Action proposal system and action proposal method

Abstract

To provide a system for proposing an optimum action by predicting obstruction transition and taking dissatisfaction due to delays and congestion, stress relief due to rests, or the like into account when movement cannot be performed as scheduled because traffic obstruction occurs.SOLUTION: An action proposal system includes one or more processors and one or more storage devices. At least one of the one or more storage devices holds user's passage records in a traffic network and information on obstruction that occurs in the traffic network, and at least one of the one or more processors predicts a congestion situation in each time zone of each section of the traffic network when obstruction occurs in the traffic network on the basis of the passage records and the information on the obstruction, generates a plurality of action patterns of the user of a prediction object, and predicts a location in each time zone of the user of a prediction object about each of the plurality of action patterns on the basis of the predicted congestion situation.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a system that, when a traffic disruption occurs and traffic jams, stops, congestion, or the like prevent users from traveling as planned, suggests to a user the optimal action to take to avoid the impact as much as possible, depending on the type of disruption. [Background technology]

[0002] Technologies for providing users with information about traffic include, for example, the technology described in JP 2019-169028 A (Patent Document 1) and the technology described in JP 2018-010454 A.

[0003] Patent document 1 states that "the traffic congestion prediction system includes an input unit that inputs as input information traffic information indicating the traffic volume, speed, and vehicle length of vehicles traveling on the road at each sampling time at each of a plurality of points on the road, a first learning unit that uses the traffic information and information indicating whether traffic congestion has occurred on the road within a predetermined period as teacher data to generate a first trained model in which variables for predicting whether traffic congestion will occur within a predetermined period of time are machine-learned, and a first traffic congestion prediction unit that, when traffic information is input to the input unit as information to be predicted, calculates prediction information indicating whether traffic congestion will occur on the road at a first time point which is a predetermined period from a reference time point, based on the machine-learned variables in the trained model."

[0004] Patent Document 2 states that "the congestion prediction device has a boarding / alighting station prediction calculation unit that generates boarding / alighting station prediction information indicating the time and station at which a user enters and the time and station at which the user is predicted to exit, based on seat reservation information indicating a seat reservation made in advance and ticket information read from the ticket at the ticket gate; a station congestion prediction calculation unit that generates station congestion prediction information that predicts the number of users within each station at each future time, based on the boarding / alighting station prediction information and a predicted timetable indicating the arrival and departure times of each future train at each station; and a train congestion prediction calculation unit that generates train congestion prediction information that predicts the number of users on board each train at each future time, based on the station congestion prediction information and onboard number of people information indicating the current boarding status of each train." [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2019-169028 A [Patent Document 2] JP 2018-010454 A Summary of the Invention [Problem to be solved by the invention]

[0006] Nowadays, many people carry smartphones, and by using the route guidance application installed on the smartphone, users can find out the options for how to reach a destination, such as by train, bus, car, taxi, or on foot, as well as the estimated arrival time. Similar guidance can also be obtained from the car's onboard car navigation system (hereinafter referred to as car navigation), although it is limited to car travel. Many of these route guidance systems also have a function to display information to inform the user when traffic is disrupted due to accidents or other problems. However, in many cases, this only informs the user of the current situation and does not include a reliable prediction of future developments, which can leave the user unsure of what to do.

[0007] Regarding the current functionality of route guidance systems when there is an obstacle, the situation is slightly different between car navigation systems that guide cars and transfer guide apps that guide mainly rail routes. First, regarding car navigation systems, they are broadly divided into two types: dedicated systems installed in cars and car navigation apps on smartphones. The former differ in that they obtain data about the vehicle, such as the number of rotations of the wheels, and use it to determine the current location, while the latter do not normally use such data. However, both have in common the fact that they use GPS to determine the current location, obtain external information using communication functions, calculate the route on the device using map data, and provide route guidance by voice or on the map screen. For this reason, the term car navigation system used here refers to both types collectively.

[0008] Traffic congestion information is particularly important for car navigation systems when using expressways. Cameras and other surveillance equipment are installed at key locations on expressways to monitor the current situation, and data such as the location of traffic congestion and the speed of cars there is obtained in real time by the expressway management department. The location of the congestion and the level of congestion (slowness of flow) are published on websites, and signs on the expressway also display the estimated time it will take to get through the congestion ahead. Car navigation systems can use this current information to reflect the guidance, but because it is difficult to predict the progress of the congestion situation, it is difficult to decide whether it is best to stay on the same route or to take a detour. Road management companies also publish forecasts of congestion depending on the day of the week and holidays, but do not publish detailed forecasts such as how the current congestion situation will change in 20 minutes, 1 hour, or 2 hours.

[0009] However, if we accept that there is uncertainty, it should be possible to predict with a certain degree of accuracy the occurrence of congestion and the transition of current congestion by using detailed information held by the management side. In the case of natural congestion caused by traffic concentration, the location where the congestion will occur is almost known, and the increase or decrease in traffic volume can be predicted from camera monitoring and real-time data on the number of vehicles passing through interchanges (ICs). In addition, in the case of congestion caused by an accident, it is possible to make a rough prediction of the extent of the congestion and the prospect of it being resolved by obtaining information from traffic managers who have arrived at the scene about the number of lanes that have been restricted and the expected completion date of handling the accident.

[0010] For example, Patent Document 1 describes a system that inputs information such as traffic volume at multiple points on a road and predicts whether or not congestion will occur after a certain time has passed. Although data exists for predicting the transition of congestion conditions within a few hours, there is currently no service that makes predictions and suggests actions to users.

[0011] Next, regarding railways, the most common type of disruption that has a major impact on passengers is the suspension of service due to accidents or breakdowns. When such a disruption occurs, displays and announcements are made on the train and in the station, and the information is also made available on the Internet. Railway transfer information apps are usually used only to check routes before departure, but they can also be used as a tool for passengers to find out information when they notice a disruption. However, even here, there is little information provided by the railway company about the expected resolution of the disruption. In some cases, announcements such as "service is expected to resume in 30 minutes" are made, but in many cases such information is not available. Even if service resumes as announced, it may continue to run at a slow speed because there is a train in front, and it may take much longer than usual to travel the same distance, making it difficult for ordinary passengers to predict the extent of the disruption.

[0012] However, the railway side that manages the operation usually has detailed forecast information for the restoration of the timetable. When the timetable is disrupted to a certain extent, the timetable is usually rearranged, including suspending service and running back, in order to restore the timetable as soon as possible and minimize the confusion. In other words, in such cases, the timetable is not waited for to naturally converge to the original state, but the operation management department plans how to converge and converges according to the plan. Therefore, how long the slow operation will continue after operation resumes, whether there will be meetings at stations along the way, etc. are planned and decided for each train. While riding on the train, there may be an announcement such as "We will stop at the next station for about 5 minutes," but the schedule is not informed very far into the future, and there is no way to know what schedule other trains are running. As a result, current transfer guide apps can find out the information when there is a disruption and search for an alternative route that does not use the disrupted line, but it is difficult to predict whether it is more likely to reach the destination faster by not changing the behavior or by detouring.

