IDENTIFYING INADEQUATE SEARCH CONTENT

• US 20080249786A1
• Filed: 04/03/2007
• Published: 10/09/2008
• Est. Priority Date: 04/03/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Rosencrantz, Matt, Varian, Hal R., Cutts, Matthew D., Oldham, Jeffrey David
• Granted Patent: US 7,668,823 B2
• Time in Patent Office: Days
• US Class Current: 705/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods for identifying inadequate search content are provided. Inadequate search content, for example, can be identified based on statistics associated with the search queries related to the content.

Claims

1. A system comprising:

a statistics collection engine operable to generate query statistics associated with one or more queries received from a plurality of browsers;

a statistics analysis engine operable to divide the queries into one or more topics, the statistics analysis engine being further operable to generate topic statistics associated with the one or more topics, the topic statistics comprising one or more of an aggregate rank or an aggregate relevance of a topic corpus associated with each of the topics;

a comparator operable to identify a topic based upon a comparison of the topic statistics with the query statistics; and

a topic distribution engine operable to notify one or more users of an identified topic.

2. The system of claim 1, wherein the topic distribution engine is operable to present identified topics in a display environment.

3. The system of claim 2, wherein the statistic analysis engine is further operable to derive an index associated with identified topics.

4. The system of claim 3, wherein the index associated with the topics is based upon a degree to which the topics are underserved.

5. The system of claim 1, wherein the topic distribution engine is operable to notify a searcher searching the identified topic that the identified topic is underserved, and the system further comprises a user contribution environment operable to allow the searcher to create additional content associated with the identified topic.

6. The system of claim 1, further comprising a content generator operable to generate content associated with the identified topic

7. The system of claim 6, further comprising an ad sales engine operable to sell advertising space to be included in the generated content.

8. The system of claim 1, wherein the notification engine is operable to generate a stub topic in a collaborative environment.

9. The system of claim 8, wherein the collaborative environment is associated with a web site to which users contribute content.

10. The system of claim 1, wherein the aggregate rank of the topic corpus comprises a plurality of web page rankings associated with web pages resulting from queries related to the topics.

11. The system of claim 10, wherein rankings are based upon a quality of content associated with the topic corpus.

12. The system of claim 11, wherein the quality of the content is based upon a number of pages linking to a web page associated with the queries.

13. The system of claim 1, wherein the aggregate relevance of the topic corpus comprises a plurality of web page relevance scores associated with web pages resulting from queries related to the topics.

14. The system of claim 13, wherein relevance scores are based upon a level of match between the queries and one or more web pages associated with the queries.

15. The system of claim 1, wherein the query aggregator is operable to cluster queries based upon common results received for the clustered queries thereby defining the topics.

16. The system of claim 1, further comprising:

an aggregation engine operable to retrieve available content associated with the identified topic;

a content generation engine operable to assemble the retrieved content into an aggregated web page.

17. A method, comprising:

determining statistics associated with a first topic;

determining if the first topic is underserved based on the statistics; and

inviting additional content for inclusion in a topic corpus associated with the first topic based on the determination.

18. The method of claim 17, wherein determining statistics further comprises determining a search volume and a quality index for searches associated with the first topic.

19. The method of claim 17, further comprising:

comparing the statistics associated with the first topic to statistics associated with a second topic; and

determining whether the first topic is underserved based upon comparison of the statistics associated with the first topic to statistics associated with the second topic.

20. The method of claim 17, further comprising deriving relationships between a plurality of search queries and a topic.

21. The method of claim 20, wherein deriving relationships between a plurality of search queries comprises examining clusters of similar results to derived relationships.

22. The method of claim 20, wherein deriving relationships between a plurality of search queries comprises examining refinements associated with search queries.

23. The method of claim 20, wherein deriving relationships between a plurality of search queries comprises analyzing synonyms associated with a search query.

24. The method of claim 17, wherein inviting additional content comprises distributing the first topic to content generators based on content associated with the first topic.

25. The method of claim 24, wherein distributing the first topic comprises providing an underserved topic search interface to content generators.

26. The method of claim 24, wherein distributing the first topic comprises providing a stub article to a user contribution site.

27. The method of claim 24, further comprising:

generating an index associated with the first topic; and

sorting a plurality of underserved topics, including the first topic, based on the index.

28. The method of claim 17, further comprising:

aggregating the topic corpus; and

generating a web page based upon aggregating the topic corpus.

29. The method of claim 28, wherein the web page allows a user to access the topic corpus from a single web page.

30. One or more computer readable media storing instructions that are executable by a processing device, and upon such execution cause the processing device to perform operations comprising:

receiving a search query;

generating results for the search query based upon relevance of a plurality of documents to the search query and ranking of the plurality of documents;

comparing the results of the search query with results from other search queries;

determining whether the results are anomalous based on the comparison; and

notifying the searcher that results from the search query are anomalous based on the determination.