Information processing device and information processing method

Abstract

To improve the prediction accuracy of a predictive movement time predicted for an object vehicle used for an on-demand type vehicle allocation service to require in order to travel a movement route.SOLUTION: According to the application, an information processing device includes an acquisition part for acquiring a predictive travel time calculated by a route retrieval service for calculating a predictive travel time predicted to require to travel a travel route of a vehicle from a departure place to a destination, a determination part for determining a correction coefficient to be used in calculating a predictive movement time predicted to require for an object vehicle to travel the movement route on the basis of an actual time required being a time required for the object vehicle used for the on-demand type vehicle allocation service to actually travel the movement route, and a calculation part for calculating the predictive movement time on the basis of the predictive travel time and the correction coefficient.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and an information processing method.

Background Art

[0002] Conventionally, various techniques for predicting the travel time of a vehicle on a travel route from a departure point to a destination have been known. For example, there is a technique of recording the required time on a route traveled in the past and predicting the required time based on the data traveled in the past when traveling to the same destination on the same route again.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the above conventional technology, since the required time on the route traveled in the past is only recorded and the required time is only predicted based on the data traveled in the past when traveling to the same destination on the same route again, it is not always possible to improve the prediction accuracy of the predicted travel time predicted to be required for the target vehicle used in the on-demand vehicle dispatch service to move along the travel route.

[0005] An object of the present application is to make it possible to improve the prediction accuracy of the predicted travel time predicted to be required for the target vehicle used in the on-demand vehicle dispatch service to move along the travel route.

Means for Solving the Problems

[0006] The information processing device according to this embodiment includes: an acquisition unit that acquires the predicted travel time calculated by a route search service that calculates the predicted travel time that is expected to be required for a vehicle to travel along a route from a departure point to a destination; a determination unit that determines a correction coefficient used when calculating the predicted travel time that is expected to be required for a target vehicle to travel along the travel route, based on the actual required time, which is the time that a target vehicle used in an on-demand ride-hailing service actually travels along a travel route corresponding to the travel route; and a calculation unit that calculates the predicted travel time based on the predicted travel time and the correction coefficient. [Effects of the Invention]

[0007] According to one embodiment, it is possible to improve the accuracy of predicting the estimated travel time that a target vehicle used in an on-demand ride-hailing service is expected to need to travel along a route. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a scatter plot showing the relationship between predicted travel time and actual travel time for the comparative technologies. [Figure 2] Figure 2 shows an example of the configuration of an information processing device according to the embodiment. [Figure 3] Figure 3 is a graph showing the relationship between predicted driving time and predicted travel time according to the embodiment. [Figure 4] Figure 4 is a diagram illustrating the correction coefficient according to the embodiment. [Figure 5] Figure 5 is a diagram illustrating the process for determining the correction coefficient for each region according to the embodiment. [Figure 6] Figure 6 is a flowchart showing the processing procedure by the information processing device according to the embodiment. [Figure 7] Figure 7 is a diagram illustrating the process for determining the correction coefficient for each travel distance in the modified example. [Figure 8]Figure 8 is a hardware configuration diagram showing an example of a computer that implements the functions of an information processing device. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing apparatus and information processing method according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing apparatus and information processing method according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] (Embodiment) [1. Introduction] Conventionally, route search services are known that calculate the estimated travel time required to travel a vehicle's route from a point of origin to a destination. For example, a route search service records map information including the point of origin and destination. For example, the map information includes information about roads that the vehicle can travel on. For example, a route search service accepts the user's specification of the point of origin and destination. Alternatively, instead of accepting the user's specification of the point of origin, the route search service may obtain location information indicating the user's current location from an in-vehicle device installed in the user's vehicle or from the user's terminal device.

[0011] For example, when a route search service receives a specified origin and destination from a user, it refers to map information to search for a vehicle route from the origin to the destination. Next, the route search service calculates the estimated travel time required for the vehicle to travel the searched route. The route search service also provides the user with information regarding the route and estimated travel time. In the following, the route calculated by the route search service may be simply referred to as "route," and the estimated travel time may be simply referred to as "estimated travel time."

[0012] Furthermore, technologies related to on-demand ride-hailing services are already known. Here, an on-demand ride-hailing service is a service that dispatches vehicles capable of carrying multiple passengers in response to requests from users of the on-demand ride-hailing service (hereinafter sometimes referred to as "passengers"). In other words, an on-demand ride-hailing service is a transportation service provided by on-demand buses or shared taxis. In the case of on-demand buses, the driving operations may be performed by an automated driving system installed in the vehicle instead of a driver performing the driving operations.

[0013] Furthermore, in order to provide an on-demand ride-hailing service, it is necessary to determine the operating schedule of the target vehicles used for the on-demand ride-hailing service (hereinafter sometimes simply referred to as "target vehicles"). Specifically, the operating schedule of the target vehicles is determined based on the estimated travel time (hereinafter sometimes simply referred to as "estimated travel time") that is predicted to be required for the target vehicles to travel along the route corresponding to the route. In addition, the estimated travel time may be calculated based on the estimated driving time.

