# US 2012/0254151 A1 · System and method for keyword extraction

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

- Number: US 2012/0254151 A1
- Document ID: US20120254151A1
- Status: Published application
- Kind: A1
- Application number: 13/495,840
- Filed: 2012-06-13
- Published: 2012-10-04
- Earliest claimed: 2006-06-09
- Assignees: eBay Inc.
- Inventors: Alec Reitter; Barb Chang; Ken Sun; Raghav Gupta; Alvaro Bolivar; Alan Lewis
- Web page: https://patentgrep.com/patent/US20120254151A1

## CPC

- G06F 16/951: Indexing; Web crawling techniques
- G06F 16/903: Querying (for retrieval from the web G06F16/953)
- G06F 16/9035: Filtering based on additional data, e.g. user or group profiles
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A computer-implemented system and method for keyword extraction are disclosed. The system in an example embodiment includes a keyword extraction component to extract relevant keywords from content of a web page, to identify items relevant to the extracted keywords, and to rank the relevant items.

## Claims

### Claim 1

A method comprising:
using a keyword extraction service to extract relevant keywords from content of a web page;
identifying items relevant to the extracted keywords; and
ranking the relevant items.

### Claim 2 (depends on 1)

The method as claimed in claim 1 wherein the web page is identified using a uniform reference locator (URL).

### Claim 3 (depends on 1)

The method as claimed in claim 1 wherein the keyword extraction service is activated when a user accesses the web page.

### Claim 4 (depends on 1)

The method as claimed in claim 1 wherein the keyword extraction service is activated off-line without being triggered by user access of the web page.

### Claim 5 (depends on 1)

The method as claimed in claim 1 further including performing a search using the extracted keywords.

### Claim 6 (depends on 1)

The method as claimed in claim 1 wherein the keyword extraction service may extract relevant keywords from content of the web page using a plurality of extraction processes, the method further including determining which of a plurality of extraction processes is most efficient for the content of the web page.

### Claim 7 (depends on 1)

The method as claimed in claim 1 wherein metadata tags are generated automatically based on the content of the web page.

### Claim 8 (depends on 1)

The method as claimed in claim 1 wherein the keyword extraction service further identifies category information associated with the content of the web page.

### Claim 9 (depends on 1)

The method as claimed in claim 1 wherein the relevancy of the extracted keywords to the items is based on information from the group: measures of item popularity, measures of web site popularity, aggregate user behavior on the web site; user feedback, listings availability, and catalog data.

### Claim 10 (depends on 1)

The method as claimed in claim 1 further including using the extracted keywords to produce a contextual advertisement placement.

### Claim 11 (depends on 1)

The method as claimed in claim 1 further including using the extracted keywords to automatically initiate a re-fetch of content of the web page.

### Claim 12

An article of manufacture comprising a machine-readable medium having machine executable instructions embedded thereon, which when executed by a machine, cause the machine to:
use a keyword extraction service to extract relevant keywords from content of a web page;
identify items relevant to the extracted keywords; and
rank the relevant items.

### Claim 13 (depends on 12)

The article of manufacture as claimed in claim 12 wherein the web page is identified using a uniform reference locator (URL).

### Claim 14 (depends on 12)

The article of manufacture as claimed in claim 12 wherein the keyword extraction service is activated when a user accesses the web page.

### Claim 15

A system comprising:
a processor;
a memory coupled to the processor to store information related to keywords; and
a keyword extraction component to extract relevant keywords from content of a web page, to identify items relevant to the extracted keywords, and to rank the relevant items.

### Claim 16 (depends on 15)

The system as claimed in claim 15 wherein the web page is identified using a uniform reference locator (URL).

### Claim 17 (depends on 15)

The system as claimed in claim 15 wherein the keyword extraction component is activated when a user accesses the web page.

### Claim 18 (depends on 15)

The system as claimed in claim 15 wherein the keyword extraction component is activated off-line without being triggered by user access of the web page.

### Claim 19 (depends on 15)

The system as claimed in claim 15 being further operable to perform a search using the extracted keywords.

### Claim 20 (depends on 15)

The system as claimed in claim 15 wherein the keyword extraction component may extract relevant keywords from content of the web page using a plurality of extraction processes, the system being further operable to determine which of a plurality of extraction processes is most efficient for the content of the web page.

### Claim 21 (depends on 15)

The system as claimed in claim 15 wherein metadata tags are generated automatically based on the content of the web page.

### Claim 22 (depends on 15)

The system as claimed in claim 15 wherein the keyword extraction component being further operable to identify category information associated with the content of the web page.

### Claim 23 (depends on 15)

The system as claimed in claim 15 wherein the relevancy of the extracted keywords to the items is based on information from the group: measures of item popularity, measures of web site popularity, aggregate user behavior on the web site; user feedback, listings availability, and catalog data.

### Claim 24 (depends on 15)

The system as claimed in claim 15 being further operable to use the extracted keywords to produce a contextual advertisement placement.

### Claim 25 (depends on 15)

The system as claimed in claim 15 being further operable to use the extracted keywords to automatically initiate a re-fetch of content of the web page.
