Automated generation, performance monitoring, and evolution of keywords in a paid listing campaign

• US 7,962,463 B2
• Filed: 03/08/2006
• Issued: 06/14/2011
• Est. Priority Date: 10/31/2005
• Status: Expired due to Fees

• Current Assignee: RPX Corporation
• Original Assignee: Lycos Incorporated (Brightcom Group Ltd.)
• Inventors: Cava, William
• Primary Examiner(s): Lu, Kuen S
• Assistant Examiner(s): Lee, Rachel J
• Application Number:
  US11/371,209
• Publication Number:
  US 20070100803A1
• Time in Patent Office: 1,924 Days
• Field of Search: None
• US Class Current: 707/706
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

Keyword candidates are identified by in response to receiving an identification of a web page. Content of the web page is analyzed to identify terms from the web page. An automated keyword expansion is performed using the identified terms to produce a set of candidate keywords. Keyword suggestions are generated for the web page using the set of candidate keywords, and one or more of the keyword suggestions are used in a paid listing campaign. A performance of a paid listing campaign is compared with a performance threshold. An automated keyword expansion is performed using one or more keywords from the set of keywords to produce a set of alternative keywords in response to the comparison. One or more alternative keywords are selected from the set of alternative keywords for use in the paid listing campaign.

Claims

1. A computer-implemented method comprising:

receiving, by one or more computers, an identification of a web page;

extracting a set of keywords from the web page;

generating, from an automated keyword expansion of the set of keywords, a set of candidate keywords;

assigning one or more of the candidate keywords one or more confidence scores according to a ranking algorithm;

comparing the one or more confidence scores to a confidence threshold;

identifying, based on comparing, one or more candidate keywords that are associated with one or more confidence scores above the confidence threshold;

selecting, from the one or more candidate keywords that are associated with the one or more confidence scores above the confidence threshold, one or more keyword suggestions for the web page;

retrieving a performance threshold for the one or more keyword suggestions;

measuring, by the one or more computers, one or more performance values for the one or more keyword suggestions;

identifying a keyword suggestion associated with a performance value that is less than the performance threshold;

identifying a keyword suggestion associated with a performance value that is greater than the performance threshold;

performing the automated keyword expansion on the identified keyword suggestion associated with the performance value that is greater than the performance threshold;

generating, based on the performing, one or more alternate keyword suggestions;

replacing the identified keyword suggestion associated with the performance value that is less than the performance threshold with an alternate keyword suggestion;

measuring a performance value for the alternate keyword suggestion; and

comparing the measured performance value for the alternate keyword suggestion to the performance threshold.

2. The method of claim 1, wherein the identification of the web page comprises a unique address associated with the web page.

3. The method of claim 1, further comprising:

performing an automated evaluation of an advertising campaign associated with the web page that uses one or more of the one or more keyword suggestions,

wherein the one or more alternative keyword suggestions are at least partly based on the automated evaluation.

4. The computer-implemented method of claim 1 wherein the performance threshold relates to at least one of (i) a click rate associated with a paid listing campaign that comprises the one or more keyword suggestions, (ii) a conversion rate associated with the paid listing campaign, (iii) a ratio between the click rate and a cost for the paid listing campaign, or (iv) a ratio between the conversion rate and the cost for the paid listing campaign.

5. The method of claim 1, wherein the one or more keyword suggestions are associated with a paid listing campaign in accordance with a pay-per-click model.

6. The method of claim 1, wherein a confidence score is based on usage data comprising empirical click-rate data and cost-per-click data.

7. The method of claim 5, further comprising:

removing from the paid listing campaign, the identified keyword suggestion associated with the performance value that is less than the performance threshold.

