Information processing apparatus and information processing method

Abstract

To make an efficient vehicle allocation plan according to the movement demand of a user who uses an on-demand type vehicle allocation service.SOLUTION: An information processing device according to the present application includes an acquisition unit that acquires travel demand data indicating a travel demand of a user who uses an on-demand vehicle dispatch service, a clustering unit that clusters the travel demand data into a plurality of clusters on the basis of a distance between the travel demand data, and a determination unit that determines vehicle dispatch plan information regarding a vehicle dispatch plan of a vehicle to be allocated to a main travel demand that is a travel demand representing a main cluster that is a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold data number among the plurality of clusters.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an information processing device and an information processing method. [Background technology]

[0002] A technique for creating a vehicle allocation plan for vehicles to be allocated in response to demand from users of a vehicle allocation service that allows ride-sharing is known. For example, a technique is known in which multiple boarding and alighting request data of multiple users who wish to ride-sharing are grouped based on similarities in boarding information or alighting information contained in the boarding and alighting request data, a taxi is assigned to each group, clusters are generated so that the number of passengers in each taxi is equal to or less than a predetermined number, ride-sharing routes are created for the generated clusters, and a vehicle allocation plan is generated based on the travel routes. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-17285 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned conventional technology, multiple boarding and alighting request data of multiple users wishing to share a ride are grouped based on the similarity of the boarding information or alighting information contained in the boarding and alighting request data, a taxi to be dispatched is assigned to each group, clusters are generated so that the number of people riding in each taxi is no more than a predetermined number, ride-sharing routes are created for the generated clusters, and a vehicle dispatch plan is generated based on the driving routes.Therefore, it is not necessarily possible to create an efficient vehicle dispatch plan that meets the transportation needs of users who use on-demand vehicle dispatch services. [Means for solving the problem]

[0005] The information processing device according to the embodiment includes an acquisition unit that acquires travel demand data indicating the travel demand of users who use on-demand vehicle dispatch services; a clustering unit that clusters the travel demand data into multiple clusters based on the distance between the travel demand data; and a determination unit that determines vehicle dispatch plan information regarding a vehicle dispatch plan to be allocated to a major travel demand, which is a travel demand that represents a major cluster among the multiple clusters, that is, a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold number of data. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram showing the transportation demands of users of on-demand vehicle dispatch services. [Figure 2] FIG. 2 is a diagram showing travel demand data and main travel demand data. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram for explaining a method for calculating the distance between travel demand data according to the embodiment. [Figure 6] FIG. 6 is a diagram for explaining a method for calculating the distance between travel demand data according to the embodiment. [Figure 7] FIG. 7 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, a detailed description will be given of an information processing device and an information processing method according to the present application (hereinafter referred to as an "embodiment") with reference to the drawings. Note that the information processing device and the information processing method according to the present application are not limited to the embodiment. Furthermore, the same components in the following embodiments are denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0008] Furthermore, the vehicle allocation plan information according to this embodiment is obtained by solving a mathematical optimization problem. For example, the information processing device according to this embodiment can determine the vehicle allocation plan information by solving an integer programming problem, which is an example of a mathematical optimization problem. Furthermore, for example, the information processing device can determine the vehicle allocation plan information by solving the mathematical optimization problem using a greedy algorithm. Below, as an example, a case will be described in which the information processing device determines the vehicle allocation plan information by solving an integer programming problem.

[0009] (Embodiment) 1. Introduction FIG. 1 is a diagram showing the travel demand of users who use on-demand vehicle dispatch services. On-demand vehicle dispatch services (hereinafter sometimes abbreviated as "vehicle dispatch services") are services that dispatch vehicles according to users' travel demands, such as when, from where, and to where they want to travel. Users make reservations for vehicle dispatch services in advance and use vehicles provided by the vehicle dispatch services. For example, a user makes a reservation for a vehicle dispatch service by transmitting reservation information related to the reservation for the vehicle dispatch service from their own terminal device 10 (FIG. 3) to an information processing device 100 (FIG. 3). Here, the reservation information includes travel demand data indicating the user's travel demand. The travel demand data includes information indicating the user's desired boarding point (also referred to as the departure point), disembarking point (also referred to as the arrival point), boarding time (also referred to as the departure time), disembarking time (also referred to as the arrival time), and the number of users wishing to board. In the following, when there is no need to distinguish between the boarding point and the disembarking point, the boarding point and the disembarking point may be referred to as "boarding and disembarking points."

[0010] The information processing device 100 according to the embodiment receives reservation information from the terminal device 10. The information processing device 100 receives multiple pieces of reservation information from the terminal devices 10 of multiple users. When the information processing device 100 receives multiple pieces of reservation information, it acquires multiple pieces of travel demand data included in each of the multiple pieces of reservation information. When the information processing device 100 acquires multiple pieces of travel demand data, it determines vehicle allocation plan information regarding a vehicle allocation plan to be assigned to each piece of travel demand data based on the multiple pieces of travel demand data. Specifically, when the information processing device 100 acquires multiple pieces of travel demand data, it may represent each piece of travel demand data using multi-dimensional scaling (MDS). Next, the information processing device 100 clusters the travel demand data into multiple clusters based on the distance between the travel demand data. Next, the information processing device 100 determines vehicle allocation plan information regarding a vehicle allocation plan to be assigned to a major travel demand, which is a travel demand of a major cluster, which is a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold data number (e.g., 10). Next, the information processing device 100 determines vehicle allocation plan information regarding a vehicle allocation plan to be allocated to each of a plurality of travel demands belonging to the major cluster, based on vehicle allocation plan information regarding a vehicle allocation plan to be allocated to the major travel demand. This allows the information processing device 100 to efficiently create a vehicle allocation plan to cover the travel demands belonging to the major cluster. Furthermore, the information processing device 100 can separately create a vehicle allocation plan to cover the travel demands belonging to the major cluster and a vehicle allocation plan to cover the travel demands belonging to minor clusters smaller than the major cluster. This allows the information processing device 100 to create an efficient vehicle allocation plan according to the travel demands of users who use on-demand vehicle allocation services.

