Google Inc.

Lucien Pech

Albert Graells

Veselin Raychev

Fabien Viger

Systems and methods for generating a plurality of trip patterns are provided. One exemplary method includes receiving transit graph data describing a plurality of nodes respectively corresponding to a plurality of transit stations and a plurality of arcs respectively connecting the plurality of nodes. The method also includes performing a plurality of identification iterations. Each identification iteration includes determining an optimal transit trip connecting an origin node to a destination node based on a cost model. Each identification iteration also includes revising the cost model based on the determined optimal transit trip, such that the arc costs associated with one or more arcs associated with the optimal transit trip are increased. Each optimal transit trip can have an associated trip pattern describing a sequence of nodes traversed by such optimal transit trip. One exemplary system can include a transit planning platform that includes a trip pattern identification module.

Systems and methods for generating a plurality of trip patterns

Systems and methods for recommending time independent or 'guidebook' transit routes between an origin and a destination are provided. A score is generated for each transit route. The score can be used to evaluate and prioritize the transit routes so that one or more transit routes can be recommended to a user. The score can be computed based on characteristics of a trip duration function generated for the transit route. The trip duration function specifies a trip cost (e.g. a trip duration) for the transit route as a function of time (such as departure time or arrival time) over the time interval. The trip duration function can be a piecewise linear function with one or more linear trip segments. Each linear trip segment models the trip cost, including waiting time, of a transit trip associated with the transit route over at least a portion of the time interval.

Guidebook transit routing

A public transportation journey planning system and method provides transit graph data from which routes can be selected using a route searching technique, for vehicle schedules that are not defined in terms of actual arrival and departure times at stations but rather in terms of a repeat schedule having common repeat period (P) for successive vehicles between start and end times of the day.

Public transportation journey planning

A computer-implemented method of constructing a transit transfer network from transit data comprises processing transit data to define a plurality of transfer endpoints; determining a set of acceptable transfer durations for each of a plurality of transfers associated with the transfer endpoints; determining one or more groups of endpoints to be merged, each group comprising two or more endpoints, wherein transfers associated with the endpoints in each said group have one or more common acceptable transfer durations; and merging the endpoints in each group to form one or more merged endpoints.

Constructing a transit transfer network from transit data

Systems and methods for generating transit trips between an origin and a destination are provided. Searches can be undertaken to identify optimal departure times from a source station and/or one or more intermediate stations while maintaining a lowest cost arrival time at a destination station. In this manner, public transportation journey schedules for routes can be determined and recommendations can be provided even if different journey schedules show identical costs.

Systems and methods for generating transit trips

Configurations are disclosed for providing diversity in transit routes to determine optimal public transit routes for journeys or trips between a source station and a target station. The subject technology performs a forward and backward search of a generated query graph (based on a query between the source and target stations). An arrival label set is determined according to a specified queue order and domination function that takes into account different criteria, such as a duration time and an associated penalty of a label. The arrival label set is then filtered to remove dominated labels. The subject technology then determines one or more optimal paths from the source station to the target station based on the filtered label set.

Growing community of inventors

Zurich, Switzerland

Lucien Pech