Abstract: An action selection learning device includes a memory; and a processor coupled to the memory and configured to generate a reference model that is a set of model parameter vectors that indicate an influence level of each factor that influences selection of an action alternative, calculate a selection probability for each action alternative, for each of the model parameter vectors, calculate a model parameter vector for each user using a subset of model parameter vectors extracted from the reference model, based on the selection probability for each action alternative and a selection history of the action alternative by each user, generate the action alternatives based on the model parameter vector for each user, and transmit the generated action alternatives to a terminal device.

Abstract: An estimation method executed by a computer, the estimation method includes estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship; selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and generating the machine learning model based on the selected training data.

Abstract: A navigation support method executed by a computer includes: storing performance estimation models regarding speed of a vessel for each of vessel maneuvering patterns; accepting one of the vessel maneuvering patterns to be used in a navigation; calculating the speed of the vessel on a route of the vessel, based on one of the performance estimation models that corresponds to the accepted one of the vessel maneuvering patterns among the performance estimation models, and meteorological arid hydrographic forecast data; and displaying an arrival time on the route that is optimal, based on the speed of the vessel that has been calculated.

Abstract: A navigation support method executed by a computer includes: classifying vessel voyage data according to each meteorological and hydrographic condition; calculating characteristic distribution of vessel maneuvering for each meteorological and hydrographic condition, using the vessel voyage data that has been classified; extracting a plurality of vessel maneuvering patterns from the characteristic distribution of vessel maneuvering that has been calculated for each meteorological and hydrographic condition, and aggregating the vessel voyage data for each of the vessel maneuvering patterns; and generating a learning model for each of the vessel maneuvering patterns from the vessel voyage data aggregated for each of the vessel maneuvering patterns, using meteorological and hydrographic actual data as an explanatory variable and vessel performance as an objective variable.

Abstract: A non-transitory computer-readable recording medium has stored therein a program that causes a computer to execute a process, the process comprising: acquiring a first model that is created using a plurality of pieces of training data and outputs a first estimation result estimated with respect to first input data and a second model that is created based on a physical law or human knowledge and outputs a second estimation result estimated with respect to second input data; identifying, by comparing the first model and the second model with each other, a missing class that is not included in classes of the second input data among classes of the first input data; extending the second model with a correction term for input of input data of the missing class; and generating a composite model in which the extended second model and the first model are fused together.

Abstract: An estimation method executed by a computer, the estimation method includes estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship; selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and generating the machine learning model based on the selected training data.

Abstract: A congestion management apparatus includes a memory configured to store, on a per-action-option basis, upper limits on numbers of users allowed to be guided to action options, and a processor coupled to the memory and configured to: generate the action options by time slot for a user; calculate for each of the generated action options, choice probabilities of the action options with respect to the user, and store the calculated choice probabilities in the memory; and calculate for each of the action options, estimated numbers of previous users assumed to have selected the action options, based on choice probabilities of each of the action options with respect to the previous users, the choice probabilities being obtained from the memory, wherein the processor is configured to extract, based on the upper limits and the estimated numbers for the action options, action options to be presented to the user.

Abstract: A moving means display method includes: selecting, based on first position information that indicates a position of a user and second position information that indicates positions of one or more respective vehicles, one or more vehicles located within a predetermined range; selecting, based on the first position information and third position information that indicates positions of one or more respective drivers, one or more drivers located within a predetermined range; and displaying two types of services from among a service in which one of the selected one or more vehicles is lent to the user, a service in which one of the selected one or more drivers drives a vehicle of the user as a substitute driver, and a service in which one of the selected one or more drivers drives a vehicle other than the vehicle of the user to transport the user.

Abstract: A transportation service reservation method executes, by a computer, a process including receiving a ride request specifying an origin and a destination, generating feasible products having service types, by referring to a storage unit that stores information indicating a schedule allocated to each vehicle and the service types of the schedule, for each vehicle capable of providing products having the service types, computing a choice probability of each product forming an assortment of the feasible products, for each of assortments satisfying a predetermined condition amongst the subsets of the feasible product set that are generated, computing an expected value of a number of future ride requests, and selecting an assortment to be presented with respect to the ride request, from the assortment satisfying the predetermined condition, based on the choice probability and the expected value.

Abstract: An action selection learning device includes a memory; and a processor coupled to the memory and configured to generate a reference model that is a set of model parameter vectors that indicate an influence level of each factor that influences selection of an action alternative, calculate a selection probability for each action alternative, for each of the model parameter vectors, calculate a model parameter vector for each user using a subset of model parameter vectors extracted from the reference model, based on the selection probability for each action alternative and a selection history of the action alternative by each user, generate the action alternatives based on the model parameter vector for each user, and transmit the generated action alternatives to a terminal device.

