公开(公告)号：US11887046B1

公开(公告)日：2024-01-30

申请号：US16945289

申请日：2020-07-31

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Christopher Andrew Stephens ,  Alexander Clark Prater ,  Alexander Michael McNamara ,  Sridhar Boyapati ,  David Echevarria Ignacio ,  David William Bettis ,  Korwin Jon Smith ,  Kevin Alexander Lee ,  Aaron Craig Thompson ,  Gary Paolo Raden ,  Sudarshan Narasimha Raghavan ,  Dilip Kumar ,  Félix Joseph Étienne Pageau

IPC: G06Q10/087 ,  G06Q10/08 ,  G06T7/00 ,  G06V40/10 ,  H04N7/18

CPC classification number: G06Q10/087 ,  G06Q10/08 ,  G06T7/0004 ,  G06V40/10 ,  H04N7/181 ,  G06T2207/30108 ,  G06T2207/30196

Abstract: A system may use sensor data from a facility to generate tentative values associated with an event, such as the identification of an item removed from a shelf of the facility. A confidence value associated with each of the tentative values may be less than a confidence threshold. In response, inquiry data seeking confirmation of a tentative value from an associate is generated and sent to one or more associates in the facility. Responses from the associates are collected to determine a selection of one of the tentative values. The selected tentative value is designated as output data for the system. Thereafter, the output data and the original sensor data are designated as training data, which can then be used to train or update machine learning systems. Subsequent use of the updated machine learning systems can yield more accurate results.

公开(公告)号：US10733565B1

公开(公告)日：2020-08-04

申请号：US14502280

申请日：2014-09-30

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Christopher Andrew Stephens ,  Alexander Clark Prater ,  Alexander Michael McNamara ,  Sridhar Boyapati ,  David Echevarria Ignacio ,  David William Bettis ,  Korwin Jon Smith ,  Kevin Alexander Lee ,  Aaron Craig Thompson ,  Gary Paolo Raden ,  Sudarshan Narasimha Raghavan ,  Dilip Kumar ,  Félix Joseph Étienne Pageau

IPC: G06Q10/08 ,  H04N7/18 ,  G06K9/00 ,  G06T7/00

Abstract: Described is an interactive data processing system configured to facilitate selection by a human associate of tentative values generated by an automated system from sensor data. In one implementation, an event may take place in a materials handling facility. The event may comprise a pick or place of an item from an inventory location, movement of a user, and so forth. The sensor data associated with the event is processed by an automated system to determine tentative values associated with the event. In some situations, an uncertainty may exist as to which of the tentative values accurately reflects the actual event. The sensor data and tentative values may be provided to a human associate. The associate may select one of the tentative values. The selected tentative value and the sensor data may be used to train the automated system.

公开(公告)号：US09306895B1

公开(公告)日：2016-04-05

申请号：US14020168

申请日：2013-09-06

Applicant: Amazon Technologies, Inc.

Inventor： Gary Paolo Raden ,  Nikolay Georgiev Hristov ,  Soonhan Mahae Koh

IPC: G06F15/16 ,  H04L12/58

CPC classification number: H04L51/30 ,  H04L51/12 ,  H04L51/34

Abstract: Technologies are described herein for predicting and resolving message deliverability events. A message deliverability event is an event initiated by a mailbox provider that results in the refusal of the mailbox provider to deliver a message to the inbox of its intended recipient, or that results in a mailbox provider delaying the delivery of a message to the inbox of its intended recipient. The transmission of messages to mailbox providers and responses to the transmission of the messages can be monitored. Based upon the monitoring, a determination can be made as to whether the probability of a future message deliverability event exceeds a threshold with regard to one or mailbox providers. If there the probability of a message deliverability event exceeds the threshold, one or more actions may be taken to reduce the probability that the future message delivery event will occur.

Abstract translation: 这里描述了用于预测和解决消息传递性事件的技术。 消息传递性事件是由邮箱提供商发起的事件，导致邮箱提供商拒绝将邮件传递到其预期收件人的收件箱，或导致邮箱提供商将邮件传递延迟到收件箱的收件箱 其预期收件人。 可以监控向邮箱提供商传送邮件和传送邮件的响应。 基于监视，可以确定关于一个或者邮箱提供者的未来消息传送事件的概率是否超过阈值。 如果消息可传递性事件的概率超过阈值，则可以采取一个或多个动作来减少未来消息传递事件发生的概率。