[0014] However, there may be a difference between the actual travel time (hereinafter sometimes abbreviated as "actual travel time"), which is the time it takes for a vehicle used in an on-demand ride-hailing service to actually travel the route corresponding to the travel route, and the predicted travel time. Figure 1 is a scatter plot showing the relationship between predicted travel time and actual travel time for the comparative technology. In Figure 1, the horizontal axis is predicted travel time (in minutes) and the vertical axis is actual travel time (in minutes), and the points corresponding to the data showing the relationship between predicted travel time and actual travel time for the comparative technology are plotted. In Figure 1, when the predicted travel time and actual travel time match, the points corresponding to the data are distributed on the line L1. However, in reality, there are many points distributed at positions far from the line L1. In other words, there are many cases where the difference between predicted travel time and actual travel time is somewhat large.

[0015] For example, the data corresponding to point P1 included in region R1 in the graph shown in FIG. 1 is distributed below the straight line L1, so the actual required time is shorter than the predicted travel time. Specifically, for the data corresponding to point P1, the predicted travel time was 35 minutes, while the actual required time was 17 minutes. That is, for the data corresponding to point P1, the predicted travel time was 18 minutes longer than the actual required time. Thus, the comparative technique tended to calculate a longer predicted travel time compared to the actual required time (i.e., having too much of a margin).

[0016] As described above, the operation schedule of the target vehicle is determined based on the predicted travel time. However, when the difference between the predicted travel time and the actual required time is large, it becomes difficult to establish an efficient operation schedule. Here, an efficient operation schedule refers to an operation schedule that transports more passengers in a shorter time. For example, in the case of the data corresponding to point P1 in FIG. 1, since 18 minutes of the difference between the predicted travel time and the actual required time is wasted, the operation schedule of the target vehicle determined based on the predicted travel time cannot be said to be efficient. Therefore, a technique for improving the prediction accuracy of the predicted travel time that is predicted to be required for the target vehicle used in an on-demand vehicle dispatch service to move along a travel route is desired.

[0017] [2. Configuration Example of Information Processing Apparatus] [[ID=IO]]FIG. 2 is a diagram showing a configuration example of an information processing apparatus according to an embodiment. As shown in FIG. 2, the information processing apparatus according to the embodiment, the information processing apparatus 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing apparatus 100 may have an input unit (e.g., a keyboard, a mouse, etc.) for receiving various operations from an administrator or the like of the information processing apparatus 100, and a display unit (e.g., a liquid crystal display, etc.) for displaying various information.

[0018] (Communication Unit 110) The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from, for example, an in-vehicle device mounted on a target vehicle used for an on-demand vehicle dispatch service. Here, the in-vehicle device is an information processing device used by the driver of the target vehicle. For example, the in-vehicle device may be a terminal device (such as a smartphone) possessed by the driver of the target vehicle.

[0019] (Memory unit 120) The memory unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. For example, the memory unit 120 stores passenger information, reservation information, driving information, and performance information generated by the acquisition unit 131.

[0020] (Control unit 130) The control unit 130 is a controller, and is realized, for example, when various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 100 are executed with the RAM as a working area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. The control unit 130 is also a controller and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0021] The control unit 130 has an acquisition unit 131, a determination unit 132, a calculation unit 133, and a provision unit 134 as functional units, and realizes or executes the information processing operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 2, and other configurations are also possible as long as they perform the information processing described later. Also, each functional unit represents the function of the control unit 130 and does not necessarily have to be physically separated.

[0022] (Acquisition part 131) The acquisition unit 131 acquires attribute information relating to the attributes of users (hereinafter referred to as "passengers") who use the on-demand ride-hailing service. For example, the acquisition unit 131 acquires passenger attribute information from terminal devices used by passengers. For example, the acquisition unit 131 acquires information such as the passenger's age, gender, and residential area as passenger attribute information. When the acquisition unit 131 acquires passenger attribute information, it generates passenger information that associates passenger identifiable information (such as a passenger ID) with the passenger attribute information, and stores the passenger information in the storage unit 120.

[0023] Furthermore, the acquisition unit 131 receives reservation information regarding the details of reservations for the use of target vehicles (hereinafter abbreviated as "target vehicles") used in the on-demand ride-hailing service. For example, the acquisition unit 131 receives reservation information from terminal devices used by passengers. For example, the acquisition unit 131 receives reservation information from each of multiple passengers. For example, the acquisition unit 131 receives information that can identify the passenger (such as a passenger ID), as well as information indicating the departure point, destination, departure time, arrival time, and whether or not ride-sharing is permitted, as reservation information. When the acquisition unit 131 receives reservation information, it generates reservation information that associates the reservation-identifying information (such as a reservation ID) with the reservation information, and stores the reservation information in the storage unit 120.

[0024] Furthermore, the acquisition unit 131 determines the departure and destination of the target vehicle based on the reservation information. Subsequently, once the acquisition unit 131 has determined the departure and destination of the target vehicle, it calls the route search service via API (Application Programming Interface) and uses the route search service to calculate the vehicle's route from the departure to the destination. The acquisition unit 131 also uses the route search service to calculate the estimated travel time required to travel the vehicle's route from the departure to the destination. In this way, the acquisition unit 131 obtains the estimated travel time calculated by the route search service that calculates the estimated travel time required to travel the vehicle's route from the departure to the destination. When the acquisition unit 131 obtains the estimated travel time, it generates travel information that associates information that can identify the travel route (such as a travel route ID), the travel route, and the estimated travel time, and stores the travel information in the storage unit 120.

