determining unit 130 may output information indicating the determined handling policy to the management terminal 200.

[0027] Next, an example of the operation of the travel assistance device 100 will be described with reference to Fig. 3. In this disclosure, each step in a flowchart will be expressed using a number assigned to each step, such as "S1".

[0028] 3 is a flowchart explaining an example of the operation of the operation support device. The simulation unit 110 performs a simulation of people flow in the transportation facility using a changed schedule, which is a schedule that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility (S1). The estimation unit 120 estimates the congestion degree of places related to the transportation facility from the result of the simulation (S2). The determination unit 130 determines a response policy that satisfies a condition related to the congestion degree from the result of the estimation (S3).

[0029] In this way, the traffic support device 100 of the first embodiment performs a simulation of people flow in a transportation facility using a changed schedule, which is a schedule that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility. The traffic support device 100 also estimates the congestion degree of places related to the transportation facility from the result of the simulation. Then, the traffic support device 100 determines a response policy that satisfies a condition related to the congestion degree from the result of the estimation.

[0030] When a schedule is changed due to an abnormality, the behavior of transportation users differs from that when the transportation operates according to a normal schedule. In response to this, the traffic assistance device 100, with the above configuration, can determine a response policy taking into account situations that may occur when the transportation operates according to the changed schedule. In other words, the traffic assistance device 100 can present a response policy according to situations that may occur after the schedule is changed.

[0031] <Second embodiment> Next, a travel support device according to a second embodiment will be described. In the second embodiment, a further example of the travel support device 100 described in the first embodiment will be described. Note that some of the contents overlapping with the first embodiment will not be described.

[0032] FIG. 4 is a diagram showing a schematic diagram of an example of the configuration of the operation support system 1000. In the example of FIG. 4, the operation support device 100 is communicably connected to the management terminal 200, the display 300, and the mobile terminal 400 via a wireless or wired network. The operation support device 100 performs various estimations regarding situations that may occur when a transportation facility operates according to a changed timetable. In addition, the operation support device 100 determines a course of action for the situation based on the results of the estimation. Then, the operation support device 100 may perform various outputs to at least one of the management terminal 200, the display 300, and the mobile terminal 400 according to the determined course of action.

[0033] The management terminal 200 is a terminal used by an employee of the transportation facility. For example, the management terminal 200 may be a terminal used by a commander of a railway company. The management terminal 200 may also be a terminal installed in a station or the like. The display 300 may be installed in a vehicle or a station of the transportation facility. For example, the display may be a signage device installed near the door of a railway vehicle. The mobile terminal 400 may be a terminal carried by a user of the transportation facility. For example, the mobile terminal 400 may be a smartphone, a tablet terminal, or the like.

[0034] [Details of the driving support device 100] Fig. 5 is a block diagram showing an example of a functional configuration of the travel assistance device 100. As shown in Fig. 5, the travel assistance device 100 includes a simulation unit 110, an estimation unit 120, a determination unit 130, and an output unit 140. The travel assistance device 100 also includes a storage device 190. Note that the storage device 190 may be an external device connected to the travel assistance device 100 so as to be able to communicate with the travel assistance device 100.

[0035] The simulation unit 110 includes a generation unit 1101 and a prediction unit 1102. The generation unit 1101 generates a transportation schedule. The generation unit 1101 is an example of a generation means. The prediction unit 1102 predicts people flow when the transportation operates according to the generated schedule. The prediction unit 1102 is an example of a prediction means.

[0036] The generating unit 1101 generates an altered timetable when an abnormality occurs in a transportation facility. Predetermined information on a normal timetable is stored in the storage device 190. For example, the generating unit 1101 generates an altered timetable by changing the operation order and operation route of trains affected by the abnormality from the normal timetable based on operation data related to the abnormality. The operation data related to the abnormality includes information on the location where the cause of the abnormality occurred, such as an accident or equipment failure, the time required to resolve the cause, and information indicating the line and train affected by the abnormality. The operation data related to the abnormality is acquired from the management terminal 200, for example. The generating unit 1101 generates an altered timetable such that the operation of the transportation facility after the abnormality occurs returns to operation according to the normal timetable.

[0037] The method of generating the modified timetable may be realized by various methods. The generating unit 1101 may generate the modified timetable using a learning model generated by machine learning. For example, the generating unit 1101 may generate the modified timetable using a learning model generated by reinforcement learning. In this case, for example, the operation status and delay time of the transportation facility are defined as the state. In addition, a positive reward is set when the time until the operation returns to the normal timetable is shortened, and a negative reward is set when the time is lengthened. Then, an agent is set that determines the action required when the timetable is changed. The action at this time includes, for example, a change in the train's stop station, a change in the departure and arrival time, and a change in the operation route. Then, the agent is made to learn an action that transitions from the defined state to a state that has a higher reward. By using the agent that has been trained in this way, the generating unit 1101 can generate a modified timetable that shortens the time until the operation returns to the normal timetable.

[0038] Without being limited to this example, the generating unit 1101 may generate the changed schedule by using a learning model that has learned the relationship between operation data related to past abnormalities and schedule change patterns. In this case, the learning model may be generated by various algorithms such as a neural network, a decision tree, and a random forest.

[0039] The prediction unit 1102 uses information on the flow of users of the transportation facility to predict future pedestrian flow when the transportation facility operates according to the generated revised timetable. The information on user flow may be information indicating the inflow and outflow of users for each station. For example, the information on user flow is information indicating the number of users over time for each combination of departure point and destination. Such information indicating the number of users over time for each combination of departure point and destination is sometimes called OD (Origin Destination) data. The information on user flow is stored in the storage device 190. The information on user flow may be information on past performance.

[0040] The prediction unit 1102 predicts the transfer routes of users when the train operates according to the changed timetable, using information on the flow of users. The prediction unit 1102 then predicts the number of users for each train, station, or platform.

