# US 2020/0394242 A1 · Methods and systems for social network based content recommendations

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

- Number: US 2020/0394242 A1
- Document ID: US20200394242A1
- Status: Published application
- Kind: A1
- Application number: 17/005,679
- Filed: 2020-08-28
- Published: 2020-12-17
- Earliest claimed: 2014-11-25
- Assignees: eBay Inc.
- Applicants: eBay Inc.
- Inventors: Michael Gilbert; Elizabeth Churchill
- Web page: https://patentgrep.com/patent/US20200394242A1

## CPC

- G06F 16/9536: Search customisation based on social or collaborative filtering
- G06F 16/245: Query processing
- G06F 16/24578: {using ranking}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods are presented for generating recommendations using multi-level social network analysis of user behavior. In some embodiments, the system receives a set of user interactions, from a plurality of users, performed on a set of data objects; generates a set of associations between the set of data objects; and identifies a set of data object clusters indicative of the set of associations. The system generates an organization of the set of data objects based on the set of associations and the set of data object clusters and causes presentation of a plurality of data objects of the set of data objects on a user interface of a user device based on the organization.

## Claims

### Claim 1

A computer-implemented method comprising:
monitoring, by at least one processor, a set of user interactions of a user with a first listing for a first product of a first product category and a second listing for a second product of a second product category;
generating, based at least in part on the set of user interactions, a network graph associated with the user, the network graph indicating an association between the first product category and the second product category;
receiving a query from the user;
identifying, by the at least one processor, a plurality of recommendations indicative of a plurality of listings based at least in part on the query and the network graph; and
causing, by the at least one processor, presentation of at least one recommendation of the plurality of recommendations on a user interface of a user device based at least in part on the identifying.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
ranking the plurality of recommendations based at least in part on the network graph, wherein causing presentation of the at least one recommendation is based at least in part on the ranking.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
determining an association strength between the first product category and the second product category based at least in part on the set of user interactions, wherein the ranking is based at least in part on determining the association strength.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
generating a weight for each recommendation of the plurality of recommendations based at least in part on the association strength and the set of user interactions, wherein ranking the plurality of recommendations is based at least in part on the weight generated for each recommendation of the plurality of recommendations.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
determining a first tie strength between the user and a second user, wherein identifying the plurality of recommendations is based at least in part on the first tie strength.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
determining a second tie strength between the first listing and the second listing based at least in part on monitoring the set of user interactions, wherein identifying the plurality of recommendations is based at least in part on the first tie strength and the second tie strength.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
determining a second tie strength between the first listing and the second listing based at least in part on monitoring the set of user interactions; and
selectively adjusting the second tie strength based at least in part on the first tie strength, wherein identifying the plurality of recommendations is based at least in part on a selectively adjusted second tie strength.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
identifying a second network graph associated with a second user, the second network graph generated based at least in part on an additional set of user interactions of the second user; and
identifying at least one relationship between the network graph and the second network graph, wherein identifying the plurality of recommendations is based at least in part on the second network graph.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
identifying, based at least in part on the network graph and the second network graph, an association between the first product category and a third product category, wherein identifying the plurality of recommendations is based at least in part on identifying the association between the first product category and the third product category.

### Claim 10

A system, comprising:
one or more processors; and
a non-transitory machine-readable storage medium coupled to the one or more processors, the non-transitory machine-readable storage medium including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
monitoring a set of user interactions of a user with a first listing for a first product of a first product category and a second listing for a second product of a second product category;
generating, based at least in part on the set of user interactions, a network graph associated with the user, the network graph indicating an association between the first product category and the second product category;
receiving a query from the user;
identifying a plurality of recommendations indicative of a plurality of listings based at least in part on the query and the network graph; and
causing presentation of at least one recommendation of the plurality of recommendations on a user interface of a user device based at least in part on the identifying.

### Claim 11 (depends on 10)

The system of claim 10, wherein the operations further comprise:
ranking the plurality of recommendations based at least in part on the network graph, wherein causing presentation of the at least one recommendation is based at least in part on the ranking.

### Claim 12 (depends on 11)

The system of claim 11, wherein the operations further comprise:
determining an association strength between the first product category and the second product category based at least in part on the set of user interactions, wherein the ranking is based at least in part on determining the association strength.

### Claim 13 (depends on 12)

The system of claim 12, wherein the operations further comprise:
generating a weight for each recommendation of the plurality of recommendations based at least in part on the association strength and the set of user interactions, wherein ranking the plurality of recommendations is based at least in part on the weight generated for each recommendation of the plurality of recommendations.

### Claim 14 (depends on 10)

The system of claim 10, wherein the operations further comprise:
determining a first tie strength between the user and a second user, wherein identifying the plurality of recommendations is based at least in part on the first tie strength.

### Claim 15 (depends on 14)

The system of claim 14, wherein the operations further comprise:
determining a second tie strength between the first listing and the second listing based at least in part on monitoring the set of user interactions, wherein identifying the plurality of recommendations is based at least in part on the first tie strength and the second tie strength.

### Claim 16 (depends on 14)

The system of claim 14, wherein the operations further comprise:
determining a second tie strength between the first listing and the second listing based at least in part on monitoring the set of user interactions; and
selectively adjusting the second tie strength based at least in part on the first tie strength, wherein identifying the plurality of recommendations is based at least in part on a selectively adjusted second tie strength.

### Claim 17 (depends on 10)

The system of claim 10, wherein the operations further comprise:
identifying a second network graph associated with a second user, the second network graph generated based at least in part on an additional set of user interactions of the second user; and
identifying at least one relationship between the network graph and the second network graph, wherein identifying the plurality of recommendations is based at least in part on the second network graph.

### Claim 18 (depends on 17)

The system of claim 17, wherein the operations further comprise:
identifying, based at least in part on the network graph and the second network graph, an association between the first product category and a third product category, wherein identifying the plurality of recommendations is based at least in part on identifying the association between the first product category and the third product category.

### Claim 19

A non-transitory machine-readable storage medium comprising processor executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising:
monitoring a set of user interactions of a user with a first listing for a first product of a first product category and a second listing for a second product of a second product category;
generating, based at least in part on the set of user interactions, a network graph associated with the user, the network graph indicating an association between the first product category and the second product category;
receiving a query from the user;
identifying a plurality of recommendations indicative of a plurality of listings based at least in part on the query and the network graph; and
causing presentation of at least one recommendation of the plurality of recommendations on a user interface of a user device based at least in part on the identifying.

### Claim 20 (depends on 19)

The non-transitory machine-readable storage medium of claim 19, wherein the operations further comprise:
ranking the plurality of recommendations based at least in part on the network graph, wherein causing presentation of the at least one recommendation is based at least in part on the ranking.