[0013] When the management side makes a schedule for the restoration of the timetable, the first important information is the content of the disruption, and in the case of a typical event with many similar cases, it is easy to predict the time required to respond. In addition, if the train driver or on-site staff reports on the situation, the prediction becomes more accurate. After the time for resuming operation is predicted, the timetable is reorganized before that time. At the time of this reorganization, the detailed schedule of each train is decided, and the question remains as to whether operation can actually be resumed as predicted. If it is not possible to resume operation at the scheduled time, if there is a slight delay, the reorganized schedule will be carried out as is, but if there is a large delay, the schedule will be reorganized again. If the content of the disruption is unique or the cause is unknown due to a train malfunction, it is difficult to predict the resumption of operation immediately after the disruption occurs, and the resumption schedule will be undecided, but it is still important to predict the resumption as early as possible and make a plan for resuming operation while considering the possibility of changes. In this way, the accuracy of the expected resumption of operation varies depending on the content of the disruption, but in any case, if the information is used while knowing that it is not certain, it may be useful information for passengers.

[0014] For example, Patent Document 2 describes a system that predicts the number of people on board each train based on seat reservation information, ticket information read by a ticket gate, and predicted future timetables, etc. However, there is currently no system that makes predictions and suggests user actions based on the results.

[0015] The present invention has been made in consideration of the above problems, and aims to provide a system that, when a traffic disruption occurs due to unexpected traffic congestion, service suspension, crowding, etc. and a person is unable to travel as planned, predicts the subsequent progression of the disruption, calculates its impact on the person traveling, and suggests the optimal action from options such as continuing the trip, taking a detour, or taking a break, in other words, the action that maximizes satisfaction by combining dissatisfaction due to a delay in arriving at the destination, stress felt due to traffic congestion and crowding, and stress relief by taking a break. [Means for solving the problem]

[0016] In order to solve at least one of the above problems, the present invention provides an action suggestion system having one or more processors and one or more storage devices, wherein at least one of the one or more storage devices holds a passage record of users in a transportation network and information regarding a disruption that has occurred in the transportation network, and at least one of the one or more processors predicts the congestion situation in each time period for each section of the transportation network in the event of a disruption in the transportation network based on the passage record and the information regarding the disruption, generates a plurality of behavioral patterns of the user to be predicted, and predicts the location of the user to be predicted in each time period for each of the plurality of behavioral patterns based on the predicted congestion situation. Effect of the Invention

[0017] According to one aspect of the present invention, a system can be constructed that assists an individual in selecting an action to be taken when a traffic disruption occurs by predicting which action will be affected by the traffic disruption and to what extent.

[0018] Other objects, configurations and advantages than those mentioned above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0019] [Figure 1A] 1 is a block diagram showing a configuration of an optimal action suggestion system according to a first embodiment of the present invention. [Figure 1B] 1 is a block diagram showing a hardware configuration of an optimal action suggestion system according to a first embodiment of the present invention. [Diagram 2] 4 is a flowchart showing the flow of processing of each device in the first embodiment of the present invention. [Diagram 3] FIG. 2 is an explanatory diagram illustrating an example of a traffic congestion prediction result in the first embodiment of the present invention. [Figure 4] FIG. 2 is an explanatory diagram showing an example of the influence of traffic congestion for each behavior pattern in the first embodiment of the present invention. [Diagram 5] FIG. 4 is an explanatory diagram showing an example of the contents of store data in the first embodiment of the present invention. [Figure 6] 10 is a flowchart showing the flow of processing of each device in Example 2 of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. First, an outline of the embodiment of the present invention will be described.

[0021] In an embodiment of the present invention, first, the information on the disruption collected by the department that manages and operates the traffic on expressways, railways, etc. and other information on the traffic conditions are integrated to predict the transition of the disruption and the recovery of the traffic conditions after the disruption is resolved. At this time, the distribution of the congestion conditions and its changes, which can be calculated at the same time, are also predicted. Although the method of making predictions differs depending on the type of traffic, important data that can be commonly used by the administrators of toll traffic networks such as expressways and railways include data on the time and place where each user entered and exited. By using all the data and averaging the data for the same day and the same time period, the traffic flow under normal circumstances (the transition of the number of vehicles and the number of passengers at each location) is modeled in detail. Furthermore, the real-time data on the entry and exit of the day is used to correct the prediction for the current day and beyond. The calculation of this prediction may be performed on a server for monitoring and managing the traffic conditions of the department that manages the traffic, or the data may be transferred to a server dedicated to the action suggestion service independent of the above and the calculation may be performed on that dedicated server.

[0022] It is preferable that the action suggestion service dedicated server also stores information on stores that can be used for rest along the transportation network route. The stores to be targeted are those within the area that can be entered for a fee, i.e., service areas (SA) and parking areas (PA) on expressways, and stores inside the ticket gates on railways, but this is not necessary and it is preferable to target stores outside of these areas in order to expand the range of rest options for users. The data handled is information that is useful to users, such as the store name, the content of the store's services, business hours, number of seats, number of products, number of parking spaces, current congestion level, and parking availability. The data is constantly updated on a server installed on the store side and is accumulated in the action suggestion service dedicated server via the Internet to keep the information up to date.

[0023] Next, data on the current location and destination are obtained from the terminal device used by the user as information on the user using the system. The terminal device is assumed to be a smartphone carried by the user or a car navigation system installed in the car. The destination is manually input by the user, and the current location is automatically identified by the terminal device using GPS. To assist in identifying the current location, auxiliary data such as vehicle speed and wheel rotation speed are also used if available.

[0024] The terminal device then transmits information about the current location and destination to a server dedicated to the action suggestion service via the Internet. The server selects relevant data about the traffic conditions along the user's route, its future forecast, and the status of available rest areas, and transmits this data to the user's terminal device.

[0025] Next, the terminal device calculates the expected satisfaction level for multiple options for the user's actions based on the information obtained from the server. When there is a traffic disruption, satisfaction level will basically be lower than normal, and it is best to minimize the degree of this decrease. Here, the term "dissatisfaction level" is used to mean negative satisfaction level, and minimizing dissatisfaction level is synonymous with maximizing satisfaction.

