Computer-implemented systems and methods for real-time risk-informed return item collection using an automated kiosk

Patent metadata

Field	Value
Publication number	US-10657591-B1
Application number	US-201916542588-A
Country	US
Kind code	B1
Filing date	Aug 16, 2019
Priority date	Aug 16, 2019
Publication date	May 19, 2020
Grant date	May 19, 2020

Abstract

Disclosed embodiments provide systems and methods related to collecting return items using an automated kiosk based on a real time risk decision. The automated kiosk captures return item information representing a return item and transmits the return item information and a request for return risk level relating to the return item to a server operable to execute a machine learning model trained on historical information to determine the risk level. The server determines the risk level based on the received return by using the machine learning model and transmits the determined risk level to the kiosk in real-time. Based on the determined risk level and a return amount associated with the return item, the server may also process a refund in real-time.

First claim

What is claimed is:

1. An automated kiosk for collecting return items based on a real time risk decision, comprising:
one or more memory devices storing instructions;
an imaging device;
one or more containers, each container associated with an identifier associated with a status of empty or occupied;
a network interface;
a display screen;
one or more processors configured to execute the instructions to perform operations comprising:
responding to user input by capturing, with the imaging device, return item information representing a return item;
transmitting, via the network interface, the return item information and a request for return risk level relating to the return item to a server operable to execute a machine learning model trained on historical information to predict a risk score, wherein the server is configured to prepare the return risk level in response to the request by:
predicting a risk score of the return request based on the captured return item information by deploying the machine learning model;
determining a risk level based on the predicted risk score;
transmitting the determined risk level to the kiosk;

receiving the transmitted risk level through the network interface from the server;
displaying a return result on the display screen based on the received risk level; and
accepting the return item based on the received risk level, and

wherein the operations are performed in real-time.

2. The automated kiosk of claim 1 , wherein the return item information includes at least one of:
an order ID,
an item ID,
a product barcode,
a pre-generated QR code, or
a pre-generated return ID.

3. The automated kiosk of claim 1 , wherein the server is configured to prepare the return risk level using a supervised machine learning model trained on historical information including at least one of a return history, a return amount, a list of returned products, or a return time.

4. The automated kiosk of claim 1 , wherein the risk level is divided into high, medium, and low.

5. The automated kiosk of claim 1 , wherein the operations further comprise:
responding to a user input by capturing, with the imaging device, additional information when the received risk level is medium; and
transmitting, via the network interface to a server, the additional information, and a request for new return risk level relating to the return item, and
wherein the additional information includes a picture of the return item, a picture of the user, or additional proof relating to the return.

6. The automated kiosk of claim 1 , further comprising a receptacle, and further wherein the processor is configured to execute the instructions to perform operations comprising:
ejecting, via the receptacle, one of the containers associated with an empty status for the user to store the return item when the risk level is low or medium.

7. The automated kiosk of claim 6 , further comprising:
accepting the return item via the ejected container;
causing the processor to perform operations comprising:
transmitting, via the network interface to a server, a return confirmation, wherein the server is configured to process a refund by:
storing the return item information;
determining a refund based on the determined risk level and a return amount;
processing a refund based on the determined refund;
transmitting the determined refund to the kiosk;

receiving the determined refund through the network interface from the server; and
displaying the received refund on the display screen.

8. The automated kiosk of claim 7 , wherein the refund is instant when the risk level is low and the return amount is lower than a predefined amount.

9. The automated kiosk of claim 7 , wherein the refund is fast when the risk level is low and the return amount is higher than a predefined amount.

10. The automated kiosk of claim 7 , wherein the refund is postponed when the risk level is medium.

11. A method for collecting return items using an automated kiosk based on a real time risk decision, comprising:
responding to user input by capturing, with an imaging device, return item information representing a return item;
transmitting, via the network interface, the return item information and a request for return risk level relating to the return item to a server operable to execute a machine learning model trained on historical information to predict a risk score, wherein the server is configured to prepare the return risk level in response to the request by:
predicting a risk score of the return request based on the captured return item information by deploying the machine learning model;
determining a risk level based on the predicted risk score; and
transmitting the determined risk level to the kiosk;

receiving the transmitted risk level through the network interface from the server;
displaying a return result on the display screen based on the received risk level; and
accepting the return item based on the received risk level, and
wherein the operations are performed in real-time.

12. The method of claim 11 , wherein the server is configured to prepare the return risk level using a supervised machine learning model trained on historical information including at least one of a return history, a return amount, a list of returned products, or a return time.

13. The method of claim 11 , wherein the risk level is divided into high, medium, and low.

14. The method of claim 11 , wherein the method further comprises:
responding to a user input by capturing, with the imaging device, additional information when the received risk level is medium; and
transmitting, via the network interface to a server, the additional information, and a request for new return risk level relating to the return item, and
wherein the additional information includes a picture of the return item, a picture of the user, or additional proof relating to the return.

15. The method of claim 11 , wherein the method further comprises ejecting, via a receptacle, one of containers associated with an empty status for the user to store the return item when the risk level is low or medium.

16. The method of claim 15 , wherein the method further comprises:
accepting the return item via the ejected container;
transmitting, via the network interface to the server, a return confirmation,
wherein the server is configured to process a refund by:
storing the return item information;
determining a refund based on the determined risk level and a return amount;
processing a refund based on the determined refund;
transmitting the determined refund to the kiosk;

receiving the determined refund through the network interface from the server; and
displaying the received refund on the display screen.

17. The method of claim 16 , wherein the refund is instant when the risk level is low, and the return amount is lower than a predefined amount.

18. The method of claim 16 , wherein the refund is fast when the risk level is low, and the return amount is higher than a predefined amount.

19. The method of claim 16 , wherein the refund is postponed when the risk level is medium.

20. A system comprising:
a network;
an automated kiosk for collecting return items based on a real time risk decision, comprising:
an imaging device;
a network interface;
a display screen;
one or more memory devices storing instructions; and
one or more processors configured to execute the instructions to perform operations comprising:
responding to user input by ca

Assignees

• Coupang Corp

Inventors

• Chen Yonghui
• Jin Xin
• Zhou Yan

Classifications

• G06Q20/208

  Input by product or record sensing, e.g. weighing or scanner processing · CPC title

• G06Q40/00 Primary

  Finance; Insurance; Tax strategies; Processing of corporate or income taxes · CPC title

• G06Q40/025 Primary

  Physics · mapped topic

• G06Q40/03 Primary

  Credit; Loans; Processing thereof · CPC title

• Y02W90/00

  Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation · CPC title