Identifying and ranking attributes of entities

• US 10,185,751 B1
• Filed: 05/06/2015
• Issued: 01/22/2019
• Est. Priority Date: 11/09/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Mann, Benjamin J., Brown, Randolph G., Provine, John R., Fortuna, Vinicius J., Hogue, Andrew W.
• Primary Examiner(s): Mofiz, Apu M
• Assistant Examiner(s): Agharahimi, Farhad
• Application Number:
  US14/705,102
• Time in Patent Office: 1,357 Days
• Field of Search: 707769, 707770
• 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 one or more computers, the method comprising:

receiving, by the one or more computers, a query from a device over a communication network;

distributing, by the one or more computers, a partial query count for the query among multiple different entities to generate a partial query count for each of the multiple different entities;

determining, by the one or more computers, a likelihood that the query refers to a particular entity, wherein the particular entity is classified as being included in a category of entities;

determining, by the one or more computers, that the likelihood satisfies a threshold;

in response to determining that the likelihood satisfies the threshold, selecting, by the one or more computers, a set of attributes of the particular entity to indicate in response to the query, the attributes in the set including at least one attribute that is not specified by the query, the set of attributes determined based at least in part on measures of query submissions for queries related to the category and at least one of the partial query counts corresponding to the particular entity;

generating, by the one or more computers and in response to the query received from the device over the communication network, a search results page that identifies (i) information about the particular entity for the attributes in the set, and (ii) search results that each refer to a different document identified in response to the query; and

providing, by the one or more computers and for display at the device and in a response to the query, the search results page that identifies (i) information about the particular entity for the attributes in the set, and (ii) search results that each refer to a different document identified in response to the query.

2. The method of claim 1, wherein selecting the set of attributes of the particular entity comprises:

accessing a set of scores each corresponding to different attributes, each of the scores being based on (i) a measure of query submissions for queries that refer to a particular attribute and the particular entity, and (ii) a measure of query submissions for queries that refer to the particular attribute and other entities in the category; and

selecting a subset of the different attributes based on the scores.

3. The method of claim 1, wherein determining a likelihood that the query refers to a particular entity comprises:

obtaining, for each entity of a set of multiple different entities, a probability score indicating a likelihood that the query refers to the entity; and

identifying the probability score indicating the highest likelihood.

4. The method of claim 1, wherein selecting the set of attributes of the particular entity comprises identifying a set of attributes determined based at least in part on query counts for entities that are different from the particular entity and that are classified as being included in the category.

5. The method of claim 1, wherein selecting the set of attributes of the particular entity comprises identifying a set of attributes determined for the particular entity prior to receiving the query.

6. The method of claim 1, further comprising:

determining that the particular entity is included in multiple categories of entities; and

determining a ranking of the multiple different categories with respect to the particular entity.

7. The method of claim 6, further comprising determining, based on the ranking of the multiple different categories, a dominant category for the particular entity;

wherein selecting the set of attributes comprises selecting a set of attributes that is determined based at least in part on the dominant category.

8. 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:

receiving, by the one or more computers, a query from a device over a communication network;

distributing, by the one or more computers, a partial query count for the query among multiple different entities to generate a partial query count for each of the multiple different entities;

determining, by the one or more computers, a likelihood that the query refers to a particular entity, wherein the particular entity is classified as being included in a category of entities;

determining, by the one or more computers, that the likelihood satisfies a threshold;

in response to determining that the likelihood satisfies the threshold, selecting, by the one or more computers, a set of attributes of the particular entity to indicate in response to the query, the attributes in the set including at least one attribute that is not specified by the query, the set of attributes determined based at least in part on measures of query submissions for queries related to the category and at least one of the partial query counts corresponding to the particular entity;

generating, by the one or more computers and in response to the query received from the device over the communication network, a search results page that identifies (i) information about the particular entity for the attributes in the set, and (ii) search results that each refer to a different document identified in response to the query; and

providing, by the one or more computers and for display at the device and in a response to the query, the search results page that identifies (i) information about the particular entity for the attributes in the set, and (ii) search results that each refer to a different document identified in response to the query.

9. The non-transitory computer storage medium of claim 8, wherein selecting the set of attributes of the particular entity comprises:

accessing a set of scores each corresponding to different attributes, each of the scores being based on (i) a measure of query submissions for queries that refer to a particular attribute and the particular entity, and (ii) a measure of query submissions for queries that refer to the particular attribute and other entities in the category; and

selecting a subset of the different attributes based on the scores.

10. The non-transitory computer storage medium of claim 8, wherein determining a likelihood that the query refers to a particular entity comprises:

obtaining, for each entity of a set of multiple different entities, a probability score indicating a likelihood that the query refers to the entity; and

identifying the probability score indicating the highest likelihood.

11. The non-transitory computer storage medium of claim 8, wherein selecting the set of attributes of the particular entity comprises identifying a set of attributes determined based at least in part on query counts for entities that are different from the particular entity and that are classified as being included in the category.

12. The non-transitory computer storage medium of claim 8, wherein selecting the set of attributes of the particular entity comprises identifying a set of attributes determined for the particular entity prior to receiving the query.

13. The non-transitory computer storage medium of claim 8, wherein the operations further comprise:

determining that the particular entity is included in multiple categories of entities; and

determining a ranking of the multiple different categories with respect to the particular entity.

14. The non-transitory computer storage medium of claim 13, wherein the operations further comprise determining, based on the ranking of the multiple different categories, a dominant category for the particular entity;

wherein selecting the set of attributes comprises selecting a set of attributes that is determined based at least in part on the dominant category.

15. 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, by the one or more computers, a query from a device over a communication network;

distributing, by the one or more computers, a partial query count for the query among multiple different entities to generate a partial query count for each of the multiple different entities;

determining, by the one or more computers, a likelihood that the query refers to a particular entity, wherein the particular entity is classified as being included in a category of entities;

determining, by the one or more computers, that the likelihood satisfies a threshold;

in response to determining that the likelihood satisfies the threshold, selecting, by the one or more computers, a set of attributes of the particular entity to indicate in response to the query, the attributes in the set including at least one attribute that is not specified by the query, the set of attributes determined based at least in part on measures of query submissions for queries related to the category and at least one of the partial query counts corresponding to the particular entity;

generating, by the one or more computers and in response to the query received from the device over the communication network, a search results page that identifies (i) information about the particular entity for the attributes in the set, and (ii) search results that each refer to a different document identified in response to the query; and

providing, by the one or more computers and for display at the device and in a response to the query, the search results page that identifies (i) information about the particular entity for the attributes in the set, and (ii) search results that each refer to a different document identified in response to the query.

16. The system of claim 15, wherein selecting the set of attributes of the particular entity comprises:

accessing a set of scores each corresponding to different attributes, each of the scores being based on (i) a measure of query submissions for queries that refer to a particular attribute and the particular entity, and (ii) a measure of query submissions for queries that refer to the particular attribute and other entities in the category; and

selecting a subset of the different attributes based on the scores.

17. The system of claim 15, wherein determining a likelihood that the query refers to a particular entity comprises:

obtaining, for each entity of a set of multiple different entities, a probability score indicating a likelihood that the query refers to the entity; and

identifying the probability score indicating the highest likelihood.