[0011] When the information processing device 100 determines the vehicle allocation plan information, the information processing device 100 transmits the vehicle allocation plan information to an in-vehicle device mounted on the vehicle. The vehicle is allocated according to the vehicle allocation plan information.

[0012] FIG. 2 is a diagram illustrating travel demand data and major travel demand data. The left and right diagrams of FIG. 2 show a map MP1 of the same region. The left diagram of FIG. 2 shows multiple travel demand data mapped on the map MP1. Each of the multiple lines mapped on the map MP1 represents a respective one of the multiple travel demand data acquired by the information processing device 100. For example, line D11 mapped on the map MP1 represents one travel demand data. For example, line D11 corresponds to a line connecting a boarding point and a disembarking point included in the travel demand data. The right diagram of FIG. 2 shows multiple major travel demand data mapped on the map MP1. Each of the multiple lines mapped on the map MP1 represents one of the multiple major travel demand data corresponding to each of the multiple major travel demands. Here, the major travel demand data is data indicating major travel demand, which is travel demand representing a major cluster, which is a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold data number, among multiple clusters. For example, line MD1 mapped on the map MP1 represents one major travel demand data. For example, the line MD1 corresponds to the line connecting the boarding point and the dropping off point included in the main travel demand data.

[0013] [2. Example of information processing system configuration] Fig. 3 is a diagram showing an example of the configuration of an information processing system 1 according to an embodiment. As shown in Fig. 3, the information processing system 1 includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are connected to each other via a network N so as to be able to communicate with each other via a wired or wireless connection. The network N is, for example, a wide area network (WAN) such as the Internet. Note that the information processing system 1 shown in Fig. 3 may include a plurality of terminal devices 10 and a plurality of information processing devices 100.

[0014] The terminal device 10 is an information processing device used by a user who uses an on-demand vehicle dispatch service. The terminal device 10 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The terminal device 10 displays information received from the information processing device 100 or the like using a web browser or an application. The terminal device 10 transmits reservation information related to a reservation for the vehicle dispatch service to the information processing device 100 in response to an operation by the user.

[0015] The information processing device 100 is an information processing device that performs information processing according to the embodiment, and is realized by, for example, a server device, a cloud system, or the like. The information processing device 100 receives reservation information from a terminal device 10. The information processing device 100 receives multiple pieces of reservation information from the terminal devices 10 of multiple users. When the information processing device 100 receives multiple pieces of reservation information, it acquires multiple pieces of travel demand data included in each of the multiple pieces of reservation information. When the information processing device 100 acquires multiple pieces of travel demand data, it clusters the travel demand data into multiple clusters based on the distance between the travel demand data. Next, the information processing device 100 determines vehicle allocation plan information related to a vehicle allocation plan for vehicles to be allocated to major travel demands, which are travel demands of major clusters, which are clusters among the multiple clusters, where the number of travel demand data belonging to the cluster is equal to or greater than a threshold number of data.

[0016] [3. Configuration example of information processing device] 4 is a diagram showing an example of the configuration of an information processing device according to an embodiment. The information processing device 100 according to the embodiment includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 may also include an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0017] (Communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from, for example, the terminal device 10 and an in-vehicle device (not shown). Here, the in-vehicle device is an information processing device used by the driver of the vehicle. For example, the in-vehicle device may be a terminal device (such as a smartphone) carried by the driver of the vehicle.

[0018] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 stores various programs. For example, the storage unit 120 stores an information processing program according to the embodiment. The storage unit 120 stores information related to the travel demand data acquired by the acquisition unit 131.

[0019] (control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) using RAM as a work area to execute various programs (corresponding to examples of information processing programs) stored in a storage device inside the information processing device 100. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0020] The control unit 130 has an acquisition unit 131, a clustering unit 132, a determination unit 133, and a provision unit 134 as functional units, and realizes or executes the information processing actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may have other configurations as long as they perform the information processing described below. Furthermore, each functional unit indicates a function of the control unit 130, and does not necessarily have to be physically distinct.

[0021] (Acquisition part 131) The acquisition unit 131 acquires travel demand data indicating travel demand of users who use on-demand vehicle dispatch services. Specifically, the acquisition unit 131 receives reservation information from the terminal device 10. The acquisition unit 131 receives multiple pieces of reservation information from the terminal devices 10 of multiple users. When the acquisition unit 131 receives multiple pieces of reservation information, it acquires multiple pieces of travel demand data included in each of the multiple pieces of reservation information. When the acquisition unit 131 acquires multiple pieces of travel demand data, it stores information related to the multiple pieces of travel demand data in the storage unit 120.

[0022] (Clustering unit 132) The clustering unit 132 clusters the travel demand data into multiple clusters based on the distance between the travel demand data. Specifically, the clustering unit 132 calculates a direction vector corresponding to the travel direction indicated by the travel demand data based on the travel demand data, calculates the distance between the travel demand data according to the angle between the direction vectors, and clusters the travel demand data into multiple clusters based on the distance between the travel demand data. For example, the clustering unit 132 acquires information indicating the position coordinates of the boarding point and the disembarking point based on information indicating the boarding point and the disembarking point included in the travel demand data. Next, the clustering unit 132 may calculate a direction vector based on the information indicating the position coordinates of the boarding point and the disembarking point. Next, the clustering unit 132 calculates the angle between the direction vectors. Next, the clustering unit 132 may determine whether the angle between the direction vectors exceeds a threshold angle. For example, the clustering unit 132 calculates the distance between travel demand data using different calculation methods when the angle between the direction vectors exceeds a threshold angle and when the angle between the direction vectors is equal to or smaller than the threshold angle.

