QUERY GENERATION FOR SEARCHABLE CONTENT

• US 20160267184A1
• Filed: 03/10/2016
• Published: 09/15/2016
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: BloomReach, Inc.
• Original Assignee: BloomReach, Inc.
• Inventors: De Datta, Raj K., Garg, Ashutosh, Vardhan, Abhay, Levy, Joshua, Sridhar, Srinath
• Granted Patent: US 9,785,713 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

Query generation for searchable content is provided. In some embodiments, query generation for searchable content includes receiving searchable content (e.g., the searchable content can include a unique identifier for the searchable content, such as a Uniform Resource Locator (URL) for a web site, and the web site can include one or more web pages); and generating a set of queries, the set of queries including one or more queries (e.g., the set of queries can include ranked queries) that are relevant to the searchable content.

Claims

1. (canceled)

2. A method, comprising:

receiving an identifier for a web site comprising searchable content, wherein the searchable content includes one or more web pages of the web site, and wherein the web site is to be modified for higher rankings in organic search results of a search engine;

generating a set of queries for the web site using an inverse search engine executed on a processor, wherein the generated set of queries includes one or more queries that are relevant to the searchable content of the web site, wherein generating the set of queries comprises;

determining candidate queries for the searchable content of the web site; and

determining a topicality for each of the candidate queries; and

modifying the web site for organic searches using the generated set of queries to generate a modified version of the web site.

3. The method recited in claim 2, wherein the identifier for the web site includes a Uniform Resource Locator (URL) for the web site.

4. The method recited in claim 2, wherein the searchable content of the web site is received as an input to the inverse search engine, the generated set of queries includes ranked queries, and the generated set of queries including the ranked queries is provided as an output from the inverse search engine.

5. The method recited in claim 2, further comprising:

performing a feedback loop to determine whether the modified version of the web site is resulting in higher rankings in organic search results of the search engine.

6. The method recited in claim 2, wherein determining of the topicality for each of the candidate queries comprises:

determining a local meaning of each of the candidate queries;

determining a global meaning or popular meaning of each of the candidate queries; and

determining a difference between the local meaning and the global meaning or popular meaning of each of the candidate queries.

7. The method recited in claim 2, wherein generating the set of queries further comprises:

determining a relevance for each of the candidate queries, wherein determining the relevance is based on a number of terms of each candidate query present in a web page of the web site.

8. The method recited in claim 2, further comprising:

generating the set of queries using query modeling.

9. The method recited in claim 2, further comprising:

determining competitors for the searchable content of the web site.

10. The method recited in claim 2, further comprising:

determining potential queries for the searchable content of the web site; and

performing a domain clustering for the searchable content of the web site, wherein the domain clustering comprises classifying the web site into a domain based on web site content, and wherein the candidate queries are a subset of the potential queries based on the domain clustering for the searchable content of the web site.

11. The method recited in claim 2, further comprising:

determining a score for each of the candidate queries, wherein the score is used for ranking each of the candidate queries.

12. The method recited in claim 2, further comprising:

determining potential queries for the searchable content of the web site, wherein determining potential queries comprises querying a search engine log to identify the potential queries relevant to the web site comprising the searchable content;

performing a domain clustering for the searchable content of the web site, wherein the domain clustering comprises classifying the web site into a domain based on web site content, and wherein the candidate queries are a subset of the potential queries based on the domain clustering for the searchable content; and

determining a score for each of the candidate queries, wherein the score is used for ranking each of the candidate queries.

13. The method recited in claim 2, wherein modifying the web site further comprises:

populating one or more queries of the set of queries in a widget on a web page of the web site, wherein the web page includes at least a subset of the searchable content of the web site, and wherein the one or more queries of the set of queries in the widget on the web page are searchable content of the web page.

