JP2020038725A - Information processing system, method for processing information, and information processing program - Google Patents

Abstract

To provide an information processing system, a method for processing information, and an information processing program which can predict a congestion at low cost.SOLUTION: A control unit 23 in an information processing system 2 includes an information acquisition unit 231, an extraction unit 232, and a prediction unit 233. The information processing system 231 acquires route information from a route information database 221 in a storage unit 22. The extraction unit 232 extracts at least one station from boarding stations and exit stations from the route information. The extraction unit 232 extracts at least one of extracted boarding trains which a user gets on and of extracted exit trains which a user gets off. The prediction unit 233 generates congestion prediction information by predicting a congestion related to the train on the basis of the extracted boarding stations and exit stations and the information on the extracted trains. Using the route information can reduce the cost of congestion.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing system for performing congestion prediction, an information processing method, and an information processing program.

  2. Description of the Related Art A system for predicting a congestion state of a train is known. For example, Patent Literature 1 discloses a vehicle congestion status prediction system that predicts a congestion status based on a history of a boarding rate for each day of the week and for each time zone. In this vehicle congestion situation prediction system, a train provided with human sensors arranged for each seat position and each standing position is shown.

JP 2013-73396 A

  However, in the technique of Patent Literature 1, the history of the past occupancy rate is necessary to predict the congestion situation, and it is necessary to provide a human sensor in the train to acquire the history of the past occupancy rate. is there. For this reason, there is a problem that costs are increased in hardware.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide an information processing system, an information processing method, and an information processing program capable of predicting congestion at low cost.

  According to one aspect of the present invention, at least one of a boarding station and a drop-off station, a train to be boarded at the boarding station, and at least one of a train to be dropped off at the boarding station, from a plurality of pieces of route information. An information processing system is provided, comprising: an extraction unit that extracts one train; and a prediction unit that performs congestion prediction related to the train based on the extracted information about the station and the train.

  According to the present invention, congestion can be predicted at low cost because path information is used.

FIG. 1 is a block diagram showing a schematic configuration of an information processing system 2 according to a first embodiment of the present invention. The figure which shows an example of the structure of the route information database 221. 9 is a flowchart illustrating an example of a processing operation of the information processing system 2. The figure which shows the 1st example of the point table created in step S3. The figure which shows the 2nd example of the point table created in step S3. The figure which shows the 3rd example of the point table created in step S3. The figure which shows the 4th example of the point table created in step S3. The figure which shows the 5th example of the point table created in step S3. The figure which shows an example of the structure of the route information database 221. 9 is a flowchart illustrating an example of a processing operation of the information processing system 2. The figure which shows an example of the point table created in step S3 '. The figure which shows an example of the technique of extracting a vehicle based on the position of a facility. The figure which shows another example of the technique of extracting a vehicle based on the position of a facility. FIG. 11 is a block diagram showing a schematic configuration of an information processing system 100 according to a fourth embodiment of the present invention. FIG. 15 is a sequence diagram showing an example of the processing operation of the information processing system 100 in FIG. 14. The figure which shows an example of the screen displayed on a display.

  Hereinafter, embodiments of the present invention will be specifically described with reference to the drawings.

(First embodiment)
FIG. 1 is a block diagram illustrating a schematic configuration of an information processing system 2 according to the first embodiment of the present invention. The information processing system 2 includes a storage unit 22 and a control unit 23.

  The storage unit 22 stores a route information database 221. The route information database 221 includes a plurality of pieces of route information. The route information is information indicating how to move from the departure point to the destination (or at least a part thereof). In the present embodiment, it is assumed that the route information includes at least one train getting on and off. I assume.

  The route information is, for example, route information obtained by a route search performed in response to a user request. Such route information may be a result of a route search performed by a route search unit (not shown) in the information processing system 2 or a result of a route search performed by another device.

  The route information may be route information based on user registration other than the result of the route search. For example, when a commuter pass held by the user is registered, a commuting route (outbound route) in which a typical commuting time zone (for example, 8:00 to 10:00 on weekdays) arrives at the work location, A commuting route (return route) in which a typical leaving time (for example, 17:00 to 19:00 on weekdays) is the arrival time at home may be included in the route information database 221 as route information.

  FIG. 2 is a diagram illustrating an example of the structure of the route information database 221. As illustrated, the route information database 221 has date information, boarding information, one or more pieces of transfer information, and getting off information associated with each other using the route ID as an index. Hereinafter, the route information whose route ID is “X” is referred to as “route information X”.

  The date information indicates a date when the route is moved. The boarding information includes the boarding station, the departure time of the train boarding at the boarding station, the route boarding at the boarding station, and the train ID of the boarding board. The transfer information includes the transfer station, the arrival time at the transfer station, the departure time of the train to be boarded at the transfer station, the route to be boarded at the transfer station, and the train ID of the train to be boarded. The disembarkation information includes the disembarkation station and the arrival time at the disembarkation station. Here, the train is uniquely specified by the date, the route, and the train ID. Hereinafter, the train whose train ID is “Y” is referred to as “train Y”.

  For example, the route information 002 indicates that the route is as follows. It will move on September 2, 2013. Then, the user gets on the S-line train Z005 that departs from the S2 station at 11:31. The train arrives at S4 station at 11:35 and gets off the train. Then, take the T-line train Y007, which departs the station at 11:41. And we arrive at T1 station at 11:49.

  Note that there may be no transfer like the route information 001. Although not shown, there may be two or more transfers. Further, there is a case where the getting off station is different from the getting on station in the transfer (for example, when moving from the getting off station to the getting on station on foot), and in that case, the transfer information may include the getting off station and the getting on station.

  The route information may include information other than the information shown in FIG. 2, such as a route from the departure point to the boarding station or a route from the getting off station to the destination.

