# US 12,223,684 B2 · Neural network based physical condition evaluation of electronic devices, and associated systems and methods

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

- Number: US 12,223,684 B2
- Document ID: US12223684B2
- Status: Granted
- Kind: B2
- Application number: 18/472,994
- Filed: 2023-09-22
- Published: 2024-03-14
- Granted: 2025-02-11
- Earliest claimed: 2019-02-18
- Assignees: ecoATM, LLC
- Applicants: ecoATM, LLC
- Inventors: John Silva; Babak Forutanpour
- Web page: https://patentgrep.com/patent/US12223684B2

## CPC

- G06V 10/141: Control of illumination
- G02B 27/30: Collimators
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06Q 30/0283: Price estimation or determination
- G06T 7/0004: {Industrial image inspection}
- G06T 7/0008: {checking presence/absence}
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- 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
- H04N 23/56: provided with illuminating means
- G06T 2207/10024: Color image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30108: Industrial image inspection
- G06V 2201/06: Recognition of objects for industrial automation
- Y02W 90/00: Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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})
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- Y02W: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT

## Abstract

Systems and methods for evaluating the physical and/or cosmetic condition of electronic devices using machine learning techniques are disclosed. In one example aspect, an example system includes a kiosk that comprises an inspection plate configured to hold an electronic device, one or more light sources arranged above the inspection plate configured to direct one or more light beams towards the electronic device, and one or more cameras configured to capture at least one image of a first side of the electronic device. The system also includes one or more processors in communication with the one or more cameras configured to extract a set of features of the electronic device and determine, via a first neural network, a condition of the electronic device based on the set of features.

## Claims

### Claim 1

A system for evaluating a condition of an electronic device, the system comprising:
a kiosk that includes:
one or more cameras configured to capture at least one image of a first side of the electronic device; and
one or more processors in communication with the one or more cameras, the one or more processors configured to:
apply a first machine learning model to the at least one image of the electronic device,
wherein the first machine learning model is trained to output, based on analyzing the at least one image, a brand and/or model of the electronic device and a cosmetic rating of the electronic device specific to the brand and/or model;
determine the condition of the electronic device based on the cosmetic rating; and
determine, via a second machine learning model, an offer price for the electronic device based on the determined condition,
wherein the second machine learning model is different from the first machine learning model.

### Claim 2 (depends on 1)

The system of claim 1, wherein the one or more processors are configured to determine that the at least one image captured by the one or more cameras is defective.

### Claim 3 (depends on 1)

The system of claim 1, wherein the second machine learning model is configured to use a sub-model to predict a resale value of the electronic device to provide the offer price.

### Claim 4 (depends on 1)

The system of claim 1, wherein the kiosk includes:
a flipping mechanism configured to flip the electronic device to allow the one or more cameras to capture at least another image of the electronic device.

### Claim 5 (depends on 1)

The system of claim 1, wherein the second machine learning model is configured to use a sub-model to predict an incoming number of electronic devices.

### Claim 6 (depends on 1)

The system of claim 1, wherein the second machine learning model is configured to use a sub-model to predict processing costs associated with the electronic device.

### Claim 7 (depends on 1)

The system of claim 1, wherein the one or more cameras are configured to capture multiple images corresponding to multiple sides of the electronic device under different lighting conditions, and wherein the one or more processors are configured to process and combine the multiple images into a single input image.

### Claim 8 (depends on 1)

The system of claim 1, wherein the offer price is based on a location of the kiosk, a time at which the electronic device is examined, and/or an age of the electronic device.

### Claim 9 (depends on 1)

The system of claim 1, wherein the offer price is based on a predicted repair cost for the electronic device, a risk of counterfeit or fraud, and/or an anticipated demand for the electronic device.

### Claim 10 (depends on 1)

The system of claim 1, wherein the second machine learning model is configured to use sub-models distributed across different locations in a network in accordance with a cloud-based computing service.

### Claim 11

A computer-implemented method for evaluating a condition of an electronic device, the method comprising:
capturing, by at least one camera of a kiosk, at least one image of a first side of the electronic device;
applying a first machine learning model to the at least one image of the electronic device,
wherein the first machine learning model is trained to output, based on analyzing the at least one image, a brand and/or model of the electronic device and a cosmetic rating of the electronic device specific to the brand and/or model;
determining the condition of the electronic device based on the cosmetic rating; and
determining, via a second machine learning model, an offer price for the electronic device based on the determined condition,
wherein the second machine learning model is different from the first machine learning model.

### Claim 12 (depends on 11)

The method of claim 11, comprising:
capturing, via the at least one camera, at least one image of a second side of the electronic device that is different from the first side.

### Claim 13 (depends on 12)

The method of claim 12, comprising:
prior to capturing the at least one image of the second side of the electronic device:
flipping the electronic device such that light beams of multiple light sources of the kiosk are directed towards the second side of the electronic device.

### Claim 14 (depends on 11)

The method of claim 11, comprising:
processing multiple images of multiple sides of the electronic device such that the multiple images have a uniform size; and
combining the multiple images into a single image to be provided to the first machine learning model.

### Claim 15 (depends on 11)

The method of claim 11, comprising:
determining whether the at least one image captured by the at least one camera is acceptable or defective,
wherein applying the first machine learning model to the at least one image is performed only when the at least one image captured by the at least one camera is determined to be acceptable.

### Claim 16 (depends on 11)

The method of claim 11, comprising:
using, by the second machine learning model, a sub-model to predict a resale value of the electronic device to provide the offer price.

### Claim 17 (depends on 11)

The method of claim 11, comprising:
receiving an input from a user indicating an acceptance or a rejection of the offer price; and
training the second machine learning model in part based on the at least one image and the input from the user.

### Claim 18 (depends on 11)

The method of claim 11, comprising using, by the second machine learning model, a sub-model to predict an incoming number of electronic devices to provide the offer price.

### Claim 19 (depends on 11)

The method of claim 11, comprising using, by the second machine learning model, a sub-model to predict processing costs associated with the electronic device to provide the offer price.

### Claim 20 (depends on 11)

The method of claim 11, wherein the offer price is based on a predicted repair cost for the electronic device, a risk of counterfeit or fraud, and/or an anticipated demand for the electronic device.