Privacy control in a connected environment
First Claim
Patent Images
1. A home assistant device, comprising:
- a microphone;
a speaker;
one or more processors; and
memory storing instructions, wherein the processor is configured to execute the instructions such that the processor and memory are configured to;
detect first speech including a first question spoken by a user of the home assistant device using the microphone;
determine that the first speech includes a first hardware activation phrase preceding the first question, wherein the first hardware activation phrase indicates an intention of the user to provide the first question of the first speech to a cloud server;
provide the first question to the cloud server;
receive a first response from the cloud server providing a first answer to the first question;
play back the first answer using the speaker, the playback of the first answer having first characteristics;
detect second speech including a second question spoken by the user of the home assistant device using the microphone;
determine that the second speech includes a second hardware activation phrase preceding the second question, the first hardware activation phrase and the second hardware activation phrase being different phrases, wherein the second hardware activation phrase indicates an intention of the user to provide the second question of the second speech to local resources of the home assistant device rather than the cloud server due to increased privacy expectations regarding content of the second question in comparison with privacy expectations regarding content of the first question;
provide the second question to the local resources of the home assistant device;
receive a second response from the local resources providing a second answer to the second question; and
play back the second answer using the speaker, the playback of the second answer having second characteristics that are different than the first characteristics of the playback of the first answer due to the first response being received from the cloud server rather than the local resources.
1 Assignment
0 Petitions
Accused Products
Abstract
Privacy control in a connected environment is described. An assistant device can detect speech spoken by a user. The speech can include a hardware activation phrase that indicates whether the user intends for at least a portion of the speech to be provided to local resources or cloud resources. The speech can then be provided to the appropriate resource based on the hardware activation phrase.
-
Citations
22 Claims
-
1. A home assistant device, comprising:
-
a microphone; a speaker; one or more processors; and memory storing instructions, wherein the processor is configured to execute the instructions such that the processor and memory are configured to; detect first speech including a first question spoken by a user of the home assistant device using the microphone; determine that the first speech includes a first hardware activation phrase preceding the first question, wherein the first hardware activation phrase indicates an intention of the user to provide the first question of the first speech to a cloud server; provide the first question to the cloud server; receive a first response from the cloud server providing a first answer to the first question; play back the first answer using the speaker, the playback of the first answer having first characteristics; detect second speech including a second question spoken by the user of the home assistant device using the microphone; determine that the second speech includes a second hardware activation phrase preceding the second question, the first hardware activation phrase and the second hardware activation phrase being different phrases, wherein the second hardware activation phrase indicates an intention of the user to provide the second question of the second speech to local resources of the home assistant device rather than the cloud server due to increased privacy expectations regarding content of the second question in comparison with privacy expectations regarding content of the first question; provide the second question to the local resources of the home assistant device; receive a second response from the local resources providing a second answer to the second question; and play back the second answer using the speaker, the playback of the second answer having second characteristics that are different than the first characteristics of the playback of the first answer due to the first response being received from the cloud server rather than the local resources. - View Dependent Claims (2)
-
-
3. A method for privacy control in a connected environment, comprising:
-
detecting speech spoken by a user of an assistant device; determining, by a processor, that the speech includes a hardware activation phrase corresponding to an intention of the user to provide a first portion of the speech to one or both of local resources of the assistant device or a cloud server based on the hardware activation phrase; providing the first portion of the speech to the local resources or the cloud server based on the hardware activation phrase; receiving a first response data providing an answer to the first portion of the speech from the local resources; playing back the first response data, characteristics of the playback of the first response data based on the first response data being received from the local resources; providing a second portion of the speech to the cloud server; receiving a second response data providing an answer to the second portion of the speech from the cloud server; and playing back the second response data, characteristics of the playback of the second response data being different than the characteristics of the playback of the first response data due to the second portion of the speech being received from the cloud server rather than the local resources. - View Dependent Claims (4, 5, 6, 7, 8, 9)
-
-
10. An electronic device, comprising:
-
one or more processors; and memory storing instructions, wherein the processor is configured to execute the instructions such that the processor and memory are configured to; detect speech being spoken by a user of an assistant device; determine that the speech includes a hardware activation phrase corresponding to an intention of the user to provide a first portion of the speech to one or both of local resources of the assistant device or a cloud server based on the hardware activation phrase; provide the first portion of the speech to the local resources or the cloud server based on the hardware activation phrase; receive a first response data providing an answer to the first portion of the speech from the local resources; play back the first response data, characteristics of the playback of the first response data based on the first response data being received from the local resources; provide a second portion of the speech to the cloud server; receive a second response data providing an answer to the second portion of the speech from the cloud server; and play back the second response data, characteristics of the playback of the second response data being different than the characteristics of the playback of the first response data due to the second portion of the speech being received from the cloud server rather than the local resources. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
17. A computer program product, comprising one or more non-transitory computer-readable media having computer program instructions stored therein, the computer program instructions being configured such that, when executed by one or more computing devices, the computer program instructions cause the one or more computing devices to:
-
detect speech being spoken by a user of an assistant device; determine that the speech includes a hardware activation phrase corresponding to an intention of the user to provide a first portion of the speech to one or both of local resources of the assistant device or a cloud server based on the hardware activation phrase; provide the first portion of the speech to the local resources or the cloud server based on the hardware activation phrase; receive a first response data providing an answer to the first portion of the speech from the local resources; play back the first response data, characteristics of the playback of the first response data based on the first response data being received from the local resources; provide a second portion of the speech to the cloud server; receive a second response data providing an answer to the second portion of the speech from the cloud server; and play back the second response data, characteristics of the playback of the second response data being different than the characteristics of the playback of the first response data due to the second portion of the speech being received from the cloud server rather than the local resources. - View Dependent Claims (18, 19, 20, 21, 22)
-
Specification