  Returning to FIG. 1, the control unit 23 includes an information acquisition unit 231, an extraction unit 232, and a prediction unit 233. These units are functions realized by, for example, a processor (not shown) in the information processing system 2 executing a predetermined information processing program.

  The information acquisition unit 231 acquires route information from the route information database 221 in the storage unit 22.

  The extraction unit 232 extracts at least one of the boarding station and the getting off station from the route information. The extraction unit 232 may extract only the boarding station or only the getting off station. From one of the route information illustrated in FIG. 2, the extraction unit 232 can extract one boarding station based on the boarding information and can extract one getting-off station based on the boarding information. Further, the extraction unit 232 can extract the boarding station and the getting off station one by one based on the transfer information.

  For example, for the route information 001, the S1 station on the S line can be extracted as the boarding station, and the S2 station on the S line can be extracted as the getting off station. As for the route information 002, the S2 station of the S line and the S4 station of the T line can be extracted as the boarding stations, and the S4 station of the S line and the T1 station of the T line can be extracted as the getting off stations.

  Further, the extraction unit 232 extracts at least one train of a train to board at the extracted boarding station and a train to get off at the extracted boarding station. For example, for the route information 001, a train Z004 is extracted as a train to board at the boarding station S1 and a train to get off at the boarding station S2.

  The prediction unit 233 performs congestion prediction related to the train based on the information on the extracted boarding station and disembarkation station and the extracted train, and generates congestion prediction information. “Related to a train” means that it may be a congestion prediction of the extracted train itself or a congestion prediction of a plurality of trains including the extracted train. A specific example of the congestion prediction will be described later.

  Note that the information processing system 2 may be provided by providing each unit in the storage unit 22 and the control unit 23 in a single device, or may be provided by distributing the information in a plurality of devices.

FIG. 3 is a flowchart illustrating an example of a processing operation of the information processing system 2. First, the information acquisition unit 231 acquires route information from the storage unit 22 (Step S1). Then, the extraction unit 232 extracts the boarding station and / or the getting-off station and the train from the route information (Step S2).
Next, the prediction unit 233 creates a point table (details will be described later) by counting the number of pieces of route information for each station and each train based on the extracted stations and trains (step S3). Then, the prediction unit 233 performs the congestion prediction with reference to the point table (Step S4).

  Hereinafter, as the congestion prediction, an example in which the prediction unit 233 performs prediction regarding the number of people getting off from each train at the getting off station will be described.

  FIG. 4 is a diagram illustrating a first example of the point table created in step S3. The drawing is a drop-off point table, in which the number of pieces of route information in which each station is a drop-off station is counted as a drop-off point. The getting off point is a value according to the number of people getting off at each station. In the figure, it is assumed that the S line has six stations S1 to S6 in this order, and that the S1 station is the first station and the S6 station is the last station.

  Considering the route information 001 to 004 of the route information database 221 of FIG. 2, the getting-off point table of FIG. 4A is created. Specifically, for the train Z004, there is one piece of route information (route information 001) that gets off at the S2 station, and the getting-off point is “1”. In addition, for the train Z005, there are two pieces of route information (route information 002, 003) to get off at the S4 station, and the getting off point is "2". There is one route information (route information 004) that gets off at the same S6 station, and the getting off point is “1”.

It is assumed that the drop-off point table shown in FIG. 4B is created as a result of totalizing all the route information.
Based on this drop-off point table, the prediction unit 233 can perform congestion prediction for the train Z004, such as "the number of people getting off at S2 station is small", "the number of people getting off at S3 station is many". When the correlation between the disembarkation point and the actual number of disembarkers is known, the prediction unit 233 may estimate the number of people disembarking at each station and perform congestion prediction. Similarly, the prediction unit 233 can perform congestion prediction for the train Z005.

  In this way, the prediction unit 233 can make predictions regarding the number of people getting off each train with each station getting off. Subsequently, an example in which the prediction unit 233 performs prediction regarding the number of people who board each train at the boarding station as the congestion prediction will be described.

  FIG. 5 is a diagram illustrating a second example of the point table created in step S3. The drawing is a boarding point table in which the number of route information for each station as a boarding station is counted as a boarding point. The boarding point is a value corresponding to the number of people boarding at each station.

  Considering the route information 001 to 004 of the route information database 221 of FIG. 2, the boarding point table of FIG. 5A is created. Specifically, for the train Z004, there is one piece of route information (route information 001) to be boarded at the S1 station, and the boarding point is “1”. In addition, for the train Z005, there is one piece of route information (route information 003) for boarding at the S1 station. There is one piece of route information (route information 002) for boarding at the S2 station. There is one route information (route information 004) for boarding at the S3 station. Therefore, the exit points at the S1 to S3 stations are all “1”.

It is assumed that the boarding point table shown in FIG. 5B is created as a result of totalizing all the route information.
Based on this boarding point table, the prediction unit 233 can perform congestion prediction for the train Z004, such as "the number of passengers at the S1 station is medium", "the number of passengers at the S5 station is large", and the like. it can. When the correlation between the boarding point and the actual number of passengers is known, the prediction unit 233 may estimate the number of passengers at each station and perform congestion prediction. Similarly, the prediction unit 233 can perform congestion prediction for the train Z005.

  In this way, the prediction unit 233 can make predictions regarding the number of passengers of each train having each station as the boarding station. Subsequently, an example in which the prediction unit 233 makes a prediction regarding the congestion degree at the boarding station or the disembarkation station as the congestion prediction will be described.

  FIG. 6 is a diagram illustrating a third example of the point table created in step S3. This figure is a congestion point table, and the congestion points are values according to the number of people riding the train at the boarding station or the getting off station. The congestion point table of FIG. 6 can be created by adding the difference between the boarding point shown in FIG. 5B and the getting off point shown in FIG. 4B for each station.

