Methods, systems, and media for interpreting queries

• US 9,116,918 B1
• Filed: 11/14/2012
• Issued: 08/25/2015
• Est. Priority Date: 11/14/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kim, Yongsung
• Primary Examiner(s): Le, Hung
• Application Number:
  US13/677,020
• Time in Patent Office: 1,014 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2282 Tablespace storage structures; Management thereof
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/2454 Optimisation of common expressions
• CPC Class Codes: G06F 16/24549 Run-time optimisation
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: H04N 21/278 Content descriptor database or directory service for end-user access details of content or meta data based information retrieval of video data in video databases G06F16/739
• CPC Class Codes: H04N 21/47202 for requesting content on demand, e.g. video on demand

Abstract

Mechanisms for interpreting queries are provided. In some implementations, a method for interpreting queries is provided, comprising: receiving a search query in a search domain; determining search terms based on the search query; determining, for each of the search terms, whether a search term corresponds to an entity name, wherein the entity name is derived from metadata associated with the search domain; in response to determining that entity names correspond to a portion of the search terms, determining an entity type and an entity score associated with each of the corresponding entity names; determining a remaining portion of the entity names by removing at least one of the matching entity names based on the entity score and contextual information in the search query; and performing a search in the search domain with the remaining portion of entity names, wherein each entity name in the remaining portion of entity names is searched corresponding to the associated entity type.

Claims

1. A method for interpreting queries, the method comprising:

receiving, using a hardware processor, a search query in a search domain;

determining, using the hardware processor, a plurality of search terms based on the received search query;

determining, using the hardware processor, for each of the plurality of search terms, whether a search term of the plurality of search terms corresponds to an entity name, wherein the entity name is derived from metadata associated with the search domain;

in response to determining that a plurality of entity names corresponds to at least a portion of the plurality of search terms, determining, using the hardware processor, a plurality of entity types associated with each of the plurality of corresponding entity names, wherein each entity type is associated with a category in which content associated with the entity name is included;

determining an entity score associated with each of the plurality of entity names and corresponding entity types that indicates relatedness of an entity name to a corresponding entity type, based at least in part on a number of times media content associated with a particular entity name and entity type combination have been accessed;

determining, using the hardware processor, a remaining portion of the plurality of entity names by removing at least one of the plurality of entity types corresponding to a particular entity name based at least in part on the entity score associated with the particular entity name and the removed entity type; and

performing, using the hardware processor, a search in the search domain with the remaining portion of the plurality of entity names, wherein each entity name in the remaining portion of the plurality of entity names is searched corresponding to the associated entity type.

2. The method of claim 1, wherein the entity score is based at least in part on popularity of the entity name in the search domain.

3. The method of claim 1, wherein the entity score associated with the entity name is based at least in part on user feedback information.

4. The method of claim 1, further comprising;

retrieving metadata corresponding to the search domain;

extracting the plurality of entity names based on the retrieved metadata;

determining, for each of the plurality of entity names, the entity type and the entity score associated with the entity name; and

generating an entity table that includes, for each of the plurality of entity names, the entity name and the associated entity type and entity score.

5. The method of claim 4, further comprising supplementing the plurality of entity names in the generated entity table with curated entity information, wherein the curated entity information includes ignored terms in the search query.

6. The method of claim 4, further comprising:

determining the search domain from a plurality of search domains based on the received search query; and

accessing the entity table from a plurality of entity tables based on the determined search domain.

7. The method of claim 1, further comprising:

storing the entity table;

determining whether a predetermined amount of time has elapsed since the entity table was stored;

in response to determining that the predetermined amount of time has elapsed, retrieving updated metadata corresponding to the search domain; and

updating the entity table that includes entity names, entity types, and entity scores based on the updated metadata.

8. A system for interpreting queries, the system comprising:

a storage device for storing entity information, wherein the entity information is derived from metadata associated with a search domain; and

a processor that is configured to;

receive a search query in the search domain;

determine a plurality of search terms based on the received search query;

determine, for each of the plurality of search terms, whether a search term of the plurality of search terms corresponds to an entity name;

in response to determining that a plurality of entity names corresponds to at least a portion of the plurality of search terms, determine a plurality of entity types associated with each of the plurality of corresponding entity names, wherein each entity type is associated with a category in which content associated with the entity name is included;

determine an entity score associated with each of the plurality of entity names and corresponding entity types that indicates relatedness of an entity name to a corresponding entity type, based at least in part on a number of times media content associated with a particular entity name and entity type combination have been accessed;

determine a remaining portion of the plurality of entity names by removing at least one of the plurality of entity types corresponding to a particular entity name based at least in part on the entity score associated with the particular entity name and the removed entity type; and

perform a search in the search domain with the remaining portion of the plurality of entity names, wherein each entity name in the remaining portion of the plurality of entity names is search corresponding to the associated entity type.

