# US 2020/0394666 A1 · Machine Generated Recommendation and Notification Models

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

- Number: US 2020/0394666 A1
- Document ID: US20200394666A1
- Status: Published application
- Kind: A1
- Application number: 17/007,854
- Filed: 2020-08-31
- Published: 2020-12-17
- Earliest claimed: 2014-09-22
- Assignees: eBay Inc.
- Applicants: eBay Inc.
- Inventors: Elizabeth Churchill; Bryan Kent Ressler; Atish Das Sarma; Michael Gilbert
- Web page: https://patentgrep.com/patent/US20200394666A1

## CPC

- G06Q 30/0203: Market surveys; Market polls
- G06F 16/23: Updating
- G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536)
- G06F 16/337: {Profile generation, learning or modification}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- H04L 67/306: User profiles
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods are presented for matching a buyer and a seller on a market place system and generating calibrated user profiles. In one such system a plurality of subjective estimations of value is received. The subjective estimations of value are a measure between a predetermined minimum value and a predetermined maximum value. A user profile is generated. A plurality of user actions corresponding to the plurality of subjective estimations of value is received. The user profile is calibrated based on the plurality of user actions.

## Claims

### Claim 1

A computer-implemented method, comprising:
detecting an association of a user profile with an image depicting an item;
determining at least one characteristic of the item depicted in the image;
calibrating the user profile using the at least one characteristic;
identifying at least one different image based on the calibrated user profile; and
presenting the at least one different image at a client device associated with the user profile.

### Claim 2 (depends on 1)

The method of claim 1, wherein detecting the association of the user profile with the image depicting the item comprises detecting a placement of the image depicting the item into a storage location associated with the user profile.

### Claim 3 (depends on 1)

The method of claim 1, wherein detecting the association of the user profile with the image depicting the item comprises detecting a placement of the image depicting the item into a category of images defined by a theme and calibrating the user profile is further performed using characteristics from one or more different images included in the category of images defined by the theme.

### Claim 4 (depends on 3)

The method of claim 3, wherein the category of images defined by the theme is a private category of images accessible only by the user profile.

### Claim 5 (depends on 3)

The method of claim 3, wherein the category of images defined by the theme is a shared category of images accessible by the user profile and at least one additional user profile that is granted access to the shared category of images by the user profile.

### Claim 6 (depends on 1)

The method of claim 1, wherein detecting the association of the user profile with the image depicting the item comprises detecting a comment on the image depicting the item, or an indication of interest in the image depicting the item, by the user profile.

### Claim 7 (depends on 1)

The method of claim 1, wherein detecting the association of the user profile with the image depicting the item comprises detecting a share of the image depicting the item by the user profile with at least one other user profile.

### Claim 8 (depends on 1)

The method of claim 1, wherein detecting the association of the user profile with the image depicting the item comprises detecting a capture of the image depicting the item by an image capture device of the client device.

### Claim 9 (depends on 1)

The method of claim 1, wherein determining the at least one characteristic of the item depicted in the image is performed based on metadata associated with the image.

### Claim 10 (depends on 1)

The method of claim 1, wherein determining the at least one characteristic of the item depicted in the image includes performing image analysis to recognize the item depicted in the image.

### Claim 11 (depends on 1)

The method of claim 1, wherein the at least one characteristic of the item depicted in the image includes one or more of an item type, an item category, an item brand, a color, a shape, a price, or an item description.

### Claim 12 (depends on 1)

The method of claim 1, further comprising extracting metadata from the at least one different image and conducting a search for additional images using the metadata and presenting a result of the search at the client device.

### Claim 13

A method comprising:
detecting an association of a user profile with an image depicting an item;
determining at least one characteristic of the item depicted in the image;
identifying at least one different image depicting a different item that shares the at least one characteristic;
extracting metadata from the at least one different image and conducting a search for images using the metadata; and
causing presentation of a result of the search at a client device associated with the user profile.

### Claim 14 (depends on 13)

The method of claim 13, wherein detecting the association of the user profile with the image depicting the item comprises detecting a placement of the image depicting the item into a category of images defined by a theme and identifying the at least one different image depicting the different item is further performed using characteristics from one or more images included in the category of images defined by the theme.

### Claim 15 (depends on 13)

The method of claim 13, wherein detecting the association of the user profile with the image depicting the item comprises detecting a comment on the image depicting the item, or an indication of interest in the image depicting the item, by the user profile.

### Claim 16 (depends on 13)

The method of claim 13, wherein detecting the association of the user profile with the image depicting the item comprises detecting a share of the image depicting the item by the user profile with at least one other user profile.

### Claim 17 (depends on 13)

The method of claim 13, wherein determining the at least one characteristic of the item depicted in the image is performed based on metadata associated with the image.

### Claim 18 (depends on 13)

The method of claim 13, further comprising receiving a search term from the client device, wherein conducting the search for images is further performed using the search term.

### Claim 19 (depends on 13)

The method of claim 13, further comprising receiving data indicative of a plurality of communication mechanisms for transmitting the result of the search to the client device, wherein causing presentation of the result of the search comprises selecting one of the plurality of communication mechanisms and transmitting the result of the search to the client device using the selected communication mechanism.

### Claim 20

A system comprising:
one or more processors; and
a computer readable storage medium having instructions stored thereon that are executable by the one or more processors to perform operations comprising:
detecting an association of a user profile with an image depicting an item;
determining at least one characteristic of the item depicted in the image;
calibrating the user profile using the at least one characteristic;
identifying at least one different image based on the calibrated user profile; and
presenting the at least one different image at a client device associated with the user profile.