  For example, for the train Z004, the boarding point at the S1 station is “12” according to FIG. 5B. Since the S1 station is the first station, the getting off point is “0”. Therefore, as shown in FIG. 6, the congestion point at the S1 station is “12”.

  Next, according to FIG. 5B, the boarding point at the S2 station is “10”, and according to FIG. 4B, the getting off point at the station is “1”. Therefore, 9 (= 10-1) points are increased at the S2 station, and the congestion point at the S2 station is "21" (= 12 + 9) as shown in FIG.

  Next, according to FIG. 5B, the boarding point at the S3 station is “18”, and according to FIG. 4B, the getting off point at the station is “28”. Therefore, at the S3 station, "10" (= 28-18) points are reduced, and the congestion point at the S3 station is "11" (= 21-10) as shown in FIG.

  In the same manner, the prediction unit 233 calculates the congestion point at each station. Note that the congestion point is "0" because S6 station is the terminal station.

  Based on this point table, the prediction unit 233 determines, for the train Z004, that “the congestion degree at the S1 station is low”, “the congestion degree at the S2 station is medium”, “the congestion degree at the S5 station is high”, Congestion prediction, such as, can be performed. When the correlation between the congestion point and the number of people actually on the train is known, the prediction unit 233 may estimate the number of people on each station and use it as the congestion prediction. Similarly, the prediction unit 233 can perform congestion prediction for the train Z005.

  In this way, the prediction unit 233 can perform prediction regarding the number of people riding on each train at each station. Subsequently, an example will be described in which the prediction unit 233 performs an example prediction regarding an increase or decrease in the number of people riding on the train at the boarding station or the disembarking station as the congestion prediction.

FIG. 7 is a diagram illustrating a fourth example of the point table created in step S3. The figure shows an increase / decrease point table. The increase / decrease points are values corresponding to the difference between the number of passengers and the number of passengers at each station.
The increase / decrease point table of FIG. 7 can be created from the difference between the boarding point shown in FIG. 5 (b) and the getting off point shown in FIG. 4 (b).

  For example, for the train Z004, the boarding point at the S1 station is “12” according to FIG. 5B. Since the S1 station is the first station, the getting off point is “0”. Therefore, as shown in FIG. 7, the increase / decrease point at the S1 station is “12”.

  Next, according to FIG. 5B, the boarding point at the S2 station is “10”, and according to FIG. 4B, the getting off point at the station is “1”. Therefore, as shown in FIG. 7, the increase / decrease point at S2 station is “9” (= 10−1).

  Next, according to FIG. 5B, the boarding point at the S3 station is “18”, and according to FIG. 4B, the getting off point at the station is “28”. Therefore, as shown in FIG. 7, the increase / decrease point at the S3 station is “−10” (= 18−28) points.

  Hereinafter, similarly, the prediction unit 233 calculates the increase / decrease point at each station. Based on this point table, the prediction unit 233 can perform a congestion prediction such as “the number of people on the train Z004 greatly decreases at the station S3”. Similarly, the prediction unit 233 can perform congestion prediction for the train Z005.

  The above is an example of performing the congestion prediction for each train, but the prediction unit 233 may perform the congestion prediction for a plurality of trains included in a predetermined time range.

  FIG. 8 is a diagram illustrating a fifth example of the point table created in step S3. The figure shows an example in which trains are grouped for each time zone. More specifically, for all trains departing from S1 station between 11:00 and 11:59 (assuming only two trains Z004 and Z005), the congestion points at each station are summed up. This is illustrated. The point table of FIG. 8 can be created from the congestion point table of FIG.

  That is, in FIG. 6, the congestion point at the S1 station is “12” for the train Z004 and “19” for the train Z005. Therefore, the sum of the congestion points is “31” (= 12 + 19) as shown in FIG.

  In FIG. 6, the congestion point at station S2 is “21” for train Z004 and “30” for train Z005. Therefore, the sum of the congestion points is “51” (= 21 + 30) as shown in FIG.

  As described above, the total of the congestion points of each station is calculated. Based on this point table, the prediction unit 233 can perform a congestion prediction such as “the S-line train before noon is particularly congested at S2 and S5 stations”.

  Note that the prediction unit 233 may calculate the total of the disembarkation points from FIG. 4B and perform the congestion prediction on the number of people getting off the train at each station for each time zone. In addition, the prediction unit 233 may calculate the total of the boarding points from FIG. 5B and perform the congestion prediction regarding the number of people boarding from the train at each station for each time zone. Further, the prediction unit 233 may calculate the total of the increase / decrease points from FIG. 7 and perform the congestion prediction regarding the increase / decrease of the number of people riding the train at each station for each time zone.

  In addition, the method of organizing trains is not limited to each time zone, and can be organized for an arbitrary time range such as each day of the week or each season.

  As described above, in the first embodiment, since the route information stored in the storage unit 22 is used, the congestion prediction can be performed at low cost.

  The prediction unit 233 may perform the congestion prediction in consideration of not only the route information but also the actual congestion information. The congestion result information is information indicating a past congestion result, and may be stored in the storage unit 22 in FIG. As a specific example, the prediction unit 233 may predict that there is congestion when any one of the congestion prediction based on the route information and the congestion prediction based on the actual congestion information is congested. On the other hand, the prediction unit 233 may, for example, predict that there is no congestion when both the congestion prediction based on the route information and the congestion prediction based on the actual congestion information are not congested.

  Further, in the above-described example, as shown in FIG. 2, the route information includes the train ID, and the train is extracted based on the train ID. However, the route information does not necessarily have to include the train ID. In this case, the storage unit 22 may store a timetable information database (not shown). The timetable information indicates a departure time and / or an arrival time at each station of each train.