[0041] At this time, the prediction unit 1102 may predict the flow of people based on a simulation model generated in advance. The simulation model may be, for example, a model in which the relationship between the information on the flow of users and the information on the timetable, and the flow of people is learned by machine learning. In this case, the machine learning may be reinforcement learning, or may be a neural network, a decision tree, a random forest, or the like.

[0042] The prediction unit 1102 may output OD data predicted when operating according to the changed schedule. The prediction unit 1102 stores information indicating the predicted pedestrian flow in the storage device 190.

[0043] The modified timetable may be generated according to a prediction of people flow. For example, the generation unit 1101 generates the modified timetable. Then, the prediction unit 1102 predicts people flow for the generated modified timetable. At this time, the generation unit 1101 may generate the modified timetable again according to the result of the prediction by the prediction unit 1102. For example, the generation unit 1101 may generate the modified timetable until the number of users at a specific station after the occurrence of an abnormality becomes less than a threshold value. Furthermore, the generation unit 1101 may generate the modified timetable until the time until the number of users at a station after the occurrence of an abnormality returns to a normal state becomes less than a threshold value. That is, the generation unit 1101 may generate the modified timetable in which the index related to people flow becomes a desired value. Information indicating the predicted people flow is associated with information indicating the corresponding modified timetable and stored in the storage device 190.

[0044] The estimation unit 120 estimates the congestion degree according to the result of the simulation by the simulation unit 110. The congestion degree may be an index based on the number of users per unit area. For example, the congestion degree may be a value that increases as the number of users increases. The congestion degree may be a value that changes stepwise each time the number of users exceeds one or more thresholds. The congestion degree may be the number of users per unit area itself, or the density of users per unit area. The estimation unit 120 estimates the congestion degree in time series for each location related to the transportation facility. The locations related to the transportation facility include trains, stations, and platforms, but are not limited to this example. A train refers to a service that includes one or more vehicles. For example, the estimation unit 120 may estimate the congestion degree in time series for each train, or may estimate the congestion degree in time series for each vehicle of the train. The estimation unit 120 may estimate the congestion degree in time series for each platform, or may estimate the congestion degree for each divided area in the platform.

[0045] The determination unit 130 determines a response policy based on the result of the estimation by the estimation unit 120. The response policy may indicate measures that can be taken in a situation that may occur when the transportation facility operates according to the changed timetable. Examples of the response policies include the allocation of transportation facility employees, the distribution of various contents, and notification to organizations related to the transportation facility. In the following, an example will be described in which the determination unit 130 determines various response policies based on the result of the estimation by the estimation unit 120 and conditions related to the congestion degree.

[0046] [Transportation employee deployment] The determination unit 130 may determine the allocation of employees when the transportation facility operates according to a changed timetable. At this time, the determination unit 130 may generate allocation information indicating the allocation of employees. In this example, an example of determining the allocation of railway station staff will be described.

[0047] Assume that the estimation unit 120 estimates the congestion degree of each station or each platform in time series. At this time, the determination unit 130 may determine to allocate station staff to locations where the congestion degree is higher than a threshold. For example, the determination unit 130 may identify a station or platform where the congestion degree is higher than a threshold for each time period after the occurrence of the abnormality. Alternatively, the determination unit 130 may identify a station or platform where the congestion degree is the highest for each time period after the occurrence of the abnormality. In this case, the determination unit 130 generates allocation information indicating that more station staff will be allocated to the identified station or platform than to other stations or platforms.

[0048] Furthermore, the determination unit 130 may determine the allocation of station staff by solving an optimization problem regarding the allocation of station staff. In this case, an example of the objective function is, for example, a function that minimizes the time until the congestion level decreases. The optimal allocation of station staff shortens the time until the congestion level decreases, which leads to an improvement in the quality of service for users. Examples of explanatory variables include a changed schedule, an estimated congestion level, working hours of station staff, and the number of station staff allocated. Examples of constraint conditions include the number of station staff and the hours that station staff are available to work. By solving such an optimization problem, the determination unit 130 may determine the allocation of station staff that minimizes the time required to eliminate congestion.

[0049] The determination unit 130 may generate placement information indicating the placement of the determined station staff. Fig. 6 is a diagram showing an example of the placement information. In the example of Fig. 6, station staff to be placed at each station platform at each predetermined time are shown. The generated placement information may be stored in the storage device 190. Furthermore, the output unit 140 may output the placement information to the management terminal 200.

[0050] [Content Distribution] The decision unit 130 may decide to distribute the content.

[0051] Assume that the estimation unit 120 estimates the congestion degree of each car or each train in time series. At this time, the determination unit 130 may determine the content to be distributed and the distribution destination of the content according to the congestion degree. For example, when the congestion degree of the following train is lower than that of the preceding train, the determination unit 130 determines to distribute the content that encourages passengers to transfer to the following train. Such content is content that has as one of its purposes the leveling of the congestion degree among a plurality of trains. At this time, the determination unit 130 determines the display 300 that is to be the distribution destination of the content. For example, the determination unit 130 may determine the display on the platform of the station where the preceding train arrives and the display installed in the car of the preceding train as the distribution destination of the content.

[0052] Also, for example, when the congestion level of a train exceeds a threshold, the determination unit 130 may determine to deliver advertising content. In this case, the advertisement is, for example, an advertisement introducing a store near a station where the train arrives. Such advertising content is intended to promote a reduction in congestion at stations and platforms, promote customer acquisition for stores, and the like. The determination unit 130 may determine that the content is to be delivered to a display on the platform of the station where the train arrives and a display installed in the train's carriage.

[0053] Furthermore, the determination unit 130 may determine the content and the delivery destination of the content by solving an optimization problem related to the delivery of the content. In this case, an example of the objective function is a function that maximizes the probability that a user who views the content will react. For example, the congestion level is expected to decrease as a result of users moving due to the content. In other words, the delivery of the content leads to an improvement in the quality of service for users. The explanatory variables include a changed schedule, an estimated congestion level, the type of content, and the installation location of the display. The constraint conditions include, for example, the business hours of the store. By solving such an optimization problem, the determination unit 130 may determine the content and the delivery destination of the content that maximizes the possibility that users of the transportation facility will react.