8. An article comprising a machine-readable storage device configured to store instructions for causing a data processing apparatus to perform operations comprising:

receiving an identification of a web page;

extracting a set of keywords from the web page;

generating, from an automated keyword expansion of the set of keywords, a set of candidate keywords;

assigning one or more of the candidate keywords one or more confidence scores according to a ranking algorithm;

comparing the one or more confidence scores to a confidence threshold;

identifying, based on comparing, one or more candidate keywords that are associated with one or more confidence scores above the confidence threshold;

selecting, from the one or more candidate keywords that are associated with the one or more confidence scores above the confidence threshold, one or more keyword suggestions for the web page;

retrieving a performance threshold for the one or more keyword suggestions;

measuring one or more performance values for the one or more keyword suggestions;

identifying a keyword suggestion associated with a performance value that is less than the performance threshold;

identifying a keyword suggestion associated with a performance value that is greater than the performance threshold;

performing the automated keyword expansion on the identified keyword suggestion associated with the performance value that is greater than the performance threshold;

generating, based on the performing, one or more alternate keyword suggestions;

replacing the identified keyword suggestion associated with the performance value that is less than the performance threshold with an alternate keyword suggestion;

measuring a performance value for the alternate keyword suggestion; and

comparing the measured performance value for the alternate keyword suggestion to the performance threshold.

9. The article of claim 8, wherein the operations further comprise:

monitoring a performance of a campaign that uses at least one keyword from the one or more keyword suggestions; and

removing, from the campaign, the identified keyword suggestion associated with the performance value that is less than the performance threshold.

10. The article of claim 8, wherein a confidence score of a candidate keyword is based on at least one of a cost associated with the candidate keyword or click rate data.

18. The article of claim 8, wherein the performance threshold relates to at least one of (i) a click rate associated with a paid listing campaign that comprises the one or more first keyword suggestions, (ii) a conversion rate associated with the paid listing campaign, (iii) a ratio between the click rate and a cost for the paid listing campaign, or (iv) a ratio between the conversion rate and a cost for the paid listing campaign.

19. The article of claim 8, wherein the set of keywords is associated with a paid listing campaign in accordance with a pay-per-click model.

20. The article of claim 8, wherein a confidence score is based on usage data comprising empirical click-rate data and cost-per-click data.

11. One or more non-transitory machine-readable storage media configured to store instructions that are executable by one or more processing devices to perform functions comprising:

receiving an identification of a web page;

extracting a set of keywords from the web;

generating, from an automated keyword expansion of the set of keywords, a set of candidate keywords;

assigning one or more of the candidate keywords one or more confidence scores according to a ranking algorithm;

comparing the one or more confidence scores to a confidence threshold;

identifying, based on comparing, one or more candidate keywords that are associated with one or more confidence scores above the confidence threshold;

selecting, from the one or more candidate keywords that are associated with the one or more confidence scores above the confidence threshold, one or more keyword suggestions for the web page;

retrieving a performance threshold for the one or more keyword suggestions;

measuring one or more performance values for the one or more keyword suggestions;

identifying a keyword suggestion associated with a performance value that is less than the performance threshold;

identifying a keyword suggestion associated with a performance value that is greater than the performance threshold;

performing the automated keyword expansion on the identified keyword suggestion associated with the performance value that is greater than the performance threshold;

generating, based on the performing, one or more alternate keyword suggestions;

replacing the identified keyword suggestion associated with the performance value that is less than the performance threshold with an alternate keyword suggestion;

measuring a performance value for the alternate keyword suggestion; and

comparing the measured performance value for the alternate keyword suggestion to the performance threshold.

12. The one or more machine-readable media of claim 11, wherein the identification of the web page comprises a unique address associated with the web page.

13. The one or more machine-readable media of claim 11, wherein the operations further comprise:

performing an automated evaluation of an advertising campaign associated with the web page that uses one or more of the one or more keyword suggestions,

wherein the one or more alternative keyword suggestions are at least partly based on the automated evaluation.

14. The one or more machine-readable media of claim 11, wherein the performance threshold relates to at least one of (i) a click rate associated with a paid listing campaign that comprises the one or more keyword suggestions, (ii) a conversion rate associated with the paid listing campaign, (iii) a ratio between the click rate and a cost for the paid listing campaign, or (iv) a ratio between the conversion rate and the cost for the paid listing campaign.

15. The one or more machine-readable media of claim 11, wherein the one or more keyword suggestions are associated with a paid listing campaign in accordance with a pay-per-click model.

16. The one or more machine-readable media of claim 11, wherein a confidence score is based on usage data comprising empirical click-rate data and cost-per-click data.

17. The one or more machine-readable media of claim 15, wherein the operations further comprise:

removing, from the paid listing campaign, the identified keyword suggestion associated with the performance value that is less than the performance threshold.