  Then, the extracting unit 232 extracts the train with reference to the timetable information. By referring to the timetable information, for example, the extraction unit 232 determines the train (route information 002) that departs the station S2 in FIG. 2 at 11:31 and the train that departs the station S1 at 11:29 (route information). 003) may be specified as the same train.

  The extraction unit 232 may extract the train by specifying the route name, the station, the departure time or the arrival time at the station, the category, the destination, and the like, without using the train ID. The category may be a type such as “express”, “express”, “stop”, or a nickname of a train.

(Second embodiment)
The first embodiment described above counts the number of passengers and the number of people getting off for each train. On the other hand, in the second embodiment described below, the number of passengers and the number of getting off passengers are counted for each position (for example, vehicle or door) in the train. Then, which position in the train is congested is predicted.

  The configuration itself of the information processing system 2 is the same as that of the first embodiment shown in FIG. 1, and the processing content of each unit will be described below focusing on differences from the first embodiment.

  The extraction unit 232 extracts, in addition to the boarding station and / or the getting-off station, at least one of a boarding position of the train at the boarding station and a getting-off position of the train at the boarding station. The getting on or off position is, for example, which vehicle in the train or which door of which vehicle.

The prediction unit 233 performs a congestion prediction related to this position from the extracted station and position.
Specific examples of the congestion prediction include prediction of the number of people getting on / off at the position extracted at each station, the number of increase / decrease of the number of people riding at the position extracted at each station, and the degree of congestion at the extracted position at each station. Can be

  Hereinafter, an example in which the extraction unit 232 extracts a vehicle in a train as a boarding position or a getting-off position will be described. In this case, a route information database 221 as shown in FIG. 9 is used. The difference from FIG. 2 is that the boarding information and the transfer information include “recommended vehicles”. Recommended vehicles are information that can be given at the time of route search, and are vehicles that are convenient to travel along the route, and that require less time to transfer and vehicles that require less time to travel from the disembarkation station to the destination. And so on.

  As shown in the figure, the recommended vehicle may be specified as a relative vehicle in the train such as “first car from the front”. As another example, the recommended vehicle may be specified by an absolute car number assigned to each car of the train, such as “car 1”.

  Further, there may be two or more recommended vehicles as in the route information 004. Furthermore, the recommended vehicle may be a rough one such as a “vehicle closer to the front” or “first to third eyes”.

  FIG. 10 is a flowchart illustrating an example of a processing operation of the information processing system 2. Step S1 is the same as in the first embodiment.

  In step S <b> 2 ′, the extraction unit 232 extracts a boarding station and / or a drop-off station, a train, and a boarding vehicle for the train at the boarding station and / or a vehicle getting off the train at the drop-off station.

  The extraction unit 232 can extract a vehicle based on the recommended vehicle in the route information. For example, in the route information 001 in FIG. 9, based on the fact that the recommended vehicle in the boarding information is “first car from the front”, the extraction unit 232 determines “1 from the front as a boarding vehicle to the train Z004 at the station S1 as the boarding station. Both eyes "can be extracted. Also, in the route information 004, based on the fact that the recommended vehicle in the boarding information is “3 or 5 cars from the front”, the extraction unit 232 determines that the boarding vehicle for the train Z005 at the station S3, which is the boarding station, is “3 from the front. Or 5 eyes "can be extracted.

  In addition, since the user usually gets off from the boarded vehicle, the extraction unit 232 can extract “first vehicle from the front” as the getting-off vehicle from the train Z004 at the station S2, which is the getting-off station, in the route information 001.

  Then, in step S3 ', the prediction unit 233 creates a point table by counting the number of pieces of route information for each station and each vehicle.

  FIG. 11 is a diagram showing an example of the point table created in step S3 '. This figure shows a boarding point table.

  Considering the route information 001 to 004 of the route information database 221 in FIG. 9, the getting-off point table in FIG. 11A is created. Specifically, in FIG. 9, for the train Z004, there is one piece of route information (route information 001) that gets on the first car from the front at S2 station, and the boarding point is “1”. In addition, for the train Z005, there is one piece of route information (route information 003) that gets on the first car from the front at S1 station, and the boarding point is “1”. There is one piece of route information (route information 002) that gets on the first car at the S2 station from the front, and the boarding point is “1”.

  Here, in the route information 004, the user gets on the third or fifth car from the front at S4 station. In this case, as shown in FIG. 11, the riding points of the third and fifth cars may be equally set to “0.5”. Further, points may be assigned by weighting according to the possibility of getting on. For example, when the possibility of getting on the third car is high (such as when the third car is closer to facilities such as ticket gates and stairs at S3 station), the boarding point of the third car is set to "0.8" and the boarding point of the fifth car is set The ride point of the third car may be set to “1” and the ride point of the fifth car may be set to “0”. In any case, it is desirable that the sum of the boarding points be “1”.

  With reference to the point table created as described above, in step S4 of FIG. 10, the prediction unit 233 performs congestion prediction related to the vehicle. For example, it is assumed that the boarding point table shown in FIG. 11B is created as a result of totalizing all the route information. In this case, the prediction unit 233 can perform a more detailed congestion prediction for the train Z004, such as "the number of passengers on the first and fourth vehicles is large and the number of passengers of other vehicles is small at the station S2".

  Although the boarding point table is illustrated in FIG. 11, a getting-off point table, a congestion point table, an increase / decrease point table, and the like may be created as in the first embodiment. Then, a specific example of the congestion prediction is the same as that described in the first embodiment, except that “each train” is used instead of “each train”. For example, the prediction unit 233 performs, as the congestion prediction, the number of people who get on each vehicle at the boarding station, the number of people getting off each vehicle at the getting off station, the number of increase or decrease of the number of people getting on each vehicle at the getting on station or the getting off station, A prediction regarding the congestion degree of each vehicle at a station or a drop-off station can be made.