[0054] The determined content may be output by the output unit 140. For example, it is assumed that the determination unit 130 determines to distribute content indicating that a specific train will be changed to a display in the vehicle. In this case, for example, content as shown in FIG. 7 is output by the output unit 140. FIG. 7 is a diagram showing an example of the distributed content. In the example of FIG. 7, text information urging a user to change to a subsequent train is output to a display installed in the vehicle. Furthermore, in the example of FIG. 7, information indicating the congestion degree estimated for the train in which the display is installed and the congestion degree estimated for the subsequent train is output. In this way, the content may include information indicating the congestion degree estimated for each train.

[0055] [Notification to transportation-related organizations] The decision unit 130 may decide to notify organizations associated with the transportation facility.

[0056] The organizations related to the transportation facilities are, for example, taxi companies, hotels, hospitals, and the like within a predetermined range from the station. When the congestion level is higher than a threshold, the decision unit 130 may decide to notify the organizations related to the transportation facilities that the congestion level is high. For example, when the congestion level is high, users may travel by taxi. Therefore, a taxi company that has been notified that the congestion level is high can send more taxis to the station. Also, for example, when a railway is suspended, the congestion level increases. In such a case, users may stay at a hotel. Therefore, a hotel that has been notified that the congestion level is high can make various preparations in anticipation of an increase in guests. Also, when the congestion level is high, there is a possibility that injuries may occur due to trouble or the like. Therefore, a hospital that has been notified that the congestion level is high can prepare for a report due to the occurrence of injuries.

[0057] When the decision unit 130 decides to give a notification, the output unit 140 gives the notification. For example, when the notification is to be given to a taxi company, the output unit 140 gives a notification indicating the time period during which the congestion degree will be high to the communication terminal of the taxi company.

[0058] As described above, the determination unit 130 can determine various types of handling policies that satisfy conditions related to the congestion level based on the results of the estimation. As an example, the determination unit 130 may determine a handling policy by using information related to the congestion level to solve an optimization problem in which an index related to services provided to users of the transportation facility is an objective function. Note that the types of handling policies and the method of determining the handling policies are not limited to the above example.

[0059] [Example of operation of the driving support device 100] Next, an example of the operation of the travel assistance device 100 will be described with reference to FIG.

[0060] FIG. 8 is a flowchart explaining an example of the operation of the operation support device 100. The generation unit 1101 generates a changed timetable (S101). The prediction unit 1102 predicts people flow when a transportation facility operates according to the changed timetable (S102). For example, the prediction unit 1102 predicts users' transfer routes when the transportation facility operates according to the changed timetable using information on user flow. Then, the prediction unit 1102 may predict the number of users for each train, each station, or each platform.

[0061] The estimation unit 120 estimates the congestion degree (S103). For example, the estimation unit 120 estimates the congestion degree in time series for each location related to a transportation facility based on the result of the prediction by the prediction unit 1102.

[0062] The determination unit 130 determines a response policy according to the result of the estimation (S104). Specifically, the determination unit 130 determines various response policies based on the result of the estimation and conditions related to the congestion degree. At this time, the determination unit 130 may determine the response policy by solving an optimization problem in which an index related to services for users of the transportation facility is an objective function. For example, the determination unit 130 may determine the allocation of station staff or may determine the content to be distributed and the distribution destination of the content by solving the optimization problem.

[0063] The output unit 140 performs output according to the determined handling policy (S105). For example, when the determination unit 130 determines the placement of station staff, the determination unit 130 generates placement information. In this case, the output unit 140 outputs the placement information to the management terminal 200. For example, when the determination unit 130 determines the content to be distributed and the distribution destination, the output unit 140 outputs the content to the determined distribution destination.

[0064] Note that this operation example is merely an example. That is, the operation of the traffic support device 100 is not limited to the above example. For example, the process of S101 and the process of S102 may be repeated. That is, the generation unit 1101 may generate a modified schedule until the index related to the predicted people flow reaches a desired value.

[0065] In this way, the traffic support device 100 of the second embodiment uses a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility to perform a simulation of people flow in the transportation facility. The traffic support device 100 also estimates the congestion degree of places related to the transportation facility from the result of the simulation. Then, the traffic support device 100 determines a response policy that satisfies a condition related to the congestion degree from the result of the estimation.

[0066] When a schedule is changed due to an abnormality, the behavior of transportation users differs from that when the transportation operates according to a normal schedule. In response to this, the traffic assistance device 100, with the above configuration, can determine a response policy taking into account situations that may occur when the transportation operates according to the changed schedule. In other words, the traffic assistance device 100 can present a response policy according to situations that may occur after the schedule is changed.

[0067] Furthermore, when determining a countermeasure policy, the traffic support device 100 may use information on the congestion level to solve an optimization problem with an index related to services for users of the transportation facility as an objective function to determine the countermeasure policy. At this time, the traffic support device 100 may determine, for example, the allocation of station staff that minimizes the time required to resolve the congestion. In this way, the traffic support device 100 can determine the allocation of station staff appropriate for situations that may occur after the change in the timetable.

[0068] Furthermore, the traffic assistance device 100 may determine the content and the delivery destination of the content that maximizes the possibility of a response from users of the transportation facility. In this way, the traffic assistance device 100 can deliver the content to the delivery destination that is expected to be more effective in the situation that may occur after the change of the schedule.

[0069] [Variation 1] The destination of the content delivery includes the mobile terminal 400 of the user. That is, the travel assistance device 100 may deliver the content to the mobile terminal 400 of the user according to the result of the estimation by the estimation unit 120. In this case, the travel assistance device 100 may deliver the content via an application installed in the mobile terminal 400.

