Gaze-activated voice services for interactive workspaces
Systems and methods for providing gaze-activated voice services for interactive workspaces. In some embodiments, an Information Handling System (IHS), may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: transmit a voice command to a voice service provider; receive a textual instruction in response to the voice command; identify a gaze focus of the user; and execute the textual instruction using the gaze focus.
1. An Information Handling System (IHS), comprising:
a processor; and
a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to:
transmit a first voice command from a user operating a client device to a voice service provider, wherein the voice service provider is configured to: (i) convert the first voice command into a first textual instruction; and (ii) transmit the first textual instruction to an intelligent assistant provider distinct from the voice service provider, wherein the intelligent assistant provider comprises first contextual information, and wherein the first contextual information comprises: an identification of a totem coupled to the client device, and a first gaze focus of the user obtained concurrently with the first voice command;
receive a first totem command generated by the intelligent assistant provider based upon the first textual instruction and the first gaze focus, wherein the first totem command is of a type selected from the group consisting of: change color, change size, and rotate;
execute the first totem command;
transmit a second voice command from the user to the voice service provider, wherein the voice service provider is configured to: (i) convert the second voice command into a second textual instruction; and (ii) transmit the second textual instruction to the intelligent assistant provider, wherein the intelligent assistant provider comprises second contextual information, and wherein the second contextual information comprises a second gaze focus of the user obtained concurrently with the second voice command;
receive a second totem command generated by the intelligent assistant provider based upon the second textual instruction and the second gaze focus, wherein in response to a second target of the second gaze focus being of a different type than a first target of the first gaze focus, the second totem command is of a different type than the first totem command; and
execute the second totem command.
2. The IHS of claim 1 , wherein the first totem command is generated, at least in part, by brokering the use of different language models, and wherein at least one of the different language models is selected based upon the contextual information.
3. The IHS of claim 1 , wherein to execute the first totem command, the program instructions, upon execution, further cause the IHS to route the first totem command to an application selected by the first gaze focus.
4. The IHS of claim 1 , wherein to execute the second totem command, the program instructions, upon execution, further cause the IHS to position content at the second gaze focus.
5. The IHS of claim 1 , wherein to execute the first totem command, the program instructions, upon execution, further cause the IHS to select a mode of operation of the totem from the group consisting of: color control, brightness control, contrast control, and size control.
6. The IHS of claim 1 , wherein the first voice command is captured in response to a selected user interaction with the totem.
7. The IHS of claim 1 , wherein to execute the first totem command, the program instructions, upon execution, further cause the IHS to select a gradient of a Graphical User Interface (GUI) element displayed by the IHS.
8. The IHS of claim 1 , wherein the first contextual information comprises a position of the totem on a touchscreen.
9. A hardware memory device having program instructions stored thereon that, upon execution by an Information Handling System (IHS), cause the IHS to:
transmit a first voice command from a user operating a client device to a voice service provider, wherein the voice service provider is configured to: (i) convert the first voice command into a first textual instruction; and (ii) transmit the first textual instruction to an intelligent assistant provider distinct from the voice service provider, wherein the intelligent assistant provider comprises first contextual information, and wherein the first contextual information comprises: an identification of a totem coupled to the client device, and a first gaze focus of the user obtained concurrently with the first voice command;
receive a first totem command generated by the intelligent assistant provider based upon the first textual instruction and the first gaze focus, wherein the first totem command is of a type selected from the group consisting of: change color, change size, and rotate;
execute the first totem command;
transmit a second voice command from the user to the voice service provider, wherein the voice service provider is configured to: (i) convert the second voice command into a second textual instruction; and (ii) transmit the second textual instruction to the intelligent assistant provider, wherein the intelligent assistant provider comprises second contextual information, and wherein the second contextual information comprises a second gaze focus of the user obtained concurrently with the second voice command;
receive a second totem command generated by the intelligent assistant provider based upon the second textual instruction and the second gaze focus, wherein in response to a second target of the second gaze focus being of a different type than a first target of the first gaze focus, the second totem command is of a different type than the first totem command; and
execute the second totem command.
10. The hardware memory device of claim 9 , wherein the first contextual information comprises at least one of: a position of the totem, or a state of the totem.
11. The hardware memory device of claim 9 , wherein the program instructions, upon execution, further cause the IHS to select one of a plurality of modes of operation of the totem in response to the first totem command.
12. The hardware memory device of claim 9 , wherein the voice command is captured in response to physical interaction with the totem.
13. The hardware memory device of claim 9 , wherein the program instructions, upon execution, further cause the IHS to select a gradient of an element displayed in a Graphical User Interface (GUI) of the IHS.
14. The hardware memory device of claim 9 , wherein the program instructions, upon execution, further cause the IHS to select one of a plurality of modes of operation of the wireless totem in response to the first gaze focus.
15. The hardware memory device of claim 9 , wherein the program instructions, upon execution, further cause the IHS to select a touch layer parameter of an area of a touchscreen identified as the first gaze focus.
16. A method, comprising:
transmitting a first voice command from a user operating a client device to a voice service provider, wherein the voice service provider is configured to: (i) convert the first voice command into a first textual instruction; and (ii) transmit the first textual instruction to an intelligent assistant provider distinct from the voice service provider, wherein the intelligent assistant provider comprises first contextual information, and wherein the first contextual information comprises: an identification of a totem coupled to the client device, and a first gaze focus of the user obtained concurrently with the first voice command;
receiving a first totem command generated by the intelligent assistant provider based upon the first textual instruction and the first gaze focus, wherein the first totem command is of a type selected from the group consisting of: change color, change size, and rotate;
executing the first totem command;
transmitting a second voice command from the user to the voice service provider, wherein the voice service provider is configured to: (i) convert the second voice command into a second textual instruction; and (ii) transmit the second textual instruction to the intelligent assistant provider, wherein the intelligent assistant provider comprises second contextual information, and wherein the second contextual information comprises a second gaze focus of the user obtained concurrently with the second voice command;
receiving a second totem command generated by the intelligent assistant provider based upon the second textual instruction and the second gaze focus, wherein in response to a second target of the second gaze focus being of a different type than a first target of the first gaze focus, the second totem command is of a different type than the first totem command; and
executing the second totem command.
17. The IHS of claim 1 , wherein the program instructions, upon execution, further cause the IHS to select a touch layer parameter of an area of a touchscreen identified as the first gaze focus, and wherein the touch layer parameter comprises a palm rejection parameter.
18. The IHS of claim 17 , wherein the palm rejection parameter comprises at least one of: a threshold size of a rejection area or a latency.
19. The IHS of claim 17 , wherein the palm rejection parameter comprises an aggressiveness of a palm rejection algorithm.
20. The IHS of claim 1 , wherein the program instructions, upon execution, further cause the IHS to select a touch layer parameter of an area of a touchscreen identified as the first gaze focus, and wherein the touch layer parameter comprises a touch processing parameter that defines one or more exclusively active digitizer zones of the touchscreen where totem inputs are allowed.