REINFORCEMENT LEARNING METHOD FOR INCENTIVE POLICY BASED ON HISTORIC DATA TRAJECTORY CONSTRUCTION

WIPO Patent Application WO/2020/248220

A1

A system and method to optimize the distribution of incentives for a transportation hailing service is disclosed. A database stores state data and action data received from a client devices and transportation devices. The state data is associated with the utilization of the transportation hailing service and the action data is associated with different incentives to passengers to engage the transportation hailing service. A Q-value determination engine is trained to determine rewards associated with incentive actions from a set of virtual trajectories of states, incentive actions, and rewards, based on a history of the action data and associated state data from the database. Passengers are ordered according to V-values. An incentive policy including selected incentive actions based on the determined rewards and passengers is created. An incentive server communicates selected incentives to at least some of the client devices according to the determined incentive policy.

WO/2023/007899	EXPERIMENT PLANNING DEVICE, EXPERIMENT PLANNING METHOD, AND EXPERIMENT PLANNING SYSTEM
JP2023008775	DELIVERY METHOD AND MANAGEMENT SERVER FOR DELIVERY
WO/2021/253004	SYSTEM, METHOD, AND APPARATUS FOR DATA COLLECTION AND AGGREGATION

QU WEIYANG (US)
LI QINGYANG (US)
QIN ZHIWEI (US)
MENG YIPING (US)
YU YANG (US)
YE JIEPING (US)

PCT/CN2019/091247

December 17, 2020

June 14, 2019

Click for automatic bibliography generation  

BEIJING DIDI INFINITY TECHNOLOGY & DEV CO LTD (CN)
QU WEIYANG (US)

G06Q10/04

WO2017120001A1

2017-07-13

CN106709596A	2017-05-24
CN107657499A	2018-02-02
CN106920018A	2017-07-04
US20150261754A1	2015-09-17

NTD PATENT AND TRADEMARK AGENCY LTD. (CN)

View/Download PDF      PDF Help

Previous Patent: AUTOMATICALLY RESETTABLE PASSIVE SWING BOLT LOCK

Next Patent: INK-JET PRINTER AND SINGLE-PASS INK-JET PRINTING METHOD