Enabling an automated assistant to leverage odor sensor(s) of client device(s)
Implementations described herein are directed to leveraging odor sensor(s) of client device(s) in responding to user request(s) and/or in generating notification(s). Processor(s) of a given client device can receive a request to identify an odor in an environment of the given client device, process an odor data instance generated by the odor sensor(s) of the given client device, identify the odor based on processing the odor data instance, generate a response that identifies the odor and/or a source of the odor, and cause the response to the request to be rendered via the given client device. Processor(s) of the given client device can additionally, or alternatively, establish baseline odor(s) in the environment and generate a notification when an odor is detected that does not correspond to the baseline odor(s) and/or exclude the baseline odor(s) in generating the response to the request.
1 . A method implemented by one or more processors, the method comprising:
at a plurality of time instances:
obtaining corresponding odor data instances generated by an odor sensor of a client device of a user;
processing the corresponding odor data instances to generate corresponding outputs for the corresponding odor data instances; and
identifying, based on the corresponding outputs, one or more baseline odors associated with a physical environment of the client device; and
at a subsequent time instance that is subsequent to each of the plurality of time instances:
obtaining a given odor data instance generated by the odor sensor of the client device of the user or an additional odor sensor of an additional client device of the user that is co-located in the physical environment of the client device;
processing the given odor data instance to generate given output for the given odor data instance;
identifying, based on the given output, a given odor in the physical environment of the client device;
determining that the given odor in the physical environment of the client device does not correspond to one or more of the baseline odors associated with the physical environment of the client device; and
in response to determining that the given odor in the physical environment of the client device that does not correspond to one or more of the baseline odors associated with the physical environment of the client device:
generating synthesized speech audio data that captures synthesized speech identifying the given odor in the physical environment of the client device; and
causing the synthesized speech audio data that captures the synthesized speech identifying the given odor in the physical environment of the client device to be rendered for audible presentation to the user via one or more speakers of the client device or the additional client device of the user.
2 . The method of claim 1 , wherein identifying a given baseline odor, of the one or more baseline odors, in the physical environment of the client device based on the corresponding outputs comprises:
identifying the given baseline odor at a threshold quantity of time instances of the plurality of time instances; and
storing, in an index that includes at least the one or more baseline odors, an indication of the given baseline odor.
3 . The method of claim 2 , further comprising:
storing, in the index that includes at least the one or more baseline odors, and in association with the given baseline odor, one or more terms that describe a characteristic of the given baseline odor.
4 . The method of claim 3 , wherein the synthesized speech further identifies an indication of the characteristic of the given odor.
5 . The method of claim 1 , wherein the synthesized speech further identifies an indication that the given odor in the physical environment of the client device does not correspond to the one or more baseline odors.
6 . The method of claim 1 , further comprising:
generating, based on the given odor in the physical environment of the client device of the user, a query; and
executing, based on the query, a search over one or more databases to obtain content that is responsive to the query.
7 . The method of claim 6 , wherein the synthesized speech further identifies the content that is responsive to the query.
8 . A system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the at least one processor to be operable to:
at a plurality of time instances:
obtain corresponding odor data instances generated by an odor sensor of a client device of a user;
process the corresponding odor data instances to generate corresponding outputs for the corresponding odor data instances; and
identify, based on the corresponding outputs, one or more baseline odors associated with a physical environment of the client device; and
at a subsequent time instance that is subsequent to each of the plurality of time instances:
obtain a given odor data instance generated by the odor sensor of the client device of the user or an additional odor sensor of an additional client device of the user that is co-located in the physical environment of the client device;
process the given odor data instance to generate given output for the given odor data instance;
identify, based on the given output, a given odor in the physical environment of the client device;
determine that the given odor in the physical environment of the client device does not correspond to one or more of the baseline odors associated with the physical environment of the client device; and
in response to determining that the given odor in the physical environment of the client device that does not correspond to one or more of the baseline odors associated with the physical environment of the client device:
generate synthesized speech audio data that captures synthesized speech identifying the given odor in the physical environment of the client device; and
cause the synthesized speech audio data that captures the synthesized speech identifying the given odor in the physical environment of the client device to be rendered provided for audible presentation to the user via one or more speakers of the client device or the additional client device of the user.
