WO2018167839A1

WO2018167839A1 - Ride sharing support system, ride sharing support method, and ride sharing support program

Info

Publication number: WO2018167839A1
Application number: PCT/JP2017/010163
Authority: WO
Inventors: 阿南　泰三; 拓郎池田
Original assignee: 富士通株式会社
Priority date: 2017-03-14
Filing date: 2017-03-14
Publication date: 2018-09-20
Also published as: JP6773211B2; JPWO2018167839A1

Abstract

A ride sharing support system has: a reception unit that receives a request to board ride sharing transportation; and a generation unit that generates, on the basis of parameters indicating characteristics relating to each of a plurality of items constituting the conditions of the ride sharing transportation for each ride sharing candidate for the ride sharing transportation in accordance with the boarding request, the condition for each candidate for which the probability is the highest of the ride sharing transportation being accepted by the candidate, whereby the possibility is increased that ride sharing is feasible for the ride sharing transportation.

Description

Riding support system, riding support method, and riding support program

The present invention relates to a riding assistance system, a riding assistance method, and a riding assistance program.

The establishment of a shared taxi depends greatly on the nature of the area. For example, in a city station, there are many taxi users, and the routes of people moving from the station to a residential area are limited. However, there are few taxi users in local cities, so there are few cases where shared taxis are established except in tourist areas.

In the prior art, in order to establish a ride, those based on past usage history have been studied. For example, desired reservation information (boarding location, getting-off location, departure time) and contact information of users with usage history are stored in the reservation system, the contact information is searched using the desired reservation information as a key, and the desired reservation in the past A user of the first boarding pattern who has transmitted the same desired reservation information as the information, or a section included in the route from the boarding place A to the getting-off place B in the past may be used as the desired reservation information. A technique for informing the contact information of the user of the boarding pattern by e-mail or the like and soliciting carpooling has been studied (for example, Patent Document 1).

JP 2003-308596 A Japanese Patent Laid-Open No. 2005-15630 JP 2010-73184 A

However, with the conventional technology, it is difficult to establish a ride when there is a deviation from the past usage history of another user in a time zone or the like for a shared taxi in response to a request from a certain user.

Therefore, in one aspect, the purpose is to increase the possibility that a ride will be established in shared traffic.

In one plan, the riding support system includes a receiving unit that receives a boarding request for the boarding traffic, and a plurality of items constituting the conditions of the boarding traffic for each candidate for boarding the boarding traffic according to the boarding request. A generating unit that generates, for each of the candidates, a condition that maximizes the probability of being accepted by the candidate for the shared traffic based on a parameter indicating characteristics relating to each of the candidates.

According to one aspect, it is possible to increase the possibility of establishment of sharing in shared traffic.

It is a figure which shows the network structural example in embodiment of this invention. It is a figure which shows the hardware structural example of the riding together support system 10 in embodiment of this invention. It is a figure which shows the function structural example of the riding together support system 10 in embodiment of this invention. 5 is a flowchart for explaining an example of a processing procedure executed by the riding assistance system 10. It is a figure which shows the structural example of request history DB122. It is a figure which shows the structural example of movement pattern DB121. It is a figure which shows the structural example of proposal acceptance log | history DB123. It is a figure which shows the structural example of incentive DB125. It is a figure which shows the structural example of facility DB126. It is a figure which shows the example of a display of a proposal screen.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, a sharing support system that searches for passengers who ride in a shared taxi together with the first rider so as to increase the possibility of establishment of a ride will be described. First, a specific example of riding realized by the riding assistance system will be described.

[Specific Example 1]
For example, suppose that Mr. A leaves his home at 13:00 and requests a shared taxi with destination a station. The riding support system looks at the elderly person B who takes a 20-minute taxi trip to a hospital in the middle of station a at 14:00. It is assumed that old man B's home is between A's home and station a, and the hospital is between A's home and station a. Mr. B usually goes to the hospital by taxi at 14:00, but if it is a low-cost shared taxi, he will be accommodated for 30 minutes according to the departure time of Mr. A, and the hospital will be at 13:30. There is a possibility that you will be able to change your behavior to arrive. Therefore, the riding assistance system picks up Mr. B at 13:10, and proposes a riding taxi that arrives at the hospital at 13:30 to Mr. B via smartphone. If the proposal is accepted by Mr. B, the shared taxi will pick up Mr. A at 13:00, go to pick up Mr. B at 13:10 and leave for the hospital, station a.

