US 2021/0264275 A1 · SYSTEM FOR DYNAMIC ESTIMATED TIME OF ARRIVAL PREDICTIVE UPDATES

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.

Claims20

Dependent claims

A server comprising a processor and memory, wherein the processor is configured to:

train a neural network using a training dataset to dynamically output estimated time of arrival (ETA) predictive updates, wherein the neural network includes a plurality of subnetworks, each subnetwork corresponding to a duration between two successive events of a series of events for an order;
and
receive a first confirmation message from a user device, the first confirmation message including first information corresponding to a first event of the series of events;
and
input the first information into the neural network to automatically generate a first ETA prediction using weighted factors in the neural network, the first ETA prediction corresponding to the duration for a target event of the series of events, wherein the first ETA prediction is based on at least one output of the plurality of subnetworks.

2 more elements

A non-transitory computer readable medium storing one or more programs configured for execution by a computer system, the one or more programs comprising instructions for:

training a neural network using a training dataset to dynamically output estimated time of arrival (ETA) predictive updates, wherein the neural network includes a plurality of subnetworks, each subnetwork corresponding to a duration between two successive events of a series of events for an order;
receiving a first confirmation message from a user device, the first confirmation message including first information corresponding to a first event of the series of events;
and
inputting the first information into the neural network to automatically generate a first ETA prediction using weighted factors in the neural network, the first ETA prediction corresponding to the duration for a target event of the series of events, wherein the first ETA prediction is based on at least one output of the plurality of subnetworks.

1 more element

Dependencies are inferred from the claim text.

System for dynamic estimated time of arrival predictive updates

Life of this patent

System for dynamic estimated time of arrival predictive updates

Life of this patent

Abstract

Claims20