9 . The system of claim 8 , wherein the instructions to identify a given baseline odor, of the one or more baseline odors, in the physical environment of the client device based on the corresponding outputs comprise instructions to:
identify the given baseline odor at a threshold quantity of time instances of the plurality of time instances; and
store, in an index that includes at least the one or more baseline odors, an indication of the given baseline odor.
10 . The system of claim 9 , wherein the at least one processor is further operable to:
store, in the index that includes at least the one or more baseline odors, and in association with the given baseline odor, one or more terms that describe a characteristic of the given baseline odor.
11 . The system of claim 10 , wherein the synthesized speech further identifies an indication of the characteristic of the given odor.
12 . The system of claim 8 , wherein the synthesized speech further identifies an indication that the given odor in the physical environment of the client device does not correspond to the one or more baseline odors.
13 . The system of claim 8 , wherein the at least one processor is further operable to:
generate, based on the given odor in the physical environment of the client device of the user, a query; and
execute, based on the query, a search over one or more databases to obtain content that is responsive to the query.
14 . The system of claim 13 , wherein the synthesized speech further identifies the content that is responsive to the query.
15 . A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to be operable to perform operations, the operations comprising:
at a plurality of time instances:
obtaining corresponding odor data instances generated by an odor sensor of a client device of a user;
processing the corresponding odor data instances to generate corresponding outputs for the corresponding odor data instances; and
identifying, based on the corresponding outputs, one or more baseline odors associated with a physical environment of the client device; and
at a subsequent time instance that is subsequent to each of the plurality of time instances:
obtaining a given odor data instance generated by the odor sensor of the client device of the user or an additional odor sensor of an additional client device of the user that is co-located in the physical environment of the client device;
processing the given odor data instance to generate given output for the given odor data instance;
identifying, based on the given output, a given odor in the physical environment of the client device;
determining that the given odor in the physical environment of the client device does not correspond to one or more of the baseline odors associated with the physical environment of the client device; and
in response to determining that the given odor in the physical environment of the client device that does not correspond to one or more of the baseline odors associated with the physical environment of the client device:
generating synthesized speech audio data that captures synthesized speech identifying the given odor in the physical environment of the client device; and
causing the synthesized speech audio data that captures the synthesized speech identifying the given odor in the physical environment of the client device to be rendered for audible presentation to the user via one or more speakers of the client device or the additional client device of the user.
16 . The non-transitory computer-readable storage medium of claim 15 , wherein identifying a given baseline odor, of the one or more baseline odors, in the physical environment of the client device based on the corresponding outputs comprises:
identifying the given baseline odor at a threshold quantity of time instances of the plurality of time instances; and
storing, in an index that includes at least the one or more baseline odors, an indication of the given baseline odor.
17 . The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:
storing, in the index that includes at least the one or more baseline odors, and in association with the given baseline odor, one or more terms that describe a characteristic of the given baseline odor.
18 . The non-transitory computer-readable storage medium of claim 17 , wherein the synthesized speech further identifies an indication of the characteristic of the given odor.
19 . The non-transitory computer-readable storage medium of claim 15 , wherein the synthesized speech further identifies an indication that the given odor in the physical environment of the client device does not correspond to the one or more baseline odors.
20 . The non-transitory computer-readable storage medium of claim 15 , the operations further comprising:
generating, based on the given odor in the physical environment of the client device of the user, a query; and
executing, based on the query, a search over one or more databases to obtain content that is responsive to the query, wherein the synthesized speech further identifies the content that is responsive to the query.