14. A system, comprising:

a processor configured to;

receive an identifier for a web site comprising searchable content, wherein the searchable content includes one or more web pages of the web site, and wherein the web site is to be modified for higher rankings in organic search results of a search engine;

generate a set of queries for the web site using an inverse search engine, wherein the generated set of queries includes one or more queries that are relevant to the searchable content of the web site, wherein generating the set of queries comprises;

determine candidate queries for the searchable content of the web site; and

determine a topicality for each of the candidate queries; and

modify the web site for organic searches using the generated set of queries to generate a modified version of the web site; and

a memory coupled to the processor and configured to provide the processor with instructions.

15. The system recited in claim 14, wherein the identifier for the web site includes a Uniform Resource Locator (URL) for the web site.

16. The system recited in claim 14, wherein the searchable content of the web site is received as an input to the inverse search engine, the generated set of queries includes ranked queries, and the generated set of queries including the ranked queries is provided as an output from the inverse search engine.

17. The system recited in claim 14, wherein the processor is further configured to:

performing a feedback loop to determine whether the modified version of the web site is resulting in higher rankings in organic search results of the search engine.

18. The system recited in claim 14, wherein determining of the topicality for each of the candidate queries comprises:

determine a local meaning of each of the candidate queries;

determine a global meaning or popular meaning of each of the candidate queries; and

determine a difference between the local meaning and the global meaning or popular meaning of each of the candidate queries.

19. The system recited in claim 14, wherein generating the set of queries further comprises:

determine a relevance for each of the candidate queries, wherein determining the relevance is based on a number of terms of each candidate query present in a web page of the web site.

20. The system recited in claim 14, wherein the processor is further configured to:

generate the set of queries using query modeling.

21. The system recited in claim 14, wherein the processor is further configured to:

determine competitors for the searchable content of the web site.

22. The system recited in claim 14, wherein the processor is further configured to:

determine potential queries for the searchable content of the web site; and

perform a domain clustering for the searchable content of the web site, wherein the domain clustering comprises classifying the web site into a domain based on web site content, and wherein the candidate queries are a subset of the potential queries based on the domain clustering for the searchable content of the web site.

23. The system recited in claim 14, wherein the processor is further configured to:

determine a score for each of the candidate queries, wherein the score is used for ranking each of the candidate queries.

24. The system recited in claim 14, wherein the processor is further configured to:

determine potential queries for the searchable content of the web site, wherein determining potential queries comprises querying a search engine log to identify the potential queries relevant to the web site comprising the searchable content;

perform a domain clustering for the searchable content of the web site, wherein the domain clustering comprises classifying the web site into a domain based on web site content, and wherein the candidate queries are a subset of the potential queries based on the domain clustering for the searchable content; and

determine a score for each of the candidate queries, wherein the score is used for ranking each of the candidate queries.

25. The system recited in claim 14, wherein modifying the web site further comprises:

populating one or more queries of the set of queries in a widget on a web page of the web site, wherein the web page includes at least a subset of the searchable content of the web site, and wherein the one or more queries of the set of queries in the widget on the web page are searchable content of the web page.

26. A computer program product, the computer program product being embodied in a tangible, non-transitory computer readable storage medium and comprising computer instructions for:

receiving an identifier for a web site comprising searchable content, wherein the searchable content includes one or more web pages of the web site, and wherein the web site is to be modified for higher rankings in organic search results of a search engine;

generating a set of queries for the web site using an inverse search engine, wherein the generated set of queries includes one or more queries that are relevant to the searchable content of the web site, wherein generating the set of queries comprises;

determining candidate queries for the searchable content of the web site; and

determining a topicality for each of the candidate queries; and

modifying the web site for organic searches using the generated set of queries to generate a modified version of the web site.

27. The computer program product recited in claim 26, wherein the identifier for the web site includes a Uniform Resource Locator (URL) for the web site.

28. The computer program product recited in claim 26, wherein the searchable content of the web site is received as an input to the inverse search engine, the generated set of queries includes ranked queries, and the generated set of queries including the ranked queries is provided as an output from the inverse search engine.

29. The computer program product recited in claim 26, wherein modifying the web site further comprises:

populating one or more queries of the set of queries in a widget on a web page of the web site, wherein the web page includes at least a subset of the searchable content of the web site, and wherein the one or more queries of the set of queries in the widget on the web page are searchable content of the web page.