[0070] Fig. 9 is a block diagram showing an example of a functional configuration of the travel assistance device 100. For example, as shown in Fig. 9, the travel assistance device 100 may include an acquisition unit 150. The acquisition unit 150 acquires location information of the mobile terminal 400. The location information may be information based on a signal transmitted from a positioning satellite of the Global Navigation Satellite System (GNSS), such as a Global Positioning System (GPS) satellite.

[0071] For example, when the following train is less crowded than the preceding train, the determination unit 130 determines to deliver content indicating that the user will transfer to the following train. At this time, the determination unit 130 identifies the mobile terminal 400 of the user who is on the preceding train based on the location information acquired by the acquisition unit 150. Alternatively, the determination unit 130 may identify the mobile terminal 400 of the user who is at the station where the preceding train arrives based on the location information. Then, the determination unit 130 may determine to deliver content indicating that the user will transfer to the following train to the identified mobile terminal 400. The same applies when advertising content is delivered. Note that when advertising content is delivered to the user's mobile terminal 400, the content may include a coupon that can be used at a store.

[0072] [Variation 2] The estimation unit 120 may estimate further indicators. Specifically, the estimation unit 120 may estimate the fatigue level of users of the means of transport. For example, the estimation unit 120 estimates the congestion level of each train or vehicle. Then, the estimation unit 120 may calculate the fatigue level of users riding on the train or vehicle according to the estimated congestion level. In this case, the greater the congestion level, the greater the fatigue level. The estimation unit 120 may also calculate the fatigue level according to the difference between the normal congestion level and the estimated congestion level. The normal congestion level indicates, for example, the congestion level of the same train or at the same time when the means of transport operates according to a normal timetable. For example, the greater the difference between the normal congestion level and the estimated congestion level, the greater the fatigue level. In this way, the estimation unit 120 may estimate the fatigue level of users of the means of transport based on the congestion level.

[0073] The fatigue level does not necessarily have to be as shown in this example. For example, the prediction unit 1102 predicts the flow of people. From the predicted number of train or vehicle users and the predicted OD data, the estimation unit 120 estimates the ratio of users whose riding time is equal to or longer than a threshold among the users of the train or vehicle. This estimated ratio may be the fatigue level.

[0074] Alternatively, the estimation unit 120 may estimate the fatigue level as a weighted sum considering the user's condition. For example, when the users include people who are considered to need support from a medical point of view, such as sick people, elderly people, and people with disabilities, the estimation unit 120 may estimate the fatigue level of the users to be high. In this case, for example, the acquisition unit 150 may acquire the location information from the mobile terminal 400 along with the predetermined conditions of the users (such as age and the presence or absence of a disease).

[0075] For example, when a user satisfies a predetermined condition (such as age and the presence or absence of a disease), the estimation unit 120 may estimate the fatigue level by calculating a value obtained by multiplying the riding time of the user by a coefficient of 1 or more and comparing the calculated value with a threshold value. In this way, the estimation unit 120 can estimate the fatigue level based on the actual situation of the user by estimating the congestion level from the perspective of medical care and healthcare.

[0076] The determination unit 130 may determine a countermeasure policy that satisfies a condition related to the fatigue level based on the estimated fatigue level. For example, it is assumed that the estimation unit 120 estimates the time-series fatigue level for each train or each car of the train. For example, when the fatigue level of a user on a specific train exceeds a threshold, the determination unit 130 may determine to deliver the advertisement content to a display installed in the car of the specific train. Also, as in the first modification, when the location information of the mobile terminal 400 can be acquired, the determination unit 130 may determine to deliver the advertisement content to the mobile terminal 400 of the user on the specific train.

[0077] Also in this modified example, the determination unit 130 may determine the content and the delivery destination of the content by solving an optimization problem regarding the delivery of the content.

[0078] <Third embodiment> Next, a traffic support device according to a third embodiment will be described. In the third embodiment, an example in which a plurality of modified timetables are generated will be described. Note that some of the contents overlapping with the first and second embodiments will not be described.

[0079] [Details of Driving Support Device 101] Fig. 10 is a block diagram showing an example of a functional configuration of the travel assistance device 101. The travel assistance device 101 may be configured in place of the travel assistance device 100 of the travel assistance system 1000 of Fig. 4. The travel assistance device 101 includes a simulation unit 111, an estimation unit 121, a determination unit 131, an output unit 140, an acquisition unit 150, and a selection unit 160. The travel assistance device 101 also includes a storage device 190.

[0080] The simulation unit 111 includes a generation unit 1111 and a prediction unit 1112. The generation unit 1111 generates a plurality of changed timetables. Each of the plurality of changed timetables indicates a different operation plan. The prediction unit 1112 predicts people flow for each changed timetable. More specifically, the prediction unit 1112 predicts future people flow when the transportation facility operates according to each of the plurality of changed timetables, based on information on the flow of users of the transportation facility. The prediction unit 1112 may store each piece of information indicating the predicted people flow in the storage device 190 in association with the corresponding changed timetable.

[0081] The estimation unit 121 estimates a congestion degree for each piece of information indicating a predicted pedestrian flow. Here, each estimated congestion degree corresponds to each changed schedule. That is, the estimation unit 121 estimates a congestion degree for each changed schedule. The estimation unit 121 may store each estimated congestion degree in the storage device 190 in association with the corresponding changed schedule.

[0082] The selection unit 160 selects one of the multiple changed timetables by comparing the estimated congestion degrees. The selection unit 160 is an example of a selection means. For example, the selection unit 160 extracts the congestion degree at a specific location for each changed timetable. Then, the selection unit 160 may select, from the multiple changed timetables, the changed timetable with the smallest maximum value of the extracted congestion degrees. Alternatively, the selection unit 160 may select, from the multiple changed timetables, the changed timetable with the shortest time until the extracted congestion degree decreases to a predetermined value. Note that the method of selecting the changed timetable is not limited to this example.

[0083] The determination unit 131 determines a course of action based on the result of estimation corresponding to the changed schedule selected by the selection unit 160.

[0084] [Example of operation of the driving support device 101] Next, an example of the operation of the travel assistance device 101 will be described with reference to FIG.