[0025] Furthermore, the acquisition unit 131 acquires location history information relating to the location information history of the target vehicle from an in-vehicle device installed in the target vehicle. Subsequently, the acquisition unit 131 estimates the actual departure and destination of the target vehicle by comparing the location history information of the target vehicle with information indicating the departure and destination of the target vehicle included in the target vehicle's operating schedule. Furthermore, the acquisition unit 131 estimates the actual travel route of the target vehicle (hereinafter sometimes referred to as the "actual travel route") based on the location history information of the target vehicle and the information indicating the actual departure and destination of the target vehicle. Here, the actual travel route corresponds to the travel route that corresponds to the driving route calculated by the route search service.

[0026] Furthermore, the acquisition unit 131 estimates the departure time (hereinafter sometimes referred to as "actual departure time") when the target vehicle actually left its starting point, based on the location history information of the target vehicle. The acquisition unit 131 also estimates the arrival time (hereinafter sometimes referred to as "actual arrival time") when the target vehicle actually arrived at its destination, based on the location history information of the target vehicle. Subsequently, the acquisition unit 131 calculates the time from the actual departure time to the actual arrival time as the actual travel time. In this way, the acquisition unit 131 obtains the actual travel time, which is the time it took for the target vehicle used in the on-demand ride-hailing service to actually travel along the route corresponding to the travel route. When the acquisition unit 131 obtains the actual travel time, it generates actual information that associates information that can identify the actual travel route (such as a travel route ID), location history information corresponding to the actual travel route, the actual travel time, and information that can identify the travel route corresponding to the actual travel route (such as a travel route ID), and stores the actual information in the storage unit 120.

[0027] (Decision Section 132) Before describing the processing of the determination unit 132, we will explain the correction coefficients used when calculating the predicted travel time that the target vehicle is expected to need to travel along the travel route. Figure 3 is a graph showing the relationship between the predicted driving time and the predicted travel time according to the embodiment. The calculation unit 133 calculates the predicted travel time that the target vehicle is expected to need to travel along the travel route corresponding to the driving route, based on the predicted driving time acquired by the acquisition unit 131. In Figure 3, the calculation unit 133 calculates the predicted travel time using a linear function equation represented by "y = a*x + b", where x is the predicted driving time, y is the predicted travel time, and a and b are the two types of correction coefficients used when calculating the predicted travel time, respectively. In Figure 3, of the two types of correction coefficients, a is called the travel time coefficient. The travel time coefficient a corresponds to the slope of the linear function represented by "y = a*x + b". Also, of the two types of correction coefficients, b is called the boarding preparation coefficient. The boarding preparation coefficient b corresponds to the intercept of the linear function represented by "y = a*x + b".

[0028] Figure 4 is a diagram illustrating the correction coefficient according to the embodiment. In Figure 4, the calculation unit 133 calculates the predicted travel time as "10" minutes when the predicted travel time x is "10" minutes, the travel time coefficient a corresponding to the slope is "1", and the boarding preparation coefficient b corresponding to the intercept is "0". The calculation unit 133 also calculates the predicted travel time as "8" minutes when the predicted travel time x is "10" minutes, the travel time coefficient a corresponding to the slope is "0.8", and the boarding preparation coefficient b corresponding to the intercept is "0". Thus, reducing the travel time coefficient a corresponding to the slope from "1" to "0.8" shortens the predicted travel time calculated by the calculation unit 133 from "10" minutes to "8" minutes. In other words, reducing the travel time coefficient a has the effect of shortening the predicted travel time calculated by the calculation unit 133 (a compression effect when the predicted travel time is large). Furthermore, the calculation unit 133 calculates the predicted travel time as "11 minutes" when the predicted travel time x is "10" minutes, the travel time coefficient a corresponding to the slope is "0.8", and the boarding preparation coefficient b corresponding to the intercept is "3". In this way, increasing the boarding preparation coefficient b corresponding to the intercept from "0" to "3" increases the predicted travel time calculated by the calculation unit 133 from "8" minutes to "11" minutes. In other words, increasing the boarding preparation coefficient b has the effect of increasing the predicted travel time calculated by the calculation unit 133 (the effect of providing more time leeway overall).

[0029] The determination unit 132 determines a correction coefficient used to calculate the predicted travel time that a target vehicle is expected to take to travel along a route, based on the actual travel time, which is the time it actually took for a target vehicle used in an on-demand ride-hailing service to travel along a route corresponding to the travel route. Specifically, the determination unit 132 determines a correction coefficient to reduce the magnitude of the difference between the predicted travel time and the actual travel time. More specifically, the determination unit 132 determines a region-specific correction coefficient based on the region-specific actual travel time for the travel route.

[0030] Figure 5 is a diagram illustrating the process of determining regional correction coefficients according to the embodiment. Figure 5 shows a map MP1 that includes grid regions, which are areas A to F divided into a grid. Areas A to F may be areas divided by administrative districts such as cities, towns, and villages, or areas divided according to characteristics of the area, such as the amount of traffic or the amount of crowding. For example, the determination unit 132 determines a correction coefficient for each grid region based on the actual travel time for each grid region, which are areas divided into a grid with respect to the travel route. For example, the determination unit 132 acquires information on the vehicle's travel route acquired by the acquisition unit 131. The determination unit 132 also refers to the storage unit 120 to acquire map information of the region including the vehicle's travel route acquired by the acquisition unit 131. For example, the determination unit 132 acquires map information that divides the region including the travel route into a grid. Figure 5 shows how the departure point calculated by the route search service is included in grid region A2, and the destination calculated by the route search service is included in grid region B3. Furthermore, the route RT1 of the vehicle from the origin to the destination, calculated by the route search service, shows how it passes through grid areas A2, B1, B2, and B3.