  Further, as in FIG. 8, the data may be collected for each certain time range. Thus, the prediction unit 233 can perform a congestion prediction such as “the train on the S line before noon is particularly crowded on the third car”.

  In the above description, a train is specified, and a boarding vehicle or a dismounting vehicle of the train is extracted. However, when grouping by time range, vehicles may be extracted without specifying a train.

For example, even if the route information database 221 in FIG. 9 does not include the train ID, the vehicle can be extracted from the recommended vehicle information. As a specific example, when the trains departing from the S1 station at 11:00 to 11:59 are put together, the recommended vehicle at the S1 station in the route information 001 and 003 is “the first car from the front”, The sum of the points can be “2”.
In this case, information on the train ID is unnecessary.

  Further, the extraction unit 232 may extract the door of the train as the boarding position or the getting off position. For that purpose, the route information database 221 only needs to include the recommended door information. Then, the prediction unit 233 can perform a congestion prediction for each door by creating a point table for each door. For example, the prediction unit 233, as the congestion prediction, the number of people boarding from each door at the boarding station, the number of people getting off from each door at the getting off station, the number of increase or decrease in the number of people getting around each door at the boarding station or getting off station, It is possible to make a prediction regarding the degree of congestion near each door at a boarding station or a drop-off station.

  As described above, in the second embodiment, since the position where the passenger gets on and off the train is extracted from the route information stored in the storage unit 22 and used for the congestion prediction, it is possible to perform the congestion prediction in more detail at low cost. it can.

  In the example described above, an example has been described in which the route information database 221 includes the recommended vehicle information, and the vehicle is specified based on the recommended vehicle information. However, the route information database 221 does not necessarily need to include the recommended vehicle information.

  For example, the station information database may be stored in the storage unit 22. The station information indicates the structure of each station premises as a station network, and includes a staircase, an elevator, an escalator, a ticket gate, an entrance, an exit, a transfer gate, a restroom, a store, and a specific location on a platform (for example, stop. (A position corresponding to a train door) and a link indicating a connection relationship between the nodes. In addition, the station information may include not only the inside of the station but also the network information of the surrounding underground shopping mall.

  Then, the extraction unit 232 may specify the vehicle based on the location of the facility at the boarding station or the getting off station.

  FIG. 12 is a diagram illustrating an example of a technique for extracting a vehicle based on the location of a facility. As illustrated, the extraction unit 232 can set the vehicle closest to the facility such as the stairs as the boarding vehicle at the boarding station (or the vehicle getting off at the getting off station). In the case of FIG. 12, the “second car” closest to the stairs may be the boarding vehicle, or the “first car or second car” may be the boarding vehicle in consideration of the fact that the first car is next.

  FIG. 13 is a diagram illustrating another example of a technique for extracting a vehicle based on the location of a facility. As illustrated, the extraction unit 232 may extract a boarding vehicle from the position of the transfer route according to a combination of the route before the transfer and the route after the transfer. In the case of FIG. 13, there is a transfer route between the vicinity of the first train of the train on the route before the transfer and the vicinity of the second train of the train on the route after the transfer. Therefore, “second car” is extracted as the boarding vehicle of the train on the route after the transfer. Alternatively, “first car” is extracted as a disembarking vehicle of the train on the route before the transfer.

  The prediction unit 233 may give points according to the distance from a facility such as a staircase for each vehicle when creating the point table. For example, in the case of FIG. 12, the point of the second vehicle closest to the stairs may be set to “0.8”, and the point of the next first vehicle may be set to “0.2”.

  Further, the vehicle may be extracted or a point table may be created in consideration of both the recommended vehicle included in the route information database 221 and the location of the facility included in the station information database.

  The same applies to doors as well as vehicles.

(Third embodiment)
In the third embodiment described below, congestion prediction is performed for each train category.

  The extraction unit 232 extracts at least one of a category of a train to get on at a boarding station and a category of a train to get off at a getting off station. Then, the prediction unit 233 creates a point table for each category from the extracted station and category, and performs congestion prediction related to the category.

  The route information database 221 may include category information. In addition, when the category of a train stopped at a station is limited, the category may be estimated from a boarding station or a drop-off station.

  The train category may be, for example, a type related to a stop station such as "limited express", "express", "each stop", or a nickname of a train such as "Kodama" or "Nozomi". The prediction unit 233 can perform congestion prediction for each category, such as “Express trains are easily crowded at station A” and “Each stop is easily crowded at station B”. Of course, the congestion prediction may be performed for each vehicle or each door, or the congestion prediction may be performed for the trains included in the predetermined time for each category.

(Fourth embodiment)
The fourth embodiment described below provides a congestion prediction to a user.

  FIG. 14 is a block diagram illustrating a schematic configuration of an information processing system 100 according to the fourth embodiment of the present invention. The information processing system 100 includes a terminal device 1 and a server 4 communicably connected via a network 3.

  The terminal device 1 is used by a user, and may be a mobile electronic device such as a mobile phone, a smartphone or a tablet, or a stationary electronic device such as a personal computer or a car navigation device.

  The terminal device 1 includes a communication unit 11, an operation input unit 12, an output unit 13, and a control unit 14.

  The communication unit 11 is an interface for transmitting and receiving information between the control unit 14 and the server 4 via the network 3.

  The operation input unit 12 is an interface for a user to input an operation to the terminal device 1, and is, for example, a touch panel or a microphone in a mobile electronic device, a keyboard, a touch pad, or a dial button in a stationary electronic device.

