# US 2025/0029120 A1 · Online transaction method, system, and computer-readable non-transitory medium for identifying counterfeits

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

- Number: US 2025/0029120 A1
- Document ID: US20250029120A1
- Status: Published application
- Kind: A1
- Application number: 18/784,007
- Filed: 2024-07-25
- Published: 2025-01-23
- Earliest claimed: 2021-04-28
- Assignees: eBay Inc.
- Applicants: eBay Inc.
- Inventors: Anand Ramasubramanian; Alagu Muthuraman
- Web page: https://patentgrep.com/patent/US20250029120A1

## CPC

- G06Q 30/0185: {Product, service or business identity fraud}
- G06V 20/66: Trinkets, e.g. shirt buttons or jewellery items (recognising microscopic objects G06V20/69)
- G06Q 30/018: Certifying business or products
- G06Q 30/0248: {Avoiding fraud}
- G06Q 30/0601: Electronic shopping [e-shopping]
- G06Q 30/0609: {Qualifying participants for shopping transactions (payment transaction verification G06Q20/401)}
- G06Q 30/08: Auctions
- G06T 7/74: {involving reference images or patches}
- G06T 7/77: using statistical methods
- G06V 10/74: Image or video pattern matching; Proximity measures in feature spaces
- G06V 10/82: using neural networks
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems and methods are provided for identifying an item that is counterfeit in the marketplace. Sales of counterfeit items in marketplaces, particularly at auction places, have been an issue. There has been a need to automatically detect an item that is counterfeit when a seller submits the item for sale in the marketplace. The disclosed technology receives information about an item for transaction. The information associated with the item includes metadata related to the item and an image of the item. The method uses a database of items that are known to be not for sale (e.g., a stock photo) or is otherwise a counterfeit item. The method matches the data of the item against the data in the database and identifies the item as counterfeit based on the matched result. The matching operation includes analyzing the data (e.g., image analyses using features of the image data). Use of the disclosed technology enables automatic and efficient detection of counterfeit items as a seller submits the item for sale in the marketplace, thereby increasing reliability of the marketplace from buyers' perspective.

## Claims

### Claim 1

A method comprising:
receiving information for an item for sale on an online marketplace, the information including first data associated with the item;
identifying a category of the item from the first data;
generating, by an embedding generator of a trained model, an embedding of the first data that includes a multi-dimensional vector mapping of image data of the first data;
generating, by a match predictor of the trained model, probability distribution data based on the embedding, the probability distribution data indicating a likelihood that the first data matches at least second data in a set of data associated with image data of a set of not-for-sale items corresponding to the item in a database, the trained model comprising a neural network that pattern-matches based on one or more features associate with a predefined portion of the image data, the predefined portion being based on the category of the item;
identifying, based on the probability distribution data indicating the likelihood that the first data matches the at least second data, the item as not-for sale; and
causing suspending of the item on the online marketplace.

### Claim 2 (depends on 1)

The method of claim 1, wherein the identifying the item as not-for-sale comprises identifying the item as counterfeit.

### Claim 3 (depends on 1)

The method of claim 1, wherein the identifying the item as not-for-sale comprises identifying the item as stolen.

### Claim 4 (depends on 1)

The method of claim 1, wherein the generating the probability distribution data and the identifying the item as not-for-sale occurs in real-time as the information for the item is received.

### Claim 5 (depends on 1)

The method of claim 1, wherein the embedding includes a multi-dimensional representation of metadata including the category.

### Claim 6 (depends on 1)

The method of claim 1, wherein the one or more features is based on the category of the item.

### Claim 7 (depends on 1)

The method of claim 1, further comprising determining a confidence value that the item is not-for-sale.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
providing a notification that indicates a percentage likelihood that the item matches an identified counterfeit or stolen item.

### Claim 9 (depends on 1)

The method of claim 1, wherein the causing suspending of the item comprises disabling a listing of the item on the online marketplace.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
identifying a seller of the item;
updating a transaction state of the seller; and
providing a notification to the seller regarding a status of the seller with the online marketplace that is based on the transaction state.

### Claim 11 (depends on 1)

The method of claim 1, wherein the generating the probability distribution comprises:
determining, based on the category of the item, the one or more features of the image data; and
performing, based on the one or more features, a pixel-level comparison of the predefined portion of the image data and the image data of the set of not-for-sale items.

### Claim 12

A system comprising:
one or more processors; and
a memory storing computer-executable instructions that when executed by the one or more processors cause the system to perform operations comprising:
receiving information for an item for sale on an online marketplace, the information including first data associated with the item;
identifying a category of the item from the first data;
generating, by an embedding generator of a trained model, an embedding of the first data that includes a multi-dimensional vector mapping of image data of the first data;
generating, by a match predictor of the trained model, probability distribution data based on the embedding, the probability distribution data indicating a likelihood that the first data matches at least second data in a set of data associated with image data of a set of not-for-sale items corresponding to the item in a database, the trained model comprising a neural network that pattern-matches based on one or more features associate with a predefined portion of the image data, the predefined portion being based on the category of the item;
identifying, based on the probability distribution data indicating the likelihood that the first data matches the at least second data, the item as not-for sale; and
causing suspending of the item on the online marketplace.

### Claim 13 (depends on 12)

The system of claim 12, wherein the identifying the item as not-for-sale comprises identifying the item as counterfeit or stolen.

### Claim 14 (depends on 12)

The system of claim 12, wherein the generating the probability distribution data and the identifying the item as not-for-sale occurs in real-time as the information for the item is received.

### Claim 15 (depends on 12)

The system of claim 12, wherein the embedding includes a multi-dimensional representation of metadata including the category.

### Claim 16 (depends on 12)

The system of claim 12, wherein the one or more features is based on the category of the item.

### Claim 17 (depends on 12)

The system of claim 12, wherein the causing suspending of the item comprises disabling a listing of the item on the online marketplace.

### Claim 18 (depends on 12)

The system of claim 12, wherein the operations further comprise:
identifying a seller of the item;
updating a transaction state of the seller; and
providing a notification to the seller regarding a status of the seller with the online marketplace that is based on the transaction state.

### Claim 19 (depends on 12)

The system of claim 12, wherein the generating the probability distribution comprises:
determining, based on the category of the item, the one or more features of the image data; and
performing, based on the one or more features, a pixel-level comparison of the predefined portion of the image data and the image data of the set of not-for-sale items.

### Claim 20

A non-transitory, computer-readable medium storing instructions that when executed by one or more processors cause the one or more processors to perform operation comprising:
receiving information for an item for sale on an online marketplace, the information including first data associated with the item;
identifying a category of the item from the first data;
generating, by an embedding generator of a trained model, an embedding of the first data that includes a multi-dimensional vector mapping of image data of the first data;
generating, by a match predictor of the trained model, probability distribution data based on the embedding, the probability distribution data indicating a likelihood that the first data matches at least second data in a set of data associated with image data of a set of not-for-sale items corresponding to the item in a database, the trained model comprising a neural network that pattern-matches based on one or more features associate with a predefined portion of the image data, the predefined portion being based on the category of the item;
identifying, based on the probability distribution data indicating the likelihood that the first data matches the at least second data, the item as not-for sale; and
causing suspending of the item on the online marketplace.
