-
公开(公告)号：US09342063B1
公开(公告)日：2016-05-17
申请号：US14031890
申请日：2013-09-19
Applicant: Amazon Technologies, Inc.
Inventor： Serguei Iakhnine , James McTavish , Kirill Volgin , Vadim Bachmutsky , Vitalii Fedorenko , Kreethigha Thinakaran
CPC classification number: G06Q10/06 , G05B19/41865 , G05B2219/31376 , G06Q10/087 , Y02P90/20
Abstract: Disclosed are various embodiments for determining capacities for work buffers. Data is received that indicates past work cycles for a first stage and a second stage of a pipelined process. The pipelined process includes a work buffer between the first stage and the second stage. Staffing levels for the first stage and the second stage are received. An optimal buffer capacity for the work buffer is generated based at least in part on a predicted workflow variance for the pipelined process, the staffing levels, and the past work cycles.
Abstract translation: 公开了用于确定工作缓冲器容量的各种实施例。 接收到数据，其指示流水线过程的第一阶段和第二阶段的过去工作周期。 流水线处理包括第一阶段和第二阶段之间的工作缓冲区。 收到了第一阶段和第二阶段的人员配置。 至少部分地基于流水线过程，人员配置级别和过去工作周期的预测工作流程差异来生成工作缓冲器的最佳缓冲器容量。
-
公开(公告)号：US11836654B2
公开(公告)日：2023-12-05
申请号：US17306766
申请日：2021-05-03
Applicant: Amazon Technologies, Inc.
Inventor： Senmao Liu , Jose Ramon Algara Allegre , Rowan William Hale , Eric M. Hayward , Ziyan Huang , Jingnan Li , Robert Dreaper McDonald, Jr. , Carl Morris , Wilko Ziggy Schulz-Mahlendorf , Sharath Selvaraj , Kreethigha Thinakaran
IPC: G06Q10/0631 , G06Q10/0835 , G06Q50/28 , G06Q10/083 , G06N20/00 , G06Q10/04
CPC classification number: G06Q10/06311 , G06N20/00 , G06Q10/0835 , G06Q10/0838 , G06Q50/28 , G06Q10/04
Abstract: Features related to a system and method for scheduling a resources to perform discrete tasks are described. The scheduling features include generating schedules predicted to appeal to the tasked resource (e.g., delivery partner) such as by time, day of the week, location, item types, etc. Using machine learning, the schedule and terms thereof can be dynamically generated to suit the tastes of each tasked resource and the overall demand for services. Using historical data, the modeling also accounts for likelihood an offer will be accepted and risk of cancellation for a given resource. The machine learning may be based on a mixed integer problem as constrained by partner and system capacity parameters.
-
公开(公告)号：US20210326788A1
公开(公告)日：2021-10-21
申请号：US17306766
申请日：2021-05-03
Applicant: Amazon Technologies, Inc.
Inventor： Senmao Liu , Jose Ramon Algara Allegre , Rowan William Hale , Eric M. Hayward , Ziyan Huang , Jingnan Li , Robert Dreaper McDonald, JR. , Carl Morris , Wilko Ziggy Schulz-Mahlendorf , Sharath Selvaraj , Kreethigha Thinakaran
Abstract: Features related to a system and method for scheduling a resources to perform discrete tasks are described. The scheduling features include generating schedules predicted to appeal to the tasked resource (e.g., delivery partner) such as by time, day of the week, location, item types, etc. Using machine learning, the schedule and terms thereof can be dynamically generated to suit the tastes of each tasked resource and the overall demand for services. Using historical data, the modeling also accounts for likelihood an offer will be accepted and risk of cancellation for a given resource. The machine learning may be based on a mixed integer problem as constrained by partner and system capacity parameters.
-
公开(公告)号：US11010697B1
公开(公告)日：2021-05-18
申请号：US15896872
申请日：2018-02-14
Applicant: Amazon Technologies, Inc.
Inventor： Senmao Liu , Jose Ramon Algara Allegre , Rowan William Hale , Eric M. Hayward , Ziyan Huang , Jingnan Li , Robert Dreaper McDonald, Jr. , Carl Morris , Wilko Ziggy Schulz-Mahlendorf , Sharath Selvaraj , Kreethigha Thinakaran
Abstract: Features related to a system and method for scheduling a resources to perform discrete tasks are described. The scheduling features include generating schedules predicted to appeal to the tasked resource (e.g., delivery partner) such as by time, day of the week, location, item types, etc. Using machine learning, the schedule and terms thereof can be dynamically generated to suit the tastes of each tasked resource and the overall demand for services. Using historical data, the modeling also accounts for likelihood an offer will be accepted and risk of cancellation for a given resource. The machine learning may be based on a mixed integer problem as constrained by partner and system capacity parameters.
-
-
-
Search Results
4
records
(took 0.014 seconds)
