Query disambiguation using environmental audio

1. A method, comprising:

capturing, using at least one sensor of an information handling device, environmental audio, wherein the environmental audio comprises a plurality of different data types;

storing, in a rolling queue, a user-designated data type from the plurality of different data types, wherein the storing comprises ignoring, from the rolling queue, undesignated data types from the plurality of different data types;

receiving, at an audio capture device associated with the information handling device, a user query, wherein the user query comprises at least one deictic term;

disambiguating, using a processor and by analyzing the captured environmental audio associated with the user-designated data type stored in the rolling queue, the user query; and

providing, based on the disambiguating, a response to the user query.

2. The method of claim 1 , wherein the environmental audio corresponds to an audible conversation.

3. The method of claim 1 , wherein the environmental audio corresponds to a sound stream produced by an entity selected from the group consisting of: another device, an object, a person, and an animal.

4. The method of claim 1 , wherein the at least one deictic term corresponds to a deictic pronoun.

5. The method of claim 1 , wherein the rolling queue comprises N-seconds worth of the environmental audio.

6. The method of claim 1 , wherein the rolling queue comprises a predetermined amount of stored data.

7. The method of claim 1 , wherein the disambiguating comprises:

analyzing the environmental audio stored in the rolling queue responsive to receiving the user query;

determining a context associated with the analyzed environmental audio; and

applying a meaning to the at least one deictic term based at least in part on the determined context.

8. The method of claim 1 , wherein the disambiguating comprises:

analyzing the environmental audio responsive to capturing the environmental audio;

determining, based on the analyzing, a running context associated with the environmental audio; and

applying a meaning to the at least one deictic term based at least in part on the running context.

9. The method of claim 1 , wherein the capturing comprises continuously capturing the environmental data.

10. An information handling device, comprising:

a sensor;

an audio capture device;

a processor;

a memory device that stores instructions executable by the processor to:

capture environmental audio, wherein the environmental audio comprises a plurality of different data types;

storing, in a rolling queue, a user-designated data type from the plurality of different data types, wherein the storing comprises ignoring, from the rolling queue, undesignated data types from the plurality of different data types;

receive a user query, wherein the user query comprises at least one deictic term;

disambiguate, by analyzing the captured environmental audio associated with the user-designated data types stored in the rolling queue, the user query; and

provide, based on the disambiguating, a response to the user query.

11. The information handling device of claim 10 , wherein the environmental audio corresponds to an audible conversation.

12. The information handling device of claim 10 , wherein the environmental audio corresponds to a sound stream produced by an entity selected from the group consisting of another device, an object, a person, and an animal.

13. The information handling device of claim 10 , wherein the at least one deictic term corresponds to a deictic pronoun.

14. The information handling device of claim 10 , wherein the rolling queue comprises N-seconds worth of the environmental audio.

15. The information handling device of claim 10 , wherein the rolling queue comprises a predetermined amount of stored data.

16. The information handling device of claim 10 , wherein the instructions executable by the processor to disambiguate comprise instructions executable by the processor to:

analyze the environmental audio stored in the rolling queue responsive to receiving the user query;

determine a context associated with the analyzed environmental audio; and

apply a meaning to the at least one deictic term based at least in part on the determined context.

17. The information handling device of claim 10 , wherein the instructions executable by the processor to disambiguate comprise instructions executable by the processor to:

analyze the environmental audio responsive to capturing the environmental audio;

determine, based on the analyzing, a running context associated with the environmental audio; and

applying a meaning to the at least one deictic term based at least in part on the running context.

18. A product, comprising:

a non-transitory storage device that stores code, the code being executable by a processor and comprising:

code that captures environmental audio, wherein the environmental audio comprises a plurality of different data types;

code that stores, in a rolling queue, a user-designated data type from the plurality of different data types, wherein the storing comprises ignoring, from the rolling queue, undesignated data types from the plurality of different data types;

code that receives a user query, wherein the user query comprises at least one deictic term;

code that disambiguates, by analyzing the captured environmental audio associated with the user-designated data type stored in the rolling queue, the user query; and

code that provides, based on the disambiguating, a response to the user query.