[0085] 11 is a flowchart illustrating an example of the operation of the traffic support device 101. The generation unit 1111 generates a plurality of changed timetables (S201). The prediction unit 1112 predicts the flow of people when transportation operates according to each of the changed timetables (S202).

[0086] The estimation unit 121 estimates the congestion level for each changed schedule (S203). The selection unit 160 selects one of the changed schedules based on the estimated congestion level (S204). The determination unit 131 determines a course of action based on the result of estimation corresponding to the selected changed schedule (S205). The output unit 140 performs output according to the determined course of action (S206).

[0087] Note that this operation example is merely an example, and the operation of the travel assistance device 101 is not limited to the above example.

[0088] In this way, the travel assistance device 101 of the third embodiment generates multiple changed timetables and predicts people flow for each changed timetable. The travel assistance device 101 also estimates the congestion degree for each changed timetable. The travel assistance device 101 also selects one of the multiple changed timetables based on the estimated congestion degree. Then, the travel assistance device 101 determines a response policy based on the estimation result corresponding to the selected changed timetable.

[0089] When an abnormality occurs, there is a need to suppress congestion as much as possible. In response to this, the travel assistance device 101 can perform evaluation of multiple modified timetables based on the congestion degree. Therefore, the travel assistance device 101 can present, for example, a modified timetable that can suppress congestion as much as possible.

[0090] [Variation 3] The travel assistance device 101 may select a modified schedule based on the fatigue level.

[0091] Specifically, the estimation unit 121 estimates the congestion degree for each changed schedule. Then, the estimation unit 121 estimates the fatigue degree based on the estimated congestion degree.

[0092] The selection unit 160 selects one of a plurality of changed timetables based on the estimated fatigue level. For example, the selection unit 160 extracts the fatigue level at a specific location for each changed timetable. Then, the selection unit 160 may select, from the plurality of changed timetables, the changed timetable with the smallest maximum value of the extracted fatigue level. Alternatively, the selection unit 160 may select, from the plurality of changed timetables, the changed timetable with the shortest time until the extracted fatigue level decreases to a predetermined value. Note that the method of selecting the changed timetable is not limited to this example.

[0093] Then, the determination unit 131 determines a response policy that satisfies the condition regarding the fatigue level based on the result of the estimation corresponding to the selected changed timetable.

[0094] This allows the travel assistance device 101 to perform evaluations of a plurality of changed schedules based on the fatigue level.

[0095] [Variation 4] The selection of the schedule change may be made by a user, an example of which is a train operator.

[0096] For example, it is assumed that the congestion degree or fatigue degree is estimated for each changed timetable by the estimation unit 121. At this time, the output unit 140 outputs, to the management terminal 200, information indicating the multiple changed timetables and information indicating the congestion degree or fatigue degree estimated for each changed timetable.

[0097] A user of the management terminal 200 selects one of the changed timetables by using an input device included in the management terminal 200. The selection unit 160 accepts the selection. Then, the determination unit 131 determines a course of action based on the estimation result corresponding to the changed timetable selected by the user.

[0098] When an abnormality occurs, in addition to the need to suppress congestion and fatigue levels, there is also a need to minimize changes to the schedule. In this example, the traffic support device 101 can present to the user information indicating multiple changed schedules and the results of estimation for each of the changed schedules. This allows the traffic support device 101 to prompt the user to evaluate the changed schedule taking into account the contents of the changed schedule. Then, the traffic support device 101 can accept the selection of a changed schedule taking into account the congestion level or fatigue level and the contents of the changed schedule.

[0099] [Variation 5] A response policy may be determined for each of the multiple schedule changes.

[0100] The estimation unit 121 estimates the congestion level or fatigue level for each changed timetable. The determination unit 131 determines a handling policy for each changed timetable based on the result of estimation by the estimation unit 121. At this time, the determination unit 131 generates information indicating the handling policy determined for each changed timetable. At this time, the information indicating the handling policy may include information regarding the objective function and explanatory variables of the optimization problem used when determining the handling policy. Then, the output unit 140 outputs information indicating the multiple changed timetables and information indicating the handling policy determined for each changed timetable to the management terminal 200.

[0101] That is, in this example, the operation support device 101 can present the contents of possible countermeasures for each changed schedule to the user of the management terminal 200. This allows the operation support device 101 to prompt the user to evaluate the changed schedule taking into account the contents of the countermeasures.

[0102] The selection unit 160 may accept a selection of any of the changed timetables from the user of the management terminal 200. As a result, the selected changed timetable may be reflected in a system that manages the operation of transportation facilities, for example.

[0103] <Fourth embodiment> Next, a fourth embodiment of the operation support device will be described. In the fourth embodiment, an example in which various evaluations are performed after a transportation facility operates according to a changed timetable will be described. Note that some of the contents that overlap with the first, second, and third embodiments will not be described.

[0104] [Details of the operation support device 102] Fig. 12 is a block diagram showing an example of a functional configuration of the travel assistance device 102. The travel assistance device 102 may be configured in place of the travel assistance device 100 of the travel assistance system 1000 of Fig. 4. The travel assistance device 102 includes a simulation unit 111, an estimation unit 121, a determination unit 131, an output unit 140, an acquisition unit 151, a selection unit 160, and an evaluation unit 170. The travel assistance device 102 also includes a storage device 190.

[0105] The acquisition unit 151 acquires various data. When an abnormality occurs in a transportation facility, the generation unit 1111 generates a changed timetable. The acquisition unit 151 acquires performance data related to the situation when the transportation facility operates according to the changed timetable. As an example, the acquisition unit 151 acquires statistical data related to users when the transportation facility operates according to the changed timetable. The acquisition unit 151 is an example of an acquisition means.

[0106] An example of statistical data is the number of passengers per station, per platform, or per train. The number of passengers at a station or platform can be calculated based on information detected by a sensor such as a camera. Alternatively, the number of passengers at a station or platform may be calculated based on location information of the mobile terminal 400. Alternatively, the number of passengers at a station or platform may be calculated based on information related to an integrated circuit (IC) card and ticket read by a ticket gate, and on the performance value of OD data. The number of passengers on a train can be calculated based on information detected by a sensor such as a camera, a 3D sensor, and a weight sensor.

