Abstract: Systems and methods for optimizing an online on-demand service are provided. A method may include: obtaining driver information associated with a plurality of historical drivers corresponding to the plurality of historical orders; for each historical driver during a predetermined period of time, determining a plurality of records based on the order information and the driver information according to a decision-making processes, each record includes a driver's space-time status, a driver's action, a driver's revenue, and a driver's subsequent space-time status; and determining a value function based on the plurality of records of each historical driver according to a reinforcement learning algorithm.

Abstract: A method and system for improving scheduling decisions in an online to offline service. The method includes obtaining order information in an area associated with a first time period. The method also includes determining driver status information associated with a plurality of drivers in the area corresponding to a first time period. The method further includes determining a scheduling decision for the plurality of drivers in the area in the first time period based on the order information and the driver status information. The scheduling decision optimizes estimated overall profit for the online to offline service starting from the first time period.

Abstract: The present disclosure relates to systems and methods for distributing a request. The methods comprise obtaining a user request from a first device; determining a departure location and a departure time based on the user request; determining a target time based on the departure location and departure time; and distributing the user request to a second device based on the target time.

Abstract: A method and system for improving scheduling decisions in an online to offline service. The method includes obtaining order information in an area associated with a first time period. The method also includes determining driver status information associated with a plurality of drivers in the area corresponding to a first time period. The method further includes determining a scheduling decision for the plurality of drivers in the area in the first time period based on the order information and the driver status information. The scheduling decision optimizes estimated overall profit for the online to offline service starting from the first time period.

Abstract: Systems and methods for optimizing an online on-demand service are provided. A method may include: obtaining driver information associated with a plurality of historical drivers corresponding to the plurality of historical orders; for each historical driver during a predetermined period of time, determining a plurality of records based on the order information and the driver information according to a decision-making processes, each record includes a driver's space-time status, a driver's action, a driver's revenue, and a driver's subsequent space-time status; and determining a value function based on the plurality of records of each historical driver according to a reinforcement learning algorithm.