Authors:
Lucas Blanck, Adrian Rodriguez, Jonathan Waite
Abstract:
This disclosure proposes using existing customer detection technology to provide an algorithm to automatically assign online order pickup to lowest traffic density location.
Background:
During times where social distancing is necessary (COVID-19), there is no way for customers to automatically select a pickup location based on lowest number of people in the store. Currently, the customer must be aware of traffic patterns that location exhibits and make an educated guess on whether or not to select that store. It would be beneficial for the online ordering experience to allow the pickup option to be based on social distancing observance.
Description:
1) Retailers today already have systems in place to monitor foot traffic in their stores. This can include cameras, sensors, heatmaps, etc., which then feed these analytics into some sort of database/data store.
2) The data from those detection feeds is then fed into a new AI algorithm that can analyze patterns observed for the last few days/weeks/months and for certain times of the day (ex. afternoon) and time of the week (ex. weekends).
3) Based off of the most recent calculations, the algorithm suggests to the customer which store within a previously configured distance range is the least populated for the pickup time window selected.
ex. Shopper purchases an item online and selects "Pickup in Store" from a list of stores having adequate inventory. When selecting a store to pickup the order from, the customer is presented with a new option labeled "Least Busy" (or something similar). If this option is selected, the algorithm is referenced along with customer inputs including an (optional) allowable distance range as well as an (optional) preferred pickup time window.
TGCS Reference 2293