[0023] FIG. 5 is a diagram illustrating a method for calculating the distance between travel demand data according to an embodiment. FIG. 5 illustrates a method for calculating the distance between travel demand data D1 and travel demand data D2. The travel demand data D1 includes information indicating a boarding point PT11 and a drop-off point PT12. The clustering unit 132 calculates a direction vector V1 corresponding to the travel direction of the travel demand data D1 by subtracting the position coordinates of the boarding point PT11 from the position coordinates of the drop-off point PT12. The travel demand data D2 includes information indicating a boarding point PT21 and a drop-off point PT22. The clustering unit 132 calculates a direction vector V2 corresponding to the travel direction of the travel demand data D2 by subtracting the position coordinates of the boarding point PT21 from the position coordinates of the drop-off point PT22. Next, the clustering unit 132 calculates an angle θ between the direction vector V1 and the direction vector V2. The clustering unit 132 may determine whether the angle θ between the direction vector V1 and the direction vector V2 exceeds a threshold angle.

[0024] When the clustering unit 132 determines that the angle θ between the direction vector V1 and the direction vector V2 exceeds the threshold angle, it calculates a travel time ΔT1 required for a vehicle to travel the distance between the boarding point PT11 indicated in the travel demand data D1 and the boarding point PT21 indicated in the travel demand data D2. When the clustering unit 132 determines that the angle θ between the direction vector V1 and the direction vector V2 exceeds the threshold angle, it calculates a travel time ΔT2 required for a vehicle to travel the distance between the drop-off point PT12 indicated in the travel demand data D1 and the drop-off point PT22 indicated in the travel demand data D2. For example, the clustering unit 132 calculates the travel time required for a vehicle to travel the distance between the two boarding and alighting points by dividing the distance between the two boarding and alighting points by the average speed of the vehicle. When the clustering unit 132 determines that the angle θ between the direction vector V1 and the direction vector V2 exceeds the threshold angle, it calculates a time difference ΔT3 between the boarding time included in the travel demand data D1 and the boarding time included in the travel demand data D2. Furthermore, the clustering unit 132 calculates the sum of the travel time ΔT1, the travel time ΔT2, and the difference time ΔT3 as the distance between the travel demand data D1 and the travel demand data D2.

[0025] As described in FIG. 5, when the angle between the direction vectors exceeds a threshold angle, the clustering unit 132 calculates the distance between the travel demand data based on the vehicle travel time between the boarding points indicated by the travel demand data, the vehicle travel time between the disembarking points indicated by the travel demand data, and the difference in the travel time indicated by the travel demand data. The clustering unit 132 clusters the travel demand data into multiple clusters based on the distance between the travel demand data. For example, the clustering unit 132 clusters the travel demand data into multiple clusters so that the distance between the travel demand data belonging to each of the multiple clusters is equal to or less than a predetermined distance. The clustering unit 132 clusters the travel demand data into multiple clusters using a known clustering technique.

[0026] FIG. 6 is a diagram illustrating a method for calculating the distance between travel demand data according to an embodiment. FIG. 6 illustrates a method for calculating the distance between travel demand data D1 and travel demand data D2 when the angle θ between the direction vector V1 and the direction vector V2 shown in FIG. 5 is equal to or smaller than a threshold angle. When the clustering unit 132 determines that the angle θ between the direction vector V1 and the direction vector V2 is equal to or smaller than a threshold angle, the clustering unit 132 calculates the total travel time of a vehicle along each of the travel routes indicated by the travel demand data D1 and the travel routes indicated by the travel demand data D2. For example, the clustering unit 132 calculates the total time (t2+t4) of the travel time t2 for a vehicle to travel along the travel route from the boarding point PT11 to the disembarking point PT12 indicated by the travel demand data D1 and the travel time t4 for a vehicle to travel along the travel route from the boarding point PT21 to the disembarking point PT22 indicated by the travel demand data D2. For example, the clustering unit 132 may search for a travel route from the boarding point to the disembarking point indicated by the travel demand data. Next, the clustering unit 132 may calculate the travel time of the vehicle on the travel route indicated by the travel demand data by dividing the distance corresponding to the searched travel route by the average speed of the vehicle. Note that the clustering unit 132 may calculate the straight-line distance from the boarding point to the disembarking point indicated by the travel demand data. Next, the clustering unit 132 may calculate the travel time of the vehicle on the travel route indicated by the travel demand data by dividing the straight-line distance by the average speed of the vehicle.

[0027] Furthermore, when the clustering unit 132 determines that the angle θ between the direction vector V1 and the direction vector V2 is equal to or smaller than a threshold angle, it calculates the shortest travel time, which is the travel time of a vehicle along the shortest route in the event of a carpooling scenario. For example, the clustering unit 132 calculates the shortest route in the event of a carpooling scenario. Next, the clustering unit 132 calculates the shortest travel time by dividing the distance corresponding to the shortest route by the average speed of the vehicle. In FIG. 6, the clustering unit 132 calculates the shortest route as a travel route that starts from the boarding point PT21, travels from the boarding point PT21 to the boarding point PT11, travels from the boarding point PT11 to the disembarking point PT12, and travels from the disembarking point PT12 to the disembarking point PT22. Next, the clustering unit 132 calculates a vehicle travel time t1 on the travel route from the boarding point PT21 to the boarding point PT11, a vehicle travel time t2 on the travel route from the boarding point PT11 to the disembarking point PT12, and a vehicle travel time t3 on the travel route from the disembarking point PT12 to the disembarking point PT22. For example, the clustering unit 132 may search for a travel route between two points included in the shortest route. The clustering unit 132 may calculate the vehicle travel time on the searched travel route by dividing the distance corresponding to the searched travel route by the average speed of the vehicle. The clustering unit 132 may calculate the vehicle travel time on the travel route between two points included in the shortest route by dividing the straight-line distance between the two points included in the shortest route by the average speed of the vehicle. The clustering unit 132 also calculates the sum of the travel time t1, the travel time t2, and the travel time t3 as the shortest travel time. In addition, the clustering unit 132 calculates the difference ΔT4 between the total time (t2 + t4) of the vehicle travel time on each of the travel routes indicated by the travel demand data D1 and the travel routes indicated by the travel demand data D2 and the shortest travel time (t1 + t2 + t3), which is the vehicle travel time on the shortest route when carpooling is assumed.

