System and method for evaluating search queries to identify titles for content production

• US 8,909,623 B2
• Filed: 06/29/2010
• Issued: 12/09/2014
• Est. Priority Date: 06/29/2010
• Status: Active Grant

• Current Assignee: Leaf Group Ltd. (Graham Holdings Company)
• Original Assignee: Demand Media Incorporated (Graham Holdings Company)
• Inventors: Yehaskel, David M., Kjallbring, Henrik M.
• Primary Examiner(s): Morrison, Jay
• Assistant Examiner(s): GORTAYO, DANGELINO N
• Application Number:
  US12/826,524
• Publication Number:
  US 20110320444A1
• Time in Patent Office: 1,624 Days
• Field of Search: 707/100, 707/723, 707/722, 707/726, 707/731, 707/748, 707/769, 707/776
• US Class Current: 707/723
• CPC Class Codes: G06F 16/24539 using cached or materialised query results
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/33 Querying
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues

Abstract

Systems and methods are provided to select potential titles for online content using search query logs from web search service providers. A plurality of search queries are collected from one or more web search service providers. A lifetime value is determined for each of the search queries. Potential titles are then selected from the plurality of search queries using selection criteria including the lifetime value of the search queries. The potential titles can then be provided to content developers who develop online content based on the potential titles.

Claims

1. A method comprising:

collecting, using a computing device over a network, a plurality of search queries from at least one search query data source;

determining, using the computing device, a lifetime value for each of the plurality of search queries to provide a plurality of lifetime values, each of the plurality of lifetime values reflecting a respective estimate of respective total online revenue a respective search query is expected to generate over its lifetime, wherein determining the respective lifetime value for each of the plurality of search queries includes matching each respective search query to at least one search term having a known lifetime value, wherein matching each respective search query to the at least one search term includes computing a matching score for the respective search term using the respective search term and the respective search query, and wherein the matching score is computed according to the equation;

MatchingScore=(W_m÷

W_ltv)²×

(W_m÷

W_t),

where W_ltv is a weighted sum of words in the respective search term,

W_t is a weighted count of words in the respective search query,

W_m is a weighted count of unique matching words between the respective search term and the respective search query;

selecting, using the computing device, a plurality of potential titles from the plurality of search queries using at least one selection criteria associated with the plurality of lifetime values; and

providing the plurality of potential titles to at least one content author.

2. The method of claim 1 wherein the lifetime value for each of the plurality of search queries is set equal to the lifetime value of one of the at least one search terms having the highest matching score to the respective search query.

3. The method of claim 1 wherein the lifetime value for each of the plurality of search queries is set equal to an average of the lifetime value of a set of the at least one search terms having the highest matching scores to the respective search query.

4. The method of claim 1 wherein if one or more of the plurality of search queries do not match any of the plurality of search terms, the lifetime value of the respective search query is set to a default value.

5. The method of claim 1 wherein the at least one selection criteria comprises a minimum search query lifetime value.

6. The method of claim 1 wherein the at least one selection criteria comprises a set of rules.

7. The method of claim 1 wherein selecting the plurality of potential titles using the at least one selection criteria comprises generating metadata for each of the plurality of search queries.

8. The method of claim 1 additionally comprising:

filtering, using the computing device, the plurality of search queries.

9. The method of claim 8 wherein filtering comprises eliminating duplicate search queries from the plurality of search queries.

10. The method of claim 8 wherein filtering comprises eliminating search queries that do not appear in the plurality of search queries at least a threshold number of times.

11. The method of claim 8 wherein filtering comprises eliminating search queries having one or more words on a blacklist from the plurality of search queries.

12. The method of claim 8 wherein filtering comprises correcting misspelled words in the plurality of search queries.

13. The method of claim 1 additionally comprising:

normalizing, using the computing device, each of the plurality of potential titles.

14. The method of claim 13 wherein normalizing comprises correcting spelling errors in each of the plurality of potential titles.

15. The method of claim 13 wherein normalizing comprises correcting grammatical errors in each of the plurality of potential titles.

16. A non-transitory machine readable media storing instructions that, when executed by a computing device, cause the computing device to perform a method, the method comprising:

collecting, over a network, a plurality of search queries from at least one search query data source;

determining a lifetime value for each of the plurality of search queries to provide a plurality of lifetime values, each of the plurality of lifetime values reflecting a respective estimate of respective total online revenue a respective search query is expected to generate over its lifetime, wherein determining the lifetime value for each of the plurality of search queries includes matching each respective search query to at least one search term having a known lifetime value, wherein matching each respective search query to the at least one search term includes computing a matching score for the respective search term using the respective search term and the respective search query, and wherein the matching score is computed according to the equation;

MatchingScore=(W_m÷

W_ltv)²×

(W_m÷

W_t),

where W_ltv is a weighted sum of words in the respective search term,

W_t is a weighted count of words in the respective search query,

W_m is a weighted count of unique matching words between the respective search term and the respective search query;

selecting a plurality of potential titles from the plurality of search queries using at least one selection criteria associated with the plurality of lifetime values; and

adding the plurality of potential titles to a database stored on a computer readable medium.

17. A computer system comprising:

a processor; and

memory coupled to the processor and storing instructions that, when executed by the processor, cause the computer system to;

collect a plurality of search queries from at least one search query data source;

determine a lifetime value for each of the plurality of search queries to provide a plurality of lifetime values, each of the plurality of lifetime values reflecting a respective estimate of respective total online revenue a respective search query is expected to generate over its lifetime, wherein determining the lifetime value for each of the plurality of search queries includes matching each respective search query to at least one search term having a known lifetime value, wherein matching each respective search query to the at least one search term includes computing a matching score for the respective search term using the respective search term and the respective search query, and wherein the matching score is computed according to the equation;

MatchingScore=(W_m÷

W_ltv)²×

(W_m÷

W_t),

where W_ltv is a weighted sum of words in the respective search term,

W_t is a weighted count of words in the respective search query,

W_m is a weighted count of unique matching words between the respective search term and the respective search query;

select a plurality of potential titles from the plurality of search queries using at least one selection criteria associated with the plurality of lifetime values; and

provide the plurality of potential titles to at least one content author.