[0026] There are many factors that cause dissatisfaction in humans, but a particularly important factor related to traffic disruptions is delays in arriving at a destination. By overlaying the route and time the user will be traveling on with data on future changes in traffic conditions predicted by the server, and tracking and calculating the movement, it is possible to predict the time the user will arrive at the destination. The delay time can be calculated by comparing it with the time required under normal circumstances when there are no traffic disruptions. The degree of increase in dissatisfaction due to delays differs depending on the individual's perception, so it is not possible to accurately evaluate it, but it is possible to assume an approximate increase curve of dissatisfaction that assumes an average person, and the amount of increase in dissatisfaction can be evaluated in this way.

[0027] Another important cause of dissatisfaction is congestion. When train schedules are disrupted, it is not uncommon for trains to become more crowded than normal, and the greater the congestion, the higher the level of discomfort. In some cases, passengers can be so crowded that their feet cannot even touch the floor because of being pushed by other passengers, and if this situation continues, dissatisfaction levels rise rapidly. In the case of expressways, congestion can lead to traffic jams and cause delays, but the slow driving caused by traffic jams is itself an unpleasant experience and increases dissatisfaction levels aside from delays. The distribution of congestion levels in terms of location and time is predicted at the same time as traffic conditions are predicted by the dedicated server for the action suggestion service, and this data is used to predict the congestion that users will experience.

[0028] The behavioral options include a pattern of avoiding crowds and taking a break. In many cases, taking a break will result in a slower arrival at the destination than if no break was taken, but it is quite possible that the increase in satisfaction from avoiding crowds and being refreshed will outweigh the increase in dissatisfaction caused by a slight increase in delay when a large delay is unavoidable. The key point is to make maximizing satisfaction, not just speed of arrival, the principle for selecting behavior. The behavioral patterns considered within the terminal device are ranked in order of predicted satisfaction and presented to the user.

[0029] In order to make the evaluation of satisfaction more suitable for each individual user, it is desirable to input information about the user's preferences into the terminal device in advance. For example, a method can be considered in which the user inputs, on a 5-point scale, how important it is to arrive quickly and to avoid crowds, how well each type of restaurant matches the user's preferences, and the importance of souvenir purchasing opportunities. There is also a method in which the user allows the use of online shopping history data, allowing automatic inference of the user's preferences. The method of acquiring information about preferences is not limited to this.

[0030] In addition to setting such preference data as basic user information, it is also desirable to be able to set conditions that match the purpose of the day. For example, if you plan to board a reserved vehicle at your destination and your top priority is to arrive there by that time, or if you are returning from a trip and would prefer to avoid unpleasant congestion even if it means being a little late, it may be more important to act in accordance with the purpose of the day than your usual preferences. Since it is troublesome to input detailed settings every time, it is better to limit the input of the situation of the day to a few simple items, such as whether a quick arrival is a priority or avoiding unpleasant situations is a priority. EXAMPLES

[0031] First, a first embodiment of the present invention will be described. In this embodiment, the configuration and processing contents of an optimal action suggestion system for an expressway will be described.

[0032] FIG. 1A is a block diagram showing a configuration of an optimal action suggestion system according to a first embodiment of the present invention.

[0033] The optimal behavior proposal system 30 of this embodiment is composed of an optimal behavior proposal server 101, a user-owned terminal device 102, a store server 103, a data relay server 104, and a traffic management and congestion monitoring system 105. The optimal behavior proposal server 101 communicates with the user-owned terminal device 102, the store server 103, and the data relay server 104 via the Internet 10. The data relay server 104 communicates with the traffic management and congestion monitoring system 105 via a dedicated line 20. In other words, the optimal behavior proposal server 101 communicates with the traffic management and congestion monitoring system 105 via the Internet 10, the data relay server 104, and the dedicated line 20.

[0034] The traffic management and congestion monitoring system 105 in this embodiment refers to an existing road management information processing device that collects information from cameras and sensors on expressways and interchanges, and has the role of transmitting information that can be used to predict the status of traffic disruptions and their transition to the optimal action proposal server 101. The traffic management and congestion monitoring system 105 in this embodiment is assumed to be installed in the expressway management department.

[0035] The optimal behavior proposal server 101 is the core device of this system, which predicts the transition of traffic disruptions, accumulates information on stores that can be used for resting, and transmits disruption information and store information related to the user's route in response to a request from the user's terminal device 102. The optimal behavior proposal server 101 may be installed within the highway management department or outside. If installed outside, it will be connected to the traffic management and congestion monitoring system 105 via the Internet 10. In that case, it is preferable from the viewpoint of security to install a separate data relay server 104 within the management department and perform Internet communication via it. Figure 1 shows an example in which this data relay server 104 is installed, connected to the traffic management and congestion monitoring system 105 via a dedicated line 20, and connected to the optimal behavior proposal server 101 via the Internet 10.

[0036] The user-owned terminal device 102 refers to a smartphone or a car navigation system, and is assumed to run software dedicated to the optimal action suggestion system. The user sets personal preferences and the like in advance in this terminal device 102, and inputs the destination for the day and items of importance, etc. The terminal device 102 transmits the user's current location and destination to the optimal action suggestion server 101 via the Internet 10, receives information on obstacles and store information related to the route, performs search calculations for the optimal action, and displays the results to the user.

[0037] The store server 103 is installed in each store that can be used for resting and that participates in the optimal behavior proposal system 30, and obtains real-time information such as the degree of congestion and parking lot availability using sensors and the like, and transmits the information to the optimal behavior proposal server 101 via the Internet 10 as needed. Note that while the more stores that transmit real-time information as needed, it is not necessarily necessary for all participating stores to do so; some stores may simply register fixed information such as business hours, regular holidays, types of services, and number of parking spaces in the store server 103.

[0038] FIG. 1B is a block diagram showing a hardware configuration of the optimal action suggestion system 30 according to the first embodiment of the present invention.

[0039] The optimal behavior proposal server 101, the user-owned terminal device 102, the individual store servers 103, the data relay server 104, and the traffic management and congestion monitoring system 105 constituting the optimal behavior proposal system 30 of this embodiment can each be realized by one or more computer systems. Figure 1B shows computer system 110 as an example of such a computer system.

[0040] The computer system 110 includes a processor 111, a memory (main storage device) 112, an auxiliary storage device 113, an output device 114, an input device 115, and a communication interface (I / F) 116. The above components are connected to each other via a bus. The memory 112 and the auxiliary storage device 113 are storage devices that store programs and data used by the processor 111.

[0041] The memory 112 is configured, for example, from a semiconductor memory, and is mainly used to hold programs and data being executed. The processor 111 executes various processes in accordance with the programs stored in the memory 112. The processor 111 operates in accordance with the programs to realize various functional units.

[0042] The auxiliary storage device 113 is configured with a large-capacity storage device such as a hard disk drive or a solid-state drive, and is used to store programs and data for a long period of time.

