Keyword determinations from conversational data

• US 10,373,620 B2
• Filed: 06/12/2017
• Issued: 08/06/2019
• Est. Priority Date: 09/23/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Edara, Kiran K.
• Primary Examiner(s): Guerra-Erazo, Edgar X
• Application Number:
  US15/620,252
• Publication Number:
  US 20170323645A1
• Time in Patent Office: 785 Days
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

Topics of potential interest to a user, useful for purposes such as targeted advertising and product recommendations, can be extracted from voice content produced by a user. A computing device can capture voice content, such as when a user speaks into or near the device. One or more sniffer algorithms or processes can attempt to identify trigger words in the voice content, which can indicate a level of interest of the user. For each identified potential trigger word, the device can capture adjacent audio that can be analyzed, on the device or remotely, to attempt to determine one or more keywords associated with that trigger word. The identified keywords can be stored and/or transmitted to an appropriate location accessible to entities such as advertisers or content providers who can use the keywords to attempt to select or customize content that is likely relevant to the user.

Claims

1. A computer-implemented method, comprising:

determining that first audio data, sent from a first computing device to a second computing device, represents at least one trigger word, the determining including processing the first audio data using first data stored by the first computing device, using at least a computer-implemented speech processing algorithm;

receiving second audio data sent from the first computing device to the second computing device within a specified time period of the first audio data;

determining that the second audio data represents at least one keyword;

determining identity information associated with the first computing device using at least voice recognition and the second audio data;

determining content based at least in part on the at least one keyword and the identity information associated with the first computing device; and

sending the content to the first computing device.

2. The computer-implemented method of claim 1, further comprising storing, in a remote database, at least one of the trigger word or the keyword.

3. The computer-implemented method of claim 1, further comprising causing the first computing device to output the content on a display device.

4. The computer-implemented method of claim 1, further comprising causing the first computing device to output the content as audio.

5. The computer-implemented method of claim 1, further comprising:

determining a location of the first computing device; and

determining the content based at least in part on the location.

6. The computer-implemented method of claim 1, further comprising:

determining a first value associating the at least one keyword with a user;

determining, based at least on a change in relevance of the keyword to the user, a second value associating the at least one keyword with the user; and

storing the second value in a database.

7. The computer-implemented method of claim 6, further comprising determining the content based at least on the keyword and the second value.

8. The computer-implemented method of claim 1, further comprising:

determining a first and a second item of content associated with the at least one keyword;

determining a first relevance of the first item of content;

determining a second relevance of the second item of content;

sending the first and second items of content and associated relevance to the first computing device; and

receiving a selection of the second item of content.

9. A computer-implemented method, comprising:

determining that first audio data, sent from a first computing device to a second computing device, represents at least one trigger word, the determining including processing the first audio data using first data stored by the first computing device, using at least a computer-implemented speech processing algorithm;

determining that second audio data sent within a specified time period of the first audio data represents at least one keyword;

determining second information indicative of an identity associated with the first computing device using at least voice recognition and the second audio data;

sending to a third computing device, first information indicative of the at least one keyword and the second information indicative of an identity associated with the first computing device; and

receiving from the third computing device, content associated with the at least one keyword and associated with the identity.

10. The computer-implemented method of claim 9, further comprising storing, in a local database, at least one of the trigger word or the keyword.

11. The computer-implemented method of claim 9, further comprising outputting the content on a display of the first computing device.

12. The computer-implemented method of claim 9, further comprising outputting the content as audio using a speaker of the first computing device.

13. The computer-implemented method of claim 9, further comprising:

determining a first value associating the at least one keyword with a user;

determining, based at least on a change in relevance of the keyword to the user, a second value associating the at least one keyword with the user;

storing the second value in a local database; and

determining the content based at least on the keyword and the second value.

14. The computer-implemented method of claim 9, further comprising:

determining a first and a second item of content associated with the at least one keyword;

determining a first relevance of the first item of content;

determining a second relevance of the second item of content;

displaying, based at least in part on the first relevance and the second relevance, the first item of content and the second item of content; and

receiving a selection of the second item of content.

15. A computing system, comprising:

at least one processor; and

memory including instructions that, when executed by the at least one processor, cause the computing system to;

determine that first audio data, sent from a first computing device to a second computing device, represents at least one trigger word, the determination including processing the first audio data using first data stored by the first computing device, using at least a computer-implemented speech processing algorithm;

determine that second audio data sent within a specified time period of the first audio data represents at least one keyword;

determine second information indicative of an identity associated with the first computing device using at least voice recognition and the second audio data;

send to a third computing device, first information indicative of the at least one keyword and the second information indicative of an identity associated with the first computing device; and

receive from the third computing device, content associated with the at least one keyword and associated with the identity.

16. The computing system of claim 15, further comprising a database, the memory further including instructions that, when executed by the processor, cause the computing system to store, in a local database, at least one of the trigger word or the keyword.

17. The computing system of claim 15, further comprising a display device, the memory further including instructions that, when executed by the processor, cause the computing system to output the content on the display device.

18. The computing system of claim 15, further comprising a speaker, the memory further including instructions that, when executed by the processor, cause the computing system to output the content as audio using the speaker.

19. The computing system of claim 15, further comprising a location determining device, the memory further including instructions that, when executed by the processor, cause the computing system to:

determine a location of the first computing device; and

determine the content based at least on the location.

20. The computing system of claim 15, further comprising a database, the memory further including instructions that, when executed by the processor, cause the computing system to:

determine a first value associating the at least one keyword with a user;

determine, based at least in a change in relevance of the keyword to the user, a second value associating the at least one keyword with the user;

store the second value in the database; and

determine the content based at least on the keyword and the second value.