Identifying and ranking attributes of entities

• US 9,047,278 B1
• Filed: 11/09/2012
• Issued: 06/02/2015
• Est. Priority Date: 11/09/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Provine, John R., Fortuna, Vinicius J., Hogue, Andrew W., Mann, Benjamin J., Brown, Randolph G.
• Primary Examiner(s): Mofiz, Apu
• Assistant Examiner(s): Agharahimi, Farhad
• Application Number:
  US13/673,015
• Time in Patent Office: 935 Days
• Field of Search: 707/769, 707/770
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for query analysis. Queries are identified in query data, and an entity-descriptive portion and a suffix are determined in each query. Query counts are determined for a number of times that the respective queries occur in the query data. Based on the query counts, an entity-level count is estimated, which represents a number of query submissions that include the particular suffix and are considered to refer to a first entity. The entity is determined to be a particular type of entity. A type-level count is determined, which represents a number of query submissions that include the first suffix and are estimated to refer to entities of the particular type of entity. A score is assigned to the particular suffix based on the entity-level count and the type-level count.

Claims

1. A method performed by data processing apparatus, the method comprising:

identifying queries in query data;

determining, in each of the queries, (i) an entity-descriptive portion that refers to an entity and (ii) a suffix;

determining query counts of a number of times that the respective queries were submitted;

for at least a particular query of the identified queries, distributing the query count for the particular query among multiple different entities by assigning, to each of the multiple different entities, a partial query count that is an estimate of a number of submissions of the particular query that refer to the entity;

estimating, based at least in part on one or more of the partial query counts, an entity-level count of query submissions that include a particular suffix and are considered to refer to a first entity of the multiple different entities;

determining that the first entity is a particular type of entity;

determining a type-level count of the query submissions that include the particular suffix and are estimated to refer to entities of the particular type of entity; and

assigning, based on the entity-level count and the type-level count, a score for the particular suffix with respect to the first entity.

2. The method of claim 1, further comprising:

obtaining scores for one or more other suffixes that occur in query submissions estimated to refer to an entity of the particular entity type; and

ranking the particular suffix and the other suffixes based on their respective scores.

3. The method of claim 2, further comprising:

selecting suffixes in a highest-ranking portion of the ranked suffixes;

mapping each of the selected suffixes to a factual attribute of the first entity; and

designating the factual attributes as frequently requested facts about the first entity.

4. The method of claim 3, further comprising:

receiving a user query submission that does not include the particular suffix;

determining that a likelihood that the user query submission refers to the first entity satisfies a threshold;

in response to determining that the likelihood that the user query submission refers to the first entity satisfies a threshold;

accessing data identifying the factual attributes designated as frequently requested facts about the first entity, the factual attributes comprising a factual attribute corresponding to the particular suffix; and

providing, in response to the user query submission, information about the first entity for each of the factual attributes including information for the factual attribute corresponding to the particular suffix that is not included in the query submission.

5. The method of claim 4, wherein providing information about the first entity for each of the factual attributes comprises providing a search results page that presents the information about the first entity for each of the factual attributes with search results responsive to the user query submission.

6. The method of claim 2, further comprising:

selecting a highest-ranking portion of the ranked suffixes;

determining that one or more of the highest-ranking suffixes are each associated with an objective fact; and

in response to determining that one or more of the selected suffixes are each associated with an objective fact;

mapping each of the one or more of the selected suffixes to a factual attribute; and

designating the factual attributes as frequently requested attributes for the first entity.

7. The method of claim 1, further comprising:

based on the score assigned to the particular suffix, selecting an attribute corresponding to the particular suffix as an attribute for the first entity;

receiving a query submission that refers to the first entity; and

in response to receiving the query submission that refers to the first entity, providing data that identifies the attribute and a value of the attribute for the first entity.

8. The method of claim 1, wherein distributing the query count for the particular query among the multiple different entities comprises:

obtaining a probability score for each of the multiple different entities, wherein each of the probability scores indicates a probability that the particular query refers to the entity associated with the probability score; and

assigning the partial query counts to the multiple different entities based on the probability scores.

9. The method of claim 8, wherein obtaining a probability score for each of the multiple different entities comprises obtaining the probability scores for the multiple different entities based on the entity-descriptive portion of the particular query and the suffix of the particular query.

10. The method of claim 1, wherein assigning the score for the particular suffix with respect to the first entity comprises determining the score for the particular suffix as a combination of (i) a first value based on the entity-level count and (ii) a second value that is based on the type-level count and is limited to a maximum value.

11. The method of claim 10, wherein determining the score for the particular suffix with respect to the first entity comprises:

determining a scaled score by applying a scaling factor to the type-level count;

determining that the scaled score is greater than a predetermined maximum value; and

in response to determining that the scaled score is greater than the predetermined maximum value, determining the score for the particular suffix as a combination of the first value and the predetermined maximum value.

12. The method of claim 1, wherein multiple different suffixes are associated with the particular type of entity, each of the multiple different suffixes having a corresponding type-level count;

wherein assigning the score for the particular suffix with respect to the first entity comprises;

determining a scaling factor for the type-level count for the particular suffix based on a highest type-level count from the different type-level counts of the multiple different suffixes, the highest type-level count being different from the type-level count for the particular suffix;

determining a scaled score by applying a scaling factor to the type-level count; and

assigning the score for the particular suffix based on the entity-level count and the scaled score.

13. The method of claim 1, further comprising:

determining that, in addition to being the particular type of entity, the first entity is also a second type of entity; and

determining a second type-level count of the query submissions that include the particular suffix and are estimated to refer to entities of the second type of entity; and

wherein assigning the score for the particular suffix with respect to the first entity comprises assigning the score for the particular suffix with respect to the first entity based on the entity-level count, the type-level count for the particular type, and the second type-level count.