Abstract: A people flow simulation apparatus includes a memory configured to store incentive information and effect characteristic information in association with a plurality of person models, the incentive information indicating incentive provided for each of the plurality of person models, the effect characteristic information indicating each of characteristics of effects that the incentive has on each of the plurality of persons models, and a processor coupled to the memory and the processor configured to calculate probabilities with which a first person model goes to each of a plurality of places on the basis of first incentive information and first effect characteristic information associated with the first person model included in the plurality of person models, and select, from among the plurality of places, a first place as a destination to which the first person model goes in accordance with the calculated probabilities.

Abstract: A congestion management apparatus includes a memory configured to store, on a per-action-option basis, upper limits on numbers of users allowed to be guided to action options, and a processor coupled to the memory and configured to: generate the action options by time slot for a user; calculate for each of the generated action options, choice probabilities of the action options with respect to the user, and store the calculated choice probabilities in the memory; and calculate for each of the action options, estimated numbers of previous users assumed to have selected the action options, based on choice probabilities of each of the action options with respect to the previous users, the choice probabilities being obtained from the memory, wherein the processor is configured to extract, based on the upper limits and the estimated numbers for the action options, action options to be presented to the user.

Abstract: An operation management method performed by a computer, the method including: acquiring requests from a plurality of users for boarding and alighting including a departure location and a destination; associating each request with a vehicle corresponding to the departure location and the destination; setting, for each of the requests, a boarding/alighting point within a predetermined range including the departure location and within a predetermined range including the destination, respectively; generating a plurality of paths that pass through the boarding/alighting points; and selecting an operation path of the vehicle from the plurality of paths.

Abstract: Disclosed as a lead-free, inorganic low melting-point composition which, when applied to an object to be sealed having surfaces made of inorganic oxide and/or metal, and then subjected to heat treatment in the air in a temperature range not exceeding 400° C., sufficiently expands over the surfaces exhibiting good wettability to it, and thus is able to adhere (stick fast) to the surfaces and seal them once cooling down and making solid, and also to join two of their surfaces which are laid on each other.

Abstract: An action option presentation apparatus includes a memory, a processor coupled to the memory and configured to extract one or more action options based on route information from a departure location to a destination location that is extracted from departure location information and destination location information, and also based on information indicating one or more places at which to drop in during a period of time before travel starts in accordance with the route information.

Abstract: When plural users, including users with different disembarkation points, are using, by ride-sharing, a vehicle of a passenger transportation service that determines a fare according to at least one of usage distance or usage time, a payment amount of a passenger disembarking at a disembarkation point at which a user disembarks is calculated, based on a number of disembarking passengers at the disembarkation point, a number of passengers before disembarkation at the disembarkation point, a balance of the fare to the disembarkation point minus a paid or collected payment amount, and a compensation rate for a subsequently disembarking user.

Abstract: A transportation service reservation method executes, by a computer, a process including receiving a ride request specifying an origin and a destination, generating feasible products having service types, by referring to a storage unit that stores information indicating a schedule allocated to each vehicle and the service types of the schedule, for each vehicle capable of providing products having the service types, computing a choice probability of each product forming an assortment of the feasible products, for each of assortments satisfying a predetermined condition amongst the subsets of the feasible product set that are generated, computing an expected value of a number of future ride requests, and selecting an assortment to be presented with respect to the ride request, from the assortment satisfying the predetermined condition, based on the choice probability and the expected value.

Abstract: A reservation management apparatus obtains reservation information including reserved trip information indicating a vehicle trip that has not departed and is reserved by one of a plurality of users and reserving user information indicating the user. The reservation management apparatus determines one or more other users who are associated with the same trip information as the user, with reference to history information associating information about users who took vehicle trips that were operated with different departure dates and times in the past with trip information indicating the vehicle trips. The reservation management apparatus outputs other user information indicating at least some of the determined other users in association with the reservation information.

Abstract: A method included accepting information on a desired ride place in ride sharing and information on a desired drop-off place in the ride sharing; identifying an amount of change in at least one of travel time and travel distance in case that a past travel path of a candidate vehicle for the ride sharing is changed to a travel path that passes through the desired ride place and the desired drop-off place; and sending a request for the ride sharing to a terminal corresponding to the candidate vehicle in accordance with the identified amount of change.

Abstract: A vehicle behavior estimation device includes: a storage unit configured to store a restriction condition at a point of a vehicle for which behavior is estimated; vehicle state data that includes position information and speed information of the vehicle; behavior parameters that include speed information and acceleration information of the vehicle; and physical restriction conditions that include an upper limit and a lower limit of the acceleration information; and a processor configured to obtain the vehicle state data by using the restriction condition at the point; calculate behavior parameters of a vehicle model that satisfy a physical restriction condition from the vehicle state data and the restriction condition at the point; update the vehicle state data of the vehicle model based on the behavior parameters; and repeat processing to calculate behavior parameters by using the updated vehicle state data and to update the vehicle state data.