Information processing system and information processing method

Abstract

This will contribute to increasing the occupancy rate of company vehicles. [Solution] The information processing device includes a display control unit that controls the display of a map including the search results for a recommended route among multiple routes, based on a predetermined score for each route along the path each of the multiple routes passes through, which is based on passenger demand forecast data for commercial vehicles. This technology can be applied, for example, to an information processing device that displays the forecast results for taxi passenger demand.

Description

Technical Field

[0001] The present technology relates to an information processing apparatus, and particularly to an information processing apparatus capable of contributing to an increase in the occupancy rate of commercial vehicles such as taxis.

Background Art

[0002] In the taxi industry, efforts have been actively made to predict the demand for taxis and conduct more effective business operations (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present technology has been made in view of such a situation, and aims to contribute to an increase in the occupancy rate of commercial vehicles such as taxis.

Means for Solving the Problems

[0005] An information processing apparatus according to one aspect of the present technology includes a display control unit that controls the display of a map including a search result of a recommended route among the plurality of routes based on scores for each predetermined unit in a route through which each of the plurality of routes passes, based on ride demand prediction data of a commercial vehicle.

[0006] In one aspect of the present technology, the display of a map including a search result of a recommended route among the plurality of routes is controlled based on scores for each predetermined unit in a route through which each of the plurality of routes passes, based on ride demand prediction data of a commercial vehicle.

[0007] Furthermore, one aspect of this technology—the information processing device—can be realized by having a computer execute a program.

[0008] Furthermore, in order to realize one aspect of this technology—an information processing device—the program to be executed by a computer can be provided by transmitting it via a transmission medium or by recording it on a recording medium.

[0009] An information processing device may be an independent device or an internal block that constitutes a single device. [Effects of the Invention]

[0010] One aspect of this technology suggests that it can contribute to improving the occupancy rate of commercial vehicles.

[0011] The effects described herein are not necessarily limited to those described herein and may include any of the effects described herein. [Brief explanation of the drawing]

[0012] [Figure 1] This block diagram shows an example configuration of one embodiment of a prediction system to which this technology is applied. [Figure 2] This figure shows an example of a demand forecasting screen from a demand forecasting app. [Figure 3] This block shows an example configuration of a prediction system. [Figure 4] This figure shows an example of vehicle movement log data. [Figure 5] This diagram illustrates an example of generating actual vehicle data. [Figure 6] This figure shows an example of actual vehicle sequence data. [Figure 7] This is a flowchart explaining the process of generating actual vehicle sequence data. [Figure 8] This is a flowchart explaining the learning and prediction process. [Figure 9] This figure shows an example of the results of the first clustering. [Figure 10] It is a diagram showing an example of the result of the first clustering. [Figure 11] It is a diagram showing an example of the result of two-stage clustering. [Figure 12] It is a flowchart explaining the unknown area clustering classification process. [Figure 13] It is a diagram showing a first display example of the demand prediction screen. [Figure 14] It is a diagram showing a second display example of the demand prediction screen. [Figure 15] It is a diagram showing a third display example of the demand prediction screen. [Figure 16] It is a diagram explaining the learning of the boarding position. [Figure 17] It is a diagram showing a fourth display example of the demand prediction screen. [Figure 18] It is a diagram showing a fifth display example of the demand prediction screen. [Figure 19] It is a diagram showing a sixth display example of the demand prediction screen. [Figure 20] It is a diagram showing an example of the fare prediction screen for boarding. [Figure 21] It is a diagram explaining the learning of the boarding position. [Figure 22] It is a diagram explaining the learning of the alighting position. [Figure 23] It is a diagram explaining the learning of the boarding position. [Figure 24] It is a diagram showing an example of the demand prediction screen in the case of wide-area map display. [Figure 25] It is a diagram showing an example of the demand prediction screen in the case of detailed map display. [Figure 26] It is a diagram showing another example of detailed map display. [Figure 27] It is a flowchart explaining the voice guidance control process. [Figure 28] It is a diagram explaining the heat map for extracting favorite areas. [Figure 29] It is a diagram showing a display example of the recommended route presentation screen. [Figure 30] It is a flowchart explaining the route presentation process. [Figure 31] This diagram explains how points are awarded for riding the vehicle. [Figure 32] This figure shows an example of a demand forecast screen displaying areas where boarding is prohibited. [Figure 33] This figure shows an example of a demand forecast screen that displays the installation location. [Figure 34] This figure shows an example of a demand forecast screen displaying the last train times. [Figure 35] This figure shows an example of a demand forecast screen with the reverse lookup boarding point display function activated. [Figure 36] This figure shows an example of a demand forecast screen with the reverse lookup boarding point display function activated. [Figure 37] This diagram shows an example of a demand forecasting screen that distinguishes between dispatched vehicles, street pickups, and pickups. [Figure 38] This figure shows an example of a demand forecast screen displaying the average fare and confidence interval. [Figure 39] This figure shows an example of a demand forecast screen that displays the number of available vehicles in real time. [Figure 40] This figure shows an example of a demand forecast screen that displays the number of available vehicles in real time. [Figure 41] This figure shows an example of an evaluation screen that displays daily sales performance evaluation information. [Figure 42] This figure shows an example of the operation history screen. [Figure 43] This figure shows an example of a demand forecast screen that displays additional information taking distance and direction into consideration. [Figure 44] This figure shows an example of a demand forecast screen that displays information according to the direction of travel. [Figure 45] This is a block diagram showing an example configuration of one embodiment of a computer to which this technology is applied. [Modes for carrying out the invention]

[0013] The following describes the embodiments for implementing this technology. The description will be given in the following order. 1. Example of a prediction system configuration 2. Example of a demand forecasting app screen. 3. Block Diagram 4. Actual vehicle sequence data generation process 5. Learning and prediction processing 6. Unknown Area Cluster Classification Process 7. Combined display of area AR 8. Display of demand direction and frequency 9. Display of pinpoint predictions 10. Display of estimated waiting time 11. Display of Long-Range Prediction 12. Display of estimated travel distance 13. Display of estimated fare 14. Learning the boarding position 15. Learning the disembarking location 16. Learning the boarding position 17. Audio-based passenger demand guide 18. Recommended route presentation process 19. Signs indicating areas where boarding is prohibited. 20. Placement indication 21.Train time display 22. Reverse Lookup Boarding Point Indication 23. Classification and display of demand forecasts for dispatch / cruising / waiting at a taxi stand. 24. Display of estimated fare 25. Display of real-time number of available parking spaces Display of sales evaluation for 26.1 days 27. Display of additional information considering distance and direction. 28. Display of information according to the direction of travel 29. Example Computer Configuration

[0014] <1. Example of a prediction system configuration> Figure 1 shows an example configuration of one embodiment of a prediction system to which this technology is applied.

[0015] The prediction system 1 shown in Figure 1 consists of multiple taxis 11 and a server (information processing device) 12, and is a system that predicts the demand for taxi rides in the operating area of ​​the taxis 11 based on data acquired from the taxis 11.

[0016] Taxi 11 is a commercial vehicle that travels within a designated service area and picks up passengers. Taxi 11 is equipped with a fare meter 21, a vehicle management device 22, and a terminal device 23.

[0017] The fare meter 21 accepts "occupied" and "empty" operations from the driver. "Occupied" refers to the state where the vehicle is traveling with passengers on board, and "empty" refers to the state where the vehicle is traveling without passengers on board. When the vehicle is "occupied," the fare meter 21 calculates the fare based on at least one of the travel time or distance and displays it on the designated display unit.

[0018] The vehicle management device 22 generates vehicle movement log data that records the location (route) traveled by the taxi 11, the status of "occupied" or "vacant," etc., in chronological order at predetermined time intervals, and transmits it to the server 12 via a predetermined network. The status of "occupied" or "vacant" is obtained from the fare meter 21.

[0019] The terminal device 23 is composed of an information processing device such as a smartphone or tablet terminal. The terminal device 23 stores an application program (hereinafter also simply referred to as the demand forecasting app) that uses passenger demand forecasting data transmitted from the server 12 to display the passenger demand forecast on a display.

[0020] The demand forecasting application is launched and executed on the terminal device 23 by the driver's operation. The demand forecasting application receives passenger demand forecasting data transmitted from the server 12 via a predetermined network, and displays the forecast results on the display based on the received passenger demand forecasting data, on a map. A specific example of how the forecast results for passenger demand are displayed will be described later with reference to Figure 2, etc.

[0021] Server 12 acquires vehicle movement log data from multiple taxis 11 via the network. Server 12 then uses the acquired vehicle movement log data to generate passenger demand forecast data and transmits it to each of the multiple taxis 11 via the network.

[0022] The network connecting the server 12, the vehicle management device 22, and the terminal device 23 consists of, for example, mobile communication networks such as so-called 3G or 4G lines, the internet, public telephone networks, satellite communication networks, etc.

[0023] The driver of taxi 11 drives the taxi 11 in order to attract passengers, referring to the passenger demand forecast displayed on the terminal device 23's screen via a demand forecasting app.

[0024] <2. Example of a demand forecasting app screen> Figure 2 shows an example of a demand forecast screen displayed by the demand forecasting application on terminal device 23.

[0025] In the demand forecast screen shown in Figure 2, a map 41 is displayed, along with a current location marker 61, zoom in / out buttons 62, a demand forecast mesh 63, and a settings button 64, which are superimposed on the map 41.

[0026] Furthermore, the demand forecast screen includes a forecast time setting area 42 in a different area from the map 41 display area. The forecast time setting area 42 includes a forecast time display 71 and forecast time change buttons 72A and 72B.

[0027] The current location marker 61 indicates the current location of taxi 11. The zoom in / out buttons 62 are used to enlarge or reduce the scale of map 41.

[0028] The demand forecast mesh 63 is constructed by arranging multiple area ARs in a matrix. Each area AR represents a single region obtained by dividing the demand forecast mesh 63 into a grid. In the example in Figure 2, 28 area ARs in a 4x7 grid are placed in a portion of the map 41, but area ARs may be superimposed on all areas of the map 41.

[0029] Each area AR in the demand forecast mesh 63 is displayed with a color and density corresponding to the degree of passenger demand, based on passenger demand forecast data transmitted from the server 12. For example, in Figure 2, areas AR with a high density represent areas AR with high passenger demand, and areas AR with a low density represent areas AR with low passenger demand.

[0030] The settings button 64 is used to configure various settings related to the display of the demand forecast screen, such as selecting the items that can be displayed on the demand forecast screen and their display order. Details of each item that can be displayed on the demand forecast screen will be described later.

[0031] The forecast time display 71 in the forecast time setting area 42 displays the corresponding time in the demand forecast displayed by the demand forecast mesh 63. That is, the demand forecast mesh 63 displays the demand forecast for the time shown in the forecast time display 71. Tapping the forecast time display 71 resets it to the current time. The forecast time change buttons 72A and 72B are used to advance or rewind the forecast time in the forecast time display 71 by a predetermined unit (for example, 10 minutes).

[0032] As described above, the demand forecasting application on the terminal device 23 receives passenger demand forecasting data transmitted from the server 12, and based on the received passenger demand forecasting data, displays a demand forecasting mesh 63 on the map 41 as the forecast result on the display.

[0033] In the example shown in Figure 2, each area AR of the demand forecast mesh 63 is displayed with different colors and densities according to the degree of passenger demand. However, as shown in Figure 13 later, it is also possible to display the passenger count forecast results together.

[0034] <3. Block Diagram> Next, we will describe the detailed configuration of each device installed in the taxi 11 and the server 12.

[0035] Figure 3 is a block diagram showing an example configuration of a server 12, a fare meter 21, a vehicle management device 22, and a terminal device 23.

[0036] The fare meter 21 accepts the driver's "occupied" or "vacant" operation and displays the "occupied" or "vacant" status and the fare on a designated display unit. The fare meter 21 supplies the "occupied" or "vacant" status to the vehicle management device 22.

[0037] The vehicle management device 22 includes a position detection unit 101, a speed detection unit 102, a control unit 103, a storage unit 104, and a communication unit 105.

[0038] The position detection unit 101 is composed of, for example, a GPS (Global Positioning System) receiver and detects the current position of the taxi 11 by receiving positioning signals broadcast by positioning satellites. The position detection unit 101 also includes a gyro sensor, a geomagnetic sensor, etc., to detect the direction of travel of the taxi 11.

[0039] The speed detection unit 102 consists of a speed sensor, an acceleration sensor, etc., and detects the speed of the taxi 11. Alternatively, the speed detection unit 102 may detect the speed of the taxi 11 by obtaining a measurement value from a speed sensor that detects the rotation speed of the taxi 11's wheels.

[0040] The control unit 103 is composed of, for example, a CPU (Central Processing Unit) and RAM (Random Access Memory), and reads the operation control program stored in the storage unit 104 and controls the operation of the entire vehicle management device 22 according to the operation control program. Specifically, the control unit 103 acquires data from the fare meter 21, the position detection unit 101, and the speed detection unit 102 at regular time intervals to generate vehicle movement log data and stores it in the storage unit 104. The control unit 103 also transmits the vehicle movement log data stored in the storage unit 104 to the server 12 via the communication unit 105 at predetermined, set timings, either periodically or irregularly.

[0041] The storage unit 104 is composed of, for example, a hard disk, ROM (Read Only Memory), RAM, and NVRAM (Non-Volatile RAM), and stores vehicle movement log data. The communication unit 105 performs predetermined communication with the server 12 according to the control of the control unit 103. The communication unit 105 is composed of a network interface that performs network communication via a predetermined network.

[0042] The server 12 comprises a control unit 121, a storage unit 122, and a communication unit 123.

[0043] The control unit 121 is composed of, for example, a CPU, RAM, etc., and reads the operation control program stored in the memory unit 122, and controls the operation of the entire server 12 according to the operation control program.

[0044] Functionally, the control unit 121 comprises at least a data generation unit 131, a learning unit 132, and a prediction unit 133, and predicts ride demand for each area AR on the map 41 using machine learning. Any machine learning method can be selected, such as k-means, self-organizing maps (SOM), neural networks, or HMMs (hidden Markov models).

[0045] The data generation unit 131 stores vehicle movement log data acquired from each of the vehicle management devices 22 of multiple taxis 11 via the communication unit 123 into the storage unit 122.

[0046] Figure 4 shows an example of vehicle movement log data generated by the vehicle management device 22 of taxi 11 and transmitted to the server 12.

[0047] The vehicle management device 22 generates and stores vehicle movement log data at predetermined time intervals (for example, every minute).

[0048] The items generated as vehicle movement log data include, as shown in Figure 4, a company ID that identifies the company to which taxi 11 belongs, a radio ID that identifies the vehicle of taxi 11, a driver ID that identifies the driver operating taxi 11, a status time that indicates the time the status was generated, the latitude and longitude that are the location information of taxi 11, the direction and speed that indicate the speed and direction of travel of taxi 11, and the status of "occupied" or "vacant".

[0049] The data generation unit 131 generates actual vehicle data, which is data related to the actual vehicle, from the vehicle movement log data stored in the storage unit 122.

[0050] Figure 5 shows an example of generating actual vehicle data.

[0051] The actual vehicle data is data extracted from the vehicle movement log data regarding the boarding of taxi 11. It is generated from the vehicle movement log data, specifically from information on boarding points where the status changes from "vacant" to "occupied" and alighting points where the status changes from "occupied" to "vacant".

[0052] The actual vehicle data includes items such as ID, boarding time, departure point, arrival point, travel time, travel distance, and fare, as shown in Figure 5.

[0053] The ID is data that combines the company ID, radio ID, and crew ID from the vehicle movement log data.

[0054] The boarding time is calculated and recorded as the time between the "vacant" status time and the "occupied" status time at the point of boarding change.