[0031] In Figure 5, the determination unit 132 determines correction coefficients for each of the grid areas A2, B1, B2, and B3 based on the actual travel time in each of the grid areas. Specifically, the determination unit 132 determines the travel time coefficient a1 and the boarding preparation coefficient b1 for grid area A2 based on the actual travel time in grid area A2. For example, the determination unit 132 refers to the actual information in the memory unit 120 and extracts multiple actual information items related to travel routes passing through grid area A2 from the actual information. For example, the determination unit 132 extracts multiple actual information items from the actual information related to travel routes corresponding to the section of grid area A2 in the travel route RT1. Subsequently, the determination unit 132 calculates the actual travel time x1' required for the target vehicle to move within grid area A2 based on each of the extracted multiple actual information items. For example, the determination unit 132 calculates the actual time x1' (hereinafter sometimes referred to as "actual time x1' in grid area A2") required for the target vehicle to travel within grid area A2, based on location history information corresponding to the travel route through grid area A2 and map information that divides the area including the travel route into a grid. For example, the determination unit 132 calculates the actual time x1' in grid area A2 based on the time the target vehicle is located at the starting point in grid area A2 and the time it is located at the intersection of the boundary between grid area A2 and grid area B1 and the travel route RT1. For example, the determination unit 132 calculates the actual time x1' in grid area A2 as the average of the time difference between the time the target vehicle is located at the starting point in grid area A2 and the time it is located at the intersection of the boundary between grid area A2 and grid area B1 and the travel route RT1.

[0032] Furthermore, the decision unit 132 acquires information that can identify the travel route (such as a travel route ID) contained in each of the extracted multiple actual travel information items, and extracts travel information related to the travel route passing through grid area A2 from the travel information in the storage unit 120. For example, the decision unit 132 extracts travel information related to travel route RT1 from the travel information. Subsequently, the decision unit 132 calculates the predicted travel time x1 that is predicted to be required for the target vehicle to travel within grid area A2, based on each of the extracted multiple travel information items. For example, the determination unit 132 calculates the predicted driving time x1 (hereinafter sometimes referred to as "predicted driving time x1 in grid area A2") that the target vehicle is expected to need to travel along the driving route RT1, the total distance of the driving route RT1, and the distance of the driving route RT1 that the target vehicle travels within the grid area A2 (for example, the distance traveled from the starting point in grid area A2 to the intersection of the boundary between grid area A2 and grid area B1 and the driving route RT1).

[0033] Furthermore, when the determination unit 132 calculates the predicted travel time x1 in grid area A2, it uses the linear function equation "y1 = a1*x1 + b1" to calculate the predicted travel time y1 in grid area A2. Specifically, the determination unit 132 substitutes the predicted travel time x1 into the linear function equation "y1 = a1*x1 + b1" to calculate the predicted travel time y1.

[0034] Furthermore, when the determination unit 132 calculates the predicted travel time y1 in grid area A2, it determines the travel time coefficient a1 and the boarding preparation coefficient b1 in grid area A2 in such a way as to minimize the magnitude of the difference between the predicted travel time y1 in grid area A2 and the actual required time x1' in grid area A2. For example, the determination unit 132 uses the least squares method to determine the travel time coefficient a1 and the boarding preparation coefficient b1 that minimize the sum of squares of the difference between the predicted travel time y1 in grid area A2 and the actual required time x1' in grid area A2. For example, the decision unit 132 determines the travel time coefficient a1 and the boarding preparation coefficient b1 in grid region A2 by solving an optimization problem that minimizes the sum of squares of the difference between the predicted travel time y1 and the actual travel time x1' in grid region A2, under the constraints of a first constraint that the predicted travel time y1 must not be more than 5 minutes shorter than the actual travel time x1' (a delay of more than 5 minutes), and a second constraint that the boarding preparation coefficient b1 is a positive number.

[0035] As described above, the determination unit 132 determines the travel time coefficient a1 and the boarding preparation coefficient b1 in grid area A2 based on the actual travel time in grid area A2. Similarly, the determination unit 132 determines the travel time coefficient a2 and the boarding preparation coefficient b2 in grid area B1 based on the actual travel time in grid area B1. Furthermore, the determination unit 132 determines the travel time coefficient a3 and the boarding preparation coefficient b3 in grid area B2 based on the actual travel time in grid area B2. Furthermore, the determination unit 132 determines the travel time coefficient a4 and the boarding preparation coefficient b4 in grid area B3 based on the actual travel time in grid area B3.

