Providing result-based query suggestions

• US 8,583,675 B1
• Filed: 08/30/2010
• Issued: 11/12/2013
• Est. Priority Date: 08/28/2009
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Haahr, Paul, Martin, Charles E.
• Primary Examiner(s): ALAM, SHAHID AL
• Application Number:
  US12/871,515
• Time in Patent Office: 1,170 Days
• Field of Search: 707/711, 707/721, 707/723, 707/767, 707/728, 706/12, 715/201
• US Class Current: 707/767
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9532 Query formulation
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results

Abstract

In general, one aspect of the subject matter described can be embodied in a method that includes, for a first document that is included in first search results responsive to a first user-submitted query, selecting a plurality of previously submitted queries for which the first document was a responsive search result. The method can further include determining whether second documents that are relevant to the previously submitted query have at least a threshold level of diversity in comparison to the first search results, wherein second documents are determined to be relevant to the previously submitted query based on data that is indicative of user behavior. The method can additionally include identifying one or more queries from the selected previously submitted queries to provide as first suggested queries, and providing the one or more identified queries as first suggested queries with the first search results for the first user-submitted query.

Claims

1. A computer-implemented method comprising:

for a first document that is included in first search results responsive to a first user-submitted query, selecting a plurality of previously submitted queries for which the first document was a responsive search result, wherein the selected previously submitted queries are selected using a document-to-query-to-document model that associates the first document to the plurality of previously submitted queries and that associates each of the plurality of previously submitted queries to one or more of second documents for which each of the one or more second documents was a responsive search result;

for each of the selected previously submitted queries, determining whether there is at least a threshold level of diversity between the first search results and second documents identified as being relevant to the selected previously submitted query, wherein second documents are determined to be relevant to the previously submitted query based on data that is indicative of user behavior relative to the second documents as search results for the previously submitted query;

based on the determination of whether there is at least a threshold level of diversity between the first search results and the second documents, identifying one or more queries from the selected previously submitted queries to provide as first suggested queries; and

providing the one or more identified queries as the first suggested queries with the first search results for the first user-submitted query.

2. The method of claim 1 where the first document is associated with data for each of the selected previously submitted queries, where the data is indicative of user behavior relative to the first document as a search result for the selected previously submitted queries.

3. The method of claim 1 where associations between the first document, the plurality of previously submitted queries, and the second documents of the document-to-query-to-document model are derived from data that is indicative of user behavior relative to the first document and the second documents as search results for the plurality of previously submitted queries.

4. The method of claim 1, further comprising:

receiving a request to create the document-to-query-to-document model;

for each of the plurality of previously submitted queries, creating a query-to-document model that relates the previously submitted query to the one or more of the second documents for which each of the one or more second documents was a responsive search result; and

for each of the second documents, associating the second document to each created query-to-document model within which the second document is related to one of the plurality of previously submitted queries to create the document-to-query-to-document.

5. The method of claim 4 where receiving, creating, and associating are performed at a time prior to receiving the first user-submitted query.

6. The method of claim 1 further comprising creating a selectable user-interface for the first suggested queries to be presented as part of the first search results for the first user-submitted query.

7. The method of claim 6 where, for each of the first suggested queries, selection of the selectable user-interface for the suggested query causes the suggested query to be submitted as a second user-submitted query.

8. The method of claim 7 further comprising providing second search results that are responsive to the second user-submitted query that are different than the first search results responsive to the first user-submitted query.

9. The method of claim 8 further comprising providing second suggested queries with the second search results that each include one or more terms that do not occur in the second user-submitted query, and wherein search results responsive to the second suggested queries are different from the second search results.

10. The method of claim 6 where the one or more identified queries as the first suggested queries are presented in the selectable user-interface in association with the first document of the first search results.

11. The method of claim 1 where the determination of whether there is at least a threshold level of diversity between the first search results and the second documents is based on a determination of whether the second documents occur in the first search results.

12. The method of claim 1, further comprising, for each of the selected previously submitted queries, determining a level of term diversity for the previously submitted query in comparison to the first user-submitted query;

where identifying the one or more queries from the selected previously submitted queries to provide as first suggested queries is further based on the determined level of term diversity for each of the selected previously submitted queries.

13. The method of claim 1 where identifying the one or more queries from the selected previously submitted queries to provide as first suggested queries is further based on whether each of the selected previously submitted queries includes one or more terms that do not occur in the first user-submitted query.

16. The computer program product of claim 1, where associations between the first document, the plurality of previously submitted queries, and the second documents of the document-to-query-to-document model are derived from data that is indicative of user behavior relative to the first document and the second documents as search results for the plurality of previously submitted queries.

14. A computer program product encoded on a non-transitory computer-readable medium, operable to cause a data processing apparatus to perform operations comprising:

for a first document that is included in first search results responsive to a first user-submitted query, selecting a plurality of previously submitted queries for which the first document was a responsive search result, wherein the selected previously submitted queries are selected using a document-to-query-to-document model that associates the first document to the plurality of previously submitted queries and that associates each of the plurality of previously submitted queries to one or more of second documents for which each of the one or more second documents was a responsive search result;

for each of the selected previously submitted queries, determining whether there is at least a threshold level of diversity between the first search results and second documents identified as being relevant to the selected previously submitted query, wherein second documents are determined to be relevant to the previously submitted query based on data that is indicative of user behavior relative to the second documents as search results for the previously submitted query;

based on the determination of whether there is at least a threshold level of diversity between the first search results and the second documents, identifying one or more queries from the selected previously submitted queries to provide as first suggested queries; and

providing the one or more of identified queries as the first suggested queries with the first search results for the first user-submitted query.

15. The computer program product of claim 14 where the first document is associated with data for each of the selected previously submitted queries, where the data is indicative of user behavior relative to the first document as a search result for the selected previously submitted queries.

17. The computer program product of claim 14, the operations further comprising, for each of the selected previously submitted queries, determining a level of term diversity for the previously submitted query in comparison to the first user-submitted query;

where identifying the one or more queries from the selected previously submitted queries to provide as first suggested queries is further based on the determined level of term diversity for each of the selected previously submitted queries.

18. A system for providing one or more suggested queries with search results, the system comprising:

a non-transitory computer readable medium including a program product; and

one or more processors configured to execute the program product and perform operations comprising;

for a first document that is included in first search results responsive to a first user-submitted query, selecting a plurality of previously submitted queries for which the first document was a responsive search result, wherein the selected previously submitted queries are selected using a document-to-query-to-document model that associates the first document to the plurality of previously submitted queries and that associates each of the plurality of previously submitted queries to one or more of second documents for which each of the one or more second documents was a responsive search result;

for each of the selected previously submitted queries, determining whether there is at least a threshold level of diversity between the first search results and second documents identified as being relevant to the selected previously submitted query, wherein second documents are determined to be relevant to the previously submitted query based on data that is indicative of user behavior relative to the second documents as search results for the previously submitted query;

based on the determination of whether there is at least a threshold level of diversity between the first search results and the second documents, identifying one or more queries from the selected previously submitted queries to provide as first suggested queries; and

providing the one or more of identified queries as the first suggested queries with the first search results for the first user-submitted query.

19. The system of claim 18 where the operations further comprise, for each of the selected previously submitted queries, determining a level of term diversity for the previously submitted query in comparison to the first user-submitted query;

where identifying the one or more queries from the selected previously submitted queries to provide as first suggested queries is further based on the determined level of term diversity for each of the selected previously submitted queries.