[0043] Processor 111 may be comprised of a single processing unit or multiple processing units and may include single or multiple arithmetic units or multiple processing cores. Processor 111 may be implemented as one or more central processing units, microprocessors, microcomputers, microcontrollers, digital signal processors, state machines, logic circuits, graphic processing units, systems on a chip, and / or any device that manipulates signals based on control instructions.

[0044] Programs and data stored in the auxiliary storage device 113 are loaded into the memory 112 at the time of start-up or when necessary, and the processor 111 executes the programs, thereby carrying out various processes of the computer system 110.

[0045] The input device 115 is a hardware device for a user to input instructions and information, etc. The output device 114 is a hardware device that presents various images for input and output, such as a display device. The communication I / F 116 is an interface for connection to the Internet 10 or the dedicated line 20.

[0046] The computer system 110 may include two or more processors 111. The functions of each part of the system of this embodiment may be implemented in a plurality of computer systems 200. In this case, the plurality of computer systems 200 communicate with each other via a network. For example, some of the functions of the system of this embodiment may be implemented in one computer system 200, and the other parts may be implemented in another computer system 200.

[0047] For example, the computer system 110 that realizes the optimal action proposal server 101 of this embodiment may be a PC installed in a highway management department, or may be a server accessed by a manager via a network. In the latter case, the computer system 110 may be a virtual server on the cloud. In the latter case, the computer system 110 shown in FIG. 1B is realized by computer resources on the cloud.

[0048] FIG. 2 is a flowchart showing the flow of processing of each device in the first embodiment of the present invention.

[0049] The optimal behavior proposal server 101 first compiles vehicle count data 201 for each combination of departure IC, destination IC, and time period from the entry and exit records from ICs during normal times, and then calculates the average values ​​for each day of the week and public holiday to create a standard trend model of the daily vehicle count distribution.

[0050] Here, the entry record and exit record from the IC are one example of a vehicle passage record on the expressway, and other information, such as the number of passing vehicles measured by a sensor installed on the lane, may be used. The same applies to the following explanation.

[0051] Next, the optimal behavior proposal server 101 accumulates the actual data of the entry and exit records of each IC on the day while updating it (step 202), and predicts the transition of the number of entries and exits of each IC on the day using the data and a standard transition model of the daily vehicle number distribution (step 203). In addition, the optimal behavior proposal server 101 holds information on lane restrictions due to construction and accidents, if any, and updates it to the latest information as needed (step 204). Then, the optimal behavior proposal server 101 combines the predicted value in step 203 with information on lane restrictions and the like updated in step 204 (e.g., information on the location and time period where the number of lanes is reduced) to predict the progress of movement of each vehicle from the current time onwards (e.g., the position of each vehicle in each time period) (step 205).

[0052] The optimal behavior proposal server 101 collects the prediction results and predicts the location, time, and level of congestion by making corrections using congestion level information 206 acquired by cameras and sensors on the road (step 207). This prediction data is updated as needed to keep the current situation and predictions up to date.

[0053] For example, the optimal behavior proposal server 101 corrects the positions of each vehicle for each time period predicted in step 205, based on the location, time, and degree of congestion predicted in step 207. Then, based on the corrected positions of each vehicle for each time period and the congestion degree information 206, the optimal behavior proposal server 101 predicts the location, time, and degree of congestion again in step 207. The optimal behavior proposal server 101 may repeat this process until the prediction results converge. When the prediction results converge, the finally obtained prediction results are stored as congestion prediction data (step 208).

[0054] The store server 103 holds basic store data 211 such as business hours and service details, and also obtains real-time congestion status and parking space availability using sensors, etc., and transmits this information to the optimal behavior proposal server 101 while continuing to update it (step 212). Basic store data that does not change does not need to be transmitted every time, and it is sufficient to register it once in the optimal behavior proposal server 101. The optimal behavior proposal server 101 compiles and holds the data received from each store server 103 as store data (step 209). An example of the store data held here will be described later (see FIG. 5).

[0055] In the user-owned terminal device 102, data 213 relating to the user's preferences, such as what type of food the user likes to eat and whether arriving early is always a high priority, is input in advance. On the day of departure, the user inputs a destination 214 into the user-owned terminal device 102 and then departs. The user-owned terminal device 102 automatically acquires the current location using a method centered around GPS (step 215).

[0056] The user-owned terminal device 102 transmits the thus obtained data on the destination and current location to the optimal behavior proposal server 101, and receives data on the predicted congestion level along the route and stores where a rest area is available. For example, the optimal behavior proposal server 101 may extract related route data including the predicted congestion level for each time period along the route from the current location to the destination and information on stores where a rest area is available along the route, based on the congestion prediction data held in step 208, the store data held in step 209, and the destination and current location information received from the user-owned terminal device 102 (step 210), and transmit the extracted related route data to the user-owned terminal device 102.

[0057] The user-owned terminal device 102 uses the data to calculate predictions for multiple options of the user's behavioral pattern, such as the extent to which the user is affected by traffic disruptions, the extent to which the satisfaction level will decrease as a result, and the extent to which the satisfaction level will increase if the user takes a break, and evaluates the overall satisfaction level (step 216). Specifically, the user-owned terminal device 102 predicts the location of the user in each time period for each option of the user's behavioral pattern. An example of this prediction result will be described later with reference to FIG. 4. Then, the user-owned terminal device 102 calculates the satisfaction level for each option based on the predicted location of the user in each time period for each option and the user's experience predicted for each option. Then, the user-owned terminal device 102 displays the behavioral patterns in order of the predicted satisfaction level and proposes them to the user (step 217).

[0058] FIG. 3 is an explanatory diagram illustrating an example of a traffic congestion prediction result in the first embodiment of the present invention.

[0059] Specifically, FIG. 3 shows an example of data representing the degree of congestion predicted in step 207 of FIG. 2 and its distribution. Each row represents the congestion situation at the location of an IC or SA / PA, and the order in the table corresponds to the order of the actual locations of each IC, SA, and PA. ICs and SA / PAs are named and displayed as A, B, and C. As for the columns, the leftmost data column represents the current time, 12:00, and predictions for the future every 20 minutes are listed in each column. The 20-minute interval is just one example, and in reality it can be in smaller intervals (or coarser intervals). The numbers in each box represent how many extra minutes it takes to pass through that area compared to normal times. Note that this figure is for the inbound lanes heading from IC.G toward IC.A, and data for the outbound lanes will also exist separately.

[0060] In this figure, there are two main areas with numbers other than 0: the bottom left area (i.e., the area roughly corresponding to the section from IC.G to IC.D from 12:00 to 14:20) simulates the expected expansion of congestion due to an accident that occurred near IC.D at around 12:00, and the expected elimination of congestion once the accident processing is completed. Meanwhile, the top right area (i.e., the area roughly corresponding to the section from IC.D to IC.B from 16:00 onwards) simulates the expected natural congestion due to traffic congestion that steadily occurs from around 16:00, starting from IC.B.