[0036] In the example described above, the decision unit 132 determined a correction coefficient for each grid region, which is a grid of regions related to travel routes, as a correction coefficient for each region. However, the correction coefficients for each region are not limited to this. For example, suppose that areas A to F shown in Figure 5 are areas divided by administrative districts. In this case, the decision unit 132 determines a correction coefficient for each area A to F, which is divided by administrative districts, based on the actual travel time in each area. Alternatively, suppose that areas A to F shown in Figure 5 are areas divided according to area characteristics such as the volume of traffic or the amount of crowding. In this case, the decision unit 132 determines a correction coefficient for each area A to F, which is divided according to area characteristics, based on the actual travel time in each area.

[0037] In Figure 3 above, the calculation unit 133 calculates the predicted travel time using a linear function equation represented by "y = a*x + b", and the determination unit 132 determines the travel time coefficient a and the boarding preparation coefficient b based on the actual travel time. However, the calculation unit 133 may calculate the predicted travel time using an equation other than the linear function equation represented by "y = a*x + b", and the determination unit 132 may determine the correction coefficient included in the equation other than the linear function equation represented by "y = a*x + b" based on the actual travel time. For example, the calculation unit 133 may calculate the predicted travel time y using a multidimensional function such as a quadratic or cubic function relating to the predicted travel time x, which includes the correction coefficient. Also, the determination unit 132 may determine the correction coefficient included in the multidimensional function such as a quadratic or cubic function based on the actual travel time.

[0038] (Calculation section 133) The calculation unit 133 calculates the predicted travel time based on the predicted travel time and correction coefficient. Specifically, the calculation unit 133 calculates the predicted travel time based on the correction coefficient for each region. For example, the calculation unit 133 calculates the predicted travel time based on the correction coefficient for each grid region. For example, the calculation unit 133 calculates the predicted travel time for each grid region based on the correction coefficient for each grid region. Subsequently, the calculation unit 133 calculates the total predicted travel time by adding up the predicted travel times for each grid region.

[0039] In Figure 5, the calculation unit 133 calculates the predicted travel time y1'' in grid area A2 based on the travel time coefficient a1 and boarding preparation coefficient b1 in grid area A2 determined by the determination unit 132, and the predicted travel time x1'' in grid area A2. For example, the determination unit 132 calculates the predicted travel time y1'' in grid area A2 by substituting the predicted travel time x1'' in grid area A2 into the linear function equation "y1 = a1 * x1 + b1". Similarly, the calculation unit 133 calculates the predicted travel time y2'' in grid area B1 based on the travel time coefficient a2 and boarding preparation coefficient b2 in grid area B1 determined by the determination unit 132, and the predicted travel time x2'' in grid area B1. Furthermore, the calculation unit 133 calculates the predicted travel time y3'' in grid area B2 based on the travel time coefficient a3 and boarding preparation coefficient b3 in grid area B2 determined by the determination unit 132, and the predicted travel time x3'' in grid area B2. Furthermore, the calculation unit 133 calculates the predicted travel time y4'' in grid area B3 based on the travel time coefficient a4 and boarding preparation coefficient b4 in grid area B3 determined by the determination unit 132, and the predicted travel time x4'' in grid area B3.

[0040] Furthermore, when the calculation unit 133 calculates the predicted travel time y1'' in grid area A2, the predicted travel time y2'' in grid area B1, the predicted travel time y3'' in grid area B2, and the predicted travel time y4'' in grid area B3, it adds the predicted travel time y1'' in grid area A2, the predicted travel time y2'' in grid area B1, the predicted travel time y3'' in grid area B2, and the predicted travel time y4'' in grid area B3 to calculate the predicted travel time that the target vehicle is expected to need to travel along the travel route corresponding to the travel route RT1.

[0041] In the example described above, the calculation unit 133 calculates the predicted travel time for each grid area based on the correction coefficient for each grid area, and then calculates the total predicted travel time by adding the predicted travel times for each grid area. However, the calculation unit 133 is not limited to this process of calculating the predicted travel time based on the correction coefficient for each grid area. For example, the calculation unit 133 calculates the average of the correction coefficients in multiple grid areas, including the travel route, based on the correction coefficient for each grid area. Subsequently, the calculation unit 133 calculates the predicted travel time that is expected to be required to travel along the travel route corresponding to the travel route, based on the average of the correction coefficients in multiple grid areas, including the travel route.

[0042] Furthermore, if the calculation unit 133 calculates the predicted travel time, it determines the operating schedule of the target vehicle based on the predicted travel time. For example, the acquisition unit 131 uses existing technology to determine the operating schedule of the target vehicle based on the predicted travel time to determine the operating schedule of the target vehicle that can carry more passengers in a shorter time.

[0043] (Provider 134) When the calculation unit 133 determines the operating schedule for the target vehicle, the provision unit 134 transmits information regarding the operating schedule determined by the calculation unit 133 to the on-board device installed in the target vehicle. The on-board device receives the information regarding the operating schedule from the information processing device 100. The target vehicle operates according to the operating schedule received by the on-board device.

[0044] [3. Information Processing Procedures] Figure 6 is a flowchart showing the processing procedure by the information processing device according to the embodiment. In Figure 6, the acquisition unit 131 of the information processing device 100 acquires the predicted travel time calculated by a route search service that calculates the predicted travel time required for a vehicle to travel the route from the departure point to the destination (step S101). The determination unit 132 of the information processing device 100 determines a correction coefficient used when calculating the predicted travel time required for a target vehicle to travel the route, based on the actual required time, which is the time it took for a target vehicle used in an on-demand ride-hailing service to actually travel the route corresponding to the travel route (step S102). The calculation unit 133 of the information processing device 100 then calculates the predicted travel time based on the predicted travel time and the correction coefficient (step S103).