[0055] At the starting point, the latitude and longitude between the latitude and longitude of the "empty" vehicle and the latitude and longitude of the "occupied" vehicle at the point of change in passengers are calculated and recorded.

[0056] At the arrival point, the latitude and longitude between the latitude and longitude of the "empty" vehicle and the latitude and longitude of the "full" vehicle at the disembarkation point are calculated and recorded.

[0057] The travel time is calculated and recorded as the time (in minutes, for example) between the boarding time and the time when the status changes from "empty" to "occupied" at the point of alighting.

[0058] The distance traveled is calculated and recorded as the distance from the starting point to the destination (in units of, for example, kilometers).

[0059] The fare is calculated and recorded based on the ride time and distance, in accordance with taxi fare regulations.

[0060] Furthermore, the calculation method for each item of the actual vehicle data is not limited to the method described above, and other methods may be used. For example, each of the above items may be calculated from the first and last vehicle movement log data where the status is "actual vehicle". In addition, information on fares and distance traveled may be obtained from the vehicle management device 22 as part of the vehicle movement log data, rather than being calculated from the locations of the boarding and alighting points.

[0061] The data generation unit 131 generates actual vehicle sequence data, which is time-series data representing the number of passengers in a predetermined time unit (10 minutes), for each area AR, based on a large amount of actual vehicle data generated from vehicle movement log data of vehicle management devices 22 of a large number of taxis 11. For example, the data generation unit 131 generates actual vehicle sequence data for each area AR, which is time-series data counting the number of passengers every 10 minutes.

[0062] Figure 6 shows examples of actual vehicle sequence data for three area ARs, area 1223, area 1224, and area 1225, which are obtained by dividing the operating area of ​​taxi 11.

[0063] The horizontal axis of the actual vehicle sequence data represents the date and time, and the vertical axis represents the number of passengers. The actual vehicle sequence data shown in Figure 6 covers 8 days, but the creation period for the actual vehicle sequence data can be set to any period, such as one week, one month, or one year. For example, setting the creation period for the actual vehicle sequence data to one week allows you to capture fluctuations depending on the day of the week, and setting it to a longer period such as several months or one year allows you to capture seasonal fluctuations such as year-end and New Year holidays, Golden Week, and summer vacation, in addition to fluctuations depending on the day of the week.

[0064] For example, in the case of actual vehicle sequence data for Area 1223, the number of vehicle data entries where the boarding time falls between 10:00 and 10:10 on March 21, 2017, and the departure point is located within Area 1223, is counted as the number of boardings. The result of this count becomes the actual vehicle sequence data for Area 1223 from 10:00 to 10:10 on March 21, 2017. A similar process is performed for the entire period of acquired vehicle data to generate the actual vehicle sequence data for Area 1223.

[0065] Returning to Figure 3, the learning unit 132 generates a predictor for predicting passenger demand through learning, using a large amount of long-term real-vehicle sequence data generated based on actual vehicle data acquired from vehicle management devices 22 of numerous taxis 11.

[0066] The prediction unit 133 uses a predictor generated by the learning unit 132 to predict passenger demand for a predetermined time or time period. The prediction results from the prediction unit 133 are transmitted to the terminal device 23 as passenger demand prediction data.

[0067] The storage unit 122 stores vehicle movement log data acquired from each of the vehicle management devices 22, and actual vehicle sequence data generated from the vehicle movement log data. Intermediate vehicle data used to generate actual vehicle sequence data from vehicle movement log data may also be stored in the storage unit 122.

[0068] The communication unit 123 performs predetermined communication with the vehicle management device 22 and the terminal device 23 in accordance with the control of the control unit 121. The communication unit 123 is configured as a network interface that performs network communication via a predetermined network.

[0069] The terminal device 23 includes a control unit 141, an operation unit 142, a display unit 143, a communication unit 144, a speaker 145, and a microphone 146.

[0070] The control unit 141 is composed of, for example, a CPU, RAM, etc., and controls the operation of the entire terminal device 23 according to an operation control program stored in a memory unit (not shown). For example, the control unit 141 executes a demand forecasting application based on the operation of the user, which is the driver. The control unit 141 also functions as a display control unit that controls the display unit 143, and displays the execution results of the demand forecasting application, for example, the demand forecasting screen shown in Figure 2, on the display unit 143.

[0071] The operation unit 142 consists of multiple operation buttons provided on the terminal device 23, a touch panel superimposed on the display unit 143, etc., and receives user operations and supplies operation signals corresponding to the received operations to the control unit 141.

[0072] The display unit 143 is composed of, for example, an LCD (Liquid Crystal Display) and displays predetermined information, such as the demand forecast screen shown in Figure 2.

[0073] The communication unit 144 performs predetermined communication with the server 12 in accordance with the control of the control unit 141. The communication unit 144 is configured as a network interface that performs network communication via a predetermined network.

[0074] Speaker 145 outputs sounds such as electronic sounds, sound effects, and voice messages. Microphone 146 detects user voices and collects ambient sounds.

[0075] The server 12, fare meter 21, vehicle management device 22, and terminal device 23 are configured as described above.

[0076] The following describes in detail the processes performed by each of the following: server 12, vehicle management device 22, and terminal device 23.

[0077] <4. Actual vehicle sequence data generation process> First, the process of generating actual vehicle sequence data by the server 12 will be explained with reference to the flowchart in Figure 7. This process can be executed at predetermined intervals, such as periodically or irregularly.

[0078] First, in step S1, the data generation unit 131 of the server 12 acquires (receives) vehicle movement log data transmitted via the network from each of the vehicle management devices 22 of the multiple taxis 11. Each vehicle management device 22 can send the vehicle movement log data to the server 12 individually at any time; it does not need to be simultaneous.

[0079] In step S2, the data generation unit 131 generates actual vehicle data from the acquired vehicle movement log data. The actual vehicle data includes data calculated from items in the vehicle movement log data, such as boarding time and departure point, and external data added on the server 12 side, such as fare. Other external data that can be included include date-related information such as the day of the week and whether it is a weekday or holiday, event information related to events that took place in the relevant area AR on the day the data was acquired, and weather information. By adding external data to the actual vehicle data, it is possible to learn and predict passenger demand for each situation, such as by day of the week, whether there are events, and weather conditions.

[0080] In step S3, the data generation unit 131 generates actual vehicle sequence data for each area AR based on a large amount of actual vehicle data generated from the vehicle management devices 22 of the numerous taxis 11, stores it in the storage unit 122, and ends the actual vehicle sequence data generation process.

[0081] <5. Learning and Prediction Processing> Next, referring to the flowchart in Figure 8, we will explain the learning and prediction process that learns and predicts passenger demand using the generated real vehicle sequence data for each area AR. This process can also be executed at predetermined times, such as regularly or irregularly.

[0082] First, in step S21, the learning unit 132 of the server 12 extracts a representative area from among multiple area ARs obtained by dividing the operating area of ​​the taxi 11. The learning unit 132 selects a predetermined number of area ARs from among the multiple area ARs to be the representative area. The representative area may be determined randomly, or a knowledgeable user may select it according to predetermined criteria, for example, an area AR in the city center and an area AR in the suburbs, an area AR near a station and an area AR far from a station, or an area AR with many stations and an area AR with few stations.

[0083] In step S22, the learning unit 132 performs two-stage clustering using the actual vehicle sequence data of each area AR extracted as a representative area. More specifically, the learning unit 132 performs a first clustering using a first parameter to cluster each of the extracted area ARs, and then performs a second clustering using a second parameter to cluster each of the extracted area ARs.

[0084] For example, the learning unit 132 performs a first clustering using the mean and variance of the number of passengers per unit time (e.g., per day) within the area AR as the first parameters, and performs a second clustering using the waveform of the average number of passengers per unit time (e.g., per day) within the area AR as the second parameter. The clustering method can be, for example, the k-means method.

[0085] Figures 9 and 10 show examples of the results of a first clustering method, in which multiple area ARs, which are representative areas, are clustered using the mean and variance of the number of passengers as parameters.

[0086] Figure 9 shows the distribution of multiple area ARs extracted as representative areas, with the horizontal axis representing the mean and the vertical axis representing the variance.

[0087] Figure 10 shows the actual vehicle sequence data for multiple area ARs, which are representative areas, broken down by cluster. In Figure 10, the horizontal axis represents time (from 0:00 to 24:00), and the vertical axis represents the number of passengers.

[0088] Since actual vehicle sequence data generally exhibits similar characteristics for each time period of the day (morning, noon, night, etc.), clustering is performed using data obtained by dividing the actual vehicle sequence data into basic units (1 day).

[0089] In Figures 9 and 10, the AR (actual vehicle sequence data) for multiple areas extracted as representative areas is classified into six clusters.

[0090] Figure 11 shows an example of a two-stage clustering result, which combines the clustering results of the first and second clustering stages.

[0091] In Figure 11, the horizontal axis (columns) represents the results of the first stage of clustering, and the vertical axis (rows) represents the results of the second stage of clustering. The horizontal and vertical axes of each graph arranged in a matrix are the same as in Figure 10.

[0092] In Figure 11, columns 1, 2, 3, ... represent the clustering results from the first clustering method, where multiple area ARs arranged vertically form a group of area ARs (area AR groups) with similar mean and variances in the number of passengers. On the other hand, rows A, B, C, ... represent the clustering results from the second clustering method, where each area AR group from the first clustering method is further clustered by area ARs with similar average passenger waveforms. The numbers in each matrix graph represent the number of area ARs classified into that cluster. For example, the number "468" in the graph for cluster D-2 in row D and column 2 indicates that 468 area ARs out of the representative areas were classified into cluster D-2. The mean and variance of the number of passengers per unit time, used as the first parameter, represent the magnitude of the number of passengers per unit time and the magnitude of the change in the number of passengers within that unit time, while the waveform of the average number of passengers per unit time, used as the second parameter, represents the trend of change in the number of passengers within that unit time over time.

[0093] The second stage of clustering may be performed individually for each clustering result from the first stage, or it may be performed across multiple area ARs extracted as representative areas, separate from the clustering results of the first stage.

[0094] In this embodiment, for example, the operating area of ​​taxi 11 is divided into 4400 area ARs, and half of these 4400, 2200 area ARs, are extracted as representative meshes. Two-stage clustering is then performed on these 2200 area ARs, resulting in their classification into 44 clusters.

[0095] Next, in step S23 of Figure 8, the learning unit 132 adjusts the learning parameters of the predictor, such as the learning rate, for each cluster using the actual vehicle sequence data belonging to the cluster, and then proceeds to step S24.

[0096] In step S24, the learning unit 132 uses the adjusted learning parameters and real vehicle sequence data from one or more area ARs belonging to the cluster to train a predictor for each cluster to predict passenger demand, and then proceeds to step S25.

[0097] In step S25, the prediction unit 133 uses the predictor generated by the learning unit 132 to predict the passenger demand at a predetermined time in a predetermined area AR. For example, when predicting the passenger demand for an area AR belonging to cluster C-4, the passenger demand at a predetermined time is predicted using the predictor for cluster C-4.

[0098] The learning process in steps S21 to S24 and the prediction process in step S25 may be executed as consecutive processes, or the prediction process in step S25 may be executed at a different time than the processes in steps S21 to S24.

[0099] For example, the process in step S25 is executed immediately following the process in step S24, and the passenger demand for each area AR that constitutes the operating area of ​​the taxi 11 at a predetermined time is calculated and stored in the storage unit 122. Then, in response to a request from the terminal device 23, the demand forecast data stored in the storage unit 122 is transmitted to the terminal device 23 as passenger demand forecast data.

[0100] Alternatively, when terminal device 23 requests forecast data for the passenger demand of one or more areas AR at a predetermined time, the process in step S25 is executed, and the result of the process in step S25 is transmitted to terminal device 23 as passenger demand forecast data.

[0101] The demand forecasting application on the terminal device 23, which receives the passenger demand forecasting data, displays a demand forecasting mesh 63 with its color and density changed according to the number of passengers in each area AR, as shown in Figure 2.

[0102] Based on the above learning and prediction process, each of the 2,200 area ARs extracted as representative areas from the 4,400 area ARs that make up the service area is classified into a predetermined cluster, and passenger demand can be predicted according to the classification result.

[0103] On the other hand, for the remaining 2,200 area ARs that were not selected as representative areas (hereinafter also referred to as unknown area ARs), it is unclear at this stage which cluster they belong to, and therefore it is not possible to predict the demand for rides.

[0104] <6. Unknown Area Cluster Classification Processing> Next, I will explain the process for predicting the demand for rides in the unknown AR area.

[0105] Referring to the flowchart in Figure 12, the unknown area cluster classification process for determining the cluster to which an unknown area AR belongs will be explained. This process can be executed at predetermined intervals, such as periodically or irregularly.

[0106] First, in step S41, the learning unit 132 of the server 12 learns the characteristics (mean, variance, shape) of the actual vehicle sequence data for each cluster classified in the learning prediction process. In other words, the relationship between the actual vehicle sequence data of the 2200 area ARs extracted as representative areas and the clusters is learned by the learner.

[0107] In step S42, the prediction unit 133 of the server 12 inputs the actual vehicle sequence data of the unknown area AR into a classifier that uses the parameters obtained in the learning in step S41, and identifies the clusters of the unknown area AR.

[0108] As described above, the unknown area cluster classification process allows for the clustering of unknown areas other than the representative area using a classifier generated by learning the relationship between the clustering results of the representative area and the actual vehicle sequence data.

[0109] Once the clusters of the unknown area AR can be identified, the prediction process in step S25 described above can be performed using the predictor for the identified clusters to predict the demand for rides in the unknown area AR.

[0110] Therefore, by performing both the learning and prediction process shown in Figure 8 and the unknown area cluster classification process shown in Figure 12, it is possible to predict the passenger demand for all 4400 area ARs that make up the operating area of ​​taxi 11.

[0111] In the learning and prediction process shown in Figure 8, by extracting representative areas in step S21, the number of areas AR to be learned, or in other words, the amount of actual vehicle sequence data, can be reduced. This reduces the computational load and thus the cost and time required for passenger demand forecasting.

[0112] Furthermore, by performing two-stage clustering using the actual vehicle sequence data of each area AR extracted as a representative area in step S22, the number of learners can be reduced, thereby reducing the cost and time required for passenger demand forecasting. Specifically, if two-stage clustering is not performed, learners equal to the number of area ARs extracted as representative areas (2200) will be required. However, by performing two-stage clustering and classifying the data into a predetermined number of clusters, the number of learners required for learning can be reduced to the number of clusters (44).

[0113] Each cluster's learner can use the actual vehicle sequence data of all area ARs classified into that cluster. That is, for example, when learning the passenger demand forecast for area 1223, typically only the actual vehicle sequence data acquired in area 1223 is used for learning. In contrast, with this technology, if area 1223 is classified into cluster D-2, and there are 468 area ARs belonging to cluster D-2, learning can be performed using the actual vehicle sequence data of all 468 area ARs, including area ARs other than area 1223. Therefore, since a single learner can be trained with a larger amount of data than can be acquired for one area AR, the prediction accuracy can be improved.

[0114] Furthermore, for unknown area ARs that are not extracted as representative areas in the learning prediction process, the clusters of unknown area ARs can be identified through the unknown area cluster classification process, and the demand for rides in the unknown area ARs can be predicted using the predictors of the identified clusters.

[0115] In steps S23 and S24 described above, the learning parameters were adjusted and the predictor trained using only the actual vehicle sequence data for each area AR extracted as a representative area. However, after clusters have been identified for all unknown area ARs included in the sales area, the learning parameters may also be adjusted and the predictor trained using the actual vehicle sequence data for the unknown area ARs as well.

[0116] Therefore, according to prediction system 1 in Figure 1, learning and prediction can be performed more efficiently. Furthermore, prediction accuracy can be improved with a smaller amount of data.