[0061] FIG. 4 is an explanatory diagram illustrating an example of the influence of traffic congestion for each behavior pattern in the first embodiment of the present invention.

[0062] Specifically, Figure 4 shows an example of the results of calculations using the congestion forecast data shown in Figure 3 to show how the impact of congestion varies depending on individual behavior patterns. Here, we consider three different behavior patterns for a vehicle that enters in the uphill direction from IC.G at 12:00. First, pattern a is when the vehicle continues to move through the congestion without taking any breaks. In this case, it is expected that the vehicle will take an extra 80 minutes to pass near PA.E and an extra 20 minutes to pass near IC.D, and will reach IC.A at around 15:40. This state of movement is represented by the letter a in the figure.

[0063] Next, pattern b is when the driver takes a one-hour break at PA.E before resuming driving. In this case, the time when the driver is not driving on the expressway (the time spent resting at PA.E in the pattern b example) is displayed as (b), and the time spent driving on the expressway is displayed as b. In this case, the driver will also be driving in traffic for a short distance, and the predicted time of arrival at IC.A will be 16:00. In this example, despite taking a one-hour break, the delay in arrival is only 20 minutes compared to pattern a.

[0064] Pattern c also shows a case where the driver takes a break, but gets off the expressway at IC.F, takes a break at a store (e.g. roadside station) along a general road, and then re-enters IC.F two hours later. When using ETC2.0 (ETC is a registered trademark), if the driver temporarily gets off the expressway to use a designated roadside station, and returns within the time limit, the same toll fee as if the driver had not left the expressway is applied. This assumes the case where this system is used. Here again, the time when the driver is not traveling on the expressway (in the example of pattern c, the time spent resting at the roadside station and the time spent traveling on general roads between IC.F and the store) is shown as (c). In this case, the driver does not travel in a traffic jam, and is predicted to arrive at IC.A at 16:00, the same time as pattern b.

[0065] To compare these three patterns, it is important to note that a arrives 20 minutes earlier than b and c, the time spent driving in traffic is 100 minutes for a, 60 minutes for b, and 0 minutes for c, the break for b is 1 hour at PA.E, and the break for c is 2 hours at a roadside station. By calculating the change in satisfaction due to these factors, the optimal course of action can be determined.

[0066] Furthermore, if the break time is extended in patterns b and c, the arrival time will be significantly delayed due to the natural evening congestion shown in the upper right area of ​​Figure 3, so by comparing with the extended break patterns, it can be concluded that the above examples are optimal break times.

[0067] In order to include detours as an option, the system uses technology similar to existing route guidance that takes into account the road conditions on public roads to calculate the travel time required to travel on public roads between two specific interchanges, or to get off at a specific interchange and use public roads to get to the final destination, and similarly performs calculations to determine satisfaction.

[0068] The degree of satisfaction can be calculated, for example, by weighting the evaluation values ​​of a plurality of items. For example, the evaluation values ​​may include the length of time required for the user to arrive at the destination, the length of driving time, the length of time for low-speed driving, the length of rest time, and the content of the activities during the rest. The content of the activities during the rest may include, for example, eating and drinking and shopping, and may include the type of food (e.g., Italian or Chinese) in the case of eating and drinking, and the type of food (e.g., folk crafts or sweets) in the case of shopping.

[0069] For example, the satisfaction level may be calculated such that the shorter the time required for the user to arrive at the destination, the higher the satisfaction level, the shorter the driving time, the shorter the time spent driving at low speed, and the longer the rest time, the higher the satisfaction level. At this time, weighting may be performed based on the preferences 213 input in advance. For example, if the user gives top priority to arriving at the destination quickly, the weighting may be increased for the shorter time required for the user to arrive at the destination and decreased for the longer rest time.

[0070] Also, for example, the preference 213 may include a preference regarding the content of the behavior during the break, such as whether to prioritize eating and drinking or shopping, a preference regarding the type of food in the case of eating, a preference regarding the type of goods in the case of shopping, etc. In that case, the satisfaction level may be calculated based on whether the content of the behavior assumed from the type of service of the store to be visited during the break assumed in each behavior pattern matches the preference.

[0071] 2, step 216 is performed by the user-owned terminal device 102. This is because doing so prevents personal information such as the preferences 213 and the results of prediction of the user's detailed behavior from being known to the optimal behavior proposal server 101. However, if the user allows the optimal behavior proposal server 101 to know personal information about the user, step 216 may be performed by the optimal behavior proposal server 101.

[0072] FIG. 5 is an explanatory diagram illustrating an example of the contents of the store data in the first embodiment of the present invention.

[0073] 5 shows an example of data collected from each store server 103, consolidated on the optimal behavior proposal server 101, and stored in step 209. The optimal behavior proposal server 101 receives the data transmitted from each store server 103 in step 212, and registers the data of each store for each row in step 209.

[0074] The store data 500 shown in FIG. 5 includes the following items: store name 501, SA / PA 502, location 503, time from nearby IC 504, 505, opening time 506, closing time 507, congestion level 508, available parking space 509, store area 510, number of seats 511, service types 512-514, and general popularity rating 515, each of which corresponds to a column.

[0075] Store name 501 is information that identifies each store (for example, a name or number, etc.). SA / PA 502 indicates whether each store is at an SA or PA on the expressway. Location 503 registers data on the location of a store that is an SA or PA, such as how many kilometers away on the expressway it is located.

[0076] For stores that are not SAs or PAs (i.e., stores along general roads near expressways), the times from ICs 504 and 505 are registered as the average travel time by car from the two nearest ICs. In the example of FIG. 5, since stores E to H are both near ICs F and D, the time from IC F 504 and the time from IC D 505 are registered, but if the store is near another IC, the travel time from that IC is registered. This information is referenced when predicting the user's location for each time period for a behavior pattern that includes a break at one of these stores.

[0077] In addition, roadside stations that offer ETC2.0 discounts are the most likely targets for stores along general roads to be registered, but there is no need to be limited to them, and it is desirable to include generally popular stores as well. This is because there may be cases where a store is worth getting off the expressway and stopping by for an individual user, even if there is no toll discount.

[0078] The opening time and closing time of each store are registered in business start time 506 and business end time 507, respectively. Congestion level 508 and parking space availability 509 indicate the degree of congestion and parking space availability of each store, respectively. These are used only when the store server 103 can monitor the current congestion status in the store and the parking space availability and update the information in the optimal action proposal server 101. These items are not used for stores that cannot update in real time.