[Specific Example 2]
Similarly, suppose that Mr. A left his home at 13:00 and requested a shared taxi with destination a station. The riding support system looks at Mr. C who goes from his house by bus at 12:00 to the △ department store between Mr. A's house and station a. In the riding support system, Mr. C knows that a hamburger at a department store is a favorite food. Therefore, the riding support system issues a discount coupon for hamburgers and proposes a shared taxi to pick up Mr. C at 12:30 in order to have lunch. If you suggest a little later time for Mr. A, Mr. C may be rejected. Therefore, the riding support system proposes a shared taxi that will meet Mr. A at 12:45, with time available for Mr. A. If both Mr. A and Mr. C accept the proposal, the shared taxi will pick up Mr. C at 12:30, go to pick up Mr. A at 12:45, and head for each destination. depart.

As in the above specific examples, the riding support system is not limited to the usual movement patterns of the rider who wants to ride, such as A, and the rider candidate, such as B or C. Manage the impact on benefits such as incentives (whether providing coupons increases the probability of accepting proposals), and what incentives are involved and what proposals If this is done, it is calculated whether the probability that the multiplication will be established is high, and the proposal that maximizes the probability is raised, thereby increasing the possibility of multiplication and synthesis.

FIG. 1 is a diagram illustrating a network configuration example according to an embodiment of the present invention. In FIG. 1, the passenger support system 10 and the plurality of user terminals 20 are connected via a network such as the Internet (which may include a wireless section), for example.

The user terminal 20 is a terminal used by a shared taxi user to input a request for a ride or to receive a shared taxi proposal. In other words, in this embodiment, when a shared taxi request is generated, a shared taxi proposal is distributed to a person other than the requester. For example, a PC (Personal Computer), a mobile phone, a smartphone, a tablet terminal, or the like may be used as the user terminal 20.

The riding support system 10 is one or more computers that generate proposals (sharing taxi terms) using incentives so as to increase the probability that the riding will be established for the riding taxi according to the request for the riding taxi.

FIG. 2 is a diagram illustrating a hardware configuration example of the riding support system 10 according to the embodiment of the present invention. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, and the like that are mutually connected by a bus B.

A program that realizes processing in the riding support system 10 is provided by the recording medium 101. When the recording medium 101 on which the program is recorded is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 executes functions related to the riding support system 10 according to a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

An example of the recording medium 101 is a portable recording medium such as a CD-ROM, a DVD disk, or a USB memory. As an example of the auxiliary storage device 102, an HDD (Hard Disk Disk Drive), a flash memory, or the like can be given. Both the recording medium 101 and the auxiliary storage device 102 correspond to computer-readable recording media.

FIG. 3 is a diagram illustrating a functional configuration example of the riding assistance system 10 according to the embodiment of the present invention. In FIG. 3, the riding support system 10 includes a request receiving unit 11, a movement pattern matching unit 12, a user characteristic learning unit 13, a proposal optimization unit 14, and the like. Each of these units is realized by processing that one or more programs installed in the riding support system 10 cause the CPU 104 to execute. The riding support system 10 also uses databases (storage units) such as a movement pattern DB 121, a request history DB 122, a proposal acceptance history DB 123, a learning result DB 124, an incentive DB 125, and a facility DB 126. Each of these databases can be realized using, for example, the auxiliary storage device 102 or a storage device that can be connected to the sharing support system 10 via a network.

The request receiving unit 11 receives a ride request for a shared taxi (hereinafter referred to as “ride request”) from the user terminal 20. The boarding request includes information indicating the boarding time, arrival time, departure place, destination, and the like.

The movement pattern matching unit 12 extracts users who have a possibility of sharing a shared taxi (hereinafter referred to as “target taxi”) according to the shared request from the past usage history of the shared taxi of each user. In addition, the originator of the sharing request (hereinafter referred to as “requester”) and the user extracted by the movement pattern matching unit 12 are hereinafter referred to as “combining candidates”.

The user characteristic learning unit 13 learns a model (parameter) representing each user's characteristic (influence degree) related to each of a plurality of items constituting the shared taxi proposal (condition) based on the past proposal acceptance history. Do. The learning result is stored in the learning result DB 124. Note that the proposal acceptance history is a history of acceptance status regarding a shared taxi proposal (condition) generated for a shared taxi in response to another person's ride request, and is stored in the proposal acceptance history DB 123 for each user. Yes.