[0117] In the learning prediction process and unknown area cluster classification process described above, cluster classification and learning were performed using actual vehicle sequence data generated from all vehicle movement log data acquired from the vehicle management devices 22 of multiple taxis 11, regardless of the day of the week, weekdays, or holidays.

[0118] However, the actual vehicle sequence data may be divided into categories such as day of the week, weekdays, holidays, or weather, and cluster classification and learning may be performed for each category. This allows for the prediction of passenger demand for each predetermined condition, such as day of the week, weekdays, holidays, weather, and the presence or absence of events, and the prediction results can be displayed on the screen.

[0119] <7. Combined display of area AR> The following describes various display examples of how the demand forecasting application on the terminal device 23 displays the forecast results for passenger demand.

[0120] Figure 13 shows a first example of the demand forecast screen displayed by the demand forecasting application.

[0121] In the demand forecast screen shown in Figure 2, the demand forecast mesh 63 was composed of a matrix of area ARs of the same rectangular size. Furthermore, the number of passengers for each area AR, which was the forecast result, was not displayed on the screen.

[0122] In contrast, in the demand forecast mesh 63 of Figure 13, the number of passengers in each area AR, which is the forecast result, is displayed within the area AR.

[0123] Furthermore, the demand forecasting app combines multiple adjacent area ARs (Area ARs) where the number of passengers falls below a predetermined threshold into a single area AR and displays the total number of passengers. In the first display example in Figure 13, multiple adjacent area ARs where the number of passengers is 10 or less are combined and displayed as a single area AR. Specifically, 2x2 area ARs where the number of passengers when displayed in the same rectangular size is "4", "2", "2", and "1" are combined into a single area AR and displayed as "9". Of course, depending on the number of passengers in adjacent areas, they may not be combined even if the total is 10 or less.

[0124] When the predicted number of passengers is small, such as 0, 1, or 2, it is difficult to accurately predict demand. Therefore, demand forecasting apps can display demand forecasts in AR (Area-Based Reality) units where the number of passengers exceeds a certain value. This can improve the accuracy of the forecast and provide drivers with more useful information.

[0125] The number of passengers displayed as a prediction result may be a range of values, such as "10-13".

[0126] <8. Display of demand direction and frequency> Figure 14 shows a second example of the demand forecast screen displayed by the demand forecasting application.

[0127] In Figure 14, the color and density indicators representing the degree of AR ridership demand in each area have been omitted.

[0128] Figure 14 shows an example of displaying more detailed forecast results for an area AR that the driver is interested in (hereinafter referred to as the "area of ​​interest AR") from among the area ARs of the demand forecast mesh 63 superimposed on the map 41.

[0129] When the driver selects a specific area AR from among the area ARs of the demand forecast mesh 63 superimposed on map 41, such as by tapping (touching) a designated area AR, the demand forecasting app displays the selected area AR as shown in Figure 14.

[0130] In Figure 14, a focus area frame 211, which is wider than other area ARs, is displayed around the focus area AR designated by the driver. Arrows 212-1 to 212-8 are displayed pointing outward from the focus area frame 211. Unless otherwise specified, arrows 212-1 to 212-8 are simply referred to as arrow 212.

[0131] The direction of arrow 212 represents the direction of movement of passengers boarding in the AR area of ​​interest, and the length of arrow 212 represents the average distance traveled by passengers boarding in the AR area of ​​interest and moving in the direction of arrow 212. The width of arrow 212 (thickness in the direction perpendicular to the arrow's direction) represents the proportion of passengers boarding in the direction indicated by arrow 212 relative to all directions.

[0132] Therefore, in the example in Figure 14, among passengers who board in the area of ​​interest AR, a large proportion of them move in the direction of arrow 212-3, and passengers who move in the direction of arrow 212-4 travel a longer distance. Also, for example, among passengers who board in the area of ​​interest AR, fewer passengers move in the directions of arrows 212-2 and 212-6, and their travel distances are shorter.

[0133] For example, when a driver decides on an area AR to perform so-called "cruising" (driving the taxi 11 while looking for passengers), they can set a predetermined area AR in the demand forecast mesh 63 as the area AR of interest and display the arrow 212 to find an area AR with many passengers going in the same direction as the driver's return.

[0134] The direction of passenger movement in each area of ​​AR can be predicted by learning from information about the direction of travel (direction of movement) in the vehicle movement log data.

[0135] Note that the number of arrows 212 to display, in other words, the predicted number of passenger movement directions, may be a number other than 8 as shown in Figure 14. Also, the proportion of passengers moving in the direction of arrow 212 in all directions may be represented by a method other than the width of the arrow, such as differences in color or numerical notation.

[0136] <9. Displaying pinpoint predictions> Figure 15 shows a third example of the demand forecast screen displayed by the demand forecasting application.

[0137] Figure 15 also shows an example of a display that shows more detailed prediction results when the driver selects a predetermined area AR as the area of ​​interest AR.

[0138] Within the area AR, which is a division of the service area into predetermined units, there are locations where the pick-up location is fixed, such as taxi stands in front of train stations or hotels, and where the number of pick-ups is higher compared to other areas.

[0139] If a boarding location with a high number of passengers exists within the AR area of ​​interest, the demand forecasting app can pinpoint and display the number of passengers at that specific boarding location, separate from the total number of passengers in the AR area of ​​interest. In the following, a boarding location with a high number of passengers identified within the AR area of ​​interest will be referred to as a pinpoint boarding location.

[0140] In Figure 15, a pinpoint pick-up location mark 221 is displayed at a predetermined location within the AR area of ​​interest, representing a specific pick-up location. A pick-up count display 222 is also displayed, showing the predicted number of pick-ups at that pinpoint pick-up location mark 221. In Figure 15, "43" displayed within the AR area of ​​interest frame 211 represents the total number of pick-ups for the entire AR area of ​​interest, and of that, "29" in the pick-up count display 222 represents the number of pick-ups at the pinpoint pick-up location "Shinagawa Station Takanawa Exit Taxi Stand" indicated by the pinpoint pick-up location mark 221. By displaying the pinpoint pick-up location and the predicted number of pick-ups at that location, in addition to the total number of pick-ups for the AR area of ​​interest, the utilization rate of taxis can be increased.

[0141] The pinpoint boarding location can be estimated not by individually investigating each designated boarding location within the area's AR system, but by learning from actual vehicle data.

[0142] Specifically, as shown by the black circles on the left side of Figure 16, past boarding locations of passengers can be determined from the departure point information of actual vehicle data. By learning the past boarding locations of passengers, the estimated boarding locations and their probability (likelihood) are calculated, as shown by the black circles on the right side of Figure 16. The probability of a boarding location is represented by a number in the range of 0 to 1, and is displayed near the boarding location in Figure 16. The demand forecasting application can, for example, display estimated boarding locations where the probability of the boarding location is above a predetermined threshold (e.g., 0.8) as pinpoint boarding locations within the area of ​​interest AR.

[0143] <10. Display of estimated waiting time> Figure 17 shows a fourth example of the demand forecast screen displayed by the demand forecasting application.

[0144] Figure 17 also shows an example of a display that shows more detailed prediction results when the driver selects a predetermined area AR as the area of ​​interest AR.

[0145] In places with designated pick-up locations and high passenger volume, such as taxi stands in front of train stations or hotels, there is a method called "waiting at the designated pick-up location," where a taxi waits in line at the designated location to pick up passengers. The disadvantage of waiting at the designated pick-up location is that, for example, if there is a long line of taxis at a taxi stand, it takes time for the taxi to join the end of the line and pick up passengers.

[0146] Therefore, the demand forecasting app can display the time it takes to wait at a boarding location with a high number of passengers (a pinpoint boarding location), or in other words, the time it takes to wait at the boarding location and pick up passengers.

[0147] Specifically, as shown in Figure 17, when the pinpoint boarding location mark 221 in the area of ​​interest AR is a waiting location, the demand forecasting app displays a "start waiting" button 223 within the boarding count display 222 at the pinpoint boarding location mark 221. When the "start waiting" button 223 is tapped (touched), the demand forecasting app displays a waiting display 224 that shows the time required to wait if a waiting period is initiated. In the example in Figure 17, "20 minutes" is displayed as the waiting period.

[0148] For example, a driver can check the waiting time for pickup and select a pickup location by displaying the pickup waiting indicator 224 at a specific pickup location. The waiting time displayed on the pickup waiting indicator 224 may be a value with a certain range, such as "15-20 minutes".

[0149] The vehicle movement log data allows for the detection of the point at which the status changes from "vacant" to "occupied," and the state in which taxi 11 is moving slowly a short distance before that point. Therefore, it is possible to detect taxi 11 waiting to pick up passengers. For example, driving at a predetermined speed or below (5 km / h or less) within a predetermined period or distance prior to the time of the passenger change can be detected as waiting to pick up passengers. Thus, by learning waiting to pick up passengers, it is possible to predict the waiting time at a predetermined pick-up location.

[0150] <11. Display of Long-Range Prediction> Figure 18 shows the fifth example of the demand forecast screen displayed by the demand forecasting application.

[0151] Figure 18 also shows an example of a display that shows more detailed prediction results when the driver selects a predetermined area AR as the area of ​​interest AR.

[0152] Within the area AR, which is a division of the service area into predetermined units, there are areas and pick-up locations where a large proportion of passengers have long-distance rides (more than a predetermined distance), such as when the destination is Haneda Airport or Narita Airport. It is preferable for drivers to be able to determine the likelihood of long-distance passengers.

[0153] Therefore, as shown in Figure 18, the demand forecasting app can display a long-distance display 241 that shows the proportion of long-distance passengers in the AR area of ​​interest, in addition to the total number of passengers in the AR area of ​​interest.

[0154] In Long View 241, the proportion (ratio) of rides with long distances out of the total number of rides in the featured area AR is displayed as the "Long Distance." In addition, Long View 241 divides the ride distance into multiple categories, and the proportion of rides in each category is displayed as a bar graph called the "Long Distance Category." The "All" bar graph shown in Figure 18 shows the proportion of rides in each category for the entire service area, while the "This" bar graph shows the proportion of rides in each category for the featured area AR.

[0155] The long display 241 may display the longness and longness classification for the area of ​​interest AR, as shown in Figure 18, or it may be displayed in conjunction with the pinpoint boarding position mark 221 to display the longness and longness classification for the pinpoint boarding position.

[0156] In Figure 18, the bar graph for the long display of 241 shows the percentage of riders for each divided category (ride distance), by dividing the ride distance into multiple categories. However, it would also be acceptable to divide the fare into multiple categories and show the percentage of riders for each divided category (fare).

[0157] Additionally, the long-distance display 241 may predict passenger demand for each time of day and weather condition, and display a long-distance rating or classification specific to those time periods and weather conditions.

[0158] The degree of "longness" and the classification of a trip can be predicted by learning from actual vehicle data, including the distance traveled and the fare.

[0159] <12. Display of estimated travel distance> Figure 19 shows the sixth example of the demand forecast screen displayed by the demand forecasting application.

[0160] Figure 19 also shows an example of a display that shows more detailed prediction results when the driver selects a predetermined area AR as the area of ​​interest AR.

[0161] As shown in Figure 19, when a designated area AR is selected as the area of ​​interest AR, the demand forecasting app can display the average ride distance and its confidence interval for passengers riding in the area of ​​interest AR. The confidence interval represents the range in which the population mean is included with a predetermined level of confidence.

[0162] In ride distance display 251, the average ride distance in the featured AR area is shown as "2.4km," and the confidence interval for the average ride distance at 95% confidence is, for example, "1.1km to 3.7km." The confidence level for the confidence interval is not limited to 95% and can be set arbitrarily to 99%, etc.

[0163] In this way, by displaying the average ride distance and its confidence interval for the area of ​​interest (AR), drivers can, for example, find an area AR with a suitable ride distance for their remaining working hours, or find an area AR with a longer ride distance to use as a "cruising" route.

[0164] The ride distance display 251 may be displayed for the area of ​​interest AR, as shown in Figure 19, or it may be displayed in conjunction with the pinpoint ride location mark 221, displaying the average ride distance and confidence interval for the pinpoint ride location.

[0165] Alternatively, instead of average ride distance and confidence interval, average fare and confidence interval may be shown.

[0166] Alternatively, instead of the average ride distance and confidence interval, the average ride time and confidence interval may be shown.

[0167] Furthermore, the ride distance display 251 may predict ride demand for each time of day and weather condition, and display average ride distance and confidence interval, average fare and confidence interval, or average ride time and confidence interval, which are specific to the designated time of day and weather conditions.

[0168] <13. Display of estimated fare> Because the fare for Taxi 11 is not determined until you actually get in the taxi, some users refrain from using it. The demand forecasting app has a function that predicts and displays the fare based on the current location and destination.

[0169] Figure 20 shows an example of a fare forecast screen displayed by a demand forecasting app.

[0170] The demand forecasting app displays the estimated travel time and cost to the destination on the screen, and also displays the estimated travel time and cost for each segment of the travel route, which is divided into predetermined units.

[0171] In the fare prediction screen of Figure 20, the individual display 261 shows the time and fare required for travel in each segment. The destination display 262 shows the time and fare required for travel to the destination.

[0172] Learning the fare and travel time is difficult if the actual vehicle data shown in Figure 5 is used as is, because the same data is required for both the departure point and the arrival point. Therefore, the control unit 121 learns the time and fare required for each segmented unit of travel from the vehicle movement log data. Then, the control unit 121 calculates the time and fare required for travel to the destination by calculating the sum of the time and fare for each segmented unit included from the departure point to the arrival point. The segmented unit can be a unit divided using at least one or more of the following: a predetermined distance, a predetermined time, a unit divided by a road section (block), a unit divided by a traffic light or intersection, etc.

[0173] The travel time and fare for each segment, as well as the travel time and fare to the destination, may be displayed with a predetermined range, such as "5 minutes - 10 minutes" or "300 yen - 500 yen".

[0174] With reference to Figures 13 through 20, the various displays enable the taxi driver 11 to operate more efficiently. In other words, the demand forecasting app can present forecast results that contribute to improving the occupancy rate.

[0175] The various displays described with reference to Figures 13 to 20 can be configured as needed by the driver on the settings screen displayed on the screen by operating the settings button 64 of the demand forecasting application, including whether to turn the display on or off and the order in which the displays are shown.

[0176] <14. Learning the boarding position> Next, we will explain the learning and prediction processes performed by server 12, other than those related to passenger demand.

[0177] Figure 21 illustrates the learning process for determining the boarding position relative to a building.

[0178] For example, a user (passenger) of taxi 11 can arrange for taxi 11 from a designated location within building 271 using a dispatch application 272 run on a smartphone or other device, and board taxi 11 at a designated location 273, such as the entrance to building 271. In this case, the dispatch application 272 obtains the user's location information at the time taxi 11 is arranged from the GPS receiver in the device and transmits it to the server 12 as location information at the time of dispatch request. In addition, the user's location information at the time the user boards taxi 11 can be obtained from the vehicle movement log data transmitted from the vehicle management device 22 of taxi 11.

[0179] Server 12 learns the relationship between the location information at the time of dispatch request and the location information at the time of boarding. This allows the server to learn the boarding locations within Building 271, so that when a user requests a taxi 11 from a designated location within Building 271, the driver should drop off the taxi 11. Server 12 stores the learned results as a boarding location list in the storage unit 122. The demand forecasting application can display the learned boarding locations within Building 271 on the map 41. Furthermore, when a user designates Building 271 as their destination, the driver can use the learned boarding locations within Building 271 as the drop-off location.

[0180] Furthermore, the server 12 can also infer the pick-up location in buildings other than the building 271 where the taxi 11 was actually arranged, based on the relationship between the learned location information at the time of dispatch request and the location information at the time of boarding, and display it on the map 41.

[0181] <15. Learning the disembarking location> Figure 21 illustrates the learning of the disembarking position relative to a building.