[0079] The area and number of seats of each store are registered in store area 510 and number of seats 511, respectively. Information indicating the type of service provided by each store is registered in service types 512 to 514. Specifically, for example, information such as whether each store is a restaurant or a retail store, what type of food it provides if it is a restaurant, or what products it sells if it is a retail store may be registered.

[0080] General popularity ratings 515 are registered with ratings by users who have actually used each store. Specifically, it is assumed that data such as word-of-mouth ratings will be obtained as general popularity ratings 515 through contracts with other businesses. It is preferable, but not essential, for such information to be included in store data 500. If such information is introduced, the data needs to be updated periodically, although this need not be done frequently. EXAMPLES

[0081] First, a first embodiment of the present invention will be described. In this embodiment, the contents of an optimal behavior suggestion system for railway users will be described. The configuration and effects of the system according to the second embodiment are the same as those of the system according to the first embodiment shown in Figs. 1 to 5, except for the differences described below, and therefore the description will be omitted.

[0082] The system configuration of the second embodiment is almost the same as the optimum behavior suggestion system 30 for expressways shown in Fig. 1A, and the traffic management and congestion monitoring system 105 corresponds to the traffic management system installed in the railway traffic management department. In the second embodiment, the first candidates for the target stores are stores inside the ticket gates of the station, but it is preferable to also include stores outside the ticket gates and within walking distance in order to increase the options for behavior.

[0083] FIG. 6 is a flowchart showing the flow of processing of each device in the second embodiment of the present invention.

[0084] First, the store server 103 performs the same process as in the case of expressways, i.e., registers basic store data 211, and then transmits the current situation data related to the congestion level while updating it as needed to the optimal behavior proposal server (step 212). The optimal behavior proposal server 101 collects and stores the data received from each store server 103 as store data. The store data stored here may be similar to the store data 500 (FIG. 5) of the first embodiment, for example. However, the store data of the second embodiment may include information specifying the station where the store is located for a store inside a train station, and information specifying the nearest station and information indicating the travel time from there for a store outside a station.

[0085] In the user-owned terminal device 102, the user inputs the destination station 607, and the user-owned terminal device 102 acquires the current location mainly using the built-in GPS (step 608), and transmits them to the optimal action proposal server 101. The current location may be acquired by the user manually inputting which train the user is on. Alternatively, the user may input the scheduled departure time and the scheduled departure station instead of the current location. In that case, the scheduled departure time and the current location at that time, i.e., the departure station, are transmitted to the optimal action proposal server 101. A plurality of behavior patterns and their respective total satisfaction scores are transmitted from the optimal action proposal server 101, and the user-owned terminal device 102 presents the results to the user.

[0086] The optimal behavior proposal server 101 collects passenger number data 601 for all combinations of departure station, destination station, and time period from ticket gate passage data at each station under normal circumstances, and creates a standard model of the daily passenger number trends by taking the average by day of the week and public holiday.

[0087] Next, the optimal behavior proposal server 101 uses this model and the accumulated data of ticket gates at each station up to the present day (step 602) to predict the transition of the number of passengers by time period, departure station, and destination station from the present day onwards (step 603). When train operation is disrupted due to an accident or breakdown, the operation control department rearranges the timetable. In that case, the optimal behavior proposal server 101 receives the revised timetable data from the operation control system (step 604) and uses it to perform calculations to track what transfers passengers will make for all combinations of departure station, destination station, and first train to board (step 605). This allows the travel time required for each passenger to reach their destination at the time of the disruption and the congestion level in each section of each train to be calculated.

[0088] On the other hand, the optimal behavior proposal server 101 receives and accumulates store status data in real time from the store server 103. After acquiring information on the user's current location and destination from the user's terminal device 102 (e.g., a smartphone), the optimal behavior proposal server 101 identifies the train the user plans to board or is currently boarding, and calculates the difference in arrival time between continuing to the destination and choosing a detour, as well as the increase in travel time when a break is taken, and calculates the total satisfaction score for each behavior pattern (step 606), and transmits the result to the user's terminal device 102.

[0089] The satisfaction level can be calculated by the optimal behavior suggestion server 101 in the same manner as in the first embodiment. For example, the optimal behavior suggestion server 101 may calculate the satisfaction level based on at least one of the length of time required for the user to arrive at the destination, the length of the ride time for the user to arrive at the destination, the number of transfers for the user to arrive at the destination, and the degree of congestion of the vehicle the user rides in. In addition, when the behavior pattern includes a break at a store, the store data may be referenced and the satisfaction level may be calculated based on the content of the behavior during the break. Although omitted in FIG. 6, when information indicating the user's preferences is input, weighting based on the preferences may be performed in the same manner as in the first embodiment.

[0090] Furthermore, the system according to the embodiment of the present invention may be configured as follows.

[0091] (1) An action suggestion system (e.g., optimal action suggestion system 30), comprising one or more processors (e.g., processor 111) and one or more storage devices (e.g., at least one of memory 112 and auxiliary storage device 113), at least one of which stores a user's passage record in a transportation network (e.g., data 201 of time zone transitions of departure IC and destination IC under normal circumstances and data accumulated in step 202, or data 601 of the number of passengers for all combinations of departure station, destination station, and time zone and data accumulated in step 602), and information on disruptions occurring in the transportation network (e.g., At least one of the one or more processors holds a congestion status for each section of the transportation network in each time period when a disruption occurs in the transportation network based on the passage record and the information regarding the disruption (e.g., steps 203 to 208 or steps 603 to 605), generates a plurality of behavioral patterns of the user to be predicted, and predicts the location of the user to be predicted in each time period for each of the plurality of behavioral patterns based on the predicted congestion status (e.g., step 216 or 606).

[0092] This makes it possible to assist individuals in choosing their actions when a traffic disruption occurs by predicting which actions will be affected by the traffic disruption and to what extent each of them will be affected.

[0093] (2) In the behavior suggestion system described in (1) above, at least one of the one or more processors calculates a satisfaction level of the user to be predicted for each of the multiple behavioral patterns based on the predicted location in each time period (e.g., step 216 or 606), and suggests a behavior of the user to be predicted based on the calculated satisfaction level (e.g., step 217 or 609).

[0094] This makes it possible to predict which actions an individual can take when a traffic disruption occurs, to what extent they will be affected by the disruption, and the extent to which their satisfaction will decrease as a result, and to present the individual with the option that will minimize the decrease in satisfaction.

[0095] (3) The behavior suggestion system described in (2) above, wherein the transportation network is an expressway, the user is a person riding in a vehicle traveling on the expressway, the congestion situation is the congestion situation of the vehicles on the expressway, and the multiple behavioral patterns include at least two of continuing to drive on the expressway, taking a rest at a store on the expressway, and taking a rest at a store along a general road outside the expressway.

[0096] This makes it possible to suggest actions to take based on satisfaction levels when a traffic jam occurs on a highway.