The characteristic of the user is information indicating which component among the components of the shared taxi condition is emphasized by the user, or which component is highly influenced by the user. The components of the proposal for a shared taxi include departure time, departure time error relative to desired departure time, arrival time error relative to desired arrival time, travel time (ride time), fee, incentive (privilege), and the like. The incentive is not an indispensable parameter regarding the conditions of shared taxi, but is a parameter introduced in this embodiment in order to increase the possibility of establishment of shared taxi.

The proposal optimizing unit 14 refers to the learning result DB 124, the incentive DB 125, the facility DB 126, and the like for the riding candidate using the model learned by the user characteristic learning unit 13, and what kind of suggestion should be made. The probability that the establishment of will increase will be calculated with probability. The proposal optimizing unit 14 adjusts the contents of the proposal while narrowing down the candidates for riding based on the calculated probability. The proposal optimizing unit 14 transmits the proposal content generated for each narrowed-down candidate user terminal 20 to solicit the ride.

The proposed optimization unit 14 will be described in more detail.

As an example, assume that a user A leaves his home at X and issues a sharing request to travel to the nearest station by a shared taxi. If the shared taxi is a four-seater rider including a driver, it is necessary to search for two people in addition to the user A as a candidate for sharing (that is, the number of recruitment is two). The proposal optimizing unit 14 generates a proposal for each riding candidate n while involving the incentive I, and calculates the probability that the riding candidate n accepts the proposal for the proposal.

If the error from the desired departure time X is Δtl, the error from the arrival time is Δta, the travel time is T, and the charge is C, the riding candidate n proposes (X _n , Δtl _n , Δta _n , T _n , C _n , I _n ) are accepted as equations (1) and (2).

Z _n is a partition function. The does not include the X in the right-hand side of equation (1), the lag time (Δtl _n, Δta _n) from the planned establishment probability of riding together to the assumption that depends on the magnitude of, does not depend on the departure time Based.

Each β is a parameter (weight) constituting user characteristics. That is, β ₁ is a characteristic (influence or tolerance) with respect to the error Δtl from the desired departure time X. β ₂ is a characteristic (influence or tolerance) with respect to the error Δta from the arrival time. β ₃ is a characteristic (influence or tolerance) with respect to the travel time T. β ₄ is a characteristic (influence or tolerance) for the fee. β ₅ is a characteristic (influence degree) with respect to the incentive I. The value of each β of each user is learned by the user characteristic learning unit 13.

Incentives _{I n} may be, for example, take values of 1 or -1. If incentive vans candidates n is accepted in the past and then, a -1 if there be accepted, it is possible to represent the acceptance degree of incentives size of beta _5. The incentive may be a coupon or a gift voucher.

Proposed vans probability by vans candidates is highest, i.e., the riding together all candidates best suggestion OPT proposed acceptance probability is maximum of _{_{{X n, Δtl n, Δta}} n, T n, C n, I n} Can be obtained by the following equation (3).

The proposal optimizing unit 14 uses Formula (3) to generate a proposal that maximizes the acceptance probability P _n of the proposal of each riding candidate n for each riding candidate.

Hereinafter, the processing procedure executed by the riding support system 10 will be described. FIG. 4 is a flowchart for explaining an example of a processing procedure executed by the riding assistance system 10.

In step S101, the request receiving unit 11 receives the multiplication request transmitted from the user terminal 20 of the requester. The boarding request includes information indicating the desired departure time X or the desired arrival time Y, the departure place O, and the destination D. The request receiving unit 11 stores the sharing request in the request history DB 122.

FIG. 5 is a diagram illustrating a configuration example of the request history DB 122. As shown in FIG. 5, the request history DB 122 stores the departure place, destination, desired departure time X, desired arrival time Y, and the like of past boarding requests for each user. FIG. 5 shows a request history of a certain user.

Subsequently, the movement pattern matching unit 12 searches for a movement route (boarding route) according to the boarding request (S102). A known technique may be used for the route search. Note that the scheduled departure time, the estimated arrival time, and the like are determined according to the search for the travel route.

Subsequently, the movement pattern matching unit 12 extracts a user who has a movement experience of a route close to the searched movement route with reference to the movement pattern DB 121 (S103).