[0028] Furthermore, when the clustering unit 132 determines that the angle θ between the direction vector V1 and the direction vector V2 is equal to or smaller than the threshold angle, it calculates the difference time ΔT3 between the boarding time included in the travel demand data D1 and the boarding time included in the travel demand data D2. Furthermore, the clustering unit 132 calculates the sum of the difference time ΔT4 and the difference time ΔT3 as the distance between the travel demand data D1 and the travel demand data D2.

[0029] 6, when the angle between the direction vectors is equal to or smaller than the threshold angle, the clustering unit 132 calculates the distance between the travel demand data based on the difference between the total vehicle travel time on each of the multiple travel routes indicated by each of the multiple travel demand data and the shortest travel time, which is the vehicle travel time on the shortest route assuming carpooling, and the difference in riding time indicated by the travel demand data. The clustering unit 132 clusters the travel demand data into multiple clusters based on the distance between the travel demand data.

[0030] (Decision unit 133) The determination unit 133 determines vehicle allocation plan information related to a vehicle allocation plan to be allocated to a major travel demand, which is a travel demand that represents a major cluster, which is a cluster having a number of travel demand data belonging to the cluster equal to or greater than a threshold number of data, among the multiple clusters. For example, the determination unit 133 identifies a major cluster, which is a cluster having a number of travel demand data belonging to the cluster equal to or greater than a threshold number of data, among the multiple clusters clustered by the clustering unit 132. Next, the determination unit 133 calculates the center of gravity of each major cluster. For example, the determination unit 133 calculates the center of gravity of each major cluster by adding up all coordinates of the travel demand data belonging to the major cluster, expressed using multidimensional scaling, and dividing the sum by the number of travel demand data belonging to the major cluster. Furthermore, the determination unit 133 determines the travel demand data corresponding to the center of gravity of the major cluster as the major travel demand data.

[0031] Furthermore, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem that finds a solution that minimizes the value of an objective function indicating the sum of travel times of M vehicles when N (N is a natural number) major travel demands are met in K (K is a natural number) time intervals using M (a predetermined number of vehicles, M is a natural number) vehicles. The determination unit 133 determines the vehicle allocation plan information by solving a mathematical optimization problem that finds a solution that minimizes the value of an objective function indicating the sum of travel times of M vehicles. For example, the determination unit 133 determines the vehicle allocation plan information by solving an integer programming problem as an example of a mathematical optimization problem. Note that the determination unit 133 may determine the vehicle allocation plan information by solving the mathematical optimization problem using a greedy algorithm. Below, a case where the determination unit 133 determines the vehicle allocation plan information by solving an integer programming problem will be described as an example.

[0032] First, divide the time period you want to consider (for example, 10:00 to 11:00) into a fixed time interval dT (for example, 10 minutes). Divide the time interval you want to consider into K parts, and define the K divided time intervals T k The set T is expressed by the following formula (1).

[0033]

number

[0034] Each time interval T k Let k (k is a natural number between 1 and K) be the index corresponding to T k is simply denoted as k. T k is the k-th time interval and is expressed by the following equation (2). k =t0+kdT.

[0035]

number

[0036] In addition, if the number of boarding and alighting points included in the main travel demand data indicating the main travel demand in the time period of interest is I (I is a natural number greater than or equal to 2), then the number of boarding and alighting points s i The set S is expressed by the following formula (3).

[0037]

number

[0038] Each boarding and disembarking point i Let i (i is a natural number between 1 and I) be the index corresponding to s i is simply denoted as i.

[0039] The function representing the geographical distance between boarding and alighting points is expressed by the following equation (4). i ,s i )=0.

[0040]

number

[0041] The function representing the travel time of a vehicle between boarding and alighting points is expressed by the following equation (5). i ,s i )=0.

[0042]

number

[0043] In addition, the edges between the boarding and alighting points that the vehicle can move between in a time step dT (also called one step) are extracted as movable edges. j The set E is expressed by the following formula (6).

[0044]

number

[0045] Each movable edge e j Let j (j is a natural number from 1 to J) be the index corresponding to e j is simply written as j. Also, e j is the starting point s org From destination point dst It is defined as a directed edge towards , and is expressed by the following formula (7). org =s dst The self-cyclic edge such that is always included in the set E.

[0046]

number

[0047] The connection matrix representing the connection relationship between the accessible edge j and the boarding / alighting point i is expressed by the following formulas (8) and (9).

[0048]

number

[0049]

number

[0050] However, each element of the matrices in equations (8) and (9) satisfies the following equations (10) and (11), respectively.

[0051]

number

[0052]

number

[0053] For simplicity, the distance between the boarding and alighting points corresponding to the movable edge j is expressed by the following formula (12): The travel time between the boarding and alighting points corresponding to the movable edge j is expressed by the following formula (13):

[0054]

number

[0055]

number

[0056] Also, all vehicles have the same speed performance and can move along edges extracted as movable edges in time increments of dT. There are M vehicles. The set M of M vehicles is expressed by the following equation (14).