[0182] For example, a user gets out of taxi 11 at a designated location 274 and moves to a designated building 271, which is their destination. The user's location information at the time they get out of taxi 11, known as the drop-off location information, can be obtained from the vehicle movement log data transmitted from the vehicle management device 22 of taxi 11. The dispatch application 272 also obtains the location information of the building 271, to which the user moved after getting out of taxi 11, from the GPS receiver in the terminal and transmits it to the server 12 as the post-movement location information.

[0183] Server 12 learns the relationship between the drop-off location information and the location information after the move. This allows the driver to learn where to drop off the user at Building 271 when the user designates Building 271 as their destination. Server 12 stores the learned results as a drop-off location list in the storage unit 122. The demand forecasting application can display the learned drop-off locations at Building 271 on the map 41. Furthermore, when a user orders a taxi 11 from a designated location within Building 271 using the ride-hailing application 272, the driver can also use the learned drop-off locations at Building 271 as the pick-up location.

[0184] <16. Learning the boarding position> In the examples explained with reference to Figures 21 and 22, it was shown that learned pick-up locations can also be displayed as drop-off locations, and learned drop-off locations can also be displayed as pick-up locations. In general, the pick-up and drop-off locations for a building are often the same as or close to the taxi stand, drop-off area, or entrance, etc.

[0185] Therefore, as shown in Figure 23, the server 12 learns the boarding location information and alighting location information, learns the optimal boarding location for building 271, and stores it in the storage unit 122 as a list of boarding locations. The demand forecasting application can display the learned boarding locations for building 271 on the map 41.

[0186] <17. Audio-based passenger demand guide> Next, we will explain the audio guidance provided by the demand forecasting app regarding the predicted passenger demand.

[0187] For safety reasons, taxi drivers cannot view the demand forecast screen displayed by the demand forecasting app while driving. Therefore, in addition to displaying the predicted ride demand results on the map on the display, the demand forecasting app also has a function to notify the driver of the predicted ride demand results by sound.

[0188] Since the demand forecasting app cannot notify customers by sound of all the forecast results displayed on the demand forecasting screen, it will notify customers by sound of the current location of taxi 11 (hereinafter also referred to as the vehicle's location) and the forecast result corresponding to the direction of travel of taxi 11.

[0189] Furthermore, the demand forecasting app switches the display method of the demand forecast and the sound notification method depending on the scale of the map 41 that displays the demand forecast.

[0190] The following sections will explain, in order, the demand forecast display and sound output when the map 41 displaying the demand forecast is at a high scale, in other words, when it is a wide-area map display, and the demand forecast display and sound output when the map 41 is at a low scale, in other words, when it is a detailed map display.

[0191] Note that the demand forecasting app's sound notifications include both non-linguistic sounds (also called sound effects or electronic sounds) such as "beep, beep, beep," "bong," and "ping-pong," and voice notifications (messages) consisting of words or sentences. However, for simplicity, in the following explanation, sound effects will be simply referred to as "sound," and sound output consisting of words will be referred to as "voice."

[0192] <Example of sound notification in wide-area map display> Figure 24 shows an example of the demand forecast screen when the map 41 displaying the demand forecast is at a high magnification, in other words, when a wide-area map is displayed.

[0193] In the demand forecast screen of Figure 24, among the area ARs of the demand forecast mesh 63 superimposed on the map 41, area 411 is assumed to be an area AR predicted to have high passenger demand. In Figure 24, the display of colors and density corresponding to the degree of passenger demand for each area AR other than area 411 is omitted.

[0194] Taxi 11 is currently traveling at the location marked 421, and area 411, which is predicted to be a place with high passenger demand, is located in the direction of travel along National Highway 1.

[0195] The demand forecasting app detects the presence of area 411 with high passenger demand in the direction of travel and notifies the driver of this presence via sound or voice. For example, the demand forecasting app might output a voice message saying, "There is a high-demand area nearby in the direction of travel," followed by three consecutive beeps.

[0196] Furthermore, if taxi 11 is traveling along National Highway 1 and is at the location marked 422, the demand forecasting app will, for example, output a voice message saying, "High demand ahead," and then emit four consecutive beeps.

[0197] Thus, the demand forecasting app notifies the driver by sound or voice at a predetermined time if there is an area 411 in the direction of travel where there is high demand for passengers. The timing of notifications can be set, for example, on an area AR basis within the demand forecast mesh 63. In this case, a sound or voice notification is output each time the area AR in which the taxi 11 is located changes. Alternatively, the demand forecast app may be set to send notifications at pre-set intervals (for example, every minute) or at pre-set distances (for example, every kilometer). The timing of notifications can be changed on the settings screen displayed by operating the settings button 64.

[0198] The demand forecasting app changes the content of the voice message and the type of sound it outputs depending on the distance (proximity) to the AR area with high passenger demand detected in the direction of travel.

[0199] In the example above, when the vehicle's location is far from a high-demand area (marked 421), the demand forecasting app outputs the voice message, "There is a high-demand area nearby in the direction of travel," followed by three consecutive "beep beep beep" sounds. At closer locations, the demand forecasting app outputs the voice message, "High demand ahead," followed by four consecutive "beep beep beep" sounds. In other words, the voice output changes the message from "There is a high-demand area nearby in the direction of travel" to "High demand ahead." The sound output changes from three consecutive "beep beep beep" sounds to four consecutive "beep beep beep" sounds, and the number of consecutive "beep" sounds increases as the vehicle gets closer to a high-demand area. In addition to increasing the number of consecutive sound effects, the length of the sound could also be changed, for example, to "beep," "beep," "beep--," or the volume could be made to gradually increase. Alternatively, a combination of at least two of the number of sounds, length, or volume could be used.

[0200] For example, if there is an intersection in the direction of travel and the high-demand area is in the direction of turning right at the intersection, the demand forecasting app can output a voice message such as, "High demand in the direction of turning right at the intersection."

[0201] The degree of passenger demand at which the demand forecasting app notifies users of high-demand areas via sound or voice can also be changed on the settings screen displayed by operating the settings button 64. For example, as shown in Figure 2, each area AR of the demand forecasting mesh 63 is displayed in a color or density corresponding to the degree of passenger demand. If the degree of passenger demand distinguished by color and density on the demand forecasting screen in Figure 2 is in five stages from level 1 to level 5, it is possible to set the app to notify users when an area AR of level 5, the highest degree of passenger demand, is located in the direction of travel, or to notify users when an area AR of level 4 or higher is located in the direction of travel.

[0202] The driver can also configure in the settings screen whether to provide guidance for high-demand areas using only sound, only voice, or both sound and voice. The demand forecasting app has a notification function (notification unit) that notifies the driver of designated AR areas that are locations with high ride demand, using at least one of sound or voice.

[0203] Figure 18 explains the "Long Distance" indicator 241, which displays the percentage (ratio) of long-distance rides as the "Long Distance" when there are areas or boarding locations with a high proportion of long-distance rides.

[0204] When the demand forecasting app displays a wide-area map of the demand forecast screen on the display, it can also notify drivers of areas with high long-distance demand (AR) and the pickup location via sound or voice.

[0205] For example, if a demand forecasting app detects an area with a long-range rating (AR) that exceeds a predetermined value in the direction of travel, it will output a voice message saying, "There is a long-range area nearby," along with a different type of sound, such as a "ping," which is different from the notification for high-demand areas.

[0206] <Example of sound notification in detailed map display> Figure 25 shows an example of the demand forecast screen when the map 41 displaying the demand forecast is at a low scale, in other words, when a detailed map is displayed.

[0207] In the detailed map display of Figure 25, taxi 11 is driving at the location marked 441.

[0208] In the detailed map display, based on the learning results using actual vehicle sequence data, boarding locations where passenger demand exceeds a predetermined level within the display area shown on the screen are each displayed as circular demand points 451. Note that, to prevent the diagram from becoming cluttered, some of the symbols for the demand points 451 are omitted in Figure 25.

[0209] For example, the top 30 locations with the highest demand among the learned boarding locations within the display area shown on the screen are displayed as demand points 451. However, even if a predetermined boarding location is included in the top 30, it will be excluded if it is selected because the total number of boarding locations is small. Therefore, the boarding locations displayed as demand points 451 are those whose predicted boarding demand is at least at a predetermined first level ThA and is included in the top 30.

[0210] In the example in Figure 25, demand point 451 includes demand point 451A, which is represented by a dark circle; demand point 451B, which is represented by a light circle; and demand point 451C, which is represented by a pattern different from demand points 451A and 451B.

[0211] The difference in density between demand point 451A and demand point 451B represents the degree of predicted passenger demand. In other words, if the predicted passenger demand is at or above Level 2 ThB, which indicates high passenger demand, it is displayed as a densely packed demand point 451A. If it is at or above Level 1 ThA but below Level 2 ThB, it is displayed as a dilutely packed demand point 451B. By changing the density of demand point 451 according to the magnitude of passenger demand, for example, if demand point 451 is displayed alone without overlapping with other demand points 451, drivers can recognize the difference in passenger demand due to the difference in density. Also, if demand point 451 is displayed overlapping with other demand points 451, the density of demand point 451 will appear denser, allowing drivers to recognize areas where passenger demand is concentrated as areas with high passenger demand. Note that instead of distinguishing between two density levels, demand point 451A and demand point 451B, the density could be continuously changed according to the degree of passenger demand.

[0212] The demand points 451C, displayed with different patterns, represent demand points 451 selected from the top 30 demand points 451 with high passenger demand, and whose "long distance" is equal to or greater than a predetermined value. This allows drivers to recognize demand points 451 with high "long distance" in the detailed map display.

[0213] In Figure 25, due to drawing constraints, the demand point 451C, which has a high longness, and the other demand points 451A and 451B are shown with different patterns. However, on a display capable of color display, demand point 451C can be distinguished from demand points 451A and 451B by using different colors.

[0214] In the example above, the top 30 boarding locations within the detailed map display area were shown as demand points 451. However, the number of demand points 451 to display can be changed in the settings screen. For example, it is possible to select from the top 30, top 20, or top 10 in the settings screen.

[0215] Furthermore, in the example described above, the top 30 boarding locations were selected and displayed within the display area of ​​the detailed map. However, the top 30 locations could also be selected and displayed based on the area AR unit of the demand forecast mesh 63. In other words, the extraction unit for extracting the demand points 451 can be set as appropriate.

[0216] Next, we will explain the sound and voice guidance in the detailed map display shown in Figure 25.

[0217] Taxi 11 is traveling from its location marker 441 in a predetermined direction (for example, towards Shinagawa Station). The demand forecasting app outputs the voice message "High demand in the direction of travel" if a demand point 451 is within a predetermined distance in the direction of travel. The demand forecasting app also outputs a "beep" sound each time taxi 11 passes a demand point 451. One sound is output for each demand point 451.

[0218] In the detailed map display, a sound is emitted when passing through demand point 451, so on roads where many demand point 451 are displayed, a "beep" sound will be emitted continuously. This allows the driver to recognize that the road they are currently traveling on is a road with high passenger demand, contributing to improved recognition of areas and roads with high passenger demand in AR, and ultimately contributing to an increase in the ridership rate. The volume of the "beep" sound may also be adjusted according to the degree of passenger demand at each demand point 451.

[0219] Although different from the example in Figure 25, if there are no demand points 451 in the direction of travel of taxi 11, but many demand points 451 are in the opposite direction, the demand forecasting app will output a voice message such as, "There are high demand points in the opposite direction." Also, if there is an intersection in the direction of travel, and the road with many demand points 451 is in the direction of turning right at the intersection, the demand forecasting app will output a voice message such as, "Right turn at the intersection, high demand."

[0220] Figure 26 shows other examples of detailed map display.

[0221] In the detailed map view of Figure 26, some of the demand points 451 that were shown in the detailed map view of Figure 25 have been replaced with demand points 451D through 451F.

[0222] As shown in Figure 4, the vehicle movement log data also records the direction of travel of the taxi 11, so the direction of travel of the taxi 11 that was picked up at demand point 451 is also learned. The direction of travel of the taxi 11 at demand point 451 is learned in eight directions, for example, similar to arrows 212-1 to 212-8 in Figure 14. The demand forecasting application can display a direction (hereinafter referred to as the dominant direction) if there is a direction of travel that accounts for 50% or more of the eight directions of travel of the taxi 11 that was picked up at each demand point 451.

[0223] Demand point 451D represents demand point 451 indicating the dominant direction. Demand point 451E is displayed when there are a predetermined number or more demand points 451D with the same dominant direction within a predetermined range. In other words, demand point 451E represents a set of a predetermined number or more demand points 451D.

[0224] Demand point 451D is represented by a V-shaped symbol, as shown in Figure 26, for example, with the direction pointed to by the corner representing the dominant direction. Demand point 451E is represented by a symbol that is a further enlargement of the symbol for demand point 451D. Demand points 451D and 451E may also be represented by other symbols that indicate direction, such as arrow symbols.

[0225] Demand point 451F represents a demand point 451 that has a dominant direction and a high degree of longness. In other words, if a demand point 451D that has a dominant direction is a demand point 451 with a high degree of longness, as shown by demand point 451C in Figure 25, then the fact that it is a demand point 451 with a high degree of longness is simultaneously expressed by changing the pattern or color, as shown by demand point 451F. Similarly, if a demand point 451E has a high degree of longness, it will be displayed with a different pattern or color.

[0226] If a dominant direction exists at each of the 451 demand points displayed on the detailed map, displaying that dominant direction can help drivers determine their direction of travel, for example, when cruising, thus contributing to an increase in passenger occupancy rates. Furthermore, even at intersections where various directions are possible, drivers can determine the direction with the highest passenger demand by referring to the dominant direction around the intersection.

[0227] The method of notification by sound and voice in the detailed map display shown in Figure 26 is the same as in Figure 25, so no explanation is provided.

[0228] Even in the detailed map display, whether guidance for demand point 451 is provided by sound only, by voice only, or by both sound and voice is changed according to the setting value on the settings screen. The demand forecasting app has a notification function (notification unit) that notifies the driver of a predetermined demand point 451, which is a location with high passenger demand, using at least one of sound or voice.

[0229] As described above, the demand forecasting app can contribute to improving the occupancy rate by notifying the driver of the predicted passenger demand in the direction the taxi 11 is traveling, using sound or voice.

[0230] The method of displaying passenger demand differs depending on whether the demand forecast screen uses a wide-area map display (Figure 24) or a detailed map display (Figures 25 and 26), and accordingly, the methods of providing sound and voice notifications also differ.

[0231] Switching between wide-area map display and detailed map display can be done, for example, by the driver using the zoom in / out button 62 or by changing the settings on the settings screen. Alternatively, instead of touch panel operation, the demand forecasting application may recognize (voice recognition) the driver's voice command for "wide-area display" or "detailed display" and switch accordingly. Furthermore, the demand forecasting application may switch automatically. For example, the demand forecasting application can change to a detailed map display when it determines that the taxi 11 has entered a high-demand area indicated by the wide-area map display, and change back to a wide-area map display when it determines that it has left the high-demand area.

[0232] <Voice guidance control processing> The aforementioned audible and voice-based guidance for predicting passenger demand is necessary when the taxi 11 is empty and has no passengers, but is not necessary when it has passengers. Furthermore, audible and voice notifications can be considered noise by passengers. Therefore, the demand forecasting app can obtain the "occupied" or "empty" status detected by the fare meter 21 and control the on / off status of the audible and voice guidance accordingly.

[0233] Figure 27 is a flowchart of the voice guidance control process that controls voice guidance.

[0234] First, in step S51, the demand forecasting app determines whether the status of taxi 11 (vehicle) has been changed to "occupied".

[0235] If it is determined in step S51 that the status of taxi 11 has changed to "occupied", the process proceeds to step S52, where the demand forecasting app controls the voice guidance to be turned off. After step S52, the process returns to step S51.