FIG. 6 is a diagram illustrating a configuration example of the movement pattern DB 121. The movement pattern DB 121 stores a departure place, a destination, the number of movements, a most frequent movement time zone, and the like for each user. The contents of each record in the movement pattern DB 121 may be generated based on the request history DB 122, for example.

In step S103, for example, a record in which the departure point and the destination are included on the movement route, and the estimated arrival time of the departure point or the destination when moving along the movement route is included in the most frequent movement time zone is registered. The user who has been selected is extracted as a riding candidate. However, the extraction target may be limited to a record in which the number of movements is a predetermined value or more. That is, a riding candidate may be extracted based on a movement pattern with a high movement frequency. A record in the movement pattern DB 121 that causes extraction for a certain riding candidate is hereinafter referred to as a “target movement pattern”. Also, each extracted candidate and requester are set as a candidate n. That is, hereinafter, the requester is also treated as one passenger candidate n.

Subsequently, the user characteristic learning unit 13 learns (calculates) the value of β of each user based on the information stored in the proposal acceptance history DB 123 using Expression (4), and learns the results (calculation results). Is stored in the learning result DB 124 (S104).

FIG. 7 is a diagram showing a configuration example of the proposal acceptance history DB 123. The suggestion acceptance history DB 123 stores, for each user, information indicating how much error of departure time or arrival time is allowed for adjustment with other riding candidates for multiplication / combination.

Specifically, in the proposal acceptance history DB 123, departure time error, arrival time error, travel time, fee, incentive, proposal acceptance result, etc. are stored for each user for each past proposal. As a result, it is possible to grasp for each user whether the time is exactly, whether it is loose, what kind of incentive is weak, and what kind of proposal will be accepted in the future is highly likely to be accepted. You can know what will be.

For example, for each riding candidate n (excluding the requester), the proposal number for the riding candidate n and the proposal acceptance result is “accepted” (in order from oldest to newest) Learning is performed by estimating each β in Expression (2), where s is the number when the two are arranged. The equation for learning is given by the following equation (4).

That is, the user characteristic learning unit 13 learns the characteristic β using the equation (4). The learned β is stored in the learning result DB 124 for each user. The more the proposal is accepted, the more accurately the user characteristic β is learned.

Note that the learning by the user characteristic learning unit 13 may not be executed at this timing. For example, learning may be performed each time a response to a proposal is received.

Subsequently, the proposal optimizing unit 14 generates a proposal Opt for each multiplication candidate n using Expression (3) (S105). At this time, in addition to the requester, the proposal optimizing unit 14, for each combination of the candidate candidates n for the number of recruited persons, for each combination of the requester and the candidate candidate n for the combination. The travel route is searched so that the total power of _Pn becomes the maximum.

For example, if the recruitment number is two, a travel route of a triplet is searched when a requester and two riding candidates n are selected. As a result, for the moving path, for each of the three vans candidates n containing requester, .DELTA.TL _n, .DELTA.ta _n, _T n, _{C n} is determined. Note that Δtl and Δta of the requester are errors in the departure time of the travel route and the arrival time of the travel route with respect to the desired departure time X and the desired arrival time Y in the ride request. On the other hand, Δtl and Δta of the riding candidate n other than the requester are errors with respect to the most frequent movement time zone of the target movement pattern for the riding candidate.

The proposed optimization unit 14, for each vans candidates n, available incentives (benefits) to generate a proposed Opt while fitted to I _n at each destination or destination peripheral. Such an incentive can be specified with reference to the incentive DB 125.

FIG. 8 is a diagram illustrating a configuration example of the incentive DB 125. As shown in FIG. 8, the incentive DB 125 stores facility names, stores, privilege details, privilege conditions, and the like for each currently available privilege (coupon or present).

The facility name is the name of the facility including the store where the privilege can be used. The store name is the name of the store. The privilege content is the content of the privilege. The privilege condition is a condition for the privilege to be usable, such as a time limit of the privilege.

In addition, the location information (latitude and longitude) of each facility including a store where the privilege can be used can be specified with reference to the facility DB 126.

FIG. 9 is a diagram illustrating a configuration example of the facility DB 126. As shown in FIG. 9, the facility DB 126 stores the facility name, latitude / longitude, store name, location, and the like of each facility. The latitude and longitude are the latitude and longitude of the location of the facility. The store name is the store name of the store in which the facility is included. The location is information indicating the position of the store in the facility.