[0057]

number

[0058] Each vehicle v m Let m (m is a natural number between 1 and M) be the index corresponding to v m is simply denoted as m.

[0059] Also, each vehicle v m There is an initial position for vehicle v. m The set of initial positions S init is expressed by the following equation (15).

[0060]

number

[0061] In addition, each vehicle has a maximum number of passengers that can ride at one time (also called the maximum number of passengers or maximum load capacity). m Number of passengers q m The set Q is expressed by the following equation (16).

[0062]

number

[0063] Each vehicle is located at an initial position at an initial time t0, picks up passengers up to the maximum number of passengers allowed, and moves between boarding and disembarking points along the movable edge to transport the passengers.

[0064] In addition, N main travel demand data r indicating each of N main travel demands (N is a natural number) in the time period to be considered n The set R is expressed by the following equation (17).

[0065]

number

[0066] Each major travel demand data n Let n (n is a natural number from 1 to N) be the index corresponding to n is simply expressed as n. Also, the main travel demand data r n is a candidate CS for the departure point (also called the departure boarding / alighting point). dpt n ,candidate CS of arrival point (also called arrival boarding / alighting point) arv n , candidate departure time CT dpt n , arrival time candidate CT arv n and the number of passengers wishing to board q n Specifically, it represents a collection of major travel demand data r n is expressed by the following equation (18).

[0067]

number

[0068] For example, C.S. dpt ni When CS = 1, the main travel demand n is allowed to board at boarding / alighting point i. Similarly, CS arv ni When CT = 1, the main travel demand n is allowed to get off at the boarding / alighting point i. dpt nindicates whether the departure time is available. For example, CT dpt nk When t = 1, passengers of primary travel demand n desire to depart at time interval k. That is, at the start time t k-1 Candidates for starting point (CS dpt ni = 1, it means that the vehicle can reach any boarding / alighting point i) and depart. arv nk When t = 1, passengers of primary travel demand n want to arrive at time interval k. That is, at the end time t of time interval k k Destination candidate (CS arv ni = 1.

[0069] Next, when the above information is given, the decision variables of the optimization problem for allocating vehicle m to major travel demand n are defined as follows. Specifically, five binary variables are defined as decision variables for the optimization problem. The determination unit 133 determines vehicle dispatch plan information including information indicated by each of the five binary variables by solving the optimization problem with the following five binary variables as decision variables.

[0070] First, the binary variable indicating whether a certain vehicle m will depart after picking up passengers at pick-up / drop-off point i for primary travel demand n is expressed by the following equation (19). Also, the binary variable indicating whether a certain vehicle m will arrive after picking up / drop-off point i for primary travel demand n is expressed by the following equation (20).

[0071]

number

[0072]

number

[0073] The determination unit 133 determines vehicle allocation plan information by solving an optimization problem including, as decision variables, a binary variable (Equation (19)) indicating whether a predetermined vehicle m among a predetermined number (M vehicles) of vehicles will depart with a passenger boarding at a predetermined boarding / alighting point i among boarding / alighting points included in main travel demand data indicating a main travel demand for a main travel demand, for a main travel demand n, and a binary variable (Equation (20)) indicating whether the predetermined vehicle m will arrive with a passenger disembarking at a predetermined boarding / alighting point i among boarding / alighting points included in main travel demand data indicating a main travel demand for a main travel demand for a main travel demand. For example, the determination unit 133 determines vehicle allocation plan information including information (corresponding to the solution of Equation (19)) indicating whether a predetermined vehicle m among a predetermined number (M vehicles) of vehicles will depart with a passenger boarding at a predetermined boarding / alighting point i among boarding / alighting points included in main travel demand data indicating a main travel demand for a main travel demand, for a main travel demand n, and information (corresponding to the solution of Equation (20)) indicating whether the predetermined vehicle m will arrive with a passenger disembarking at a predetermined boarding / alighting point i among boarding / alighting points included in main travel demand data indicating a main travel demand for a main travel demand for a main travel demand for a main travel demand for a main travel demand.

[0074] Furthermore, the binary variable indicating whether a certain vehicle m departs at time k with passengers boarding for primary travel demand n is expressed by the following equation (21). Furthermore, the binary variable indicating whether a certain vehicle m arrives at time k with passengers disembarking for primary travel demand n is expressed by the following equation (22).

[0075]

number

[0076]

number

[0077] The determination unit 133 determines vehicle allocation plan information by solving an optimization problem including, as decision variables, a binary variable (Equation (21)) indicating whether a predetermined vehicle m among a predetermined number (M vehicles) of vehicles departs with a passenger boarding and a binary variable (Equation (22)) indicating whether the predetermined vehicle m arrives with a passenger disembarking, in a predetermined time interval k among a plurality of time intervals included in a time slot to be processed, in response to a major travel demand n. For example, the determination unit 133 determines vehicle allocation plan information including information (corresponding to the solution of Equation (21)) indicating whether a predetermined vehicle m among a predetermined number (M vehicles) of vehicles departs with a passenger boarding and a passenger disembarking, in a predetermined time interval k among a plurality of time intervals included in a time slot to be processed, in response to a major travel demand n, and information (corresponding to the solution of Equation (22)) indicating whether the predetermined vehicle m among a predetermined number (M vehicles) of vehicles departs with a passenger boarding and a passenger disembarking, in response to a major travel demand n, in a predetermined time interval k among a plurality of time intervals included in a time slot to be processed.

[0078] Moreover, a binary variable indicating whether a vehicle m passes through a movable edge j at time k is expressed by the following equation (23).