[0236] On the other hand, if it is determined in step S51 that the status of taxi 11 has not been changed to "occupied", the process proceeds to step S53, where the demand forecasting app determines whether the status of taxi 11 has been changed to "vacant".

[0237] If it is determined in step S53 that the status of taxi 11 has changed to "vacant", the process proceeds to step S54, where the demand forecasting app controls the voice guidance to turn on. After step S54, the process returns to step S51.

[0238] On the other hand, if it is determined in step S53 that the status of taxi 11 has not been changed to "vacant", the process returns to step S51.

[0239] The voice guidance control process shown in Figure 27 starts when the demand forecasting app is launched or when voice guidance is turned on in the settings screen, and is repeated until the demand forecasting app is closed.

[0240] As described above, the demand forecasting app can control the on / off status of voice guidance in conjunction with the "occupied" or "vacant" status detected by the fare meter 21. By controlling the guidance in conjunction with the "occupied" or "vacant" status, voice guidance can be automatically (without driver intervention) executed only when the driver needs it.

[0241] Note that the voice guidance control process in FIG. 27 is an example of a notification control process for voice guidance that outputs the boarding demand in the traveling direction as a voice message. However, notifications by sound, and notifications by both sound and voice are controlled in the same way. The status of "occupied vehicle" or "empty vehicle" may be directly acquired by the demand prediction application from the fare meter 21, or may be indirectly acquired via the vehicle management device 22.

[0242] <Other voice outputs> In addition to notifying the above-described boarding demand by sound and voice, the demand prediction application can also notify the driver of the following information by voice.

[0243] For example, the demand prediction application can acquire the train operation stop information and operation restart information from the server 12 in real time and output them as voice (messages). Thereby, the driver can quickly move to an area where the boarding demand increases according to the train operation information.

[0244] For example, the demand prediction application can acquire the end timing and start timing of an event being held in the business area of the taxi 11 from the server 12 in real time and output them as voice (messages). Thereby, the driver can quickly move to an area where the boarding demand increases according to the end or start of the event.

[0245] For example, the demand prediction application can acquire the weather information in the business area of the taxi 11, particularly information regarding sudden weather changes, from the server 12 in real time and output them as voice (messages). Thereby, the driver can quickly move to an area where the boarding demand increases according to the weather change.

[0246] The server 12 acquires train operation information, event information, weather information, etc. from the servers of partnering information providers and transmits them to the demand prediction applications of each terminal device 23.

[0247] <18. Recommended route presentation process> In the above-described embodiment, an example has been described in which the driver himself / herself determines the moving direction of the taxi 11 and drives the taxi 11 based on the display of the ride demand prediction and the voice output displayed on the display of the terminal device 23 by the demand prediction application.

[0248] Hereinafter, a recommended route presentation function will be described in which the demand prediction application searches for a route with a high ride demand based on the ride demand prediction data transmitted from the server 12 and presents a recommended route.

[0249] The demand prediction application has a navigation function (navigation processing unit) that searches for a route to a destination set by any method based on the vehicle's own position. In addition to the functions of a general navigation system (hereinafter referred to as a car navigation system) installed in the vehicle, the demand prediction application has a function of searching for a route to the destination in consideration of places predicted to have a high ride demand. Note that the destination may be a predetermined pinpoint location or a target area such as one or more areas AR divided by the demand prediction mesh 63. Hereinafter, a place predicted to have a high ride demand will be described as a boarding point. The boarding point is the same as the place referred to as the boarding position or demand point in the above description.

[0250] The recommended route suggestion feature of the demand forecasting app is used when the taxi is empty, or "cruising" for fares. By using the recommended route suggestion feature, drivers can pick up passengers in a short amount of time, reducing the amount of time spent empty and the distance driven while empty. It is especially useful for new drivers who have not been in the taxi business for long, as they may not have established areas of expertise or knowledge of high-demand locations. Even veteran drivers with long experience in the taxi business, or drivers who earn above-average sales, have areas they are good at and areas they are not good at. If they are driving in an area they are not good at, using the recommended route suggestion feature will allow them to pick up passengers in a short amount of time and reduce the amount of time they are empty and the distance driven while empty. By setting the destination in an area or location they are good at when searching for a route, it becomes possible to pick up passengers along high-demand routes (pickup points) and return to the desired area or location. By repeatedly using the recommended route suggestion feature to drive along high-demand routes (pickup points), drivers can overcome their weaknesses and expand their areas of expertise.

[0251] Drivers can pre-register (set) their preferred areas in the settings screen, or the demand forecasting app can determine (automatically register) them using the driver's vehicle movement log data and actual vehicle data. Preferred locations can be, for example, the driver's office, specific pick-up locations frequently used by drivers, or places where drivers frequently wait for passengers, such as taxi stands.

[0252] When a demand forecasting application uses data to determine its areas of expertise, it can, for example, create a heatmap for sales areas distributed in the XY plane, with the Z-axis direction representing cumulative time, as shown in Figure 28. It can then extract areas exceeding a predetermined threshold, for example, 70% of the total time, as the driver's areas of expertise. The areas of expertise may be all of the areas extracted that exceed the threshold, the single area with the longest cumulative time, or multiple areas with the longest cumulative time. The display unit for the areas of expertise may be the extracted area itself, or, to make it easier for the driver to recognize, it may be the municipality with the largest area among the extracted areas, or the municipality where the point with the longest cumulative time is located.

[0253] If the source data used to calculate the cumulative time in the Z-axis direction is vehicle movement log data, the areas where the driver spent the most time traveling can be designated as their preferred areas. Furthermore, if the source data used to calculate the cumulative time in the Z-axis direction is only vehicle movement log data with the status "on-board," the areas where the driver spent the most time carrying passengers can be designated as their preferred areas. If the source data used to calculate the cumulative time in the Z-axis direction is actual vehicle data, the areas where the driver picked up passengers most often can be designated as their preferred areas.

[0254] Figure 29 shows an example of the recommended route display screen in a demand forecasting app when the recommended route suggestion function is activated.

[0255] The recommended route display screen in Figure 29 is displayed after a recommended route has been found, for example, when a driver taps the recommended route search button displayed on the demand forecast screen, such as in Figure 2.

[0256] The recommended route display screen in Figure 29 shows a map 41 with the demand forecast mesh 63 superimposed. Each area AR of the demand forecast mesh 63 is classified and displayed by color or density according to the degree of passenger demand, as explained with reference to Figure 2. However, in the example of Figure 29, the display by color or density is omitted to make the figure easier to read. The same omission of the display by color or density according to the degree of passenger demand is also the case for Figures 32 to 44, which will be discussed later.

[0257] The route search results 501 for recommended routes are displayed on map 41. Also displayed on map 41 are a details button 511 used to reduce the zoom level of map 41, a wide-area button 512 used to increase the zoom level of map 41, and a full-screen button 513 used to switch to full-screen display.

[0258] Below map 41, a forecast time display unit 502 is located. The forecast time display unit 502 displays the forecast time for the demand forecast when a recommended route is searched, and, similar to the forecast time setting area 42 in Figure 2, the forecast time for the demand forecast can be changed.

[0259] To the right of the map 41 and the predicted time display unit 502, a recommended route information display unit 503 is located. The recommended route information display unit 503 displays the words "Recommended Route" at the top to indicate that it is a recommended route display screen.

[0260] The recommended route information display unit 503 shows "<Destination Mode>", indicating that the route search result 501 displayed on the map 41 was searched using "Destination Mode" among several search modes. The demand forecasting app uses a route search mode that takes demand points into consideration. As a device, it has three search modes: "destination mode," "immediate pick-up mode," and "nearby pick-up point mode."

[0261] The "destination mode" is a mode in which you set a destination and then search for a route that passes through a point of interest from among multiple routes to that destination. The destination can be set by the driver, The destination (target area) can also be the driver's area of ​​expertise. For example, in "destination mode," the taxi 11's current location is outside its area of ​​expertise, and it will return to its area of ​​expertise while... This is suitable for situations where you want to attract customers.

[0262] The "Instant Pickup Mode" is a mode where there is no specific destination, and the system searches for a route that passes through points of demand from your current location. The "Instant Pickup Mode" is best suited to the taxi's current location. It can be used when you are inside.

[0263] The "Nearby Pickup Point Mode" is a mode that does not have a specific destination and searches for a route that passes through high-demand points with high ratings around the current location. This feature can be used whether the user's current location is within or outside their preferred service area.

[0264] Below the "<Destination Mode>" section of the recommended route information display unit 503, there is a message indicating that the destination for route searching in "Destination Mode" is Setagaya Ward: "Return to Area 'Setagaya Ward'" It is displayed.

[0265] Furthermore, in the recommended route information presentation unit 503, information such as "recommendation level: 98 points", "number of boarding points: 108 locations", and "total demand prediction level: 6 levels" is displayed. "Recommendation level: 98 points" indicates that the recommendation level of the route search result 501 displayed on the map 41 is 98 points. The recommendation level may be a score out of 100 points, or it may be a point display indicating that the higher the numerical value, the greater the degree of recommendation. "Number of boarding points: 108 locations" indicates that the route of the route search result 501 displayed on the map 41 is a route that passes through 108 boarding points. In the demand prediction screen of FIG. 2, an example where the degree of boarding demand for each area AR distinguished by color and density is displayed in five levels from level 1 to level 5 was explained. "Total demand prediction level: 6 levels" indicates that when the levels of the boarding demands of one or more areas AR through which the route search result 501 displayed on the map 41 passes are totaled, it becomes 6 levels.

[0266] Referring to the flowchart of FIG. 30, a recommended route presentation process for searching for a recommended route considering demand points and presenting it to the driver will be described.

[0267] This process is started, for example, by tapping a recommended route search button or the like displayed on the screen of a demand prediction screen such as FIG. 2. Note that the boarding demand prediction data used in the recommended route presentation process can use data periodically transmitted from the server 12, and can also be obtained by requesting the server 12 as necessary.

[0268] First, in step S71, the demand prediction application determines whether a search mode has been specified. The search mode can be specified, for example, by selecting any one of the search mode buttons of "destination mode", "boarding immediately mode", or "nearby boarding point mode" on a mode selection screen displayed after pressing the route search button. Alternatively, when the vehicle's position is outside the preferred area, the "destination mode" is selected, and when the vehicle's position is within the preferred area, the "boarding immediately mode" or the "nearby boarding point mode" is selected. You can pre-configure it to do so.

[0269] The process in step S71 is repeated until it is determined that a search mode has been specified. If it is determined that a search mode has been specified, the process proceeds to step S72.

[0270] Then, in step S72, the demand forecasting app determines whether the specified search mode is "destination mode," "immediate pick-up mode," or "nearby pick-up point mode."

[0271] If, in step S72, it is determined that the specified search mode is the "destination mode", the process proceeds to step S73, and the processes in steps S73 through S75 are executed. If the specified search mode is determined to be “immediate loading mode”, the process proceeds to step S76, and the processes in steps S76 and S77 are executed. If it is determined that the boarding point mode is ", the process proceeds to step S78, and the processes of steps S78 to S80 are executed.

[0272] In step S73, if the specified search mode is determined to be "destination mode," the demand forecasting app sets the destination to its area of ​​expertise. The destination is default. The driver is initially set to a pre-registered preferred area, but this can be changed through driver operation.

[0273] In step S74, the demand forecasting application uses route search algorithms such as Dijkstra's algorithm or A* algorithm to search for multiple (a predetermined number) routes based on the vehicle's current position and destination. This process is similar to that of a typical car navigation system.

[0274] In step S75, the demand forecasting app calculates the sum score (SUMscore) for each route found.

[0275] The total route score, SUMscore, can be calculated, for example, by calculating the score Sc = Area AR passenger demand level [1-5] × boarding point [0,1] × directional match [cosθ] for each Area AR that the explored route passes through, and then summing the scores Sc for each Area AR from the current vehicle's position to the destination. The Area AR passenger demand level [1-5] represents the degree of passenger demand in that Area AR and can be one of levels 1 to 5. The boarding point [0,1] is "1" if a boarding point exists in that Area AR, and "0" if it does not. The directional match [cosθ] is the angle (cosθ) between the direction from the current vehicle's position to the direction of Area AR and the direction from the current vehicle's position to the destination. The closer the values ​​are, the closer the result will be to 1. For the demand forecast used in the above-mentioned Sco Sc calculation formula, the predicted time for each area AR is updated sequentially according to the distance from the vehicle's current position, for example, the number of area ARs passed. For example, assuming one area AR is 500m x 500m and the vehicle travels at 30km / h for 10 minutes, it travels 5km in 10 minutes. Therefore, the predicted time for each area AR is advanced by 10 minutes for every 10 areas traveled, and the demand forecast for the route is updated. Note that the boarding point [0,1] in the above-mentioned Sco Sc calculation formula may be the number of boarding points present in that area AR.

[0276] The total route score (SUMscore) may be calculated not based on the area AR as described above, but rather by calculating a score (Sc) for each boarding point on the route. Furthermore, if a portion of the explored route has a direction opposite to the destination, the score (Sc) may be either not added or subtracted.

[0277] The total route score (SUMscore) is not limited to the examples described above; any calculation method can be used that results in a higher SUMscore for routes with a high level of demand forecasting and many boarding points.

[0278] Furthermore, the total route score SUMscore may be calculated by adding other factors to the score Sc or total score SUMscore. For example, a coefficient or score Sc may be added depending on the length of the pick-up point, so that the longer the distance, the higher the total score SUMscore or score Sc. Alternatively, a coefficient or score Sc may be added depending on whether the route traversed in the searched route is a main road or a narrow road. The direction of travel of passengers when they boarded at each pick-up point can be identified from the departure and arrival points of past ride history (actual vehicle data). The closer the driver's destination is to the direction of travel at the pick-up point, the higher the total score SUMscore or score Sc may be.

[0279] After calculating the sum score (SUMscore) for each route in step S75, the process proceeds to step S81, which will be described later.

[0280] On the other hand, in step S76, when the specified search mode is determined to be the "immediate pick-up mode," the demand forecasting app uses graph theory to determine the predetermined route search area. Multiple routes are determined by depth-restricted search. More specifically, using nodes in graph theory as intersections and edges as roads (paths) between intersections, multiple routes are determined within the route search domain by depth-restricted search. The route search domain may be the preferred area if the vehicle's current position is within that area, or it may be within a radius of a certain number of kilometers from the vehicle's position, or it may be a predetermined number of area-arrays (ARs) centered on the vehicle's position.

[0281] In step S77, the demand forecasting app calculates the total score SUMscore for each searched route. The demand forecasting app calculates the total score SUMscore by, for example, calculating the score Sc for each boarding point on the searched route, for example, as score Sc = boarding demand level [1-5] for the area AR containing the boarding point, and summing them up.

[0282] The total route score (SUMscore) is not limited to the examples described above; any calculation method that results in a higher SUMscore for routes with a high level of demand forecasting and many boarding points can be used. Adding or subtracting the score (Sc) in the reverse direction, and updating the forecast time for demand forecasting, can be done in the same way as in "destination mode".

[0283] After calculating the total score (SUMscore) for each route in step S77, the process proceeds to step S81, which will be described later.

[0284] On the other hand, in step S78, when the specified search mode is determined to be the "nearby pick-up point mode", the demand forecasting app searches for pick-up points that are within a certain distance from the vehicle's current position. Extract the data and assign a score (Sc) to each extracted boarding point.

[0285] In “Nearby Pickup Point Mode,” the score Sc for each pickup point can be assigned, for example, as follows:

[0286] For example, a demand forecasting app might assign a higher score (Sc) to each boarding point the closer the date and time of the boarding is to the current date and time. A demand forecasting app might also assign a higher score (Sc) to each boarding point the more times (number of boardings) there have been boardings. A demand forecasting app might also assign a higher score (Sc) to each boarding point the greater the total boarding time (sum of boarding times for each boarding) or the average boarding time.