[0045] [4. Variations] The processing according to the above-described embodiment may be carried out in various other forms besides those described above.

[0046] Figure 7 is a diagram illustrating the process of determining the correction coefficient for each travel distance in a modified example. In Figure 7, the determination unit 132 determines the correction coefficient for each travel distance based on the actual time required for each travel distance of the target vehicle, which is different from the embodiment described above. Specifically, the determination unit 132 determines the correction coefficient for each travel section based on the actual time required for each travel section obtained by dividing the travel distance of the target vehicle into predetermined distances. In Figure 7, the travel distance of the target vehicle from the departure point to the destination is 15 km, and the correction coefficient for each travel section is determined based on the actual time required for each travel section obtained by dividing the travel distance of the target vehicle into 5 km intervals. Hereafter, the travel section from the departure point at a distance of 0 to 5 km may be referred to as the first travel section, the travel section from the departure point at a distance of 5 to 10 km may be referred to as the second travel section, and the travel section from the departure point at a distance of 10 to 15 km may be referred to as the third travel section.

[0047] Specifically, the decision unit 132 determines the travel time coefficient a5 and the boarding preparation coefficient b5 for the first travel section based on the actual travel time for the first travel section. For example, the decision unit 132 refers to the actual information in the memory unit 120 and extracts multiple actual information items related to the travel route including the first travel section from the actual information. Subsequently, the decision unit 132 calculates the actual travel time x5' required for the target vehicle to travel the first travel section based on each of the extracted multiple actual information items. For example, the decision unit 132 calculates the actual travel time x5' required for the target vehicle to travel the first travel section (hereinafter sometimes referred to as "actual travel time x5' in the first travel section") based on the location history information corresponding to the travel route including the first travel section and the distance of the first travel section. For example, the decision unit 132 calculates the actual travel time x5' in the first travel section based on the departure time of the target vehicle and the time when the target vehicle is located 5 km from the departure point.

[0048] Furthermore, the decision unit 132 acquires information that can identify the travel route (such as a travel route ID) contained in each of the extracted multiple pieces of actual travel information, and extracts travel information related to the travel route including the first travel section from the travel information in the storage unit 120. Subsequently, the decision unit 132 calculates the predicted travel time x 5 that is predicted to be required for the target vehicle to travel the first travel section, based on each of the extracted multiple pieces of travel information. For example, the decision unit 132 calculates the predicted travel time x 5 that is predicted to be required for the target vehicle to travel the travel route including the first travel section (hereinafter sometimes referred to as "predicted travel time x 5 in the first travel section") based on the predicted travel time that is predicted to be required for the target vehicle to travel the travel route including the first travel section, the total distance of the travel route including the first travel section, and the distance (5 km) that the target vehicle travels in the first travel section of the travel route including the first travel section.

[0049] Furthermore, when the determination unit 132 calculates the predicted travel time x5 in the first travel section, it uses the linear function equation "y5 = a5 * x5 + b5" to calculate the predicted travel time y5 in the first travel section. Specifically, the determination unit 132 substitutes the predicted travel time x5 into the linear function equation "y5 = a5 * x5 + b5" to calculate the predicted travel time y5.

[0050] Furthermore, when the determination unit 132 calculates the predicted travel time y5 in the first travel section, it determines the travel time coefficient a5 and the boarding preparation coefficient b5 in the first travel section in such a way that the magnitude of the difference between the predicted travel time y5 and the actual required time x5' in the first travel section is minimized. For example, the determination unit 132 uses the least squares method to determine the travel time coefficient a5 and the boarding preparation coefficient b5 that minimize the sum of squares of the difference between the predicted travel time y5 and the actual required time x5' in the first travel section. For example, the decision unit 132 determines the travel time coefficient a5 and the boarding preparation coefficient b5 for the first travel section by solving an optimization problem that minimizes the sum of squares of the differences between the predicted travel time y5 and the actual travel time x5' for the first travel section, under the constraints of a first constraint that the predicted travel time y5 must not be more than 5 minutes shorter than the actual travel time x5' (a delay of more than 5 minutes), and a second constraint that the boarding preparation coefficient b5 is a positive number.

[0051] As described above, the determination unit 132 determines the travel time coefficient a5 and the boarding preparation coefficient b5 for the first travel section based on the actual travel time in the first travel section. Similarly, the determination unit 132 determines the travel time coefficient a6 and the boarding preparation coefficient b6 for the second travel section based on the actual travel time in the second travel section. Furthermore, the determination unit 132 determines the travel time coefficient a7 and the boarding preparation coefficient b7 for the third travel section based on the actual travel time in the third travel section.

[0052] Furthermore, the calculation unit 133 calculates the predicted travel time based on the correction coefficient for each travel distance. For example, the calculation unit 133 calculates the predicted travel time based on the correction coefficient for each travel section. For example, the calculation unit 133 calculates the predicted travel time for each travel section based on the correction coefficient for each travel section. Subsequently, the calculation unit 133 calculates the total predicted travel time by adding up the predicted travel times for each travel section.