[0079]

number

[0080] The determination unit 133 determines vehicle allocation plan information by solving an optimization problem including, as a decision variable, a binary variable (Equation (23)) indicating whether a predetermined vehicle m among a predetermined number of vehicles (M vehicles) passes through a movable edge j, which is a section between a first and a second boarding and alighting point among boarding and alighting points included in main travel demand data indicating main travel demand and is a section that can be traveled within a time corresponding to the predetermined time interval, during a predetermined time interval k among a plurality of time intervals included in the time period to be processed. For example, the determination unit 133 determines vehicle allocation plan information including information (corresponding to the solution of Equation (23)) indicating whether a predetermined vehicle m among a predetermined number of vehicles (M vehicles) passes through a movable edge j, which is a section between a first and a second boarding and alighting point among boarding and alighting points included in main travel demand data indicating main travel demand and is a section that can be traveled within a time corresponding to the predetermined time interval, during a predetermined time interval k among a plurality of time intervals included in the time period to be processed.

[0081] Furthermore, the movement of vehicle m involves a monetary cost, which is proportional to the distance of the edge traveled by vehicle m. If the proportionality constant is represented by ρ, the movement cost of vehicle m is expressed by the following equation (24).

[0082]

number

[0083] From equation (24), the objective function indicating the total travel cost of M vehicles is expressed by the following equation (25).

[0084]

number

[0085] The determination unit 133 determines the vehicle allocation plan information by solving an optimization problem to obtain a solution that minimizes the value of an objective function (Equation (25)) that indicates the total travel cost of a predetermined number (M vehicles).

[0086] Furthermore, for every major travel demand n, a departure point, an arrival point, a departure time, and an arrival time are always assigned. That is, a vehicle allocation plan for vehicles that can accept every major travel demand n is obtained. Specifically, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem in which the constraint conditions are that a departure point, an arrival point, a departure time, and an arrival time are assigned for each major travel demand n. For example, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem in which the constraint conditions are the following equations (26) to (29).

[0087]

number

[0088]

number

[0089]

number

[0090]

number

[0091] Furthermore, for all major travel demands n, when a boarding event occurs in a certain vehicle m, a disembarking event always occurs from that vehicle m. Furthermore, a disembarking event occurs after a boarding event. Specifically, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem with the constraint that an event occurs in which a specific vehicle m departs with a user boarding, followed by an event in which a specific vehicle m arrives with a user disembarking. For example, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem with the constraints of the following equations (30) to (33):

[0092]

number

[0093]

number

[0094]

number

[0095]

number

[0096] Furthermore, the total number of passengers (users) carried by each vehicle m in all time intervals k does not exceed the number of passengers that can be accommodated by that vehicle m. Specifically, the determination unit 133 determines the number of passengers q who will board a given vehicle m in each of a plurality of time intervals included in the time period to be processed. n The number of passengers that can be accommodated in a given vehicle m is q. m The vehicle allocation plan information is determined by solving an optimization problem with the following constraint: For example, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem with the following equation (34) as a constraint.

[0097]

number

[0098] Furthermore, when focusing on an arbitrary boarding / alighting point i, if there is inflow through an edge connected in the previous step k-1, there is also outflow through an edge connected in step k. Specifically, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem in which the constraint condition is that a predetermined vehicle moves along adjacent movable edges in adjacent time intervals among multiple time intervals included in the time period to be processed. For example, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem in which the constraint conditions are the following equations (35) to (36).

[0099]

number

[0100]

number

[0101] Also, when I thought about the ride event, x dt mnk For vehicle m, major travel demand n, and time interval k such that x = 1, the location of vehicle m must be the starting point. Similarly, when considering a drop-off event, x ap mnk For vehicle m, major travel demand n, and time interval k such that ∑ m = 1, the position of vehicle m must be the arrival point. Specifically, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem with a constraint that when a given vehicle m departs or arrives at a major travel demand n in a given time interval k after picking up or dropping off a passenger, the given vehicle m is located at the departure point or arrival point of the major travel demand n. For example, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem with constraints that are Equations (38) and (39), which are obtained by expressing the following Equation (37) using a sufficiently large dummy constant L. Note that the above-described embodiment is merely an example and is not limited to this. Specifically, the determination unit 133 may determine the vehicle allocation plan information by solving a mathematical optimization problem other than an integer programming problem.

[0102]

number

[0103]

number

[0104]

number

[0105] (Provider 134) The providing unit 134 provides the vehicle allocation plan information determined by the determining unit 133. For example, the providing unit 134 may provide the vehicle allocation plan information to an in-vehicle device mounted on a vehicle used for an on-demand vehicle allocation service.

[0106] [4. Effects] As described above, the information processing device 100 according to the embodiment includes the acquisition unit 131, the clustering unit 132, and the determination unit 133. The acquisition unit 131 acquires travel demand data indicating travel demands of users who use on-demand vehicle dispatch services. The clustering unit 132 clusters the travel demand data into multiple clusters based on the distance between the travel demand data. The determination unit 133 determines vehicle dispatch plan information related to a vehicle dispatch plan to be allocated to a major travel demand, which is a travel demand that represents a major cluster, which is a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold number of data, among the multiple clusters.

[0107] This allows the information processing device 100 to efficiently create a vehicle dispatch plan that covers travel demand belonging to the major cluster. Furthermore, the information processing device 100 can separately create a vehicle dispatch plan that covers travel demand belonging to the major cluster and a vehicle dispatch plan that covers travel demand belonging to minor clusters that are smaller than the major cluster. This allows the information processing device 100 to create an efficient vehicle dispatch plan that meets the travel demand of users who use on-demand vehicle dispatch services.

