公开(公告)号：US11755906B2

公开(公告)日：2023-09-12

申请号：US17314487

申请日：2021-05-07

Applicant: DoorDash, Inc.

Inventor： Jeff Ning Han ,  William Preston Parry ,  Bing Wang ,  Rohan Balraj Chopra

IPC: G06N3/08 ,  G06Q10/0833 ,  G06Q10/083 ,  G06F16/487 ,  G06F16/48 ,  G06Q50/12

CPC classification number: G06N3/08 ,  G06F16/487 ,  G06F16/489 ,  G06Q10/0833 ,  G06Q10/0838 ,  G06Q50/12

Abstract: Described are systems and processes for generating dynamic estimated time of arrival predictive updates for delivery of perishable goods. In one aspect a system is configured for generating dynamic estimated time of arrival (ETA) predictive updates between a series of successive events for real-time delivery of orders. For each order, a plurality of delivery events and corresponding timestamps are received from devices operated by customers, restaurants, and couriers. Based on the timestamps, the system generates a plurality of ETA time predictions for one or more of the delivery events with trained predictive models that use weighted factors including historical restaurant data and historical courier performance. As additional timestamps are received for a delivery event, the trained predictive models dynamically update the ETA time predictions for successive events. The predictive models may be continuously trained by updating the weighted factors based on the received timestamps.

公开(公告)号：US20210264275A1

公开(公告)日：2021-08-26

申请号：US17314487

申请日：2021-05-07

Applicant: DoorDash, Inc.

Inventor： Jeff Ning Han ,  William Preston Parry ,  Bing Wang ,  Rohan Balraj Chopra

IPC: G06N3/08 ,  G06Q10/08 ,  G06F16/487 ,  G06F16/48

Abstract: Described are systems and processes for generating dynamic estimated time of arrival predictive updates for delivery of perishable goods. In one aspect a system is configured for generating dynamic estimated time of arrival (ETA) predictive updates between a series of successive events for real-time delivery of orders. For each order, a plurality of delivery events and corresponding timestamps are received from devices operated by customers, restaurants, and couriers. Based on the timestamps, the system generates a plurality of ETA time predictions for one or more of the delivery events with trained predictive models that use weighted factors including historical restaurant data and historical courier performance. As additional timestamps are received for a delivery event, the trained predictive models dynamically update the ETA time predictions for successive events. The predictive models may be continuously trained by updating the weighted factors based on the received timestamps.

公开(公告)号：US11037055B2

公开(公告)日：2021-06-15

申请号：US15798207

申请日：2017-10-30

Applicant: DoorDash, Inc.

Inventor： Jeff Ning Han ,  William Preston Parry ,  Bing Wang ,  Rohan Balraj Chopra

IPC: G06N3/08 ,  G06Q10/08 ,  G06F16/487 ,  G06F16/48 ,  G06Q50/12

Abstract: Described are systems and processes for generating dynamic estimated time of arrival predictive updates for delivery of perishable goods. In one aspect a system is configured for generating dynamic estimated time of arrival (ETA) predictive updates between a series of successive events for real-time delivery of orders. For each order, a plurality of delivery events and corresponding timestamps are received from devices operated by customers, restaurants, and couriers. Based on the timestamps, the system generates a plurality of ETA time predictions for one or more of the delivery events with trained predictive models that use weighted factors including historical restaurant data and historical courier performance. As additional timestamps are received for a delivery event, the trained predictive models dynamically update the ETA time predictions for successive events. The predictive models may be continuously trained by updating the weighted factors based on the received timestamps.

公开(公告)号：US20190130260A1

公开(公告)日：2019-05-02

申请号：US15798207

申请日：2017-10-30

Applicant: DoorDash, Inc.

Inventor： Jeff Ning Han ,  William Preston Parry ,  Bing Wang ,  Rohan Balraj Chopra

IPC: G06N3/08 ,  G06Q10/08 ,  G06F17/30

Abstract: Described are systems and processes for generating dynamic estimated time of arrival predictive updates for delivery of perishable goods. In one aspect a system is configured for generating dynamic estimated time of arrival (ETA) predictive updates between a series of successive events for real-time delivery of orders. For each order, a plurality of delivery events and corresponding timestamps are received from devices operated by customers, restaurants, and couriers. Based on the timestamps, the system generates a plurality of ETA time predictions for one or more of the delivery events with trained predictive models that use weighted factors including historical restaurant data and historical courier performance. As additional timestamps are received for a delivery event, the trained predictive models dynamically update the ETA time predictions for successive events. The predictive models may be continuously trained by updating the weighted factors based on the received timestamps.