# US 2021/0264513 A1 · Computer-implemented systems and methods for real-time risk-informed return item collection using an automated kiosk

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0264513 A1
- Document ID: US20210264513A1
- Status: Published application
- Kind: A1
- Application number: 17/316,764
- Filed: 2021-05-11
- Published: 2021-08-26
- Earliest claimed: 2019-08-16
- Assignees: Coupang Corp.
- Applicants: Coupang Corp.
- Inventors: Yonghui Chen; Xin Jin; Yan Zhou
- Web page: https://patentgrep.com/patent/US20210264513A1

## CPC

- G06Q 40/03: Credit; Loans; Processing thereof
- G06N 20/00: Machine learning
- G06Q 20/18: involving self-service terminals [SST], vending machines, kiosks or multimedia terminals
- G06Q 20/208: {Input by product or record sensing, e.g. weighing or scanner processing}
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 40/00: Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G07F 7/06: by returnable containers {, i.e. reverse vending systems in which a user is rewarded for returning a container that serves as a token of value}, e.g. bottles
- Y02W 90/00: Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G07F: COIN-FREED OR LIKE APPARATUS (coin sorting G07D3/00; coin testing G07D5/00; {handling coins or paper currencies apart from payment activated apparatus G07D; payment architectures, schemes or protocols G06Q20/00})
- Y02W: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT

## 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.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

An automated kiosk for collecting return items based on a real time risk decision, comprising:
one or more memory devices storing instructions;
a display screen; and
one or more processors configured to execute the instructions to perform operations in real-time, the operations comprising:
capturing return item information for a return item, the return item information comprising at least one of: an order ID, an item ID, a product barcode, a pre-generated QR code, or a pre-generated return ID;
transmitting, the return item information and a request for return risk level relating to the return item information to a server operable to execute a machine learning model 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 applying the machine learning model to the captured return item information;
determining a risk level based on the predicted risk score; and
transmitting the determined risk level to the kiosk;
receiving the transmitted risk level from the server; and
displaying, at the display screen, a return result based on the received risk level.

### Claim 22 (depends on 21)

The automated kiosk of claim 21, wherein:
the operations further comprise determining whether the return item is un-returnable; and
the return result is further based on the determination of whether the return item is un-returnable.

### Claim 23 (depends on 21)

The automated kiosk of claim 21, the operations further comprising requesting additional return item information based on the risk level being above a threshold.

### Claim 24 (depends on 23)

The automated kiosk of claim 23, wherein the requested additional return item information comprises at least one of: an image of the return item or an image of a customer associated with the return item.

### Claim 25 (depends on 21)

The automated kiosk of claim 21, wherein:
the operations further comprise:
receiving additional return item information; and
determining whether the additional return item information is valid; and
the return result is based on the determination of whether the additional return item information is valid.

### Claim 26 (depends on 25)

The automated kiosk of claim 25, wherein:
the additional return item information comprises an image of the return item; and
determining whether the additional return item information is valid comprises comparing the image of the return item to a stored image.

### Claim 27 (depends on 25)

The automated kiosk of claim 25, the operations further comprising displaying, at the display screen, a result of determining whether the additional return item information is valid.

### Claim 28 (depends on 25)

The automated kiosk of claim 25, wherein either:
determining whether the additional return item information is valid comprises determining that the additional return item information is valid, and the return result is an acceptance result; or
determining whether the additional return item information is valid comprises determining that the additional return item information is not valid, and the return result is a rejection result.

### Claim 29 (depends on 21)

The automated kiosk of claim 21, wherein:
the return result is an acceptance result; and
the operations further comprise ejecting, based on the return result being an acceptance result, a container for returning the return item.

### Claim 30 (depends on 21)

The automated kiosk of claim 21, the operations further comprising determining a refund amount and a refund timing, the refund amount and the refunding timing being based on the return result and the risk score.

### Claim 31 (depends on 21)

The automated kiosk of claim 21, wherein:
the risk level is determined from among multiple risk levels; and
the multiple risk levels are defined according to a percentage of total returns.

### Claim 32 (depends on 21)

The automated kiosk of claim 21, wherein the machine learning model comprises a Gradient Boosting Tree Model.

### Claim 33 (depends on 21)

The automated kiosk of claim 21, wherein the machine learning model is configured to receive an input comprising at least one of: a return history, a return amount, a list of return products, or a return time.

### Claim 34

A method for collecting return items based on a real time risk decision, comprising:
capturing return item information for a return item, the return item information comprising at least one of: an order ID, an item ID, a product barcode, a pre-generated QR code, or a pre-generated return ID;
transmitting, the return item information and a request for return risk level relating to the return item information to a server operable to execute a machine learning model 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 applying the machine learning model to the captured return item information;
determining a risk level based on the predicted risk score; and
transmitting the determined risk level to the kiosk;
receiving the transmitted risk level from the server; and
displaying, at the display screen, a return result based on the received risk level.

### Claim 35 (depends on 34)

The method of claim 34, further comprising requesting additional return item information based on the risk level being above a threshold.

### Claim 36 (depends on 34)

The method of claim 34, the method further comprising:
receiving additional return item information; and
determining whether the additional return item information is valid, wherein the return result is based on the determination of whether the additional return item information is valid.

### Claim 37 (depends on 36)

The method of claim 36, wherein:
the additional return item information comprises an image of the return item; and
determining whether the additional return item information is valid comprises comparing the image of the return item to a stored image.

### Claim 38 (depends on 34)

The method of claim 34, further comprising determining a refund amount and a refund timing, the refund amount and the refunding timing being based on the return result and the risk score.

### Claim 39 (depends on 34)

The method of claim 34, further comprising determining a refund amount and a refund timing, the refund amount and the refunding timing being based on the return result and the risk score.

### Claim 40 (depends on 34)

The method of claim 34, wherein:
the risk level is determined from among multiple risk levels; and
the multiple risk levels are defined according to a percentage of total returns.