  The output unit 13 is an interface that outputs various information from the terminal device 1 to the user, and is, for example, a liquid crystal display that displays an image. Specifically, the output unit 13 displays information such as a GUI (Graphical User Interface) for receiving an operation from the user, and route information to be described later. Alternatively, the output unit 13 may be a speaker that outputs information by voice.

  Further, the output unit 13 does not need to directly present information to the user. For example, the output unit 13 may be an interface that outputs a video signal and / or an audio signal to a display unit and / or an audio reproduction unit that is externally connected, or outputs data to a printing device that is externally connected. It may be an interface that performs the processing, or may be an apparatus that outputs and stores the data in the terminal device 1 or an external storage device.

  The control unit 14 includes a search condition setting unit 141, an information transmitting unit 142, and an information receiving unit 143. These units are functions realized by, for example, a processor (not shown) in the information processing system 100 executing a predetermined information processing program.

  The search condition setting unit 141 sets a search condition. The search condition setting unit 141 can set search conditions by receiving search conditions such as information on a departure place, a destination, and time from the user via the operation input unit 12. Alternatively, the search condition setting unit 141 may set at least a part of the search conditions other than the user input.

  The information transmitting unit 142 transmits various information such as search conditions to the server 4 via the network 3.

  The information receiving unit 143 receives various types of information such as route information generated by the server 4 from the server 4 via the network 3. The received information is output from the output unit 13 by an output control unit (not shown) in the control unit 14.

  The server 4 includes a communication unit 41, a storage unit 42, and a control unit 43.

  The communication unit 41 is an interface for transmitting and receiving information between the control unit 43 and the terminal device 1 via the network 3.

  The storage unit 42 stores a congestion prediction information database 421 and a route network information database 422.

  The congestion prediction information database 421 includes the congestion prediction information generated by the information processing system 2 in FIG. In addition, all or a part of the information processing system 2 and a part of the server 4 in FIG. 14 are provided in one device, and the congestion prediction information generated by the prediction unit 233 is written in the congestion prediction information database 421. Good. Alternatively, the information processing system 2 and the server 4 may be separate devices, and the congestion prediction information generated by the prediction unit 233 may be written to the congestion prediction information database 421 via the network 3.

  The congestion prediction information may be updated each time one piece of congestion prediction information is generated, or may be updated at regular intervals.

  The route network information database 422 includes, for example, map information and traffic network information as route network information.

  The map information includes map data such as road maps of the whole country and each region, and map object information associated with the map data. The map data is a map representing actual roads. The map object information includes shape information on the shape of the facility displayed on the map, note information on a note displayed on the map, symbol information on a symbol displayed on the map, and the like.

  The traffic network information is information that defines a traffic network such as a railroad or a bus or a road network. The information on the transportation network includes route information, timetable information, fare information, and the like of transportation means. The information on the road network is represented by a combination of data of nodes, which are nodes on the road network representation such as intersections, and data of links, which are road sections between nodes. The node is specified by, for example, latitude and longitude, and corresponds to the position of the detailed map. The map information and the road network information are used for a route search.

  The control unit 43 includes an information receiving unit 431, a route searching unit 432, and an information transmitting unit 433. These units are functions realized by, for example, a processor (not shown) in the information processing system 100 executing a predetermined information processing program.

The information receiving unit 431 receives the search condition from the terminal device 1 via the network 3.
The information receiving unit 431 receives congestion information and route network information from the congestion prediction information database 421 and the route network information database 422 in the storage unit 42, respectively.

  The route search unit 432 performs route search based on search conditions using route network information to generate route information. The route information includes, for example, information such as a means of travel from the departure place to the destination, a travel distance, a time and fee required for travel, a departure time and an arrival time. Also, the route search unit 432 checks whether there is congestion prediction information related to the generated route information. If there is related congestion prediction information, the information reception unit 431 is controlled to receive the congestion prediction information.

  The information transmitting unit 433 transmits path information and congestion prediction information to the terminal device 1 from the communication unit 41 via the network 3.

  FIG. 15 is a sequence diagram illustrating an example of the processing operation of the information processing system 100 in FIG.

  First, the search condition setting unit 141 sets a search condition according to an operation on the operation input unit 12 by a user operation. The search condition is transmitted to the server 4 by the information transmitting unit 142 (Step S11).

  The information receiving unit 431 of the server 4 receives the search condition (Step S21). Then, the route search unit 432 performs a route search based on the search conditions, and generates route information (Step S22). The route information generated here may be written in the route information database 221 of FIG. Thereafter, the route search unit 432 confirms whether or not the congestion prediction information regarding the generated route information exists in the congestion prediction information database 421 (Step S23).

  Even when there is congestion prediction information, if the number of route information (the number of points in the point table) is small and the accuracy of congestion prediction is considered low, the route search unit 432 determines that there is no congestion prediction information. You may.

  When there is congestion prediction information (YES in step S23), the information receiving unit 431 acquires the congestion prediction information from the congestion prediction information database 421 (step S24). Then, the route search unit 432 adds the obtained congestion prediction to the route information (Step S25). The route information is transmitted to the terminal device 1 by the information transmitting unit 433 (Step S26).

  On the other hand, when there is no congestion prediction information (NO in step S23), the route information is transmitted to the terminal device 1 by the information transmitting unit 433 as it is (step S26).

  The information receiving unit 143 of the terminal device 1 receives the route information. Then, the route information is output from the output unit 13 (Step S12). The output format is congestion such as which station is likely to be seated, which station is crowded, which vehicle (near door) is likely to be seated, and which vehicle (near door) is congested. It is desirable to be able to grasp the situation visually and intuitively. Hereinafter, an output example in the case where the output unit 13 is a display and the operation input unit 12 is a touch panel arranged on the display will be described.