[0053] In the example described above, the determination unit 132 determined a correction coefficient for each travel section obtained by dividing the travel distance of the target vehicle into predetermined distance intervals, but the correction coefficients for each travel distance are not limited to this. For example, the determination unit 132 determines a correction coefficient for each travel distance based on the actual time taken for each travel distance of the target vehicle. For example, the determination unit 132 determines multiple different correction coefficients for each travel distance based on the actual time taken for multiple different travel distances such as 5km, 10km, 15km, etc.

[0054] Furthermore, the determination unit 132 determines a correction coefficient for each category of facility based on the actual travel time for each category of facility located within a predetermined range from the destination of the travel route. For example, the determination unit 132 identifies the categories of facilities located within a predetermined range from the destination of the travel route (e.g., hospitals, airports, or commercial facilities) based on map information including the travel route. Subsequently, the determination unit 132 determines a correction coefficient for each category of identified facility based on the actual travel time for each category of facility. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each category of facility.

[0055] Furthermore, the determination unit 132 determines a correction coefficient for each number of passengers based on the actual travel time for each number of passengers in the target vehicle. For example, the acquisition unit 131 acquires actual information including the number of passengers in the target vehicle in advance and stores it in the storage unit 120. The determination unit 132 refers to the number of passengers in the target vehicle included in the actual information and determines a correction coefficient for each number of passengers based on the actual travel time for each number of passengers in the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each number of passengers.

[0056] Furthermore, the determination unit 132 determines a correction coefficient for each passenger attribute based on the actual travel time for each passenger attribute of the target vehicle. For example, the acquisition unit 131 acquires actual information, including attribute information regarding the passenger attributes of the target vehicle, in advance and stores it in the storage unit 120. The determination unit 132 refers to the passenger attribute information of the target vehicle included in the actual information and determines a correction coefficient for each number of passengers based on the actual travel time for each passenger attribute of the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each passenger attribute.

[0057] Furthermore, the determination unit 132 determines a correction coefficient for each number of boarding and alighting points based on the number of boarding and alighting points where passengers of the target vehicle board and alight. For example, the acquisition unit 131 acquires actual information, including the number of boarding and alighting points where passengers of the target vehicle board and alight, in advance and stores it in the storage unit 120. The determination unit 132 refers to the number of boarding and alighting points of the target vehicle included in the actual information and determines a correction coefficient for each number of passengers based on the actual travel time for each number of boarding and alighting points of the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each number of boarding and alighting points.

[0058] [5. Effects] As described above, the information processing device 100 according to the embodiment comprises an acquisition unit 131, a determination unit 132, and a calculation unit 133. The acquisition unit 131 acquires the predicted travel time calculated by a route search service that calculates the predicted travel time that is expected to be required for a vehicle to travel the route from the departure point to the destination. The determination unit 132 determines a correction coefficient used when calculating the predicted travel time that is expected to be required for a target vehicle to travel the route, based on the actual required time, which is the time that a target vehicle used in an on-demand ride-hailing service actually travels along the route corresponding to the travel route. The calculation unit 133 calculates the predicted travel time based on the predicted travel time and the correction coefficient.

[0059] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time, thereby improving the accuracy of the prediction of the predicted travel time that is expected to be required for a target vehicle used in an on-demand ride-hailing service to travel along a route.

[0060] Furthermore, the determination unit 132 determines a correction coefficient to reduce the magnitude of the difference between the predicted travel time and the actual required time.

[0061] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined to reduce the magnitude of the difference between the predicted travel time and the actual required time, thereby improving the prediction accuracy of the predicted travel time.

[0062] Furthermore, the determination unit 132 determines a correction coefficient for each region based on the actual travel time for each region related to the travel route. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each region.

[0063] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time for each region related to the travel route, thereby improving the accuracy of the predicted travel time.

[0064] Furthermore, the determination unit 132 determines a correction coefficient for each grid region, which is a grid-like division of the region related to the travel route, based on the actual travel time for each grid region. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each grid region.

[0065] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time for each grid region, which is a grid-like division of the region related to the travel route. This improves the accuracy of the predicted travel time prediction.

[0066] Furthermore, the determination unit 132 determines a correction coefficient for each travel distance based on the actual travel time for each distance of the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each travel distance.

[0067] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time for each distance traveled by the target vehicle, thereby improving the accuracy of the predicted travel time.

[0068] Furthermore, the determination unit 132 determines a correction coefficient for each travel section based on the actual travel time for each travel section obtained by dividing the travel distance of the target vehicle into predetermined distances. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each travel section.

[0069] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time for each travel section obtained by dividing the travel distance of the target vehicle into predetermined distances, thereby improving the accuracy of the predicted travel time.

[0070] Furthermore, the determination unit 132 determines a correction coefficient for each category of facility based on the actual travel time for each category of facility located within a predetermined range from the destination of the travel route. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each category of facility.

[0071] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual required time for each category of facility located within a predetermined range from the destination of the travel route, thereby improving the accuracy of the predicted travel time.

[0072] Furthermore, the determination unit 132 determines a correction coefficient for each number of passengers based on the actual travel time for each number of passengers in the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each number of passengers.

[0073] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time for each number of passengers in the target vehicle, thereby improving the accuracy of the predicted travel time.

