公开(公告)号：US11544754B2

公开(公告)日：2023-01-03

申请号：US16998895

申请日：2020-08-20

Applicant: Amazon Technologies, Inc.

Inventor： Justin Farley ,  Mark Thill ,  David Prody ,  Juan Carlos Lopez Sanchez ,  Justin Shane McRoberts ,  Daniel Micol-Ponce ,  Bradley Louis James Rosenfeld

IPC: G06Q30/02 ,  G06Q30/06 ,  G06Q10/08 ,  G06Q10/10 ,  H04L9/40 ,  G06Q30/00

Abstract: Features are disclosed for providing items from an item store to an item store consumer. An item store organizer can request an item store from an item redemption system based on item store parameters. The item store organizer can receive a single use token from the item redemption system to provide initial access to the item store. The item redemption system can validate the item store consumer based on the single use token. The item redemption system can further validate redemption requests from the item store consumer based on the item store parameters. The item redemption system can fulfill the redemption request based on payment information of the item store organizer and shipping information of the item store consumer. The item redemption system can transmit redemption information to the item store organizer based on fulfilling the redemption request.

公开(公告)号：US11475002B1

公开(公告)日：2022-10-18

申请号：US16446279

申请日：2019-06-19

Applicant: Amazon Technologies, Inc.

Inventor： Srinivasan Sundar Raghavan ,  Daniel Micol-Ponce ,  Noelia Moron ,  Hersh Nagar ,  Jaime Vallori ,  Vamsi Krishna Vutukuru

IPC: G06F16/00 ,  G06F16/2453 ,  G06N20/00 ,  G06F16/2455

Abstract: Devices and techniques are generally described for dynamic policy determination using machine learning. In some examples, first goal data may be received. A first machine learning model may generate a first computer-executable policy based at least in part on the first goal data. In some examples, a first search query may be received. In various examples, the first search query may be modified by the first computer-executable policy to generate a modified search query. In some examples, first feedback data related to user interaction with search results of the modified search query may be determined. In various examples, at least one parameter of the first machine learning model may be updated based at least in part on the first feedback data to generate a second machine learning model.

公开(公告)号：US20220058704A1

公开(公告)日：2022-02-24

申请号：US16998895

申请日：2020-08-20

Applicant: Amazon Technologies, Inc.

Inventor： Justin Farley ,  Mark Thill ,  David Prody ,  Juan Carlos Lopez Sanchez ,  Justin Shane McRoberts ,  Daniel Micol-Ponce ,  Bradley Louis James Rosenfeld

IPC: G06Q30/06 ,  G06Q10/08 ,  G06Q30/02 ,  G06Q10/10 ,  H04L29/06

Abstract: Features are disclosed for providing items from an item store to an item store consumer. An item store organizer can request an item store from an item redemption system based on item store parameters. The item store organizer can receive a single use token from the item redemption system to provide initial access to the item store. The item redemption system can validate the item store consumer based on the single use token. The item redemption system can further validate redemption requests from the item store consumer based on the item store parameters. The item redemption system can fulfill the redemption request based on payment information of the item store organizer and shipping information of the item store consumer. The item redemption system can transmit redemption information to the item store organizer based on fulfilling the redemption request.