KEYWORD DETERMINATIONS FROM VOICE DATA

• US 20140337131A1
• Filed: 07/30/2014
• Published: 11/13/2014
• 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.
• Granted Patent: US 9,111,294 B2
• Time in Patent Office: Days
• US Class Current: 705/14.53
• 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 of determining interests of a user, comprising:

capturing voice content using a microphone of a computing device, the voice content being spoken by a user of the computing device;

analyzing the captured voice content, using at least one sniffer algorithm executing on the computing device, to detect a trigger word in the voice content spoken by the user, the trigger word corresponding to a set of trigger words stored by the computing device;

analyzing a portion of the captured voice content to locate at least one keyword in the voice content, each of the at least one keyword being an object of the trigger word;

storing the at least one located keyword from the voice content to a local data store on the computing device; and

sending the at least one located keyword to a remote data store accessible to at least one process capable of using the at least one located keyword to determine one or more topics of potential interest to the user and select recommended content to be provided to the user, the recommended content being selected based at least in part upon the one or more topics of potential interest.