[0074] Furthermore, the determination unit 132 determines a correction coefficient for each passenger attribute based on the actual travel time for each passenger attribute of the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each passenger attribute.

[0075] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the actual travel time for each attribute of passengers in the target vehicle, thereby improving the accuracy of the predicted travel time.

[0076] Furthermore, the determination unit 132 determines a correction coefficient for each number of boarding and alighting points based on the number of boarding and alighting points where passengers board and alight from the target vehicle. The calculation unit 133 calculates the predicted travel time based on the correction coefficient for each number of boarding and alighting points.

[0077] As a result, the information processing device 100 can calculate the predicted travel time based on a correction coefficient determined based on the number of boarding and alighting points for passengers of the target vehicle, thereby improving the accuracy of the predicted travel time prediction.

[0078] [6. Hardware Configuration] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 8. Figure 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0079] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0080] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 receives data from other devices via a predetermined communication network and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined communication network.

[0081] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600. Note that an MPU (Micro Processing Unit) or GPU (Graphics Processing Unit) may be used instead of the CPU 1100.

[0082] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0083] For example, when computer 1000 functions as an information processing device 100, the CPU 1100 of computer 1000 realizes the functions of the control unit 130 by executing programs loaded onto RAM 1200. The CPU 1100 of computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0084] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0085] [7. Other] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0086] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0087] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent. [Explanation of symbols]

[0088] 100 Information Processing Devices 110 Communications Department 120 Storage section 130 Control Unit 131 Acquisition Department 132 Decision Section 133 Calculation Section 134 Provision Department

Claims

1. An acquisition unit that acquires the predicted driving time calculated by a route search service that calculates the predicted driving time required to travel the vehicle's route from the starting point to the destination, A determination unit that determines a correction coefficient used when calculating the predicted travel time that is predicted to be required for a target vehicle to travel along the travel route, based on the actual travel time, which is the time it took for the target vehicle used in the on-demand ride-hailing service to actually travel along the travel route corresponding to the said travel route, A calculation unit that calculates the predicted travel time based on the predicted travel time and the correction coefficient, Equipped with, The aforementioned determination unit, Based on the actual required time for each region corresponding to the aforementioned travel route, the correction coefficient for each region is determined. The calculation unit described above, Based on the correction coefficient for each region, the predicted travel time is calculated. Information processing device.

2. The aforementioned determination unit, The correction coefficient is determined so as to reduce the magnitude of the difference between the predicted travel time and the actual required time. The information processing apparatus according to claim 1.

3. The aforementioned determination unit, Based on the actual required time for each grid region obtained by dividing the region corresponding to the aforementioned travel route into a grid, the correction coefficient for each grid region is determined. The calculation unit described above, The predicted travel time is calculated based on the correction coefficient for each grid region. The information processing apparatus according to claim 1.

4. The aforementioned determination unit, Based on the actual required time for each distance traveled by the target vehicle, the correction coefficient for each distance traveled is determined. The calculation unit described above, The predicted travel time is calculated based on the correction coefficient for each travel distance. The information processing apparatus according to claim 1.

5. The aforementioned determination unit, Based on the actual time required for each travel section obtained by dividing the travel distance of the target vehicle into predetermined distance intervals, the correction coefficient for each travel section is determined. The calculation unit described above, The predicted travel time is calculated based on the correction coefficient for each travel section. The information processing apparatus according to claim 1.

6. The aforementioned determination unit, Based on the actual required time for each category of facility located within a predetermined range from the destination of the aforementioned travel route, the correction coefficient for each category of facility is determined. The calculation unit described above, The predicted travel time is calculated based on the correction coefficients for each category of facility. The information processing apparatus according to claim 1.

7. The aforementioned determination unit, Based on the actual required time for each number of passengers in the subject vehicle, the correction coefficient for each number of passengers is determined. The calculation unit described above, Based on the correction coefficient for each number of passengers, the predicted travel time is calculated. The information processing apparatus according to claim 1.

8. The aforementioned determination unit, Based on the actual required time for each passenger attribute of the target vehicle, the correction coefficient for each passenger attribute is determined. The calculation unit described above, The predicted travel time is calculated based on the correction coefficient for each of the passenger's attributes. The information processing apparatus according to claim 1.

9. The aforementioned determination unit, Based on the number of boarding and alighting points where passengers board and alight from the aforementioned vehicle, the correction coefficient for each number of boarding and alighting points is determined. The calculation unit described above, The predicted travel time is calculated based on the correction coefficient for each number of boarding / alighting points. The information processing apparatus according to claim 1.

10. An information processing method implemented by a program executed by an information processing device, An acquisition step of obtaining the predicted driving time calculated by a route search service that calculates the predicted driving time required to travel the vehicle's route from the starting point to the destination, A determination step of determining a correction coefficient used when calculating the predicted travel time that is predicted to be required for a target vehicle to travel along the travel route, based on the actual travel time, which is the time it took for the target vehicle used in the on-demand ride-hailing service to actually travel along the travel route corresponding to the said travel route, A calculation step for calculating the predicted travel time based on the predicted travel time and the correction coefficient, Includes, The aforementioned decision-making process is, Based on the actual required time for each region corresponding to the aforementioned travel route, the correction coefficient for each region is determined. The calculation process described above is: Based on the correction coefficient for each region, the predicted travel time is calculated. Information processing methods.

Images