SEARCH RESULT RANKING AND PRESENTATION

• US 20160321267A1
• Filed: 07/08/2016
• Published: 11/03/2016
• Est. Priority Date: 08/08/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhou, Chen, Ding, Chen, Huynh, David Francois, Lou, JinYu, Huang, Yanlai, Shen, Hongda, Li, Guanghua, Li, Yiming, Chai, Yangyang
• Granted Patent: US 10,445,328 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24526 Internal representations for queries
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

Methods and systems are provided for ranking search results and generating a presentation. In some implementations, a search system generates a presentation based on a search query. In some implementations, a search system ranks search results based on data stored in a knowledge graph. In some implementations, a search system identifies a modifying concept such as a superlative in a received search query, and determines ranking properties based on the modifying concept.

Claims

1. A computer implemented method for providing search results, the method comprising:

receiving a search query;

identifying, using one or more processors, a modifying concept in the search query;

generating, using one or more processors, a query tree based on the search query;

retrieving, using one or more processors, search results from a knowledge graph, based at least in part on the query tree;

determining, using one or more processors, at least one ranking property based at least on the modifying concept; and

ranking, using one or more processors, the search results based at least in part on the at least one ranking property.

2. The method of claim 1, wherein the at least one ranking property includes an ordering direction.

3. The method of claim 1, wherein generating the query tree further comprises:

generating a plurality of query trees based on the second portion of the search query;

determining a score for each query tree of the plurality of query trees; and

selecting a query tree from the plurality of query trees based at least in part on the score.

4. The method of claim 1, wherein the modifying concept is explicit in the search query.

5. The method of claim 1, wherein the modifying concept is implicit in the search query.

6. The method of claim 1, wherein the modifying concept is objective.

7. The method of claim 1, wherein the modifying concept is subjective.

8. A computer implemented method for search, the method comprising:

identifying, using one or more processors, a modifying concept based on a search query;

determining, using one or more processors, a rule for ranking search results based at least in part on the modifying concept and on a knowledge graph from which at least one of the search results was obtained; and

ranking, using one or more processors, search results based at least in part on the rule.

9. The method of claim 8, wherein determining the rule for ranking search results comprises:

identifying in the knowledge graph an entity type associated with the search query; and

retrieving data related to the modifying concept and the entity type, wherein the data comprises at least the rule.

10. The method of claim 8, wherein determining the rule for ranking search results comprises:

identifying, in the knowledge graph, a property associated with the search query; and

retrieving data related to the modifying concept and the property, wherein the data comprises at least the rule.

11. The method of claim 8, wherein identifying the modifying concept comprises identifying at least one desired ranking property from the search query.

12. The method of claim 8, wherein determining the rule for ranking search results comprises:

retrieving a quality score from the knowledge graph for each respective search result of the search results, wherein the quality is score is associated with the modifying concept; and

determining the rule for ranking search results based at least in part on the quality score.

13. The method of claim 8, wherein determining the rule for ranking search results comprises determining the frequency of occurrence of the modifying concept in each respective search result of the search results.

14. The method of claim 8, wherein determining the rule comprises:

identifying an entity reference in the knowledge graph based on the search query;

identifying two or more entity types associated with the entity reference;

determining a weight for each of the two or more entity types based at least in part on the relationship of the entity reference with each respective entity type; and

determining data based at least in part on the weight and the two or more entity types, wherein the data comprises at least the rule.

15. The method of claim 8, wherein determining the rule for ranking search results comprises:

identifying a first and second entity reference in a search query;

retrieving, from the knowledge graph, a set of search results based at least in part on the first entity reference;

determining a related entity score for each respective search result of the set of search results, wherein the related entity score is based at least in part on the co-occurrence of data related to the first entity reference and data related to the second entity reference in each respective search result; and

determining at least the rule based on the related entity score.

16. The method of claim 8, wherein the modifying concept comprises a range filter.

17. The method of claim 8, wherein the modifying concept is explicit.

18. The method of claim 8, wherein the modifying concept is implicit.

19. The method of claim 8, wherein the modifying concept is subjective.

20. The method of claim 8, wherein the modifying concept is objective.

21. A system for providing search results, the system comprising:

a database comprising a knowledge graph; and

one or more computers configured to perform operations comprising;

receiving a search query;

identifying a modifying concept in a search query;

generating a query tree based on the search query;

retrieving search results from the knowledge graph, based at least in part on the query tree;

determining at least one ranking property based at least on the modifying concept; and

ranking the search results based at least in part on the at least one ranking property.