Propagating query classifications

• US 9,659,097 B1
• Filed: 08/21/2014
• Issued: 05/23/2017
• Est. Priority Date: 04/19/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Adams, Henele I., Kim, Hyung-Jin
• Primary Examiner(s): Huang, Miranda
• Application Number:
  US14/464,974
• Time in Patent Office: 1,006 Days
• Field of Search: 707728, 707725, 707726, 707731, 707751, 707768
• CPC Class Codes: G06F 16/35 Clustering; Classification
• 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: G06F 16/9538 Presentation of query results

Abstract

In general, one aspect described can be embodied in a method for determining a classification for a query. The method can include receiving a request to determine whether to assign a classification to a first query, identifying a plurality of search entities that are associated with the first query based upon data associated with each of the plurality of search entities and the first query, and determining whether to assign the classification to the first query based upon classifications for the identified search entities.

Claims

1. A computer-implemented method comprising:

receiving, at a computer system, a request to classify a first query;

obtaining, by the computer system, session data for the first query, wherein;

the session data for the first query identifies a plurality of sessions in which the first query occurs,

each session of the plurality of sessions includes (i) one or more queries submitted in succession by a single respective user for the session and (ii) one or more search entities returned in response to executing the one or more queries, and

each search entity of the one or more search entities is assigned one or more classifications;

selecting, by the computer system from the session data for the plurality of sessions in which the first query occurs, a first plurality of search entities, wherein the first plurality of search entities are the search entities that frequently occur in the plurality of sessions in response to executing the first query;

identifying, by the computer system, one or more potential classifications for the first query;

for each potential classification of the one or more potential classifications,

determining a first measure of how many of the first plurality of search entities have been assigned the potential classification;

determining that the first measure satisfies a classification threshold; and

in response to determining that the first measure satisfies the classification threshold,

assigning the respective potential classification to the first query;

determining that a second query occurs in the same first session with the first query; and

assigning the potential classification to the second query.

2. The method of claim 1, wherein selecting, by the computer system from the session data for the first query, the first plurality of search entities comprises selecting a plurality of search entities having at least a threshold amount of session data.

3. The method of claim 1, wherein the one or more search entities in the plurality of sessions comprise other search queries occurring with the first query in the plurality of query sessions.

4. The method of claim 1, wherein the one or more search entities in the plurality of sessions comprise one or more documents that were returned in response to other queries submitted with the first query in the plurality of query sessions.

5. The method of claim 4, wherein the first plurality of search entities comprises documents having an associated length of time that satisfies a threshold, wherein each length of time represents how long the respective single user viewed each document after selecting the document.

6. The method of claim 1, wherein the queries in the plurality of query sessions comprise one or more refinements to the first query, and assigning the potential classification to a second query that occurs in the same first session with the first query comprises assigning the potential classification to the one or more refinements to the first query.

7. The method of claim 1, wherein determining the first measure of how many of the first plurality of search entities have been assigned the potential classification comprises weighting a classification assigned to each of the first plurality of search entities according to a measure of proximity of the search entity to the first query in one or more query sessions.

8. The method of claim 1, wherein determining the first measure of how many of the first plurality of search entities have been assigned the potential classification comprises weighting a classification assigned to each of the first plurality of search entities according to user behavior data relative to the first query.

9. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving, at a computer system, a request to classify a first query;

obtaining, by the computer system, session data for the first query, wherein;

the session data for the first query identifies a plurality of sessions in which the first query occurs,

each session of the plurality of sessions includes (i) one or more queries submitted in succession by a single respective user for the session and (ii) one or more search entities returned in response to executing the one or more queries, and

each search entity is assigned one or more classifications;

selecting, by the computer system from the session data for the first query, a first plurality of search entities, wherein the first plurality of search entities are the search entities that frequently occur in the plurality of query sessions in response to executing the first query;

identifying, by the computer system, one or more potential classifications for the first query;

for each potential classification of the one or more potential classifications,

determining a first measure of how many of the first plurality of search entities have been assigned the potential classification;

determining that the first measure have been assigned the classification satisfies a classification threshold; and

in response to determining that the first measure have been assigned the classification satisfies the classification threshold,

assigning the potential classification to the first query,

determining that a second query occurs in the same first session with the first query; and

assigning the potential classification to the second query.

10. The system of claim 9, wherein selecting, by the computer system from the session data for the first query, the first plurality of search entities comprises selecting a plurality of search entities having at least a threshold amount of session data.

11. The system of claim 9, wherein the one or more search entities in by the plurality of sessions comprise other search queries occurring with the first query in the plurality of query sessions.

12. The system of claim 9, wherein the one or more search entities in by the plurality of sessions comprise one or more documents that were returned in response to other queries submitted with the first query in the plurality of query sessions.

13. The system of claim 12, wherein the first plurality of search entities comprises documents having an associated length of time that satisfies a threshold, wherein each length of time represents how long the respective single user viewed each document after selecting the document.

14. The system of claim 9, wherein the queries in the plurality of query sessions comprise one or more refinements to the first query, and assigning the potential classification to a second query that occurs in the same first session with the first query comprises assigning the potential classification to the one or more refinements to the first query.

15. The system of claim 9, wherein determining the first measure of how many of the first plurality of search entities have been assigned the potential classification comprises weighting a classification assigned to each of the first plurality of search entities according to a measure of proximity of the search entity to the first query in one or more query sessions.

16. The system of claim 9, wherein determining the first measure of how many of the first plurality of search entities have been assigned the potential classification comprises weighting a classification assigned to each of the first plurality of search entities according to user behavior data relative to the first query.

17. A computer program product, encoded on one or more non-transitory computer storage media, comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

receiving, at a computer system, a request to classify a first query;

obtaining, by the computer system, session data for the first query, wherein;

the session data for the first query identifies a plurality of sessions in which the first query occurs,

each session of the plurality of sessions includes (i) one or more queries submitted in succession by a single respective user for the session and (ii) one or more search entities returned in response to executing the one or more queries, and

each search entity is assigned one or more classifications;

selecting, by the computer system from the session data for the first query, a first plurality of search entities, the first plurality of search entities are search entities that frequently occur in the plurality of query sessions in response to executing the first query;

identifying, by the computer system, one or more potential classifications for the first query;

for each potential classification of the one or more potential classifications,

determining a first measure of how many of the first plurality of search entities have been assigned the potential classification;

determining that the first measure satisfies a classification threshold; and

in response to determining that the first measure satisfies the classification threshold,

assigning the potential classification to a first query,

determining that a second query occurs in the same first session with the first query; and

assigning the classification to the second query.