[0097] (4) In the behavior suggestion system described in (3) above, at least one of the one or more processors calculates the satisfaction level for each of the multiple behavior patterns based on at least one of the length of time required for the user to be predicted to arrive at the destination, the length of time the user to be predicted will drive the vehicle, the length of time the vehicle will be traveling at low speed, the length of rest periods, and the content of behavior during rest periods (e.g., step 216).

[0098] This makes it possible to appropriately calculate the satisfaction level of each option for action when a traffic jam occurs on a highway.

[0099] (5) In the behavior suggestion system described in (4) above, at least one of the one or more storage devices holds information indicating preferences of the user to be predicted (e.g., preference 213), and the information indicating the preferences of the user to be predicted includes at least one of the degree of the user's desire to arrive at the destination early, the degree of the user's desire to take a break, and preferences regarding behavior during the break, and at least one of the one or more processors calculates the satisfaction level by weighting at least one of the length of time required for the user to be predicted to arrive at the destination, the length of time the vehicle is driven, the length of time the vehicle is traveling at low speed, the length of the break, and the content of the behavior during the break, based on the information indicating the preferences of the user to be predicted.

[0100] This makes it possible to appropriately calculate the satisfaction level of each option for action when a traffic disruption occurs on an expressway, based on the individual circumstances of each user.

[0101] (6) In the behavior suggestion system described in (5) above, the storage device holds store information (e.g., store data 500) including at least one of the following for each of a plurality of stores: location, travel time to use the store, congestion level, business hours, and services provided; and at least one of the one or more processors predicts the location of the user to be predicted during each time period and calculates the satisfaction level for a behavior pattern including a break in a store among the plurality of behavior patterns, based on the store information.

[0102] This makes it possible to appropriately calculate the satisfaction level of each option for action when a traffic disruption occurs on an expressway, based on the individual circumstances of each user.

[0103] (7) In the action suggestion system described in (6) above, one of the one or more processors outputs the plurality of action patterns in descending order of the degree of satisfaction.

[0104] This allows you to suggest actions based on satisfaction.

[0105] (8) The behavior suggestion system described in (5) above, comprising a behavior suggestion server (e.g., an optimal behavior suggestion server 101) and a terminal device (e.g., a user-owned terminal device 102) used by a user to be predicted, the one or more processors including a processor of the behavior suggestion server and a processor of the terminal device, the one or more storage devices including a storage device of the behavior suggestion server and a storage device of the terminal device, information indicating preferences of the user to be predicted is held in the storage device of the terminal device, the processor of the behavior suggestion server predicts the congestion situation (e.g., steps 203 to 210), and the processor of the terminal device predicts the location of the user to be predicted (e.g., step 216), calculates the satisfaction level of the user to be predicted (e.g., step 216), and suggests behavior for the user to be predicted (e.g., step 217).

[0106] This makes it possible to properly calculate the user's satisfaction level and suggest actions to be taken without the server learning the user's personal information.

[0107] (9) The behavior suggestion system according to (3) above, wherein the storage device holds congestion degree information (e.g., congestion degree information 206) from sensors installed on the expressway, the user passage record in the traffic network includes the number of vehicles entering and exiting each entrance / exit for each time period under normal circumstances (e.g., time period transition data 201 of the departure IC and destination IC under normal circumstances) and the number of vehicles entering and exiting each entrance / exit for each time period up to the current time on the day (e.g., data accumulated in step 202), and the information regarding the disruption occurring in the traffic network includes information on the location and time period in which the number of lanes is reduced, and at least one of the one or more processors predicts the number of vehicles entering and exiting each entrance / exit for each time period after the current time based on the passage record (e.g., data accumulated in step 202). Based on the predicted number of entries and exits for each entrance / exit for each time period from the current time onwards and information regarding the disruption that has occurred in the traffic network, a location of each vehicle for each time period is predicted (e.g., step 205), and based on the predicted location of each vehicle for each time period and congestion level information from the sensor, a location, time and level of congestion on the expressway is predicted (e.g., step 207), and the predicted location of each vehicle for each time period is corrected based on the predicted location, time and level of congestion on the expressway (e.g., correction of the prediction in step 205 based on the result of step 207), thereby predicting the congestion situation in each time period for each section of the traffic network in the event of a disruption in the traffic network.

[0108] This makes it possible to predict congestion on expressways with high accuracy.

[0109] (10) The behavior suggestion system described in (2) above, wherein the transportation network is a railway, the user is a person riding on a train, the congestion situation is the congestion situation of people riding on the train, and the multiple behavioral patterns include at least two of traveling along the originally planned route, traveling by changing the route, taking a break at a store within a railway station, and taking a break at a store outside the railway station.

[0110] This makes it possible to suggest actions to take based on satisfaction levels when a traffic disruption occurs on a railway.

[0111] (11) In the behavior suggestion system described in (10) above, at least one of the one or more processors calculates the satisfaction level for each of the multiple behavior patterns based on at least one of the length of time required for the user to be predicted to arrive at the destination, the length of the ride time for the user to be predicted to arrive at the destination, the number of transfers for the user to be predicted to arrive at the destination, and the degree of congestion of the vehicle in which the user to be predicted will ride.

[0112] This makes it possible to appropriately calculate the satisfaction level of each option for action when a traffic jam occurs on a highway.

[0113] (12) The behavior suggestion system described in (10) above, wherein the records of users passing through the transportation network include the number of users of each train from the departure station to the destination station under normal circumstances (e.g., data 601 on the number of passengers for all combinations of departure station, destination station, and time period) and information on ticket gates for each time period up to the current time at each station on the day (e.g., data accumulated in step 602), and the information on the disruption that has occurred in the transportation network includes information on the suspended sections and the suspended time periods, and at least one of the one or more processors predicts the number of users of each train from the departure station to the destination station for each time period from the current time onwards based on the records of users passing through the transportation network (e.g., step 603), and predicts the congestion situation in each time period for each section of the transportation network in the event of a disruption in the transportation network by tracking the movement of each user when transferring for combinations of departure station, destination station, and train based on the predicted number of users of each train from the departure station to the destination station and the information on the disruption that has occurred in the transportation network (e.g., step 605).

[0114] This makes it possible to predict train congestion with high accuracy.

[0115] The present invention is not limited to the above-mentioned embodiment, but includes various modifications. For example, the above-mentioned embodiment has been described in detail for a better understanding of the present invention, and is not necessarily limited to those including all of the configurations described. Also, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Also, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0116] In addition, the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. In addition, the above-mentioned configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as a program, table, file, etc. that realizes each function can be stored in a storage device such as a non-volatile semiconductor memory, a hard disk drive, or an SSD (Solid State Drive), or in a computer-readable non-transitory data storage medium such as an IC card, an SD card, or a DVD.

