Identifying canonical content items for answering online questions

• US 9,396,263 B1
• Filed: 10/14/2013
• Issued: 07/19/2016
• Est. Priority Date: 10/14/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Unger, Alexander Ketner, Haugen, Frances Bordwell, Vanderwater, Kathryn Rose
• Primary Examiner(s): Syed, Farhan
• Application Number:
  US14/053,522
• Time in Patent Office: 1,009 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

Methods relating to canonical content items are provided. An example method may include receiving an online question by an asking user. The method may further include identifying one or more topics of the received online question. The method may further include matching at least one canonical content item from a plurality of canonical content items to the received online question based on the identified one or more topics, wherein each canonical content item of the plurality of canonical content items is associated with a model explanation of a topic. In addition, the method may include providing the matched at least one canonical content item to the asking user. Systems and computer-readable media are also described.

Claims

1. A computer-implemented method comprising:

receiving, at a server, an online question by an asking user from a user device of the asking user over a communications network;

identifying, with the server, one or more topics of the received online question;

matching, with the server, at least one canonical content item from a plurality of canonical content items to the received online question based on the identified one or more topics, wherein each canonical content item of the plurality of canonical content items includes a model explanation of a topic stored at the server, wherein each model explanation comprises an asked question portion and a corresponding answer portion, and wherein each canonical content item is based on a set of similar content items from a plurality of content items;

providing, to the user device over the communications network, the asked question portion and the corresponding answer portion of the matched at least one canonical content item to the asking user;

executing one or more clustering techniques over the plurality of content items to determine each set of similar content items, wherein the plurality of content items relates to user-submitted online questions and corresponding user-submitted online answers;

compiling the plurality of canonical content items based on a curating process associated with one or more clusters of content items from each set of similar content items from the plurality of content items; and

receiving a rating, by the asking user, for the matched at least one canonical content item, wherein the rating identifies the asking user'"'"'s approval of the model explanation of the topic associated with the matched at least one canonical content item and is used as a factor in the curating process associated with one or more clusters of content items.

2. The method of claim 1, wherein the curating process comprises selecting at least some canonical content items of the plurality of canonical content items by selecting a representative content item from the one or more clusters of content items.

3. The method of claim 1, wherein the curating process comprises selecting at least some canonical content items of the plurality of canonical content items by synthesizing a set of content items from the one or more clusters of content items into a single content item.

4. The method of claim 1, wherein the matched at least one canonical content item comprises a group of matched canonical content items and the providing the matched at least one canonical content item to the asking user comprises:

providing the asked question portion of each of the group of matched canonical content items to the asking user;

receiving a selection by the asking user indicating one of the provided asked question portions of the group of matched canonical content items; and

providing the corresponding answer portion of the indicated one of the provided asked question portions of the group of matched canonical content items.

5. The method of claim 1, wherein the at least one canonical content item comprises a video clip that presents the asked question portion and the corresponding answer portion.

6. The method of claim 1, wherein the at least one canonical content item comprises a set of related canonical content items, and wherein each canonical content item of the set of related canonical content items is associated with a different entity.

7. A system comprising:

one or more processors; and

a memory including instructions that, when executed by the one or more processors, cause the one or more processors to;

receive an online question by an asking user;

identify one or more topics of the received online question;

match at least one canonical content item from a plurality of canonical content items to the received online question based on the identified one or more topics, wherein each canonical content item of the plurality of canonical content items includes a model explanation of a topic, wherein each model explanation comprises an asked question portion and a corresponding answer portion, and wherein each canonical content item is based on a set of similar content items from a plurality of content items;

provide the asked question portion and the corresponding answer portion of the matched at least one canonical content item to the asking user;

execute one or more clustering techniques over the plurality of content items to determine each set of similar content items, wherein the plurality of content items relates to user-submitted online questions and corresponding user-submitted online answers;

compile the plurality of canonical content items based on a curating process associated with one or more clusters of content items from each set of similar content items from the plurality of content items; and

receive a rating, by the asking user, for the matched at least one canonical content item, wherein the rating identifies the asking user'"'"'s approval of the model explanation of the topic associated with the matched at least one canonical content item and is used as a factor in the curating process associated with the one or more clusters of content items.