[0108] In addition, the clustering unit 132 calculates a direction vector corresponding to the direction of travel indicated by the travel demand data based on the travel demand data, calculates the distance between the travel demand data according to the angle between the direction vectors, and clusters the travel demand data into multiple clusters based on the distance between the travel demand data.

[0109] Generally, when the angle between the direction vectors is large, the difference in direction between the travel demand data is large, and therefore it is considered that ride-pooling is not effective. On the other hand, when the angle between the direction vectors is small, the difference in direction between the travel demand data is small, and therefore it is considered that ride-pooling is effective. As a result, when the angle between the direction vectors is large, ride-pooling is not effective, and therefore the information processing device 100 can calculate the distance between the travel demand data without taking ride-pooling into consideration. On the other hand, when the angle between the direction vectors is small, ride-pooling is effective, and therefore it is possible for the information processing device 100 to calculate the distance between the travel demand data while taking ride-pooling into consideration.

[0110] In addition, when the angle between the direction vectors exceeds a threshold angle, the clustering unit 132 calculates the distance between the travel demand data based on the vehicle travel time between the boarding points indicated by the travel demand data, the vehicle travel time between the disembarking points indicated by the travel demand data, and the difference in the boarding time indicated by the travel demand data, and clusters the travel demand data into multiple clusters based on the distance between the travel demand data.

[0111] As a result, when the angle between the direction vectors is large, the information processing device 100 can calculate the distance between the travel demand data without taking into consideration carpooling, since carpooling is not effective.

[0112] Furthermore, when the angle between the direction vectors is equal to or less than a threshold angle, the clustering unit 132 calculates the distance between the travel demand data based on the difference between the total vehicle travel time on each of the multiple travel routes indicated by each of the multiple travel demand data and the shortest travel time, which is the vehicle travel time on the shortest route assuming vehicle sharing, and the difference in riding time indicated by the travel demand data, and clusters the travel demand data into multiple clusters based on the distance between the travel demand data.

[0113] As a result, when the angle between the direction vectors is small, carpooling is effective, and therefore the information processing device 100 can calculate the distance between the travel demand data taking carpooling into consideration.

[0114] In addition, the determination unit 133 determines vehicle dispatch plan information including information indicating whether a predetermined vehicle out of a predetermined number of vehicles will depart with a passenger on board and information indicating whether the vehicle will arrive with a passenger off at a predetermined boarding and alighting point out of the boarding and alighting points included in the main travel demand data indicating the main travel demand, in response to the main travel demand.

[0115] This enables the information processing device 100 to determine efficient vehicle dispatch plan information including information indicating whether a specified vehicle will depart with passengers boarding at a specified boarding / disembarking point and information indicating whether a specified vehicle will arrive with passengers disembarking.

[0116] In addition, the determination unit 133 determines vehicle dispatch plan information including information indicating whether a predetermined vehicle out of a predetermined number of vehicles will depart with passengers on board and information indicating whether a predetermined vehicle will arrive with passengers off in a predetermined time section out of a plurality of time sections included in the time period to be processed, in response to the main travel demand.

[0117] This enables the information processing device 100 to determine efficient vehicle dispatch plan information including information indicating whether a specified vehicle will depart with passengers on board and information indicating whether a specified vehicle will arrive with passengers off during a specified time period for a major travel demand.

[0118] In addition, the determination unit 133 determines vehicle allocation plan information including information indicating whether a specified vehicle among a predetermined number of vehicles will pass through a movable edge, which is a section between a first and a second boarding and alighting point among boarding and alighting points included in the main travel demand data indicating main travel demand, during a specified time period among multiple time periods included in the time period to be processed, and which is a section that can be traveled within the time corresponding to the specified time period.

[0119] This allows the information processing device 100 to determine efficient vehicle allocation plan information including information indicating whether a predetermined vehicle will pass through a movable edge in a predetermined time interval.

[0120] Furthermore, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem that finds a solution that minimizes the value of an objective function that indicates the total sum of travel costs for a predetermined number of vehicles.

[0121] This allows the information processing device 100 to efficiently determine vehicle allocation plan information so as to reduce the total travel cost of a predetermined number of vehicles.

[0122] Furthermore, the determination unit 133 determines vehicle allocation plan information by solving an optimization problem in which the constraints are that a departure point, an arrival point, a departure time, and an arrival time are assigned for each of the major travel demands.

[0123] This allows the information processing device 100 to solve the optimization problem under appropriate constraint conditions, and therefore, to appropriately determine vehicle allocation plan information.

[0124] In addition, the determination unit 133 determines the vehicle dispatch plan information by solving an optimization problem in which the constraint condition is that an event occurs in which a specified vehicle departs with passengers on board, and then an event occurs in which a specified vehicle arrives with passengers off.

[0125] This allows the information processing device 100 to solve the optimization problem under appropriate constraint conditions, and therefore, to appropriately determine vehicle allocation plan information.

[0126] In addition, the determination unit 133 determines the vehicle dispatch plan information by solving an optimization problem in which the constraint is that the number of passengers boarding a specified vehicle is equal to or less than the number of passengers that the specified vehicle can accommodate in each of multiple time intervals included in the time period to be processed.

[0127] This allows the information processing device 100 to solve the optimization problem under appropriate constraint conditions, and therefore, to appropriately determine vehicle allocation plan information.

[0128] In addition, the determination unit 133 determines the vehicle allocation plan information by solving an optimization problem in which a constraint is that a specified vehicle moves between adjacent movable edges in adjacent time intervals among multiple time intervals included in the time period to be processed.

[0129] This allows the information processing device 100 to solve the optimization problem under appropriate constraint conditions, and therefore, to appropriately determine vehicle allocation plan information.

[0130] In addition, the determination unit 133 determines the vehicle dispatch plan information by solving an optimization problem with a constraint that, when a specified vehicle departs or arrives with passengers boarding or disembarking within a specified time interval for a major travel demand, the specified vehicle is located at the departure point or arrival point of the major travel demand.