[0107] The acquiring unit 151 may acquire, as the statistical data, information indicating the number of users in a time series at a place related to the transportation facility after the occurrence of the abnormality. The acquiring unit 151 may also acquire, as the statistical data, the degree of congestion in a time series at a place related to the transportation facility after the occurrence of the abnormality.

[0108] The evaluation unit 170 performs various evaluations using the statistical data acquired by the acquisition unit 151. As an example, the evaluation unit 170 generates evaluation information regarding the simulation based on the statistical data and the result of the simulation by the simulation unit 111. The evaluation unit 170 is an example of an evaluation means.

[0109] For example, the evaluation unit 170 compares the statistical data with information indicating the flow of people predicted by the prediction unit 1112. More specifically, the number of users based on the statistical data in a specific location and time period is compared with the predicted number of users. The evaluation unit 170 calculates an index indicating the accuracy of the simulation according to the result of the comparison. Then, the evaluation unit 170 generates evaluation information indicating the calculated index. Note that the evaluation information may be information indicating the result of the comparison. Then, for example, the evaluation information is output to the management terminal 200 by the output unit 140.

[0110] In this way, the travel assistance device 102 can allow the user to understand how accurately the simulation was performed. In addition, when the simulation is performed based on a simulation model generated by machine learning, it is also possible to improve the accuracy of the simulation model by performing further learning based on such evaluation information.

[0111] The subject of evaluation by the evaluation unit 170 and the method of evaluation are not limited to the above examples. For example, the evaluation unit 170 may generate evaluation information regarding the changed schedule based on statistical data.

[0112] For example, the evaluation unit 170 evaluates the changed schedule using the congestion degree based on statistical data. As an example, the evaluation unit 170 generates evaluation information indicating whether the changed schedule has suppressed the congestion degree depending on whether the congestion degree based on statistical data exceeds a threshold. This allows the operation support device 102 to allow the user to understand whether the changed schedule has had an effect on suppressing the congestion degree.

[0113] The evaluation unit 170 may also use statistical data to evaluate the handling policy. For example, assume that station staff are assigned according to the assignment of station staff indicated as the handling policy. At this time, the evaluation unit 170 extracts a transition in the congestion degree at the location where the station staff is assigned from the congestion degree based on the statistical data. Then, the evaluation unit 170 generates evaluation information on the assignment of station staff from the time required to resolve the congestion degree based on the extracted transition. In this way, by generating evaluation information on the handling policy, the operation support device 102 can allow the user to understand to what extent the handling policy has affected the suppression of the congestion degree.

[0114] [Example of operation of the driving support device 102] Next, an example of the operation of the traffic support device 102 will be described with reference to Fig. 13. In this operation example, the process shown in Fig. 8 or Fig. 11 is performed, and the traffic support device 102 evaluates the simulation after the transportation facility operates according to the changed timetable.

[0115] 13 is a flowchart for explaining an example of the operation of the operation support device 102. The acquisition unit 151 acquires statistical data (S301). For example, the acquisition unit 151 acquires, as statistical data, information indicating the number of users over time at locations related to a transportation facility when the transportation facility operates according to a changed timetable.

[0116] The evaluation unit 170 compares the statistical data with information indicating the predicted human flow (S302). For example, the evaluation unit 170 compares the number of users based on the statistical data with the predicted number of users in a specific location and time period. The evaluation unit 170 also generates evaluation information according to the result of the comparison (S303). For example, the evaluation unit 170 generates evaluation information indicating an index indicating the accuracy of the simulation.

[0117] Then, the output unit 140 outputs the generated evaluation information to the management terminal 200 (S304).

[0118] Note that this operation example is merely an example, and the operation of the travel assistance device 102 is not limited to the above example.

[0119] In this way, the traffic assistance device 102 of the fourth embodiment acquires statistical data on users when public transportation operates according to a changed timetable, and generates evaluation information on the simulation using the statistical data and the results of the simulation.

[0120] This allows the travel assistance device 102 to present evaluation information regarding the simulation. Therefore, the travel assistance device 102 can allow the user to understand how accurately the simulation was performed by presenting, for example, statistical data and the results of the simulation.

[0121] [Variation 6] The evaluation of the response policy is not limited to the above example. For example, when advertisement content is distributed to the mobile terminal 400, the travel assistance device 102 can also perform the following process.

[0122] In this case, the acquiring unit 151 may acquire statistical data regarding the user's reaction to the content. Examples of the statistical data include the ratio of users who caused the content to be displayed on the mobile terminal 400, and the number of users who performed some operation on the displayed content. In addition, when the content is an advertisement including a coupon, the statistical data may be the number of times the coupon was used, or the ratio of the number of times the coupon was used to the number of distribution destinations, etc.

[0123] The evaluation unit 170 uses the statistical data to evaluate the content distribution. As an example, the evaluation unit 170 generates evaluation information indicating whether the content distribution was effective or not, depending on whether the value indicated in the statistical data exceeds a threshold. Alternatively, the evaluation unit 170 may generate evaluation information indicating the effectiveness of the content distribution in stages, depending on the value indicated in the statistical data. Then, the output unit 140 outputs the generated evaluation information to the management terminal 200.

[0124] This allows the travel assistance device 102 to allow the user to understand how effective the content distribution was.

[0125] <Example of hardware configuration for driving support device> The hardware constituting the travel support device of the above-mentioned first, second, third, and fourth embodiments will be described. FIG. 14 is a block diagram showing an example of the hardware configuration of a computer device constituting the travel support device in each embodiment. The travel support device and the travel support method described in each embodiment and each modified example are realized in a computer device 90. For example, the travel support device and the like described in each embodiment and each modified example may have the hardware configuration shown in FIG.

