Content identification expansion

• US 7,657,514 B2
• Filed: 01/30/2007
• Issued: 02/02/2010
• Est. Priority Date: 01/30/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Szulczewski, Piotr
• Primary Examiner(s): Lee; Wilson
• Application Number:
  US11/668,719
• Publication Number:
  US 20080183660A1
• Time in Patent Office: 1,099 Days
• Field of Search: 707 1- 10, 705/14
• US Class Current: 1/1
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Content of a first type, such as web pages, are identified in response to a query. One or more correlated entities are identified based on the content of the first type. Content of a second type, such as advertisements, are identified based on the one or more of the correlated entities.

Claims

1. A computer-implemented method, comprising:

identifying, by a computer system, content of a first type responsive to a query, the content of the first type being a set web documents that a search engine determines to be responsive to the query;

identifying, by the computer system, correlated entities based on the content of the first type, each of the correlated entities being one or more terms that occurs in multiple web documents in the set of web documents; and

identifying first content of a second type based on the correlated entities, the first content of the second type being first advertisements, each of the first advertisements determined to be responsive to at least one of the correlated entities;

wherein identifying correlated entities based on the content of the first type comprises, for each correlated entity;

determining that a term occurs in multiple web documents in the set of documents; and

identifying the term as a correlated entity in response to the determination.

2. The method of claim 1, wherein:

the correlated entities comprise multi-word expressions.

3. The method of claim 1, comprising:

determining, by the computer system for each correlated entity, an average frequency of occurrence of the correlated entity in the web documents in which the correlated entity occurs; and

ranking, by the computer system, the correlated entities based on an average frequencies of occurrence.

4. The method of claim 3, wherein:

determining, by the computer system, for each correlated entity, locations of the correlated entity in each of the web documents in which the correlated entity occurs; and

ranking, by the computer system, the correlated entities based on locations of the correlated entities in the web documents.

5. The method of claim 1, wherein:

identifying first content of the second type based on one or more of the correlated entities comprises;

identifying second content of the second type responsive to the query, the second content of the second type being second advertisements determined to be responsive to the query;

identifying third advertisements from the first and second advertisements, the third advertisements being advertisements that are identified in both the first advertisements and second advertisements; and

filtering the first and second advertisements so that the third advertisements are presented first among the first and second advertisements and with a list of the web documents.

6. The method of claim 1, further comprising:

determining if the number of identified second advertisements exceeds a threshold; and

identifying the correlated entities, the first content of the second type, the third advertisements and filtering the first and second advertisements only if the number of second advertisements does not exceed the threshold.

7. The method of claim 1, further comprising:

for each of the first advertisements, determining a relevance measure that measure the relevance between the query and the first advertisement; and

selecting for presentation only the first advertisements having a relevance measure that exceeds a threshold.

8. A system, comprising:

one or more processors; and

a memory system in data communication with the one or more processors and storing instructions executable by the one or more processors and that upon such execution the instructions cause the one or more processors to perform operations comprising;

identifying content of a first type responsive to a query, the content of the first type being a set web documents a search engine determines to be responsive to the query;

identifying correlated entities based on the content of the first type, each of the correlated entities being one or more terms that occurs in multiple web documents in the set of web documents; and

identifying first content of a second type based on the correlated entities, the first content of the second type being first advertisements, each of the first advertisements determined to be responsive to at least one of the correlated entities;

wherein identifying correlated entities based on the content of the first type comprises, for each correlated entity;

determining that a term occurs in multiple web documents in the set of documents; and

identifying the term as a correlated entity in response to the determination.

9. The system of claim 8, wherein the one or more processors upon executing the instructions perform operations comprising:

determining, for each correlated entity, an average frequency of occurrence of the correlated entity in the web documents in which the correlated entity occurs; and

ranking the correlated entities based on an average frequencies of occurrence.

10. The system of claim 8, wherein the one or more processors upon executing the instructions perform operations comprising:

determining, by the computer system, for each correlated entity, locations of the correlated entity in each of the web documents in which the correlated entity occurs; and

ranking, by the computer system, the correlated entities based on locations of the correlated entities in the web documents.

11. The system of claim 8, wherein the one or more processors upon executing the instructions perform operations comprising:

identifying second content of the second type, the second content of the second type being second advertisements determined to be responsive to the query;

identifying third advertisements from the first and second advertisements, the third advertisements being advertisements that are identified in both the first advertisements and second advertisements; and

filtering the first and second advertisements so that the third advertisements are presented first among the first and second advertisements and with a list of the web documents.

12. The system of claim 8, wherein the one or more processors upon executing the instructions perform operations comprising:

determining if the number of identified second advertisements exceeds a threshold; and

identifying the correlated entities, the first content of the second type, the third advertisements and filtering the first and second advertisements only if the number of second advertisements does not exceed the threshold.

13. The system of claim 8, wherein the one or more processors upon executing the instructions perform operations comprising:

for each of the first advertisements, determining a relevance measure that measure the relevance between the query and the first advertisement; and

selecting for presentation only the first advertisements having a relevance measure that exceeds a threshold.