9. The system of claim 8, wherein the entity score is based at least in part on popularity of the entity name in the search domain.

10. The system of claim 8, wherein the entity score associated with the entity name is based at least in part on user feedback information.

11. The system of claim 8, wherein the processor is further configured to:

retrieve metadata corresponding to the search domain;

extract the plurality of entity names based on the retrieved metadata;

determine, for each of the plurality of entity names, the entity type and the entity score associated with the entity name; and

generate an entity table that includes, for each of the plurality of entity names, the entity name and the associated entity type and entity score.

12. The system of claim 11, wherein the processor is further configured to supplement the plurality of entity names in the generated entity table with curated entity information, wherein the curated entity information includes ignored terms in the search query.

13. The system of claim 11, wherein the processor is further configured to:

determine the search domain from a plurality of search domains based on the received search query; and

access the entity table from a plurality of entity tables based on the determined search domain.

14. The system of claim 11, wherein the processor is further configured to:

store the entity table in the storage device;

determine whether a predetermined amount of time has elapsed since the entity table was stored;

in response to determining that the predetermined amount of time has elapsed, retrieve updated metadata corresponding to the search domain; and

update the entity table that includes entity names, entity types, and entity scores based on the updated metadata.

15. A non-transitory computer-readable medium containing computer-executable instructions that, when executed by a processor, cause the processor to perform a method for interpreting queries, the method comprising:

receiving a search query in a search domain;

determining a plurality of search terms based on the received search query;

determining, for each of the plurality of search terms, whether a search term of the plurality of search terms corresponds to an entity name, wherein the entity name is derived from metadata associated with the search domain;

in response to determining that a plurality of entity names corresponds to at least a portion of the plurality of search terms, determining a plurality of entity types associated with each of the plurality of corresponding entity names, wherein each entity type is associated with a category in which content associated with the entity name is included;

determining an entity score associated with each of the plurality of entity names and corresponding entity types that indicates relatedness of an entity name to a corresponding entity type, based at least in part on a number of times media content associated with a particular entity name and entity type combination have been accessed;

determining a remaining portion of the plurality of entity names by removing at least one of the plurality of entity types corresponding to a particular entity name based at least in part on the entity score associated with the particular entity name and the removed entity type; and

performing a search in the search domain with the remaining portion of the plurality of entity names, wherein each entity name in the remaining portion of the plurality of entity names is searched corresponding to the associated entity type.

16. The non-transitory computer-readable medium of claim 15, wherein the entity score is based at least in part on popularity of the entity name in the search domain.

17. The non-transitory computer-readable medium of claim 15, wherein the entity score associated with the entity name is based at least in part on user feedback information.

18. The non-transitory computer-readable medium of claim 15, wherein the method further comprises:

retrieving metadata corresponding to the search domain;

extracting the plurality of entity names based on the retrieved metadata;

determining, for each of the plurality of entity names, the entity type and the entity score associated with the entity name; and

generating an entity table that includes, for each of the plurality of entity names, the entity name and the associated entity type and entity score.

19. The non-transitory computer-readable medium of claim 18, wherein the method further comprises supplementing the plurality of entity names in the generated entity table with curated entity information, wherein the curated entity information includes ignored terms in the search query.

20. The non-transitory computer-readable medium of claim 18, wherein the method further comprises:

determining the search domain from a plurality of search domains based on the received search query; and

accessing the entity table from a plurality of entity tables based on the determined search domain.

21. The non-transitory computer-readable medium of claim 15, wherein the method further comprises:

storing the entity table;

determining whether a predetermined amount of time has elapsed since the entity table was stored;

in response to determining that the predetermined amount of time has elapsed, retrieving updated metadata corresponding to the search domain; and

updating the entity table that include entity names, entity types, and entity scores based on the updated metadata.