[0131] This allows the information processing device 100 to solve the optimization problem under appropriate constraint conditions, and therefore, to appropriately determine vehicle allocation plan information.

[0132] [5. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 7. Fig. 7 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, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0133] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0134] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0135] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via an input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600. Note that an MPU (Micro Processing Unit) or a GPU (Graphics Processing Unit) may be used instead of the CPU 1100.

[0136] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0137] For example, when the computer 1000 functions as the information processing device 100, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0138] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0139] [6. 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 using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0140] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0141] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content. [Explanation of symbols]

[0142] 100 Information processing device 110 Communications Department 120 Storage section 130 Control Unit 131 Acquisition Department 132 Clustering Department 133 Decision Section 134 Provision Department

Claims

1. an acquisition unit that acquires travel demand data indicating travel demands of users who use on-demand vehicle dispatch services; a clustering unit that clusters the travel demand data into a plurality of clusters based on the distances between the travel demand data; a determination unit that determines vehicle allocation plan information related to a vehicle allocation plan to be allocated to a major travel demand that is a travel demand representative of a major cluster, which is a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold data number, among the plurality of clusters; An information processing device comprising:

2. The clustering unit Based on the travel demand data, a direction vector corresponding to the travel direction indicated by the travel demand data is calculated, and the distance between the travel demand data is calculated according to the angle formed by the direction vectors, and the travel demand data is clustered into a plurality of clusters based on the distance between the travel demand data. The information processing device according to claim 1 .

3. The clustering unit If the angle between the direction vectors exceeds a threshold angle, the distance between the travel demand data is calculated based on the travel time of the vehicle between the boarding points indicated by the travel demand data, the travel time of the vehicle between the disembarking points indicated by the travel demand data, and the difference in the travel time indicated by the travel demand data, and the travel demand data is clustered into a plurality of clusters based on the distance between the travel demand data. The information processing device according to claim 2 .

4. The clustering unit If the angle between the direction vectors is equal to or less than a threshold angle, the distance between the travel demand data is calculated based on the difference between the total travel time of the vehicle on each of a plurality of travel routes indicated by each of the plurality of travel demand data and the shortest travel time, which is the travel time of the vehicle on the shortest route assuming carpooling of the vehicle, and the difference in riding time indicated by the travel demand data, and the travel demand data is clustered into a plurality of clusters based on the distance between the travel demand data. The information processing device according to claim 2 .

5. The determination unit determining the vehicle allocation plan information including information indicating whether a predetermined vehicle out of a predetermined number of vehicles will depart with the user boarding and whether the vehicle will arrive with the user disembarking at a predetermined boarding and disembarking point out of the boarding and disembarking points included in the main travel demand data indicating the main travel demand in response to the main travel demand; The information processing device according to claim 1 .

6. The determination unit determining the vehicle allocation plan information, which includes information indicating whether a predetermined vehicle out of a predetermined number of vehicles will depart with the user on board and information indicating whether the vehicle will arrive with the user off during a predetermined time period out of a plurality of time periods included in the time period to be processed, in response to the major travel demand; The information processing device according to claim 1 .

7. The determination unit determine the vehicle allocation plan information including information indicating whether a predetermined vehicle out of a predetermined number of vehicles passes through a movable edge, which is a section between a first boarding / alighting point and a second boarding / alighting point among boarding / alighting points included in the main travel demand data indicating the main travel demand, during a predetermined time section out of a plurality of time sections included in the time period to be processed, and which is a section that can be traveled within a time corresponding to the predetermined time section; The information processing device according to claim 1 .

8. The determination unit The vehicle allocation plan information is determined by solving an optimization problem that finds a solution that minimizes the value of an objective function that indicates the total travel cost of a predetermined number of vehicles. The information processing device according to claim 1 .

9. The determination unit The vehicle dispatch plan information is determined by solving the optimization problem under the constraint that a departure point, an arrival point, a departure time, and an arrival time are assigned for each of the major travel demands. The information processing device according to claim 8 .

10. The determination unit The vehicle allocation plan information is determined by solving the optimization problem, which has as a constraint that an event occurs in which a predetermined vehicle departs with the user on board, and then an event occurs in which the predetermined vehicle arrives with the user off. The information processing device according to claim 8 .

11. The determination unit The vehicle allocation plan information is determined by solving the optimization problem, which has a constraint that the number of users boarding a specified vehicle is equal to or less than the number of passengers that can be boarded in the specified vehicle in each of a plurality of time sections included in the time period to be processed. The information processing device according to claim 8 .

12. The determination unit The vehicle allocation plan information is determined by solving the optimization problem, which has a constraint that a predetermined vehicle moves along adjacent movable edges in adjacent time intervals among a plurality of time intervals included in the time period to be processed. The information processing device according to claim 8 .

13. The determination unit When a predetermined vehicle departs or arrives at a predetermined time interval with the user boarding or disembarking in response to the major travel demand, the predetermined vehicle is located at the departure point or arrival point of the major travel demand as a constraint, and the vehicle dispatch plan information is determined by solving the optimization problem. The information processing device according to claim 8 .

14. An information processing method realized by a program executed by an information processing device, an acquisition step of acquiring travel demand data indicating travel demands of users who use on-demand vehicle dispatch services; a clustering step of clustering the travel demand data into a plurality of clusters based on the distances between the travel demand data; a determination step of determining vehicle allocation plan information related to a vehicle allocation plan to be allocated to a major travel demand that is a travel demand representative of a major cluster, which is a cluster in which the number of travel demand data belonging to the cluster is equal to or greater than a threshold data number, among the plurality of clusters; An information processing method including:

Images