Task initiation using sensor dependent context long-tail voice commands
In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers previously used across a population of users. The library may include association(s) between each voice-based trigger and responsive action(s) previously performed in response to the voice-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more responsive actions associated with the selected voice-based trigger in the library may be determined. Based on the one or more responsive actions, current responsive action(s) may be performed by a target client device selected based on sensor-dependent context. Feedback associated with performance of the current responsive action(s) may be received from the user and used to alter a strength of an association between the selected voice-based trigger and the one or more responsive actions.
1. A method comprising:
receiving, at a first client device, a given voice command from a user, wherein the given voice command is ambiguous as to what responsive action it is meant to invoke;
disambiguating the given voice command to identify a given responsive action to perform, wherein the disambiguating comprises:
identifying a context of the user detected using one or more sensors of the first client device or another client device;
selecting, from a library of voice-based triggers previously used across a population of users, a selected voice-based trigger, wherein the library includes one or more associations between each respective voice-based trigger of the library of voice-based triggers and one or more responsive actions previously invoked automatically at one or more other client devices operated by one or more other users of the population of users in response to the respective voice-based trigger, and wherein the selecting is based at least in part on a measure of similarity between the given voice command and the selected voice-based trigger;
determining a plurality of candidate responsive actions associated with the selected voice-based trigger in the library, wherein each candidate responsive action of the plurality of candidate responsive actions is associated with a different client device of a plurality of client devices that are controllable by the user;
based on the context of the user, selecting a target client device from the plurality of client devices; and
based on the selected target device, selecting the given responsive action from the plurality of candidate responsive actions associated with the selected voice-based trigger in the library; and
performing, at the target client device, the given responsive action.
2. The method of claim 1 , wherein the selected voice-based trigger includes one or more terms or tokens that are analogous to one or more terms or tokens in the given voice command.
3. The method of claim 1 , further comprising:
receiving, from the user, feedback associated with the performance of the given responsive action; and
altering a strength of an association between the selected voice-based trigger and the given responsive action based on the feedback;
wherein the altering comprises weakening or strengthening the association between the selected voice-based trigger and the given responsive action based on the feedback.
4. The method of claim 1 , wherein the plurality of candidate responsive actions include altering an air conditioning parameter in a building and altering an air conditioning parameter in a vehicle, and the context of the user indicates whether the user is in the building or in the vehicle.
5. The method of claim 1 , wherein the target client device is the first client device.
6. The method of claim 1 , wherein the target client device is different than the first client device.
7. The method of claim 1 , wherein the measure of similarity is a measure of syntactic or semantic similarity.
8. A system comprising one or more processors and memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to operate an interactive assistant module configured to perform the following operations:
receiving, at a first client device, a given voice command from a user, wherein the given voice command is ambiguous as to what responsive action it is meant to invoke;
disambiguating the given voice command to identify a given responsive action to perform, wherein the disambiguating comprises:
identifying a context of the user detected using one or more sensors of the first client device or another client device;
selecting, from a library of voice-based triggers previously used across a population of users, a selected voice-based trigger, wherein the library includes one or more associations between each respective voice-based trigger of the library of voice-based triggers and one or more responsive actions previously invoked automatically at one or more other client devices operated by one or more other users of the population of users in response to the respective voice-based trigger, and wherein the selecting is based at least in part on a measure of similarity between the given voice command and the selected voice-based trigger;
determining a plurality of candidate responsive actions associated with the selected voice-based trigger in the library, wherein each candidate responsive action of the plurality of candidate responsive actions is associated with a different client device of a plurality of client devices that are controllable by the user;
based on the context of the user, selecting a target client device from the plurality of client devices;
based on the selected target device, selecting the given responsive action from the plurality of candidate responsive actions associated with the selected voice-based trigger in the library; and
performing, at a target client device controlled by the user, the given responsive action.
9. The system of claim 8 , wherein the selected voice-based trigger includes one or more terms or tokens that are analogous to one or more terms or tokens in the given voice command.
10. The system of claim 8 , further comprising:
receiving, from the user, feedback associated with the performance of the given responsive action; and
altering a strength of an association between the selected voice-based trigger and the given responsive action based on the feedback;
wherein the altering comprises weakening or strengthening the association between the selected voice-based trigger and the given responsive action based on the feedback.
11. The system of claim 8 , wherein the plurality of responsive actions include altering an air conditioning parameter in a building and altering an air conditioning parameter in a vehicle, and the context of the user indicates whether the user is in the building or in the vehicle.
12. The system of claim 8 , wherein the target client device is the first client device.
13. The system of claim 8 , wherein the target client device is different than the first client device.
14. The system of claim 8 , wherein the measure of similarity is a measure of syntactic or semantic similarity.
15. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:
receiving, at a first client device, a given voice command from a user, wherein the given voice command is ambiguous as to what responsive action it is meant to invoke;
disambiguating the given voice command to identify a given responsive action to perform, wherein the disambiguating comprises:
identifying a context of the user detected using one or more sensors of the first client device or another client device;
selecting, from a library of voice-based triggers previously used across a population of users, a selected voice-based trigger, wherein the library includes one or more associations between each respective voice-based trigger of the library of voice-based triggers and one or more responsive actions previously invoked automatically at one or more other client devices operated by one or more other users of the population of users in response to the respective voice-based trigger, and wherein the selecting is based at least in part on a measure of similarity between the given voice command and the selected voice-based trigger;
determining a plurality of candidate responsive actions associated with the selected voice-based trigger in the library, wherein each candidate responsive action of the plurality of candidate responsive actions is associated with a different client device of a plurality of client devices that are controllable by the user;
based on the context of the user, selecting a target client device from the plurality of client devices;
based on the selected target device, selecting the given responsive action from the plurality of candidate responsive actions associated with the selected voice-based trigger in the library; and
performing, at a target client device controlled by the user, the given responsive action.
16. The at least one non-transitory computer-readable medium of claim 15 , wherein the plurality of candidate responsive actions include altering an air conditioning parameter in a building and altering an air conditioning parameter in a vehicle, and the context of the user indicates whether the user is in the building or in the vehicle.
17. The at least one non-transitory computer-readable medium of claim 15 , wherein the target client device is the first client device.