[0126] 14, a computer device 90 includes a processor 91, a RAM (Random Access Memory) 92, a ROM (Read Only Memory) 93, a storage device 94, an input / output interface 95, a bus 96, and a drive device 97. Note that the driving assistance device and the like may be realized by a plurality of electric circuits.

[0127] The storage device 94 stores a program (computer program) 98. The processor 91 executes the program 98 of the reception support system using the RAM 92. Specifically, for example, the program 98 includes a program that causes a computer to execute processes shown in FIG. 3, FIG. 8, FIG. 11, FIG. 13, etc. As the processor 91 executes the program 98, the functions of the components of the operation support device are realized. The program 98 may be stored in the ROM 93. The program 98 may be recorded in the storage medium 80 and read out using the drive device 97, or may be transmitted to the computer device 90 from an external device (not shown) via a network (not shown).

[0128] The input / output interface 95 exchanges data with peripheral devices (such as a keyboard, a mouse, and a display device) 99. The input / output interface 95 functions as a means for acquiring or outputting data. The bus 96 connects each component.

[0129] There are various variations in the method of implementing the travel assistance device. For example, each component included in the travel assistance device can be implemented as a dedicated device. Furthermore, the travel assistance device can be implemented based on a combination of multiple devices.

[0130] The scope of each embodiment also includes a processing method for recording a program for implementing each configuration in the functions of each embodiment on a storage medium, reading the program recorded on the storage medium as code, and executing the program on a computer. That is, a computer-readable storage medium is also included in the scope of each embodiment. Also, the storage medium on which the above-mentioned program is recorded and the program itself are included in each embodiment.

[0131] The storage medium is, for example, a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD (Compact Disc)-ROM, a magnetic tape, a non-volatile memory card, or a ROM, but is not limited to these examples. Furthermore, the programs recorded on the storage medium are not limited to programs that execute processes independently, but also include programs that operate on an OS (Operating System) and execute processes in cooperation with other software and functions of an expansion board, which are included in the scope of each embodiment.

[0132] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0133] Furthermore, the above embodiments and modifications can be combined as appropriate.

[0134] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.

[0135] <Additional Notes>

[0136] [Appendix 1] a simulation means for simulating the flow of people in the transportation facility by using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; an estimation means for estimating a congestion degree of a place related to the transportation facility from a result of the simulation; A decision means for deciding a policy that satisfies a condition related to the congestion degree based on the result of the estimation. Operation support equipment.

[0137] [Appendix 2] The estimation means estimates a fatigue level of a user of the transportation facility based on a congestion level, The determination means determines a response policy that satisfies a condition related to a fatigue level. 2. A navigation assistance device as described in appendix 1.

[0138] [Appendix 3] the decision means determines the response policy by solving an optimization problem in which an index related to services provided to users of the transportation facility is an objective function using information related to the congestion level; 2. A navigation assistance device as described in appendix 1.

[0139] [Appendix 4] The determination means determines the allocation of station staff to minimize the time required to resolve the congestion. 4. A navigation assistance device as described in appendix 3.

[0140] [Appendix 5] The determining means determines content and a delivery destination of the content that maximizes the likelihood of a response from users of the transportation facility. 4. A navigation assistance device as described in appendix 3.

[0141] [Appendix 6] A selection means is provided, The simulation means includes: A generation means for generating a schedule for the transportation facility; A prediction means for predicting a flow of people when the transportation facility operates according to the generated timetable, The generating means generates a plurality of changed timetables, The prediction means predicts a flow of people for each change in schedule, The estimation means estimates a congestion degree for each change in schedule, The selection means selects one of a plurality of changed schedules by comparing the estimated congestion degrees, The determination means determines a course of action based on a result of estimation corresponding to the selected changed timetable. 2. A navigation assistance device as described in appendix 1.

[0142] [Appendix 7] An acquisition means for acquiring statistical data on users when the transportation facility operates according to the changed schedule; and an evaluation means for generating evaluation information regarding the simulation using the statistical data and a result of the simulation. 2. A navigation assistance device as described in appendix 1.

[0143] [Appendix 8] The simulation means performs a simulation of the flow of people in the transportation facility using a machine learning model that has learned the relationship between information on user flow, timetable information, and people flow. 2. A navigation assistance device as described in appendix 1.

[0144] [Appendix 9] The estimation means estimates a fatigue level of users of the transportation facility based on a congestion level for each changed schedule, The selection means selects one of a plurality of changed schedules by comparing the estimated fatigue levels, The determination means determines a course of action that satisfies a condition related to a fatigue level from a result of estimation corresponding to the selected changed timetable. 7. A navigation assistance device as described in appendix 6.

[0145] [Appendix 10] A simulation of people flow in the transportation facility is performed using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; Estimating the degree of congestion of a location related to the transportation facility from the results of the simulation; Based on the result of the estimation, a policy that satisfies a condition regarding the degree of congestion is determined. Operation support method.

[0146] [Appendix 11] In the estimation, a fatigue level of a user of the transportation facility is estimated based on a congestion level; In the determination, a policy for dealing with the fatigue level is determined. 11. A method for assisting operations as described in appendix 10.

[0147] [Appendix 12] In the determination, the response policy is determined by solving an optimization problem in which an index related to services provided to users of the transportation facility is used as an objective function using information on the congestion level. 11. A method for assisting operations as described in appendix 10.

[0148] [Appendix 13] In the determination, the allocation of station staff is determined to minimize the time required to resolve the congestion. 13. A method for assisting operations as described in appendix 12.

[0149] [Appendix 14] determining content and a distribution destination for the content that maximizes the likelihood of a response from users of the transportation facility in said determining; 13. A method for assisting operations as described in appendix 12.

[0150] [Appendix 15] In the simulation, a plurality of changed schedules are generated, and a prediction of the flow of people is performed for each changed schedule; In the estimation, a congestion degree is estimated for each change in schedule, By comparing the estimated congestion levels, one of several different schedule changes is selected, In the determination, a response policy is determined based on the result of the estimation corresponding to the selected changed timetable. 11. A method for assisting operations as described in appendix 10.

