KEYWORD-BASED CONTENT SUGGESTIONS

• US 20080168032A1
• Filed: 01/05/2007
• Published: 07/10/2008
• Est. Priority Date: 01/05/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Criou, Nathalie, Venkatakrishnan, Sridhar, Mahadevan, Chandramouli
• Granted Patent: US 8,463,830 B2
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0256 User search

Abstract

A system and related methods suggest content based on user input and another metric. In one implementation, web-sites are suggested to advertisers in response to keyword input and by factoring in how often such web-sites were selected or “clicked on” as a result of corresponding search queries. Search logs are processed to determine how often certain query terms led to web-sites being selected. Web-sites are ranked accordingly. Keywords from advertisers are matched to the web-site rankings to present the top web-sites.

Claims

1. A method comprising:

receiving input corresponding to at least one keyword associated with an on-line advertisement; and

indicating at least one suggested content source for the advertisement based on whether the suggested content source was previously selected in a previous query corresponding to the keyword.

2. The method of claim 1, further including determining a term from the previous query corresponding to the keyword received, and indicating a content source for the on-line advertisement by selecting a content source associated with the term.

3. The method of claim 2, further comprising indicating multiple suggested content sources for the on-line advertisement by selecting from a set of content sources associated with the term.

4. The method of claim 1, wherein the content source is a web-site.

5. A computer system comprising:

means for determining content vectors from logs related to web-based queries, the vectors corresponding to web-sites both returned from the queries and selected as a result of the queries;

means for ranking the web-sites by how often the content vectors occurred in corresponding web queries;

means for receiving user input corresponding to at least one keyword associated with an on-line advertisement;

means for correlating the keyword to at least one of the content vectors;

means for determining a set of recommended web-sites for the keyword as a function of the ranking of the web-sites.

6. The system of claim 5, wherein the means for determining content vectors includes means for processing the logs over a period of time to identify terms associated with corresponding web-sites and means for determining, for the corresponding web-sites, the top terms that led to selection of the corresponding web-sites.

7. The system of claim 6, wherein the means for processing the logs includes means for identifying single terms and word pairs.

8. The method of claim 5, wherein the means for correlating the keyword to at least one of the content vectors comprises identifying multiple terms corresponding to the keyword.

9. A method of creating an on-line advertisement, comprising:

receiving a selection from a plurality of advertisement placement options, one of the options being a web-site-based placement;

receiving data related to the placement of the advertisement;

determining at least one content vector corresponding to the data received, wherein the content vector is derived from previous queries leading, to selections of web-sites resulting from the queries;

presenting suggested web-sites corresponding to the content vector for the web-site-based placement of the advertisement; and

enabling selection of one of the suggested web-sites for possible placement of the on-line advertisement.

10. The method of claim 9, wherein the step of presenting the web-sites includes:

accessing a data structure indicating a number of times the content vector occurred in the previous queries leading to selections of the web-sites; and

suggesting a set of the top web-sites according to the number of times the content vector occurred.

11. The method of claim 10, wherein suggested web-sites are presented up to a threshold number in accordance with the number of times the content vector occurred.

12. The method claim 9, wherein receiving the data includes receiving a plurality of keywords in response to user input, and further comprising determining a set of content vectors corresponding to the keywords, and wherein presenting the web-sites includes recommending the web-sites as a function of the set of content vectors.

13. A computer-implemented method comprising:

determining content vectors from a log related to queries, the vectors corresponding to content sources both returned from the queries and selected as a result of the queries;

ranking the content sources by how often the content vectors occurred in corresponding queries;

receiving user input corresponding to at least one keyword associated with an on-line advertisement;

correlating the keyword to at least one of the content vectors; and

determining a set of recommended content sources for the keyword as a function of the ranking of the content sources.

14. The method of claim 13, wherein the queries are web-based queries and the content sources are web-sites.