Granted Patent B1

US 12,632,496 · App. 18/937,953 · Granted May 19, 2026

Inventors: Jason Sanders (New York, NY); John J. Lee (Long Island City, NY); Gabriel Taubman (Brooklyn, NY)

Assignee: GOOGLE LLC

G06F16/634

Abstract

Claims (61)

1 . A computer-implemented method comprising:

receiving, at a computing device, a spoken query provided by a user, wherein the spoken query provided by the user satisfies a threshold volume level;

receiving, at the computing device, background audio produced by a source in an environment of the computing device;

determining that at least a portion of the background audio is collected in a fixed time interval before the user provided the spoken query and/or after the user provided the spoken query;

transmitting, from the computing device to a remote computing device, the spoken query provided by the user and at least the portion of the background audio that is collected in the fixed time interval before the user provided the spoken query and/or after the user provided the spoken query, wherein transmitting the spoken query from the computing device to the remote computing device causes the remote computing device to:

execute a search based on the spoken query to obtain one or more search results; and

filter, based on the portion of the background audio, the one or more search results, wherein the one or more search results are filtered based on one or more related terms of a set of related terms that describe entities being associated in an entity-relationship model with a known audio segment that is identified based on the portion of the background audio that is produced by the source in the environment of the computing device;

receiving, from the remote computing device, the one or more filtered search results; and

causing, in response to receiving the one or more filtered search results, one or more of the filtered search results to be rendered via the computing device for presentation to the user.

2 . The method of claim 1 , wherein the one or more filtered search results include only search results that include one or more of the related terms of the set of related terms that describe entities that are associated in the entity-relationship model with the known audio segment that is identified based on the background audio.

3 . The method of claim 1 , wherein the one or more search results are further filtered based on one or more of the search results satisfying a threshold score.

4 . The method of claim 1 , wherein the one or more filtered search results include only search results that include one or more related terms of the set of related terms that describe entities that are associated in the entity-relationship model with the known audio segment that is identified based on the background audio.

5 . The method of claim 1 , wherein receiving one or more of the filtered search results is in response to:

the spoken query being provided to a search engine to execute the search based on the spoken query to obtain the one or more search results;

scored results being received from the search engine; and

the search results being filtered based on a score for a search result containing at least one of the related terms being altered.

6 . The method of claim 1 , wherein the one or more search results are further filtered based on:

at least a portion of the background audio being recognized by matching at least the portion of the background audio to an acoustic fingerprint; and

the known audio segment being identified based on the background audio comprising the known audio segment associated with the acoustic fingerprint.

7 . The method of claim 1 , wherein the one or more search results are further filtered based on the set of related terms being generated based on a database being queried based on the known audio segment based on the background audio.

8 . A system comprising:

memory storing instructions; and

one or more processors operable to execute the instructions to:

receive, at a computing device, a spoken query provided by a user, wherein the spoken query provided by the user satisfies a threshold volume level;

receive, at the computing device, background audio produced by a source in an environment of the computing device;

determine that at least a portion of the background audio is collected in a fixed time interval before the user provided the spoken query and/or after the user provided the spoken query;

transmit, from the computing device to a remote computing device, the spoken query provided by the user and at least the portion of the background audio that is collected in the fixed time interval before the user provided the spoken query and/or after the user provided the spoken query, wherein transmitting the spoken query from the computing device to the remote computing device causes the remote computing device to:

execute a search based on the spoken query to obtain one or more search results; and

filter, based on the portion of the background audio, the one or more search results, wherein the one or more search results are filtered based on one or more related terms of a set of related terms that describe entities being associated in an entity-relationship model with a known audio segment that is identified based on the portion of the background audio that is produced by the source in the environment of the computing device;

receive, from the remote computing device, the one or more filtered search results; and

cause, in response to receiving the one or more filtered search results, one or more of the filtered search results to be rendered via the computing device for presentation to the user.

9 . The system of claim 8 , wherein the one or more filtered search results include only search results that include one or more of the related terms of the set of related terms that describe entities that are associated in the entity-relationship model with the known audio segment that is identified based on the background audio.

10 . The system of claim 8 , wherein the one or more search results are further filtered based on one or more of the search results satisfying a threshold score.

11 . The system of claim 8 , wherein the one or more filtered search results include only search results that include one or more related terms of the set of related terms that describe entities that are associated in the entity-relationship model with the known audio segment that is identified based on the background audio.

12 . The system of claim 8 , wherein receiving one or more of the filtered search results is in response to:

the spoken query being provided to a search engine to execute the search based on the spoken query to obtain the one or more search results;

scored results being received from the search engine; and

the search results being filtered based on a score for a search result containing at least one of the related terms being altered.

13 . The system of claim 8 , wherein the one or more search results are further filtered based on:

at least a portion of the background audio being recognized by matching at least the portion of the background audio to an acoustic fingerprint; and

the known audio segment being identified based on the background audio comprising the known audio segment associated with the acoustic fingerprint.

14 . The system of claim 8 , wherein the one or more search results are further filtered based on the set of related terms being generated based on a database being queried based on the known audio segment based on the background audio.

15 . A non-transitory computer readable storage medium configured to store instructions that, when executed by one or more processors, cause one or more of the processors to:

receive, at a computing device, a spoken query provided by a user, wherein the spoken query provided by the user satisfies a threshold volume level;

receive, at the computing device, background audio produced by a source in an environment of the computing device;

determine that at least a portion of the background audio is collected in a fixed time interval before the user provided the spoken query and/or after the user provided the spoken query;

transmit, from the computing device to a remote computing device, the spoken query provided by the user and at least the portion of the background audio that is collected in the fixed time interval before the user provided the spoken query and/or after the user provided the spoken query, wherein transmitting the spoken query from the computing device to the remote computing device causes the remote computing device to:

execute a search based on the spoken query to obtain one or more search results; and

filter, based on the portion of the background audio, the one or more search results, wherein the one or more search results are filtered based on one or more related terms of a set of related terms that describe entities being associated in an entity-relationship model with a known audio segment that is identified based on the portion of the background audio that is produced by the source in the environment of the computing device;

receive, from the remote computing device, the one or more filtered search results; and

cause, in response to receiving the one or more filtered search results, one or more of the filtered search results to be rendered via the computing device for presentation to the user.

16 . The non-transitory computer readable storage medium of claim 15 , wherein the one or more filtered search results include only search results that include one or more of the related terms of the set of related terms that describe entities that are associated in the entity-relationship model with the known audio segment that is identified based on the background audio.

17 . The non-transitory computer readable storage medium of claim 15 , wherein the one or more search results are further filtered based on one or more of the search results satisfying a threshold score.

18 . The non-transitory computer readable storage medium of claim 15 , wherein the one or more filtered search results include only search results that include one or more related terms of the set of related terms that describe entities that are associated in the entity-relationship model with the known audio segment that is identified based on the background audio.

19 . The non-transitory computer readable storage medium of claim 15 , wherein receiving one or more of the filtered search results is in response to:

the spoken query being provided to a search engine to execute the search based on the spoken query to obtain the one or more search results;

scored results being received from the search engine; and

the search results being filtered based on a score for a search result containing at least one of the related terms being altered.

20 . The non-transitory computer readable storage medium of claim 15 , wherein the one or more search results are further filtered based on:

at least a portion of the background audio being recognized by matching at least the portion of the background audio to an acoustic fingerprint; and

the known audio segment being identified based on the background audio comprising the known audio segment associated with the acoustic fingerprint.

Assignments (2)

Continuity (7)

References Cited (62)