Therefore, the proposal optimizing unit 14 can specify the facility of each passenger candidate n or the facility in the vicinity of the destination with reference to the facility DB 126, and refer to the incentive DB 125 for the benefits available at the facility. Can be identified.

The proposal optimizing unit 14 generates a proposal for the triplet that maximizes the total power of the probability _Pn while changing the incentive for each of the multiplicative candidates n included in the triplet and changing the movement route. . The proposal optimizing unit 14 executes such processing for all three-person patterns (however, one of the three-person groups is always a requester). As a result, an optimal proposal Opt is generated for each pattern of three people.

Subsequently, the proposal optimizing unit 14 determines the optimal proposal Opt for each combination candidate n (in the above example, each pattern of a triplet), and the acceptance probability Pn of each candidate n in the optimal proposal Opt, Based on the above, a candidate n for sharing is selected as a proposal destination (that is, a solicitation target for sharing) (S106). Specifically, the proposal optimizing unit 14 sums the probabilities P _n obtained from the formula (1) with respect to the proposal Opt for each of the two riding candidates n excluding the requester for each pattern of the triplet. Calculate The proposal optimizing unit 14 has the expected value (2.0 of the recruitment number) within the total for each pattern of the triplet, and the triple candidate n for the total closest to the expected value Select. In addition, with the selection of the riding candidate n, the proposal Opt for each selected riding candidate is also determined.

Subsequently, the proposal optimizing unit 14 transmits each proposal Opt in the optimum proposal Opt for the combination (the triplet) to each user terminal 20 of the requester and each selected combination candidate n. (S107). As a result, on each user terminal 20, a screen including a proposal Opt for each (hereinafter referred to as “suggest screen”) is displayed. For example, e-mail may be used for sending the proposal. In this case, the mail address of each user may be stored in advance in the auxiliary storage device 102 or the like.

FIG. 10 is a diagram showing a display example of the proposal screen. In FIG. 10, the proposal screen 510 includes a map area 511, an operation information area 512, an incentive display area 513, a cancel button 514, a reservation confirmation button 515, and the like.

In the map area 511, a map showing the starting point and the destination in the proposal Opt of the user is displayed. In the operation information area 512, parameters excluding incentives are displayed among the parameters constituting the proposal Opt. Incentives are displayed in the incentive display area 513. When an incentive is selected, the contents of the incentive may be displayed as shown in a balloon.

Cancel button 514 is a button for accepting rejection of a proposal. The reservation confirmation button 515 is a button for accepting proposal acceptance.

Therefore, when the user selects the cancel button 514, the user terminal 20 transmits information indicating rejection of the proposal to the riding assistance system 10. On the other hand, when the user selects the reservation confirmation button 515, the user terminal 20 transmits information indicating acceptance of the proposal to the riding assistance system 10.

When the proposal optimization unit 14 receives a response from each user terminal 20 of the transmission destination of the proposal, the proposal optimization unit 14 associates the acceptance result (acceptance or rejection) included in the response with the proposal for the transmission destination, and proposes acceptance history Store in the DB 123 (S108).

It should be noted that if the number of users who have accepted the ride is greater than or equal to the number of applicants, adjustments may be made as appropriate.

In addition, the movement pattern matching part 12 may extract all the users of the past joint traffic as a joint candidate, for example. In this case, a multiplication candidate unrelated to the movement route is also extracted. However, in the generation of the optimum proposal by the proposal optimization unit 14, the acceptance probability of such a multiplication candidate is low. It is unlikely that a person will be selected. Therefore, even if the movement pattern matching unit 12 extracts all users, this embodiment can be realized. However, the movement pattern matching unit 12 can extract the number of candidates that can be combined, thereby reducing the amount of calculation performed by the proposed optimization unit 14.

As described above, according to the present embodiment, the proposal is selected based on the acceptance probability of the proposal by the common candidate, and the common candidate having a high acceptance probability is selected as the proposal destination. Therefore, it is possible to increase the possibility that the ride is established in the ride traffic.

In addition, by including an incentive (privilege) in the proposal, it is possible to increase the probability that the proposal is accepted by the riding candidate even if the proposal has a slight error with respect to the desire of the riding candidate.

As a result of the above, for example, an increase in the number of shared traffic users can be expected to improve the profits of the traffic operators. In addition, commercial facilities can issue coupons using passenger traffic as an initiating agent to attract customers.