[0151] [Appendix 16] Acquire statistical data on users when the transportation facility operates according to the changed schedule, generating evaluation information regarding the simulation using the statistical data and the results of the simulation; 11. A method for assisting operations as described in appendix 10.

[0152] [Appendix 17] In the simulation, a machine learning model is used to learn the relationship between information on user flow, timetable information, and people flow, to simulate people flow in the transportation facility. 11. A method for assisting operations as described in appendix 10.

[0153] [Appendix 18] In the estimation, a fatigue level of a user of the transportation facility based on a congestion level is estimated for each changed schedule; In the selection, one of a plurality of change schedules is selected by comparing the estimated fatigue levels; In the determination, a response policy that satisfies a condition regarding a fatigue level is determined based on a result of the estimation corresponding to the selected changed timetable. 16. The navigation assistance device according to claim 15.

[0154] [Appendix 19] A process of simulating the flow of people in a transportation facility using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; A process of estimating a congestion level of a place related to the transportation facility from a result of the simulation; and determining a policy for dealing with the congestion level based on the result of the estimation. program.

[0155] [Appendix 20] In the process of estimating, a fatigue level of a user of the transportation facility is estimated based on a congestion level; In the process of determining, a policy of action that satisfies a condition related to a fatigue level is determined. 19. The program according to claim 19.

[0156] [Appendix 21] In the process of determining, the response policy is determined by solving an optimization problem in which an index related to services provided to users of the transportation facility is used as an objective function using information about the congestion level. 19. The program according to claim 19.

[0157] [Appendix 22] In the process of determining, a station staff allocation that minimizes the time required to resolve the congestion is determined. 22. The program according to claim 21.

[0158] [Appendix 23] determining content and a delivery destination of the content that maximizes the likelihood of a response from users of the transportation facility in the process of determining the content; 22. The program according to claim 21.

[0159] [Appendix 24] Perform further processing of your choice, In the process of performing the simulation, a plurality of changed schedules are generated, and a prediction of the flow of people is performed for each changed schedule; In the estimating process, a congestion degree is estimated for each changed schedule, In the selection process, one of a plurality of changed schedules is selected by comparing the estimated congestion degrees; In the process of determining, a response policy is determined based on the result of estimation corresponding to the selected changed timetable. 19. The program according to claim 19.

[0160] [Appendix 25] A process of acquiring statistical data on users when the transportation facility operates according to the changed schedule; and generating evaluation information regarding the simulation by utilizing the statistical data and a result of the simulation. 19. The program according to claim 19.

[0161] [Appendix 26] In the process of performing the simulation, a machine learning model is used to learn the relationship between information on user flow, timetable information, and people flow, to simulate people flow in the transportation facility. 19. The program according to claim 19.

[0162] [Appendix 27] In the estimating process, a fatigue level of a user of the transportation facility based on a congestion level is estimated for each changed schedule; In the selection process, one of a plurality of changed schedules is selected by comparing the estimated fatigue levels; In the process of determining, a response policy that satisfies a condition related to a fatigue level is determined based on the result of the estimation corresponding to the selected changed timetable. 25. The program according to claim 24. [Explanation of symbols]

[0163] 100, 101, 102 Operation support equipment 110, 111 Simulation Section 1101, 1111 Generation part 1102, 1112 Prediction Department 120, 121 Estimation part 130, 131 Decision Section 140 Output section 150, 151 Acquisition Department 160 Selection section 170 Evaluation Department 1000 Operation Support System

Claims

1. a simulation means for simulating the flow of people in the transportation facility by using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; an estimation means for estimating a congestion degree of a place related to the transportation facility from a result of the simulation; A decision means for deciding a policy that satisfies a condition related to the congestion degree based on the result of the estimation. Operation support equipment.

2. The estimation means estimates a fatigue level of a user of the transportation facility based on a congestion level, The determination means determines a response policy that satisfies a condition related to a fatigue level. The driving assistance device according to claim 1 .

3. the decision means determines the response policy by solving an optimization problem in which an index related to services provided to users of the transportation facility is an objective function using information about the congestion level; The driving assistance device according to claim 1 .

4. The determination means determines the allocation of station staff to minimize the time required to resolve the congestion. The driving assistance device according to claim 3.

5. The determining means determines content and a delivery destination of the content that maximizes the likelihood of a response from users of the transportation facility. The driving assistance device according to claim 3.

6. A selection means is provided, The simulation means includes: A generation means for generating a schedule for the transportation facility; A prediction means for predicting a flow of people when the transportation facility operates according to the generated timetable, The generating means generates a plurality of changed timetables, The prediction means predicts a flow of people for each change in schedule, The estimation means estimates a congestion degree for each change in schedule, The selection means selects one of a plurality of changed schedules by comparing the estimated congestion degrees, The determination means determines a course of action based on a result of estimation corresponding to the selected changed timetable. The driving assistance device according to claim 1 .

7. An acquisition means for acquiring statistical data on users when the transportation facility operates according to the changed schedule; and an evaluation means for generating evaluation information regarding the simulation using the statistical data and a result of the simulation. The driving assistance device according to claim 1 .

8. The simulation means performs a simulation of the flow of people in the transportation facility using a machine learning model that has learned the relationship between information on user flow, timetable information, and people flow. The driving assistance device according to claim 1 .

9. A simulation of people flow in the transportation facility is performed using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; Estimating the degree of congestion of a location related to the transportation facility from the results of the simulation; Based on the result of the estimation, a policy that satisfies a condition regarding the degree of congestion is determined. Operation support method.

10. A process of simulating the flow of people in a transportation facility using a changed timetable, which is a timetable that may be changed when an abnormality occurs in the operation of the transportation facility, and information on the flow of users of the transportation facility; A process of estimating a congestion level of a place related to the transportation facility from a result of the simulation; and determining a policy for dealing with the congestion level based on the result of the estimation. program.

Images