14. The method of claim 1, further comprising:

determining that the first entity is assigned to each of multiple different entity types; and

determining a ranking of the multiple different entity types with respect to the first entity.

15. The method of claim 14, further comprising determining, based on the ranking of the multiple different entity types, a dominant entity type for the first entity;

wherein determining the type-level count of the query submissions that include the particular suffix and are estimated to refer to entities of the particular type of entity comprises determining a dominant type-level count of the query submissions that include the particular suffix and are estimated to refer to entities of the dominant entity type; and

wherein assigning the score to the particular suffix based on the entity-level count and the type-level count comprises assigning the score to the particular suffix based on the entity-level count and the dominant type-level count.

16. 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;

identifying queries in query data;

determining, in each of the queries, (i) an entity-descriptive portion that refers to an entity and (ii) a suffix;

determining query counts of a number of times that the respective queries were submitted;

for at least a particular query of the identified queries, distributing the query count for the particular query among multiple different entities by assigning, to each of the multiple different entities, a partial query count that is an estimate of a number of submissions of the particular query that refer to the entity;

estimating, based at least in part on one or more of the partial query counts, an entity-level count of query submissions that include a particular suffix and are considered to refer to a first entity of the multiple different entities;

determining that the first entity is a particular type of entity;

determining a type-level count of the query submissions that include the particular suffix and are estimated to refer to entities of the particular type of entity; and

assigning, based on the entity-level count and the type-level count, a score for the particular suffix with respect to the first entity.

17. The system of claim 16, wherein the operations further comprise:

obtaining scores for one or more other suffixes that occur in query submissions estimated to refer to an entity of the particular entity type; and

ranking the particular suffix and the other suffixes based on their respective scores.

18. The system of claim 17, wherein the operations further comprise:

selecting suffixes in a highest-ranking portion of the ranked suffixes;

mapping each of the selected suffixes to a factual attribute of the first entity; and

designating the factual attributes as frequently requested facts about the first entity.

19. The system of claim 18, wherein the operations further comprise:

receiving a user query submission that does not include the particular suffix;

determining that a likelihood that the user query submission refers to the first entity satisfies a threshold;

in response to determining that the likelihood that the user query submission refers to the first entity satisfies a threshold;

accessing data identifying the factual attributes designated as frequently requested facts about the first entity, the factual attributes comprising a factual attribute corresponding to the particular suffix; and

providing, in response to the user query submission, information about the first entity for each of the factual attributes including information for the factual attribute corresponding to the particular suffix that is not included in the query submission.

20. The system of claim 16, wherein the operations further comprise:

based on the score assigned to the particular suffix, selecting an attribute corresponding to the particular suffix as an attribute for the first entity;

receiving a query submission that refers to the first entity; and

in response to receiving the query submission that refers to the first entity, providing data that identifies the attribute and a value of the attribute for the first entity.

21. The system of claim 16, wherein distributing the query count for the particular query among the multiple different entities comprises:

obtaining a probability score for each of the multiple different entities, wherein each of the probability scores indicates a probability that the particular query refers to the entity associated with the probability score; and

assigning the partial query counts to the multiple different entities based on the probability scores.

22. A non-transitory computer storage medium storing a computer program, the program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

identifying queries in query data;

determining, in each of the queries, (i) an entity-descriptive portion that refers to an entity and (ii) a suffix;

determining query counts of a number of times that the respective queries were submitted;

for at least a particular query of the identified queries, distributing the query count for the particular query among multiple different entities by assigning, to each of the multiple different entities, a partial query count that is an estimate of a number of submissions of the particular query that refer to the entity;

estimating, based at least in part on one or more of the partial query counts, an entity-level count of query submissions that include a particular suffix and are considered to refer to a first entity of the multiple different entities;

determining that the first entity is a particular type of entity;

determining a type-level count of the query submissions that include the particular suffix and are estimated to refer to entities of the particular type of entity; and

assigning, based on the entity-level count and the type-level count, a score for the particular suffix with respect to the first entity.

23. The computer storage medium of claim 22, wherein the operations further comprise:

obtaining scores for one or more other suffixes that occur in query submissions estimated to refer to an entity of the particular entity type; and

ranking the particular suffix and the other suffixes based on their respective scores.

24. The computer storage medium of claim 23, wherein the operations further comprise:

selecting suffixes in a highest-ranking portion of the ranked suffixes;

mapping each of the selected suffixes to a factual attribute of the first entity; and

designating the factual attributes as frequently requested facts about the first entity.

25. The computer storage medium of claim 24, wherein the operations further comprise:

receiving a user query submission that does not include the particular suffix;

determining that a likelihood that the user query submission refers to the first entity satisfies a threshold;

in response to determining that the likelihood that the user query submission refers to the first entity satisfies a threshold;

accessing data identifying the factual attributes designated as frequently requested facts about the first entity, the factual attributes comprising a factual attribute corresponding to the particular suffix; and

providing, in response to the user query submission, information about the first entity for each of the factual attributes including information for the factual attribute corresponding to the particular suffix that is not included in the query submission.

26. The computer storage medium of claim 22, wherein the operations further comprise:

based on the score assigned to the particular suffix, selecting an attribute corresponding to the particular suffix as an attribute for the first entity;

receiving a query submission that refers to the first entity; and

in response to receiving the query submission that refers to the first entity, providing data that identifies the attribute and a value of the attribute for the first entity.

27. The computer storage medium of claim 22, wherein distributing the query count for the particular query among the multiple different entities comprises:

obtaining a probability score for each of the multiple different entities, wherein each of the probability scores indicates a probability that the particular query refers to the entity associated with the probability score; and

assigning the partial query counts to the multiple different entities based on the probability scores.