  FIG. 16 is a diagram illustrating an example of a screen displayed on the display. FIG. 16A shows that the boarding station is the S1 station on the S line (departure time: 19:15) and the getting off station is the S6 station on the S line (arrival time: 19:48). It is a screen when there is prediction information. As shown in the figure, an icon A1 indicating that there is congestion prediction information is displayed (when there is no congestion prediction information, such an icon is not displayed or is displayed as not selectable). Then, when the user selects the position on the touch panel where the icon A1 is displayed, the congestion prediction information is displayed on the display. This congestion prediction information relates to a train departing from S1 station at 19:15.

  FIG. 16B shows an example in which the congestion prediction is a prediction relating to the number of people getting off. In this screen, the number of people getting off at each station is schematically shown for each vehicle. For example, the mark M1 of the first car at S5 station, which is an intermediate station, indicates that there is a high possibility that a large number of people get off and can sit down. On the other hand, the fourth mark M2 at the stations S1 to S6 indicates that the number of persons getting off is small and the possibility of sitting is low. Further, the mark M3 of the other station indicates that the number of people getting off is medium.

  By referring to such congestion prediction information, the user can grasp that if he gets on the first eye of S1 station, he is more likely to sit at S5 station on the way than when he gets on another vehicle.

  FIG. 16C shows an example in which the congestion prediction is a prediction regarding the number of people riding at each station. In this screen, the number of people riding at each station is schematically shown for each vehicle. For example, the first vehicle indicates that the stations S1 to S6 are congested. The third vehicle is relatively vacant at stations S1 and S2, but somewhat congested after station S3. The fourth vehicle is relatively vacant at the S1 station, but slightly congested at the S2 station, and congested after the S3 station.

  With reference to such congestion prediction information, the user is more likely to sit in the third car at S1 station than in the case of taking another vehicle, and is not so congested up to S6 station even if he cannot sit. I can understand.

  FIG. 15 shows an example in which the congestion prediction information is added and the path information is transmitted from the server 4 to the terminal device 1. However, the information transmission unit 433 of the server 4 may separately transmit the route information and the congestion prediction information to the terminal device 1. For example, initially, only information indicating that there is route information and congestion prediction information may be transmitted to the terminal device 1.

  Then, the congestion prediction information may be transmitted from the server 4 to the terminal device 1 in response to a request from the terminal device 1.

Further, a vehicle on which the user of the terminal device 1 is riding is specified by a position acquisition unit (not shown) such as GPS in the terminal device 1, and position information indicating the position of the terminal device 1 is periodically transmitted to the server 4. .
Then, based on the position information and the congestion prediction information, the server 4 determines, based on the position information and the congestion prediction information, a station where the number of persons getting off the vehicle on which the user is riding or the timing when the congestion degree is reduced (specifically, Or a specific time), the congestion prediction information may be transmitted to the terminal device 1.

  As described above, in the fourth embodiment, congestion prediction information is presented to a user who has performed a route search. Therefore, the user can easily grasp the congestion state.

  At least a part of the information processing system described in the above embodiment may be configured by hardware or may be configured by software. When configured with software, a program that realizes at least a part of the function of the information processing system may be stored in a recording medium such as a flexible disk or a CD-ROM, and may be read and executed by a computer. The recording medium is not limited to a removable medium such as a magnetic disk or an optical disk, but may be a fixed recording medium such as a hard disk device or a memory.

  Further, a program for realizing at least a part of the function of the information processing system may be distributed via a communication line (including wireless communication) such as the Internet. Further, the program may be encrypted, modulated, or compressed, and distributed via a wired or wireless line such as the Internet, or stored in a recording medium.

Further, the information processing system may be operated by one or more information processing apparatuses.
When a plurality of information processing apparatuses are used, one of the information processing apparatuses may be a computer, and the computer may execute a predetermined program to realize a function as at least one unit of the information processing system.

  Based on the above description, those skilled in the art may be able to conceive additional effects and various modifications of the present invention, but aspects of the present invention are not limited to the individual embodiments described above. Absent. Various additions, changes, and partial deletions can be made without departing from the concept and spirit of the present invention derived from the contents defined in the claims and equivalents thereof.

1 terminal device 11 communication unit 12 operation input unit 13 output unit 14 control unit 141 search condition setting unit 142 information transmission unit 143 information reception unit 2 information processing system 22 storage unit 221 route information database 23 control unit 231 information acquisition unit 232 extraction unit 233 prediction unit 4 server 41 communication unit 42 storage unit 421 congestion prediction information database 422 route network information database 43 control unit 431 information reception unit 432 route search unit 433 information transmission unit

Claims (26)