In the present embodiment, the shared taxi has been described as an example of the shared traffic. However, the present embodiment may be applied to other shared traffic such as a shared bus.

In the present embodiment, the request receiving unit 11 is an example of a receiving unit. The proposal optimizing unit 14 is an example of a generating unit.

As mentioned above, although the Example of this invention was explained in full detail, this invention is not limited to such specific embodiment, In the range of the summary of this invention described in the claim, various deformation | transformation * It can be changed.

DESCRIPTION OF SYMBOLS 10 Sharing support system 11 Request receiving part 12 Movement pattern matching part 13 User characteristic learning part 14 Proposal optimization part 20 User terminal 100 Drive apparatus 101 Recording medium 102 Auxiliary storage apparatus 103 Memory apparatus 104 CPU
105 Interface device 121 Movement pattern DB
122 Request history DB
123 Proposal Acceptance History DB
124 Learning result DB
125 Incentive DB
126 Facility DB
B bus

Claims

A receiving unit for receiving a boarding request for shared traffic;
Based on parameters indicating characteristics of each of a plurality of items constituting the conditions of the shared traffic for each candidate for shared traffic according to the boarding request, the shared traffic is accepted by the candidate. A generating unit that generates a condition that maximizes the probability for each candidate;
A riding support system characterized by comprising:
The plurality of items constituting the conditions of the shared traffic include a privilege when using the shared traffic.
The sharing support system according to claim 1.
The plurality of items constituting the conditions of the shared traffic include an error with respect to a desired time for at least one of the departure time and the arrival time of the shared traffic.
The riding together support system according to claim 2 characterized by things.
The plurality of items constituting the conditions for the shared traffic include travel time in the shared traffic,
The riding support system according to claim 3.
The generation unit generates, for each candidate, a condition that maximizes the acceptance probability of all candidates related to the combination for each combination of a predetermined number of candidates among a plurality of candidates. Selecting the predetermined number of candidates to be proposed for the shared traffic based on the total acceptance probability in the conditions generated for each;
The riding together support system according to any one of claims 1 to 4 characterized by things.
Receive boarding requests for shared traffic,
Based on parameters indicating characteristics of each of a plurality of items constituting the conditions of the shared traffic for each candidate for shared traffic according to the boarding request, the shared traffic is accepted by the candidate. A condition that maximizes the probability is generated for each candidate.
A sharing support method, wherein a computer executes processing.
The plurality of items constituting the conditions of the shared traffic include a privilege when using the shared traffic.
The riding support method according to claim 6.
The plurality of items constituting the conditions of the shared traffic include an error with respect to a desired time for at least one of the departure time and the arrival time of the shared traffic.
The riding support method according to claim 7.
The plurality of items constituting the conditions for the shared traffic include travel time in the shared traffic,
The riding support method according to claim 8, wherein:
For each combination of a predetermined number of candidates among a plurality of candidates, a condition that maximizes the acceptance probability of all candidates related to the combination is generated for each candidate, and is generated for each combination. Based on the total acceptance probability in the condition, select the predetermined number of candidates to be proposed for the shared traffic,
The riding support method according to any one of claims 6 to 9, wherein the computer executes the processing.
Receive boarding requests for shared traffic,
Based on parameters indicating characteristics of each of a plurality of items constituting the conditions of the shared traffic for each candidate for shared traffic according to the boarding request, the shared traffic is accepted by the candidate. A condition that maximizes the probability is generated for each candidate.
A riding support program for causing a computer to execute processing.
The plurality of items constituting the conditions of the shared traffic include a privilege when using the shared traffic.
12. The riding support program according to claim 11, characterized in that:
The plurality of items constituting the conditions of the shared traffic include an error with respect to a desired time for at least one of the departure time and the arrival time of the shared traffic.
The riding support program according to claim 12, wherein:
The plurality of items constituting the conditions for the shared traffic include travel time in the shared traffic,
The riding support program according to claim 13.
For each combination of a predetermined number of candidates among a plurality of candidates, a condition that maximizes the acceptance probability of all candidates related to the combination is generated for each candidate, and is generated for each combination. Based on the total acceptance probability in the condition, select the predetermined number of candidates to be proposed for the shared traffic,
15. The riding support program according to claim 11, which causes a computer to execute processing.