DYNAMIC SUMMARY GENERATOR

• US 20160098397A1
• Filed: 10/02/2014
• Published: 04/07/2016
• Est. Priority Date: 10/02/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Doherty, Ryan P., Mote, Nicolaus T.
• Granted Patent: US 9,965,474 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 16/93 Document management systems
• 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 receiving a request for information about a term from a user; obtaining, at one or more processors, one or more characteristics of the user; obtaining, at the one or more processors, a template including a plurality of attributes associated with the term; generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the plurality of attributes in the template; and providing for output, data representing the response.

Claims

1. A computer-implemented method comprising:

receiving a request for information about a term from a user;

obtaining, at one or more processors, one or more characteristics of the user;

obtaining, at the one or more processors, a template including one or more attributes associated with the term;

generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the one or more attributes in the template; and

providing for output, data representing the response.

2. The method of claim 1, wherein obtaining the template including the one or more attributes associated with the term comprises:

identifying, from a collection of documents, one or more documents that include the term;

identifying, for each of the one or more documents, a respective description that has a semantic relation to the term; and

determining a respective attribute for each respective description.

3. The method of claim 1, wherein obtaining the template including the one or more attributes associated with the term comprises:

selecting a template from among a plurality of templates associated with the term based on the one or more characteristics of the user.

4. The method of claim 1, wherein generating the response comprises:

obtaining a first description for a particular attribute of the one or more attributes;

generating a second description using the first description based on the one or more characteristics of the user; and

generating the response, wherein the response includes the second description for the particular attribute.

5. The method of claim 4, wherein generating the second description using the first description comprises substituting one or more first words of the first description by one or more second words.

6. The method of claim 1, wherein an attribute is associated with attribute metadata, and wherein a description is associated with description metadata.

7. The method of claim 6, wherein obtaining the template comprises adding one or more attributes to the template based on (i) attribute metadata of the one or more attributes and (ii) the one or more characteristics of the user.

8. The method of claim 7, wherein adding the one or more attributes to the template comprises adding the one or more attributes to the template in response to determining that the attribute metadata of the one or more attributes match the at least one characteristic.

9. The method of claim 6,

wherein a particular attribute of the one or more attributes is associated with a plurality of descriptions, and

wherein generating the response comprises selecting a description from the plurality of descriptions for the particular attribute based on description metadata of the plurality of descriptions and the one or more characteristics of the user.

10. The method of claim 1, comprising:

receiving, from a second user, a second request for information about the term;

obtaining one or more characteristics of the second user;

obtaining a second template including one or more attributes associated with the term;

generating, based on the one or more characteristics of the second user, a second response, the second response including a respective description for each attribute of the one or more attributes in the second template; and

providing for output, data representing the second response.

11. The method of claim 10, wherein the second template for the second user is different from the template for the user.

12. The method of claim 1, wherein the one or more characteristics of the user includes an age of the user, an education level of the user, an interest of the user, a gender of the user, or a search history of the user.

13. A computer-readable medium storing software having stored thereon instructions, which, when executed by one or more computers, cause the one or more computers to perform operations of:

receiving a request for information about a term from a user;

obtaining, at one or more processors, one or more characteristics of the user;

obtaining, at the one or more processors, a template including one or more attributes associated with the term;

generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the one or more attributes in the template; and

providing for output, data representing the response.

14. The computer-readable medium of claim 13, wherein obtaining the template including the one or more attributes associated with the term comprises:

identifying, from a collection of documents, one or more documents that include the term;

identifying, for each of the one or more documents, a respective description that has a semantic relation to the term; and

determining a respective attribute for each respective description.

15. The computer-readable medium of claim 13, wherein obtaining the template including the one or more attributes associated with the term comprises:

selecting a template from among a plurality of templates associated with the term based on the one or more characteristics of the user.

16. The computer-readable medium of claim 13, wherein generating the response comprises:

obtaining a first description for a particular attribute of the one or more attributes;

generating a second description using the first description based on the one or more characteristics of the user; and

generating the response, wherein the response includes the second description for the particular attribute.

17. A system comprising:

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

receiving a request for information about a term from a user;

obtaining, at one or more processors, one or more characteristics of the user;

obtaining, at the one or more processors, a template including one or more attributes associated with the term;

generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the one or more attributes in the template; and

providing for output, data representing the response.

18. The system of claim 17, wherein obtaining the template including the one or more attributes associated with the term comprises:

identifying, from a collection of documents, one or more documents that include the term;

identifying, for each of the one or more documents, a respective description that has a semantic relation to the term; and

determining a respective attribute for each respective description.

19. The system of claim 17, wherein obtaining the template including the one or more attributes associated with the term comprises:

selecting a template from among a plurality of templates associated with the term based on the one or more characteristics of the user.

20. The system of claim 17, wherein generating the response comprises:

obtaining a first description for a particular attribute of the one or more attributes;

generating a second description using the first description based on the one or more characteristics of the user; and

generating the response, wherein the response includes the second description for the particular attribute.