[0287] The demand forecasting app assigns a score (Sc) to each boarding point, with higher scores for locations reachable by going straight or turning left from the vehicle's current position, and lower scores for locations reachable by turning right.

[0288] For example, as shown in Figure 31, suppose taxi 11 is traveling at the location marked 505, and there are three possible pick-up points: pick-up point HS1, which can be reached by going straight; pick-up point HS2, which can be reached by turning left; and pick-up point HS3, which can be reached by turning right. In Japan, where traffic is on the left, pick-up points HS1 (going straight) and HS2 (turning left) are relatively easy to reach, but pick-up point HS3 (turning right), which requires crossing the oncoming lane, depends heavily on the timing of traffic lights and oncoming vehicles, and often takes a long time to reach. Therefore, the demand forecasting app can assign higher scores (Sc) to pick-up points HS1 and HS2 than to pick-up point HS3.

[0289] Furthermore, on roads in foreign countries where right-hand traffic is adopted, a score (Sc) is assigned such that locations reachable by going straight or turning right are given higher scores, while locations reachable by turning left are given lower scores. In other words, going straight and turning in a direction that does not require crossing the oncoming lane are given higher scores, while turning in a direction that requires crossing the oncoming lane are given lower scores (Sc).

[0290] The demand forecasting app assigns a score (Sc) to each boarding point, with the score increasing the closer the point is to the vehicle's current location.

[0291] The demand forecasting app assigns a score (Sc) to each boarding point, with the score increasing as the proportion of the area within the AR where the boarding point is located (for example, the number of boarding points / the total number of boarding points in the entire AR area) increases.

[0292] The demand forecasting app assigns a score (Sc) to each boarding point, with the score increasing as the degree of agreement with the destination's direction increases, provided a destination is set.

[0293] The sum of the scores (Sc) assigned to each boarding point as described above becomes the final score (Sc) for each boarding point. Note that the above is just one example of how scores (Sc) may be assigned to each boarding point; other criteria may also be used to assign scores (Sc).

[0294] In step S79, the demand forecasting application refers to the score Sc assigned to each boarding point and searches for multiple routes using a predetermined number of boarding points with high scores Sc as waypoints. More specifically, it first refers to the score Sc assigned to each boarding point and extracts a predetermined number of boarding points with high scores Sc. Then, multiple (determined number) routes are searched using a route search algorithm so as to pass through the extracted boarding points.

[0295] In step S80, the demand forecasting app calculates the total score SUMscore for each searched route. The demand forecasting app calculates the total score SUMscore by, for example, summing the scores Sc of each boarding point present on the searched route. Alternatively, the total score SUMscore may be the number of boarding points present on the route.

[0296] After calculating the total score SUMscore for each route in step S80, the process proceeds to step S81.

[0297] In step S81, among the multiple routes calculated in one of the search modes, “Destination Mode,” “Get on Now Mode,” or “Nearby Pickup Point Mode,” the total score The route with the highest SUMscore is displayed on the screen as the recommended route. The recommended route display screen shown in Figure 29 is an example where the search mode is set to "destination mode".

[0298] The recommended route presentation process in Figure 30 is executed as described above. After the recommended route is presented, route guidance begins, similar to a typical car navigation system. In other words, in addition to route display on the screen, the route is also guided to the driver by voice guidance, such as "Turn right at the next intersection." When displaying the route on the screen, the symbols, colors, and patterns of the boarding points displayed on the route may be changed according to the value (size) of the boarding point's score, Sc, as shown in demand point 451 in Figure 26.

[0299] If the driver stops the recommended route guidance by operating the touch panel or other means, the recommended route guidance will end. Alternatively, the demand forecasting application on the terminal device 23 may obtain the status of "occupied," "vacant," or "on call" from the fare meter 21 or vehicle management device 22, and if the status becomes anything other than "vacant," i.e., "occupied" or "on call," it may terminate (automatically terminate) without any action from the driver.

[0300] <19. Signs indicating areas where boarding is prohibited> Taxi drivers must be aware of no-pickup zones, where picking up passengers outside of designated taxi stands is prohibited. Severe penalties apply if a driver, such as a new driver unfamiliar with these zones, picks up a passenger in such an area. For example, in the Kanto region, no-pickup zones are set up in Ginza and Shimbashi. In the Kansai region, no-pickup zones are set up in Kitashinchi and Minamichi.

[0301] The demand forecasting app can display areas where boarding is prohibited on the demand forecasting screen.

[0302] Figure 32 shows an example of a demand forecast screen displaying areas where boarding is prohibited.

[0303] In Figure 32, parts corresponding to those in Figure 29, etc., are denoted by the same reference numerals, and explanations of those parts are omitted as appropriate.

[0304] The demand forecast screen in Figure 32 displays a detailed button 511, a wide-area button 512, and a full-screen display button 513 on a map 41 overlaid with the demand forecast mesh 63. A current location button 514 is also displayed on the map 41, which switches the map display to a view based on the vehicle's position.

[0305] Furthermore, a "No-Pickup Zone" indicator 521 is displayed in areas of the map 41 that correspond to the no-pickup zone. Near the "No-Pickup Zone" indicator 521, a detailed indicator 522 is also displayed, showing detailed information about the no-pickup zone. The detailed indicator 522 includes the text "No-Pickup Zone: 10pm to 1am," indicating the time when the no-pickup zone is in effect, and an [OFF] button to remove the "No-Pickup Zone" indicator 521. Because the "No-Pickup Zone" indicator 521 is superimposed on the map 41, drivers who find it difficult to see the display of pickup points in the demand forecast, or who do not need the display of the no-pickup zone, can remove the "No-Pickup Zone" indicator 521 by operating the [OFF] button. The demand forecasting app removes the "No-Pickup Zone" indicator 521 and the detailed indicator 522 when it is outside the time when the no-pickup zone is in effect.

[0306] Furthermore, the demand forecast screen in Figure 32 is provided with a forecast time display unit 502 and an additional information display unit 531 in an area different from the display area of ​​the map 41. The additional information display unit 531 displays, for example, train operation information, event information, weather information, etc.

[0307] Information regarding areas where boarding is prohibited may be stored in advance within the demand forecasting application (terminal device 23), or it may be obtained from the server 12 or the servers of other information providers.

[0308] <20. Placement indication> Figure 17, which shows the predicted waiting time for taxis to pick up passengers, explains that there is a method called "waiting for a taxi," where a taxi waits in line at a taxi stand to pick up passengers. Places where "waiting for a taxi" takes place (hereinafter referred to as "pickup locations") include taxi stands in front of train stations and hotels, and in front of the entrances of designated office buildings. Some of these pickup locations are restricted to specific taxi companies. Taxis from other taxi companies cannot use pickup locations that are restricted to a particular taxi company. The demand forecasting app has a function to indicate that a pickup location is reserved for a specific taxi company.

[0309] Figure 33 shows an example of a demand forecast screen displaying pick-up locations for each taxi company.

[0310] The demand forecast screen in Figure 33 displays a detailed button 511, a wide-area button 512, a full-screen button 513, and a current location button 514 on a map 41 overlaid with the demand forecast mesh 63.

[0311] Furthermore, at designated boarding points 541A and 541B on map 41, boarding location indicators 551A and 551B are displayed respectively to indicate that these boarding points are boarding locations. Boarding location indicator 551A is represented by a solid circular figure, while boarding location indicator 551B is represented by a dashed circular figure, and the display methods for boarding location indicator 551A and boarding location indicator 551B are different. This difference in display method indicates that different taxi companies are authorized to use the designated pick-up locations. When there is no particular distinction between pick-up location indicator 551A and pick-up location indicator 551B, they are simply referred to as pick-up location indicator 551.

[0312] The driver can select (tap) a designated location indicator 551 to display detailed information 553 for that location. In the example in Figure 33, detailed information 553 for the location indicator 551A of the boarding point 541A is displayed.

[0313] Detailed information 553 displays information such as the name of the pick-up location, whether the taxi 11 can use the pick-up location, the time period during which it can pick up passengers, the name of the taxi company that can use the pick-up location, and other available pick-up locations displayed on the map 41 on the demand forecast screen.

[0314] In the detailed information 553 for the pick-up location display 551A in Figure 33, "Hotel Shinagawa" is displayed as the name of the pick-up location, "× (Unavailable)" is displayed to indicate whether or not taxi 11 can be used, "All day" is displayed as the time period during which passengers can be picked up, "Km Taxi Exclusive" is displayed as the name of the taxi company that can use the pick-up location, and "Osaki Think Building" is displayed as the name of the pick-up location 541B of the pick-up location display 551B, which is one of the other available pick-up locations displayed on the map 41 of the demand forecast screen.

[0315] Regarding the taxi company of a driver, the demand forecasting app can identify them by registering (entering) a company ID that identifies the company and a driver ID that identifies the driver working for Taxi 11 on the login screen or settings screen when the app is launched.

[0316] In the example screen shown in Figure 33, the pick-up location indicators 551A and 551B are represented by circular shapes surrounding the pick-up point, but the method of indicating the pick-up location is not limited to this. The pick-up location indicator 551 may change its display (color or symbol) depending on whether the taxi 11 is available or not, or it may be limited to displaying the pick-up location indicator 551 only at pick-up locations where the taxi 11 is available.

[0317] Information about pick-up locations may be pre-stored within the demand forecasting app, or it may be obtained from server 12 or other information provider servers. Since the vehicle movement log data includes a company ID that identifies the company to which taxi 11 belongs, server 12 can obtain known pick-up location information and, along with estimating the pick-up point from the history of the vehicle movement log data, determine whether that pick-up point is a pick-up location, and if so, which taxi company is available. Identifying whether a pick-up point is a pick-up location can be done by detecting taxi 11's waiting operation as described above, and the point at which the status changes from "vacant" to "occupied" after that waiting operation can be designated as the pick-up location.

[0318] The demand forecasting app's location display (551) prevents drivers from going to unnecessary locations, enabling more efficient sales operations.

[0319] <21.Train time display> On a particular railway line, the demand for taxis increases at the station where the last train departs (the so-called "last train") due to passengers missing that train. Similarly, at the station where the last train arrives, the demand for taxis also increases because other connecting lines and buses have often stopped running by that time. Furthermore, on railway lines with infrequent train service (long intervals between trains), many passengers who disembark at a particular station also use taxis. Therefore, if drivers can be provided with train schedule information, such as the last train's departure time and arrival times, they can use that information to head to the taxi stand in front of the station and thus acquire passengers.

[0320] The demand forecasting app has a function to display predetermined train times, such as the last train times, for stations on the railway lines shown on map 41, on the demand forecasting screen.

[0321] Figure 34 shows an example of a demand forecast screen displaying the last train times.

[0322] In the demand forecast screen shown in Figure 34, Map 41 displays Shinagawa Station of Keikyu Corporation, Shinagawa Station of East Japan Railway Company (JR East), and Takanawadai Station of the Toei Asakusa Line, and shows the last train times for each station.

[0323] Specifically, the time display 571 shows "Shinagawa Station 0:23 bound for Kanazawa Bunko," indicating that the last train bound for Kanazawa Bunko operated by Keikyu Corporation departs from Shinagawa Station at 0:23.

[0324] The time display 572 shows "Shinagawa Station 0:46 bound for Osaki," indicating that the last train bound for Osaki from Shinagawa Station operated by East Japan Railway Company (JR East) departs at 0:46.

[0325] The time display 573 shows "Takanawadai Station 0:31 bound for Nishimagome," indicating that the last train bound for Nishimagome on the Toei Asakusa Line departs from Takanawadai Station at 0:31.

[0326] To the right of map 41 on the demand forecast screen, a list display section 581 is displayed, which shows the train time information displayed on map 41 in a list format.

[0327] The list display unit 581 displays the same information as the time displays 571 to 573 in a predetermined order, such as in order of earliest or latest train times, or in order of closest or furthest distance from the user's current location to the station. The sort button 582 is operated to change the order in which the information is displayed on the list display unit 581, such as changing from earliest to latest train times, from closest to furthest distance from the user's current location, or from train time order to distance order from the user's current location. The train time may be either the arrival time or the departure time.

[0328] A demand forecasting app with a function to display predetermined train times, such as the last train time, increases the opportunity to acquire passengers who have missed the last train or who have just gotten off the last train. The train time display function can be turned on or off in the settings. Instead of displaying train times for all stations shown on map 41 of the demand forecasting screen, it may be limited to stations with a large number of users (above a certain value), terminal stations where multiple lines intersect, and stations that are the starting or ending points of trains. Instead of displaying stations shown on map 41, it may be set to display stations within a certain distance from the vehicle's position (for example, within a radius of 2.5 km). Alternatively, only stations located in the direction of the vehicle's travel may be displayed. The conditions for which stations' train times are displayed may be set in the settings screen.

[0329] As mentioned above, on railway lines with infrequent train service (long intervals between trains), it may be acceptable to display the times of all trains, not just the last and first trains.

[0330] The demand forecasting application can obtain train schedule data from the server 12 along with or as part of the passenger demand forecasting data and display it on the demand forecasting screen. The demand forecasting application may display the schedule in conjunction with the taxi's current location and time, for example, when a predetermined time before the train is due, or it may provide a train schedule display button on the demand forecasting screen and display the schedule based on the driver's operation.

[0331] <22. Reverse Lookup of Boarding Points> When passengers use taxi 11 with destinations such as Haneda Airport or Narita Airport, the ride distance is expected to be long. Therefore, drivers may request passengers going to specific destinations. Since the actual vehicle data records the departure and arrival points, by collecting actual vehicle data where the arrival point is a specific location, it is possible to analyze the pick-up points (departure points) where the destination is a specific location.

[0332] Therefore, the demand forecasting app includes a reverse lookup boarding point display function that allows drivers to specify a particular location as their destination, and then displays only the boarding points where passengers actually boarded with that specified location as their destination in past actual travel data. A reverse lookup boarding point refers to a boarding point where the destination is limited to a specific location. Examples of locations that can be specified as destinations include Haneda Airport, Narita Airport, and Tokyo Disney Resort (registered trademark) (hereinafter referred to as TDR).

[0333] Figure 35 shows an example of a demand forecast screen with the reverse-lookup boarding point display function activated.

[0334] The demand forecast screen shown in Figure 35 can be displayed, for example, by a driver operating the reverse lookup boarding point display button or the like, which is displayed on the demand forecast screen.

[0335] In the demand forecast screen of Figure 35, the reverse lookup boarding point display unit 601 is located next to (to the right of) the map 41 on which the demand forecast mesh 63 is superimposed. Below the map 41, the forecast time display unit 602 is located.

[0336] The reverse boarding point display unit 601 displays a list of passenger destinations for which demand forecasts are displayed, and an execution button 611 to display the demand forecasts. In the example in Figure 35, three destinations are displayed: Haneda Airport, Narita Airport, and TDR. To display the demand forecast for passengers heading to Haneda Airport, the execution button 611A is touched (selected); to display the demand forecast for passengers heading to Narita Airport, the execution button 611B is touched; and to display the demand forecast for passengers heading to TDR, the execution button 611C is touched (selected).

[0337] The forecast time display unit 602 displays the forecast time for demand forecasting, and, similar to the forecast time setting area 42 in Figure 2, it is possible to change the forecast time for demand forecasting.

[0338] Figure 36 shows an example of the demand forecast screen for passengers heading to Haneda Airport when the execute button 611A is touched. The magnification of the map 41 on the demand forecast screen can be changed by operating the details button 511 or the wide-area button 512. In the example in Figure 36, the scale of the demand forecast map 41 initially displayed by the execute button 611A is set to high magnification (wide-area map), but the scale of the demand forecast map 41 initially displayed by the execute button 611A can also be set to the same magnification as the map 41 on the demand forecast screen in Figure 35 when executed. In the demand forecast screen of Figure 36, the probability of passengers going to each boarding point and destination may also be displayed.