From multiple route information,
At least one of a boarding station and alighting station;
A train that gets on at the boarding station, and at least one train that gets off at the getting off station;
Extraction means for extracting
An information processing system comprising: a prediction unit configured to perform a congestion prediction related to the train based on the extracted information about the station and the train. The prediction means, as the congestion prediction,
The number of people who get on or off at the extracted station,
The number of increase or decrease of the number of passengers at the extracted station, and
The information processing system according to claim 1, wherein prediction is performed on at least one of the congestion degrees at the extracted stations. From multiple route information,
At least one of a boarding station and alighting station;
At least one of a boarding position of the train at the boarding station and a boarding position of the train at the getting off station;
Extraction means for extracting
An information processing system comprising: a prediction unit that performs congestion prediction related to the position based on the extracted information about the station and the position. The prediction means, as the congestion prediction,
The number of people who get on or off at the extracted position,
The number of increase or decrease of the number of passengers at the extracted position, and
Congestion degree at the extracted position,
The information processing system according to claim 3, wherein prediction is performed on at least one of the following. The route information includes recommended position information indicating a recommended boarding position or getting off position,
The information processing system according to claim 3, wherein the extraction unit extracts the position based on the recommended position information.   The information processing system according to claim 3, wherein the extraction unit extracts the position based on a position of a predetermined facility at the extracted station. The information processing system according to any one of claims 3 to 6, wherein the extraction unit extracts, as the position, a vehicle on a train or a door on a train vehicle. From multiple route information,
At least one of a boarding station and alighting station;
A category of a train to be boarded at the boarding station, and at least one category of a category of a train to be boarded at the boarding station;
Extraction means for extracting
An information processing system comprising: a prediction unit configured to perform a congestion prediction related to the category based on the extracted information about the station and the category.   The information processing system according to any one of claims 1 to 8, wherein the prediction unit performs congestion prediction for a plurality of the trains included in a predetermined time range. From multiple route information,
At least one of a boarding station and alighting station;
A train that gets on at the boarding station, and at least one train that gets off at the getting off station;
Extracting
Performing a congestion prediction related to the train based on the extracted information about the station and the train. From multiple route information,
At least one of a boarding station and alighting station;
At least one of a boarding position of the train at the boarding station and a boarding position of the train at the getting off station;
Extracting
Performing a congestion prediction related to the position based on the extracted information about the station and the position. From multiple route information,
At least one of a boarding station and alighting station;
A category of a train to be boarded at the boarding station, and at least one category of a category of a train to be boarded at the boarding station;
Extracting
Performing a congestion prediction related to the category based on the extracted information about the station and the category. Computer
From multiple route information,
At least one of a boarding station and alighting station;
A train that gets on at the boarding station, and at least one train that gets off at the getting off station;
Extraction means for extracting
An information processing program that functions as a prediction unit that predicts congestion related to the train based on the extracted information about the station and the train. Computer
From multiple route information,
At least one of a boarding station and alighting station;
At least one of a boarding position of the train at the boarding station and a boarding position of the train at the getting off station;
Extraction means for extracting
An information processing program that functions as a prediction unit that predicts congestion related to the position based on the extracted information about the station and the position. From multiple route information,
At least one of a boarding station and alighting station;
A category of a train to be boarded at the boarding station, and at least one category of a category of a train to be boarded at the boarding station;
Extraction means for extracting
An information processing program that functions as a prediction unit that predicts congestion related to the category based on the extracted information about the station and the category. In order for the information processing system according to any one of claims 1 to 9 to function by a plurality of information processing apparatuses communicably connected,
An information processing program for causing one of the information processing devices to function as at least one of the units in the information processing system according to claim 1.   An information processing program for causing a computer to function as at least one of the units in the information processing system according to claim 1. An information processing system configured by a plurality of information processing apparatuses communicably connected,
From multiple route information,
At least one of a boarding station and alighting station;
A train that gets on at the boarding station, and at least one train that gets off at the getting off station;
Extraction means for extracting
Based on the information on the extracted stations and trains, based on the prediction means for performing a congestion prediction related to the train, and to function an information processing system comprising:
An information processing program for causing at least one of the information processing devices to function as at least one of the means. An information processing system configured by a plurality of information processing apparatuses communicably connected,
From multiple route information,
At least one of a boarding station and alighting station;
At least one of a boarding position of the train at the boarding station and a boarding position of the train at the getting off station;
Extraction means for extracting
Based on the extracted information on the station and the position, a prediction unit that performs congestion prediction related to the position,
An information processing program for causing at least one of the information processing devices to function as at least one of the means. An information processing system configured by a plurality of information processing apparatuses communicably connected,
From multiple route information,
At least one of a boarding station and alighting station;
A category of a train to be boarded at the boarding station, and at least one category of a category of a train to be boarded at the boarding station;
Extraction means for extracting
Based on the information on the extracted station and category, a prediction unit that performs congestion prediction related to the category,
An information processing program for causing at least one of the information processing devices to function as at least one of the means. Information processing device,
At least one of a boarding station and alighting station extracted from the plurality of route information;
A train that gets on at the boarding station, and at least one train that gets off at the getting off station;
An information processing program functioning as output control means for outputting congestion prediction information indicating a congestion prediction related to the train predicted based on the information about the train. Information processing device,
At least one of a boarding station and alighting station extracted from the plurality of route information;
At least one of a boarding position of the train at the boarding station and a boarding position of the train at the getting off station;
An information processing program functioning as output control means for outputting congestion prediction information indicating congestion prediction related to the position predicted on the basis of information about the position. At least one of a boarding station and alighting station extracted from the plurality of route information;
A category of a train to be boarded at the boarding station, and at least one category of a category of a train to be boarded at the boarding station;
An information processing program functioning as output control means for outputting congestion prediction information indicating congestion prediction related to the category predicted based on the information about the category. By a plurality of information processing devices communicably connected,
From multiple route information,
At least one of a boarding station and alighting station;
A train that gets on at the boarding station, and at least one train that gets off at the getting off station;
Extraction means for extracting
Based on the extracted information about the station and the train, a prediction unit that performs congestion prediction related to the train, to configure an information processing system,
An information processing apparatus comprising at least one of the above means. By a plurality of information processing devices communicably connected,
From multiple route information,
At least one of a boarding station and alighting station;
At least one of a boarding position of the train at the boarding station and a boarding position of the train at the getting off station;
Extraction means for extracting
A prediction unit that performs congestion prediction related to the position, based on the extracted information about the station and the position, to configure an information processing system,
An information processing apparatus comprising at least one of the above means. By a plurality of information processing devices communicably connected,
From multiple route information,
At least one of a boarding station and alighting station;
A category of a train to be boarded at the boarding station, and at least one category of a category of a train to be boarded at the boarding station;
Extraction means for extracting
A prediction unit that performs congestion prediction related to the category based on the extracted information about the station and the category, to configure an information processing system,
An information processing apparatus comprising at least one of the above means.

Images