8. The system of claim 7, wherein the matched at least one canonical content item comprises a group of matched canonical content items and wherein the instructions that, when executed by the one or more processors, cause the one or more processors to provide the matched at least one canonical content item to the asking user, further cause the one or more processors to:

provide the asked question portion of each of the group of matched canonical content items to the asking user;

receive a selection by the asking user indicating one of the provided asked question portions of the group of matched canonical content items; and

provide the corresponding answer portion of the indicated one of the provided asked question portions of the group of matched canonical content items.

11. The system of claim 7, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to perform the curating process by selecting at least some canonical content items of the plurality of canonical content items by selecting a representative content item from the one or more clusters of content items.

12. The system of claim 7, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to perform the curating process by selecting at least some canonical content items of the plurality of canonical content items by synthesizing a set of content items from the one or more clusters of content items into a single content item.

13. The system of claim 7, wherein the at least one canonical content item comprises a video clip that presents the asked question portion and the corresponding answer portion.

14. The system of claim 7, wherein the at least one canonical content item comprises a set of related canonical content items, and wherein each canonical content item of the set of related canonical content items is associated with a different entity.

9. A machine-readable medium comprising instructions stored therein, which when executed by a machine, cause the machine to perform operations, the machine-readable medium comprising:

instructions for receiving an online question by an asking user;

instructions for identifying one or more topics of the received online question;

instructions for matching at least one canonical content item from a plurality of canonical content items to the received online question based on the identified one or more topics, wherein each canonical content item of the plurality of canonical content items includes a model explanation of a topic, wherein each model explanation comprises an asked question portion and a corresponding answer portion, and wherein each canonical content item is based on a set of similar content items from a plurality of content items;

instructions for providing the asked question portion and the corresponding answer portion of the matched at least one canonical content item to the asking user;

instructions for executing one or more clustering techniques over the plurality of content items to determine each set of similar content items, wherein the plurality of content items relates to user-submitted online questions and corresponding user-submitted online answers;

instructions for compiling the plurality of canonical content items based on a curating process associated with one or more clusters of content items from each set of similar content items from the plurality of content items; and

instructions for receiving a rating, by the asking user, for the matched at least one canonical content item, wherein the rating identifies the asking user'"'"'s approval of the model explanation of the topic associated with the matched at least one canonical content item and is used as a factor in the curating process associated with the one or more clusters of content items.

10. The machine-readable medium of claim 9, wherein the matched at least one canonical content item comprises a group of matched canonical content items and wherein the instructions for providing the matched at least one canonical content item to the asking user further comprise:

instructions for providing the asked question portion of each of the group of matched canonical content items to the asking user;

instructions for receiving a selection by the asking user indicating one of the provided asked question portions of the group of matched canonical content items; and

instructions for providing the corresponding answer portion of the indicated one of the provided asked question portions of the group of matched canonical content items.

15. The machine-readable medium of claim 9, further comprising instructions for performing the curating process by selecting at least some canonical content items of the plurality of canonical content items by selecting a representative content item from the one or more clusters of content items.

16. The machine-readable medium of claim 9, further comprising instructions for performing the curating process by selecting at least some canonical content items of the plurality of canonical content items by synthesizing a set of content items from the one or more clusters of content items into a single content item.

17. The machine-readable medium of claim 9, wherein the at least one canonical content item comprises a video clip that presents the asked question portion and the corresponding answer portion.

18. The machine-readable medium of claim 9, wherein the at least one canonical content item comprises a set of related canonical content items, and wherein each canonical content item of the set of related canonical content items is associated with a different entity.