Keyword determinations from conversational data
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.
1 . A computer-implemented method, comprising:
receiving input audio data corresponding to an utterance;
processing the input audio data to determine the utterance corresponds to a voice of a first user;
processing the input audio data to determine first content corresponding to the utterance;
determining first data associating the first content with the first user;
using the first data to determine second data corresponding to second content to be presented to the first user, the second content being unsolicited by the first user; and
using the second data to cause the second content to be presented using a device.
2 . The computer-implemented method of claim 1 , further comprising:
receiving second input audio data corresponding to a second utterance;
processing the second input audio data to determine the utterance includes a name of a second user;
processing the second input audio data to determine third content corresponding to the second utterance; and
determining third data associating the third content with the second user.
3 . The computer-implemented method of claim 1 , further comprising:
based at least in part on at least one word of the utterance, including in the first data an indication of a negative association between the first content and the first user.
4 . The computer-implemented method of claim 1 , further comprising:
storing the first data in a manner associated with a user account corresponding to the first user.
5 . The computer-implemented method of claim 1 , further comprising:
determining that a second user was present when the utterance was spoken; and
including in the first data an indication of the second user.
6 . The computer-implemented method of claim 1 , wherein the second content corresponds to a recommendation.
7 . The computer-implemented method of claim 1 , wherein the second content corresponds to an advertisement.
8 . The computer-implemented method of claim 1 , further comprising:
presenting the second content during a conversation corresponding to the utterance.
9 . The computer-implemented method of claim 1 , further comprising, prior to receiving the input audio data:
receiving second audio data;
failing to determine that the second audio data represents a trigger word; and
in response to failing to determine that the second audio data represents a trigger word, continuing to monitor incoming audio data.
10 . The computer-implemented method of claim 1 , wherein the device corresponds to a second user.
11 . A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive input audio data corresponding to an utterance;
process the input audio data to determine the utterance corresponds to a voice of a first user;
process the input audio data to determine first content corresponding to the utterance;
determine first data associating the first content with the first user;
use the first data to determine second data corresponding to second content to be presented to the first user, the second content being unsolicited by the first user; and
use the second data to cause the second content to be presented using a device.
12 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive second input audio data corresponding to a second utterance;
process the second input audio data to determine the utterance includes a name of a second user;
process the second input audio data to determine third content corresponding to the second utterance; and
determine third data associating the third content with the second user.
13 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
based at least in part on at least one word of the utterance, include in the first data an indication of a negative association between the first content and the first user.
14 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
store the first data in a manner associated with a user account corresponding to the first user.
15 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine that a second user was present when the utterance was spoken; and
include in the first data an indication of the second user.
16 . The system of claim 11 , wherein the second content corresponds to a recommendation.
17 . The system of claim 11 , wherein the second content corresponds to an advertisement.
18 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
present the second content during a conversation corresponding to the utterance.
19 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to, prior to receiving the input audio data:
receive second audio data;
fail to determine that the second audio data represents a trigger word; and
in response to failing to determine that the second audio data represents a trigger word, continue to monitor incoming audio data.
20 . The system of claim 11 , wherein the device corresponds to a second user.