[0339] Demand forecasts for passengers heading to a designated location can be categorized by time of day, weather, day of the week (weekday, day before holiday, holiday), and other conditions, and the system can display boarding points that match the conditions at the time of demand forecasting.

[0340] The one or more destinations displayed on the reverse lookup boarding point display unit 601 may be pre-set locations such as Haneda Airport, Narita Airport, and TDR as shown in Figure 35, or they may be locations that the taxi 11 frequently travels to from its current location. In addition to the examples above, destinations such as other theme parks, concert venues, event venues, and baseball stadiums can also be set.

[0341] <23. Classification and display of demand forecasts for dispatch / cruising / waiting for pickup> When a user takes a taxi 11, there are three ways to obtain one: "trip request," "cruising," and "customer waiting at stand." "Trip request" is a method of arranging a taxi 11 through a taxi company's call center or app, and having the taxi 11 come to a designated location. "Cruising" is a method of hailing an empty taxi 11 that is moving around. "Customer waiting at stand" is a method of going to a designated location and boarding a taxi 11 that is waiting there. When a demand forecasting app displays demand forecasts on its demand forecasting screen, it can distinguish between the differences in the methods of taking a taxi: "trip request," "cruising," and "customer waiting at stand." In other words, the demand forecasting app has the function of distinguishing between the differences in the methods of taking a taxi: "trip request," "cruising," and "customer waiting at stand" when displaying demand forecasts.

[0342] Figure 37 shows an example of a demand forecast screen that displays demand forecasts while distinguishing between different methods of boarding: "dispatch," "cruising," and "waiting at a designated stop."

[0343] The demand forecast screen in Figure 37 includes a map 41 overlaid with a demand forecast mesh 63, a forecast time display unit 502 that allows specifying the forecast time for demand forecasting, and an additional information display unit 531.

[0344] On the map 41 of the demand forecast screen, in addition to the detail button 511, wide area button 512, full screen display button 513, and current location button 514, there are also a display button 641, a passing display button 642, and a dispatch display button 643. Furthermore, to distinguish between the different boarding methods of "dispatch," "passenger hailing," and "waiting for a ride," boarding points 645 are displayed on the map 41 using different display methods such as color, pattern, and mark shape.

[0345] The "Pick-up" button 641 is operated to display the pick-up points 645 for the "waiting for a ride" method on the map 41. The "cruising" button 642 is operated to display the pick-up points 645 for the "cruising" method on the map 41. The "dispatch" button 643 is operated to display the pick-up points 645 for the "dispatch" method on the map 41. The "Pick-up" button 641, the "cruising" button 642, and the "dispatch" button 643 are toggle buttons, and each time they are operated, the display of the pick-up points 645 can be turned on or off for each specified pick-up method. In addition, any combination of "dispatch," "cruising," and "waiting for a ride" is possible, and for example, if both "dispatch" and "cruising" are turned on, the map 41 will display the pick-up points 645 for both the "dispatch" and "cruising" methods.

[0346] Demand forecasts for boarding points based on the difference in boarding methods—"dispatched," "cruising," or "waiting at a designated spot"—can be obtained by forecasting boarding demand for each of these methods. For "dispatched" boarding, actual vehicle data should be collected from taxis that are "in service" immediately after their status changes to "on call." For "waiting at a designated spot," actual vehicle data should be collected from taxis that are "in service" after the waiting operation. For "cruising" boarding, actual vehicle data can be collected from all other types of boarding besides "dispatched" and "waiting at a designated spot."

[0347] By displaying passenger demand (boarding points) separately for each boarding method—"dispatch," "cruising," or "waiting at a designated spot"—it's possible to present passenger demand to drivers in a way that suits their business style.

[0348] <24. Display of estimated fare> Figure 18 illustrates an example of displaying a long-distance display 241, which shows the proportion of long-distance passengers in a designated area AR, when that area AR is selected as the area of ​​interest AR.

[0349] Furthermore, Figure 19 illustrates an example in which, when a predetermined area AR is selected as the area of ​​interest AR, a ride distance display 251 is shown, which displays the average ride distance and its confidence interval for passengers riding in the area of ​​interest AR.

[0350] Furthermore, the explanation for Figure 19 stated that the demand forecasting app may display the average fare and confidence interval instead of the average ride distance and confidence interval, and that it can forecast ride demand for different times of day and weather conditions.

[0351] Figure 38 shows an example of how the average fare and confidence interval for passengers using the AR in the area of ​​interest are displayed.

[0352] As shown in Figure 38, the demand forecasting app can display a fare information display 711 that shows the average fare for passengers using the AR in the area of ​​interest, along with its confidence interval, in addition to the total number of passengers using the AR in the area of ​​interest.

[0353] In the fare display 711, the average fare for rides in the featured AR area is shown to be "2,400 yen," and the confidence interval for the average fare at, for example, 70% confidence, is shown to be "1,110 yen to 3,700 yen." The confidence level for the confidence interval is not limited to 70% and can be set arbitrarily to 80%, etc.

[0354] Furthermore, the fare display 711 indicates that the predicted fare shown is based on actual vehicle data specifically for the time period of "18:00-18:30, weekdays, rainy, October."

[0355] In this way, by displaying the average fare and its confidence interval for AR in a featured area, drivers can, for example, look for AR areas where they can expect higher fares.

[0356] The fare display 711 may show information about the area of ​​interest AR, as shown in Figure 38, or it may be displayed in conjunction with the pinpoint boarding location mark 221 (Figure 15) to show the average fare and confidence interval for the pinpoint boarding location.

[0357] Furthermore, as explained above with reference to Figure 2, each area AR of the demand forecast mesh 63 is displayed using different colors and densities according to the degree of passenger demand. However, the colors and densities could also be changed based on the expected passenger fare. In this case, a driver could, for example, choose a route where a high passenger fare is expected and perform "cruising" driving.

[0358] <25. Display of Real-Time Number of Available Vehicles> A demand forecasting app predicts and displays the demand for rides at a given time (time period). However, for example, if the app predicts a demand for 10 rides in a featured area using AR, but there are 20 taxis 11 that want to pick up passengers in that area, then the 10 taxis 11 will not be able to acquire passengers. In other words, whether or not a taxi can acquire passengers depends on the relationship between supply and demand.

[0359] Taxi companies manage the current location and status (such as "occupied," "vacant," or "on call") of each taxi in real time at their dispatch centers. By combining real-time operational data, including the current location and status of each taxi, with passenger demand forecasts, drivers can operate efficiently while also considering the supply and demand relationship mentioned above. Note that "real time" includes a slight time lag (for example, a few minutes) for collecting the current location and status information of each taxi in operation and for distributing operational data to the demand forecasting app.

[0360] Figure 39 shows an example of a demand forecast screen that displays real-time vehicle availability information based on operational data.

[0361] The demand forecast screen in Figure 39 includes a map 41 overlaid with a demand forecast mesh 63, a forecast time display unit 502 that allows specifying the forecast time for demand forecasting, and an area information display unit 741.

[0362] Each area AR, divided by the demand forecast mesh 63 on map 41, displays real-time information on the availability of taxis 11 in that area AR. The availability information for taxis 11 742 represents the number of taxis 11 currently moving within that area AR and having an "available" status.

[0363] Among the area ARs (Areas of Interest) divided by the demand forecast mesh 63, the area of ​​interest ARs designated by the driver display the area of ​​interest frame 211. The area information display unit 741 displays detailed information about the area of ​​interest frame 211 as area information. For example, the area information display unit 741 displays the predicted number of taxis for the area AR and the long-distance rate of passengers in that area AR. In the example in Figure 39, the area of ​​interest AR where the area of ​​interest frame 211 is displayed shows that there are currently 5 "vacant" taxis 11, while the predicted number of taxis for the area AR is 0.

[0364] Figure 40 shows an example of a demand forecast screen displaying real-time vehicle availability information when the map 41 is at a low scale, in other words, when it is a detailed map display.

[0365] Figure 39 shows an example of a demand forecast screen displaying real-time taxi availability information when the map 41 is at a high magnification, in other words, when displaying a wide-area map. When displaying a wide-area map, as shown in Figure 39, the number of "available" taxis 11 is displayed as taxi availability information for each area AR of the demand forecast mesh 63.

[0366] In contrast, when a detailed map is displayed, as shown in Figure 40, an icon 751 indicating the presence of an "available" taxi 11 is displayed at the location where the "available" taxi 11 is located.

[0367] Furthermore, at designated boarding points in taxi stands, the number of taxis waiting at that particular boarding point can also be displayed.

[0368] By incorporating a demand forecasting app that displays real-time vehicle availability information based on operational data, drivers can select areas with a high probability of attracting passengers and thus increase their chances of securing passengers.

[0369] Furthermore, if the demand forecasting app can acquire operational data, the recommended route suggestion process described above can include real-time information on available taxis in the operational data to search for and suggest recommended routes. That is, when selecting a predetermined route as part of a recommended route, the demand forecasting app will select a route as a recommended route if the number of predicted passenger demands is greater than or equal to the number of "available" taxis, or assign a large score Sc to that route. In addition, the demand forecasting app may include a process to select a route as a recommended route if no "available" taxis 11 have traveled on that route for a certain period from the present to a predetermined time ago, as there may be passenger demand.

[0370] <Display of sales performance evaluation for 26.1 days> The demand forecasting app can include a function that outputs sales evaluation information to drivers after the end of their workday, allowing them to assess their performance for the day. Sales evaluations can be based on high-performing drivers, such as those with high average daily sales. By using high-performing drivers as benchmarks for evaluation, the app can provide drivers with information to help them increase sales.

[0371] Figure 41 shows an example of an evaluation screen that outputs daily sales performance information. This evaluation screen is displayed, for example, in a demand forecasting application when the operation to end the day's sales is performed.

[0372] The evaluation screen in Figure 41 displays the title 811 at the top. In the example in Figure 41, it displays "10 / 11 Driving Score," indicating that it is evaluation information for the working day of October 11th.

[0373] The evaluation screen also includes an evaluation score display 812, a radar chart 813, a sales revenue graph 814, and a route history display button 815.

[0374] The rating score 812 indicates the driver's overall performance for the day, with the baseline driver score set at 100 points. By referring to this overall rating, you can see how close the driver is to the baseline performance.

[0375] Radar Chart 813 shows the evaluation results, which are a comprehensive evaluation of a driver's overall performance for the day, broken down into multiple categories. In the example in Figure 41, the evaluation is categorized into five items: revenue, occupancy rate, idle time, number of trips, and service area. Revenue represents the evaluation value from the perspective of revenue (sales) per unit of actual driving time. Occupancy rate represents the evaluation value from the perspective of "occupied" driving time / total driving time. Idle time represents the evaluation value from the perspective of "idle" time / total driving time. Number of trips represents the evaluation value from the perspective of the number of times the driver picked up a passenger. Service area represents the evaluation value from the perspective of the size of the area driven.

[0376] The revenue graph 814 displays the daily revenue trend, with the horizontal axis representing daily operating hours and the vertical axis representing revenue. The solid line 821 displayed in the revenue graph 814 represents the driver's actual sales. On the other hand, the dashed line 822 displayed in the revenue graph 814 represents ideal hypothetical sales based on the driver's actual route and the operation data of other taxis 11. For example, if the driver's actual route and the operation data of other taxis 11 are available, it is possible to analyze cases such as when the driver actually went straight at a certain intersection, but it is expected that they could have acquired a passenger if they had turned left. By analyzing such assumptions for the actual route, it is possible to predict the ideal revenue that could have been earned with a slight difference in the route. Such ideal revenue is displayed as the dashed line 822. In addition, comments are displayed on the dashed line 822 for points (locations) where there was a possibility of increasing revenue, such as "If they had turned at Higashi-Ginza 7-chome" or "If they had turned at Shimbashi 5-chome".

[0377] The Route History Display button 815 is a function that displays the driver's actual daily driving history on a map.

[0378] Figure 42 shows an example of the operation history screen displayed when the route history display button 815 is operated.

[0379] The operation history screen, as shown in Figure 42, displays the route the taxi 11 traveled from the start to the end of the day, its status ("occupied," "vacant," or "on call"), the locations and times where passengers boarded and alighted, and other information. In the example in Figure 42, the map 41 is not displayed, but in reality, it is superimposed on the map 41. Also, in the example in Figure 42, only a portion of the day's operation route is displayed, but the driver can view the entire or partial day's operation route by changing the display magnification of the map 41.

[0380] The operation history screen in Figure 42 may be displayed on a single screen together with the evaluation screen in Figure 41. The operation history screen in Figure 42 can be referenced in conjunction with the points in the sales revenue graph 814 of the evaluation screen in Figure 41 that showed potential for increasing sales revenue, which can be used as a reference for future operations.

[0381] <27. Display of additional information considering distance and direction> When displaying additional information such as train operation information, event information, or weather information, the additional information display unit 531 may be provided in an area different from the display area of ​​the map 41, as shown in the example in Figure 32. Alternatively, the additional information may be displayed on the map 41, taking distance and direction into consideration.

[0382] Figure 43 shows an example of a demand forecast screen that displays additional information considering distance and direction.

[0383] In the example shown in Figure 43, additional information 831 and additional information 832 are displayed on map 41.

[0384] Additional information 831 is information notifying that train service has been suspended at Tamachi Station on the Yamanote Line. Additional information 831 is displayed at a position corresponding to the direction of Tamachi Station, relative to the taxi's current location mark 505. In the example in Figure 43, since Tamachi Station is located outside the display area of ​​the map 41 on the demand forecast screen, only additional information 831 is displayed at the position corresponding to the direction of Tamachi Station. However, if Tamachi Station were on the map 41 on the demand forecast screen, a symbol indicating that train service has been suspended, such as × or △, would be displayed along with additional information 831 at the Tamachi Station portion of the map 41. Alternatively, only a symbol could be displayed as additional information 831, and detailed information could be displayed when the symbol is tapped (selected).

[0385] Additional information 832 is a notification that a train delay has occurred at Togoshi Station on the Toei Asakusa Line. Additional information 832 is displayed at a position corresponding to the direction of Togoshi Station, relative to the vehicle position marker 505 which indicates the current location of taxi 11.

[0386] The direction based on the vehicle position mark 505 may be a precise angle in units of 1 degree, or it may be an angle that converges to a predetermined range, such as 4 directions or 8 directions.

[0387] Similarly, regarding distance, if the distance to the location related to the additional information is far from the current location, it will be displayed farther away from the vehicle's position marker 505; if it is close, it will be displayed closer to the vehicle's position marker 505.

[0388] For example, if the additional information is information about train delays, the station that is calculated to be affected can be used as the location related to the additional information, and its direction and distance from the vehicle's position marker 505 can be calculated.

[0389] For example, if the additional information is related to an event, the location where the event is held can be used as the location related to the additional information, and the direction and distance from the vehicle's position marker 505 can be calculated.

[0390] For example, if the additional information is weather-related, such as a sudden downpour, the location of the weather phenomenon can be used as the location related to the additional information, and its direction and distance from the vehicle's position marker 505 can be calculated.

[0391] As described above, by displaying the additional information on the map 41 according to the distance and direction of the additional information and presenting it to the driver, the driver can intuitively understand the additional information.

[0392] Note that in the demand forecast screen shown in Figure 43, the display of boarding point 645 (and similarly demand point 451) on map 41, and the display of the forecast time display section 502 are omitted.

[0393] <28. Display of information according to the direction of travel> For demand forecasts, such as boarding points, and for additional information like event information and train delay information shown in Figure 43, information in the direction of travel of taxi 11 is important, but information in the opposite direction is not as important. The same applies to the route information on map 41.