[0117] In addition, the control lines and information lines are shown as those considered necessary for the explanation, and not all control lines and information lines in the product are shown. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0118] 10. Internet 20…Leased line 30…Optimal action suggestion system 101…Optimal action suggestion server 102...User-owned terminal device 103...Store server 104...Data relay server 105...Traffic management and congestion monitoring system

Claims

1. An action suggestion system, comprising: One or more processors and one or more memory devices; At least one of the one or more storage devices holds a passage record of a user in a transportation network and information regarding a disruption occurring in the transportation network; At least one of the one or more processors: predicting a congestion state in each time period for each section of the transportation network when a disruption occurs in the transportation network based on the passing record and the information regarding the disruption; A behavior suggestion system that generates multiple behavior patterns of a user to be predicted, and predicts the location of the user to be predicted during each time period for each of the multiple behavior patterns based on the predicted congestion situation.

2. The action suggestion system according to claim 1 , A behavior suggestion system characterized in that at least one of the one or more processors calculates a satisfaction level of the user to be predicted for each of the multiple behavioral patterns based on the predicted location during each time period, and suggests behavior for the user to be predicted based on the calculated satisfaction level.

3. The action suggestion system according to claim 2, The transportation network is a highway, The user is a person who is riding in a vehicle traveling on a highway, The congestion status is a congestion status of the vehicles on the expressway, The plurality of behavioral patterns include at least two of: continuing driving on the expressway, taking a rest at a store on the expressway, and taking a rest at a store along a general road outside the expressway.

4. The action suggestion system according to claim 3, The behavior suggestion system is characterized in that at least one of the one or more processors calculates the satisfaction level for each of the multiple behavior patterns based on at least one of the length of time required for the user to be predicted to arrive at the destination, the length of time the user to be predicted will be driving the vehicle, the length of time the vehicle is traveling at low speed, the length of rest periods, and the content of behavior during rest periods.

5. The action suggestion system according to claim 4, At least one of the one or more storage devices stores information indicating preferences of the user to be predicted; The information indicating the preference of the user of the prediction target includes at least one of a degree of the user's desire to arrive at a destination early, a degree of the user's desire to take a rest, and a preference regarding an action during the rest, At least one of the one or more processors calculates the satisfaction level by weighting at least one of the length of time required for the user to arrive at the destination, the length of time the vehicle is driving, the length of time the vehicle is driving at low speed, the length of rest time, and the content of the behavior during the rest period, based on information indicating the preferences of the user to be predicted.

6. The action suggestion system according to claim 5, the storage device holds store information including at least one of a location, a travel time to use the store, a congestion state, business hours, and a service content provided for each of a plurality of stores; and a behavior suggestion system, characterized in that at least one of the one or more processors predicts the location of the user to be predicted during each time period and calculates the satisfaction level for a behavior pattern among the plurality of behavior patterns that includes a break in a store, based on the store information.

7. The action suggestion system according to claim 6, An action suggestion system, characterized in that one of the one or more processors outputs the plurality of action patterns in order of decreasing satisfaction level.

8. The action suggestion system according to claim 5, An action suggestion server and a terminal device used by a user of the prediction target, the one or more processors include a processor of the action suggestion server and a processor of the terminal device; the one or more storage devices include a storage device of the action suggestion server and a storage device of the terminal device; The information indicating the preference of the user to be predicted is stored in a storage device of the terminal device; a processor of the action suggestion server predicts the congestion state; A behavior suggestion system characterized in that a processor of the terminal device predicts the location of the user to be predicted, calculates the satisfaction level of the user to be predicted, and suggests behavior for the user to be predicted.

9. The action suggestion system according to claim 3, The storage device stores congestion degree information obtained by sensors installed on the expressway, The user passage record in the transportation network includes the number of vehicles entering and exiting each entrance / exit per time period during normal times, and the number of vehicles entering and exiting each entrance / exit per time period up to the current time on the day, The information regarding the disruption occurring in the traffic network includes information regarding the location and time period in which the number of lanes is reduced, At least one of the one or more processors: Based on the passage records, predict the number of entrances and exits for each time period from the current time onwards at each entrance and exit; predicting the location of each vehicle for each time period based on the predicted number of entrances and exits for each time period from the current time onwards at each entrance and exit and information regarding disruptions occurring in the transportation network; predicting the location, time and extent of congestion on the expressway based on the predicted location of each vehicle for each time period and congestion degree information from the sensor; An action suggestion system that predicts the congestion situation at each time period for each section of the transportation network in the event of a disruption in the transportation network by correcting the predicted location of each vehicle for each time period based on the predicted location, time, and degree of congestion on the expressway.

10. The action suggestion system according to claim 2, The transportation network is a railway, The user is a person who boards a train, The congestion status is a congestion status of people riding on the train, The plurality of behavioral patterns include at least two of the following: traveling along an originally planned route, traveling by changing a route, taking a rest at a store within a railway station, and taking a rest at a store outside a railway station.

11. The action suggestion system according to claim 10, A behavior suggestion system characterized in that at least one of the one or more processors calculates the satisfaction level for each of the multiple behavioral patterns based on at least one of the length of time required for the user to be predicted to arrive at the destination, the length of the ride time for the user to be predicted to arrive at the destination, the number of transfers the user to be predicted will need to make to arrive at the destination, and the degree of congestion of the vehicle in which the user to be predicted will ride.

12. The action suggestion system according to claim 10, The user passage record in the transportation network includes the number of users of each train from the departure station to the destination station under normal circumstances, and ticket gate information for each time period up to the current time at each station on the day, The information regarding the disruption occurring in the traffic network includes information regarding the disruption section and the disruption time period, At least one of the one or more processors: predicting the number of passengers on each train from a departure station to a destination station for each time period from the current time onward based on the passage records of passengers on the transportation network; This action suggestion system predicts the congestion situation at each time period for each section of the transportation network in the event of a disruption in the transportation network by tracking the movements of each user when transferring for a combination of a departure station, a destination station, and a train, based on the predicted number of users of each train from a departure station to a destination station and information regarding a disruption that has occurred in the transportation network.

13. An action suggestion method by an action suggestion system, The action suggestion system includes one or more processors and one or more storage devices; At least one of the one or more storage devices holds a passage record of a user in a transportation network and information regarding a disruption occurring in the transportation network; The action suggestion method includes: A step in which at least one of the one or more processors predicts a congestion state in each time period for each section of the transportation network when a disruption occurs in the transportation network based on the passage record and the information regarding the disruption; A behavior suggestion method comprising the steps of: at least one of the one or more processors generating a plurality of behavior patterns of the user to be predicted; and predicting the location of the user to be predicted during each time period for each of the plurality of behavior patterns based on the predicted congestion situation.

Images