[0394] Therefore, when the demand forecasting app displays the map 41 on the demand forecasting screen, it can display more information for the direction of travel than for the opposite direction of travel.

[0395] Figure 44A shows an example of the display in Head Up mode, where the direction of travel of the taxi 11 is at the top (upper edge) of the screen.

[0396] In head-up mode, the vehicle position marker 505 is positioned such that, in the left-right direction, the right-side area R1 and the left-side area L1 are the same or nearly the same, and in the up-down direction, the upper area U1 is larger than the lower area D1.

[0397] Figure 44B shows an example of the display in North Up mode, where the north direction is at the top (upper edge) of the screen, regardless of the direction of travel of the taxi 11.

[0398] In North Up mode, the distribution between the right-side area R1 and the left-side area L1, and the distribution between the upper area U1 and the lower area D1, differs depending on the direction of travel of the taxi 11. Figure 44B shows an example of the display when the direction of travel of the taxi 11 is northeast. In this case, the right-side area R1 is larger than the left-side area L1 in the left-right direction, and the upper area U1 is larger than the lower area D1 in the up-down direction.

[0399] Other diagrams are omitted, but for example, if the direction of travel of taxi 11 is southwest, the left region L1 is larger than the right region R1 in the left-right direction, and the lower region D1 is larger than the upper region U1 in the up-down direction.

[0400] As described above, by displaying more information related to the direction of travel than information related to the opposite direction of travel, more useful information can be displayed to the driver.

[0401] <29. Computer Configuration Examples> The series of processes described above can be executed by hardware or by software. When the series of processes are executed by software, the programs that make up the software are installed on a computer. Here, a computer includes microcomputers built into dedicated hardware, as well as general-purpose personal computers that can perform various functions by installing various programs.

[0402] Figure 45 is a block diagram showing an example of the hardware configuration of a computer when the computer executes each process performed by the server 12, the vehicle management device 22, or the terminal device 23 using a program.

[0403] In a computer, the CPU (Central Processing Unit) 301, ROM (Read Only Memory) 302, and RAM (Random Access Memory) 303 are interconnected by a bus 304.

[0404] An input / output interface 305 is further connected to the bus 304. An input unit 306, an output unit 307, a storage unit 308, a communication unit 309, and a drive 310 are connected to the input / output interface 305.

[0405] The input unit 306 consists of operation buttons, a keyboard, a mouse, a microphone, a touch panel, input terminals, etc. The output unit 307 consists of a display, speakers, output terminals, etc. The storage unit 308 consists of a hard disk, a RAM disk, non-volatile memory, etc. The communication unit 309 consists of a network interface, etc. The drive 310 drives a removable recording medium 311 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory.

[0406] In a computer configured as described above, the CPU 301 loads, for example, a program stored in the memory unit 308 into the RAM 303 via the input / output interface 305 and the bus 304, and executes it, thereby performing the series of processes described above. The RAM 303 also stores data necessary for the CPU 301 to perform various processes as appropriate.

[0407] The program executed by the computer (CPU 301) can be provided by recording it on a removable recording medium 311, such as a packaged media. The program can also be provided via wired or wireless transmission media, such as a local area network, the internet, or digital satellite broadcasting.

[0408] In a computer, a program can be installed in the storage unit 308 via the input / output interface 305 by inserting the removable recording medium 311 into the drive 310. Alternatively, a program can be received by the communication unit 309 via a wired or wireless transmission medium and installed in the storage unit 308. Furthermore, programs can be pre-installed in the ROM 302 or the storage unit 308.

[0409] In this specification, a system means a collection of multiple components (devices, modules (parts), etc.), regardless of whether all components are located in the same enclosure. Therefore, multiple devices housed in separate enclosures and connected via a network, and a single device containing multiple modules in one enclosure, are both considered systems.

[0410] Furthermore, in this specification, the steps described in the flowchart may be performed chronologically in the order they are described, but they may also be performed in parallel or at any necessary time, such as when a call is made, even if they are not necessarily processed chronologically.

[0411] The embodiments of this technology are not limited to those described above, and various modifications are possible without departing from the spirit of this technology.

[0412] The above-described embodiment illustrates an example of a forecasting system for predicting the demand for taxi rides as a commercial vehicle. However, it can also be applied to systems that predict the demand for other commercial vehicles that carry passengers (people), specifically buses, trains, airplanes, ships, helicopters, etc., as well as commercial vehicles that carry goods (cargo), such as trucks and dump trucks. Furthermore, the commercial vehicle may be an unmanned transport vehicle such as a drone.

[0413] For example, a configuration can be adopted that appropriately combines all or part of the embodiments described above.

[0414] For example, this technology can be configured as cloud computing, where a single function is shared and processed collaboratively by multiple devices via a network.

[0415] Furthermore, each step described in the flowchart above can be performed by a single device, or it can be divided and performed by multiple devices.

[0416] Furthermore, if a single step includes multiple processes, those processes can be executed by a single device or shared among multiple devices.

[0417] Furthermore, the effects described herein are merely illustrative and not limiting, and other effects may also occur.

[0418] Furthermore, this technology can also be configured as follows. (1) The system includes a display control unit that divides the operating area of ​​commercial vehicles into multiple areas, predicts passenger demand for each area, and then displays the direction and distance of passengers traveling in a designated area as a prediction result on the display unit. Information processing device. (2) The display control unit causes the movement direction and movement distance to be displayed on the display unit as arrows pointing outward from the area of ​​interest. The information processing device described in (1) above. (3) The direction of the arrow represents the direction of movement, the length of the arrow represents the distance traveled, and the thickness of the arrow represents the proportion of passengers in the direction of movement across all directions. The information processing device described in (2) above. (4) The display control unit causes the display unit to display, as prediction results, the boarding locations with the most passengers and the number of passengers at those boarding locations within the area of ​​interest. The information processing device described in any of (1) to (3) above. (5) The display control unit displays the number of passengers at the boarding locations with the most passengers within the area of ​​interest, the number of passengers at those boarding locations, and the total number of passengers in the area of ​​interest as prediction results on the display unit. An information processing device according to any one of (1) to (4) above. (6) The display control unit causes the display unit to display, as prediction results, the predetermined boarding location within the area of ​​interest, the number of passengers at that boarding location, and the time required to wait at the boarding location and board the passengers. The information processing device described in any of (1) to (5) above. (7) The display control unit causes the display unit to display, as a prediction result, the percentage of rides in the area of ​​interest where the ride distance is greater than or equal to a predetermined distance. The information processing device described in any of (1) to (6) above. (8) The display control unit divides the ride distance in the area of ​​interest into multiple sections and displays the percentage of rides for each section as a prediction result on the display unit. An information processing device according to any one of (1) to (7) above. (9) The display control unit also displays the percentage of passengers for each of the categories across the entire area as a prediction result on the display unit. The information processing device described in (8) above. (10) The display control unit causes the display unit to display the estimated time and cost required to travel to the destination, as well as the estimated time and cost required for each segment of the travel route to the destination, which is divided into predetermined units, as the estimated results. The information processing apparatus described in any of (1) to (9) above. (11) The display control unit causes the average ride distance of the passengers in the area of ​​interest and its confidence interval to be displayed on the display unit as prediction results. The information processing device described in any of (1) to (10) above. (12) The display control unit causes the display unit to display the average fare of the passengers in the area of ​​interest and its confidence interval as prediction results. The information processing device described in any of (1) to (10) above. (13) The display control unit causes the average ride time of the passengers in the area of ​​interest and its confidence interval to be displayed on the display unit as prediction results. The information processing device described in any of (1) to (10) above. (14) The display control unit combines the multiple divided areas into one area if the number of passengers in adjacent areas is below a predetermined threshold, and displays the prediction result on the display unit. The information processing device described in any of (1) to (10) above. (15) It also includes a notification unit that provides audible alerts for locations with high passenger demand in the direction of travel. An information processing device according to any of (1) to (14) above. (16) The notification unit notifies the location of the area with high demand for passengers. The information processing device described in (15) above. (17) The notification unit changes the type of sound according to the scale of the prediction result displayed on the display unit to notify the user of locations with high passenger demand. The information processing device described in (15) or (16) above. (18) The notification unit changes the type of sound according to the distance to the location with high passenger demand to notify the location with high passenger demand. The information processing device described in any of (15) to (17) above. (19) The notification unit changes the type of sound according to the level of passenger demand to notify the location of the passenger demand. The information processing device described in any of (15) to (18) above. (20) The notification unit provides an audible notification each time the vehicle passes a location with high passenger demand. The information processing apparatus described in any of (15) to (19) above. (twenty one) The notification unit turns notifications on or off in conjunction with the status of "occupied" or "vacant," as described in any of (15) to (20). (twenty two) The aforementioned sound is a sound effect or a voice message. The information processing device described in any of (15) to (21) above. (twenty three) The notification unit further notifies the user of at least one of the following via voice message: train operation information, event information, and weather information. The information processing device described in any of (15) to (22) above. (twenty four) The display control unit causes the display unit to display a recommended route based on the prediction results of the predicted passenger demand. An information processing device according to any of (1) to (23) above. (twenty five) The display control unit searches for a route to the set destination and displays it on the display unit as the recommended route. The information processing device described in (24) above. (26) The aforementioned destination is an area or location that the driver is familiar with. The information processing device described in (25) above. (27) The area in which the driver excels is the area where the driver has traveled for a predetermined amount of time or more. The information processing device described in (26) above. (28) The area in which the aforementioned driver excels is the area in which the driver has carried passengers for a predetermined amount of time or more. The information processing device described in (26) or (27) above. (29) The area display unit that the aforementioned driver excels at is cities, towns, and villages. The unit of display for the location that the aforementioned driver is most proficient in is the boarding location with the highest number of passengers. The information processing device described in any of (26) to (28) above. (30) The display control unit searches for a route that passes through locations in the vicinity of the current location where passenger demand is predicted, and displays it on the display unit as the recommended route. The information processing device described in (24) above. (31) The display control unit causes the display unit to display the route with the highest total score, obtained by summing the scores of the routes taken, as the recommended route. The information processing apparatus described in any of (24) to (30) above. (32) The aforementioned total score is calculated by summing the aforementioned scores for each area based on the level of passenger demand. The information processing device described in (31) above. (33) The aforementioned total score is calculated by summing the aforementioned scores for each location where passenger demand is predicted. The information processing device described in (31) above. (34) The score for locations where crossing the oncoming lane is required is set lower than the score for locations where crossing the oncoming lane is not required. The information processing apparatus described in any of (31) to (33) above. (35) The closer the predicted direction of the passenger's movement is to the direction of their destination, the higher the score. The information processing apparatus described in any of (31) to (34) above. (36) When searching for the recommended route, the predicted time for predicting the ride demand in a given area is changed according to the distance from the current location. The information processing device described in any of (24) to (35) above. (37) Routes where the predicted number of passengers exceeds the number of available operating vehicles are displayed as recommended routes. The information processing device described in any of (24) to (36) above. (38) The display control unit further displays the no-boarding zone on the display unit. An information processing device according to any of (1) to (37) above. (39) The display control unit further causes the display unit to display the location where the "waiting" takes place. An information processing device according to any of (1) to (38) above. (40) The display control unit further causes the display unit to display the names of companies that can use the location where the "waiting" takes place. The information processing device described in (39) above. (41) The display control unit causes the display unit to further display other locations where the commercial vehicle can be used for "waiting" (a type of vehicle that may be parked or waiting). The information processing apparatus described in (39) or (40) above. (42) The display control unit further displays the train times for stations on the map that are displayed on the display unit. An information processing device according to any one of the above (1) to (41). (43) The display control unit displays the train schedules for multiple stations in a list, either in order of arrival time or in order of distance from the vehicle's current position to the station. The information processing device described in (42) above. (44) The display control unit displays only the boarding point where the passenger boarded the vehicle, with the designated location being the passenger's destination. An information processing device as described in any of (1) to (43) above. (45) The display control unit displays multiple destinations and displays only the boarding point for the selected destination. The information processing device described in (44) above. (46) The display control unit distinguishes between the different boarding methods of "dispatch," "cruising," and "waiting at a designated spot," and further displays the boarding demand forecast on the display unit. An information processing device as described in any of (1) to (45) above. (47) The display control unit turns the display of the passenger demand forecast on or off for each passenger boarding method: "dispatch," "cruising," and "waiting at a designated spot." The information processing device described in (46) above. (48) The display control unit causes the display unit to display the average fare of the passengers in the area of ​​interest and its confidence interval as prediction results. An information processing device as described in any of (1) to (47) above. (49) The display control unit causes the display unit to display the average fare for the passenger at a predetermined boarding location and its confidence interval as prediction results. An information processing device as described in any of (1) to (47) above. (50) The display control unit further displays real-time vehicle availability information on the display unit. The information processing apparatus described in any of (1) to (49) above. (51) The display control unit displays the number of available vehicles for each area as the available vehicle information. The information processing device described in (50) above. (52) The display control unit displays an icon of an empty commercial vehicle as the empty vehicle information. The information processing device according to either (50) or (51). (53) The display control unit, after the end of the day's business operations, further displays business evaluation information on the display unit to assess the day's business. The information processing device described in any of (1) to (52) above. (54) The display control unit displays actual sales and virtual sales as part of the sales evaluation information. The information processing device described in (53) above. (55) The display control unit displays the route, including the status of occupied and vacant vehicles, as part of the sales evaluation information. The information processing device described in (53) or (54) above. (56) The display control unit further displays the additional information on the map of the display unit according to the distance or direction of the additional information. An information processing device according to any of (1) to (55) above. (57) The display control unit causes the display unit to display information in the direction of travel in such a way that the amount of information displayed is greater than the amount of information in the opposite direction of travel. An information processing device according to any of (1) to (56) above. (58) Information processing device, The service area of ​​the commercial vehicles is divided into multiple areas, and the passenger demand for each area is predicted. Among these multiple areas, the direction and distance of passenger movement for a particular area of ​​interest are displayed on the display unit as prediction results. Information processing methods. (59) On the computer, The service area of ​​the commercial vehicles is divided into multiple areas, and the passenger demand for each area is predicted. Among these multiple areas, the direction and distance of passenger movement for a particular area of ​​interest are displayed on the display unit as prediction results. A program to execute a process. [Explanation of symbols]

[0419] 1 Prediction system, 11 Taxi, 12 Server, 22 Vehicle management device, 23 Terminal device, 63 Demand forecast mesh, 121 Control unit, 131 Data generation unit, 132 Learning unit, 133 Prediction unit, 141 Control unit, 142 Operation unit, 143 Display unit, 145 Speaker, 146 Microphone, 211 Area of ​​interest frame, 212 Arrow, 221 Pinpoint pick-up location mark, 222 Number of passengers display, 223 Start waiting button, 224 Waiting display, 241 Long display, 251 Distance traveled display, 261 Individual display, 262 Destination display, 301 CPU, 302 ROM, 303 RAM, 306 Input unit, 307 Output unit, 308 Storage unit, 309 Communication section, 310 Drive, 521 No-boarding zone display, 531 Additional information display section, 551 Pick-up location display, 553 Detailed information, 581 List display section, 582 Sort button, 601 Reverse lookup pick-up point display section, 641 Pick-up display button, 642 Passing display button, 643 Dispatch display button, 711 Fare display, 741 Area information display section, 742 Available vehicle information, 751 Icon, 812 Rating score display, 813 Radar chart, 814 Sales revenue graph, 815 Route history display button, 821, 822 Solid line, 831, 832 Additional information

Claims

[Claim 1] The system includes a display control unit that controls the display of a map, including the search results for a recommended route among multiple routes, based on a predetermined score for each route along the path that each of the multiple routes passes through, which is based on passenger demand forecast data for commercial vehicles. Information processing device.

Images