Artificial emotional intelligence for influencing information handling system (IHS) performance

1 . An Information Handling System (IHS) that comprises:

a processor; and

a memory coupled to the processor, the memory configured with program instructions stored thereon that, upon execution, cause the processor to:

receive an indication of a selected Artificial Intelligence (AI) model determined at least in part by an AI model selector configured in a Human Interface Device (HID), wherein the AI model selector has a plurality of discrete positions that correspond to respective AI models stored in the HID;

select, based at least in part on one or more predefined policies and rules derived from context information associated with the IHS, a primary data path and an alternative data path for receipt of sensor data obtained from the HID, wherein the primary data path and the alternative data path each comprise one of: (i) an enhanced data path that provides the sensor data to the processor without involvement by an embedded controller (EC) of the IHS; or (ii) an EC data path configured to involve the EC;

monitor communication performance of the primary data path;

in response to a determination that the primary data path experienced high latency or packet loss based at least in part on the monitored communication performance, switch from the primary data path to the alternative data path;

in response to a determination of a match between sensor data and a stored biometric profile, load the selected AI model;

identify a mood of a user based, at least in part, upon sensor data processed by the selected AI model; and

modify a processor performance setting of the IHS based, at least in part, upon the identification.

2 . The IHS of claim 1 , wherein the HID comprises a keyboard, a mouse, a trackpad, a game controller, or a stylus.

3 . The IHS of claim 1 , wherein the sensor data is indicative of at least one of: a keystroke frequency, a keystroke velocity, a pressure, a button click frequency, a button click velocity, a mouse pressure, a button pressure, or an after touch.

4 . The IHS of claim 1 , wherein the program instructions, upon execution, cause an Operating System (OS) agent to receive the sensor data over the enhanced data path without any involvement by the EC.

5 . The IHS of claim 4 , wherein the program instructions, upon execution, cause the Operating System (OS) agent to receive the sensor data over the EC data path.

6 . The IHS of claim 1 , wherein the AI model is at least partially integrated into the HID.

7 . The IHS of claim 1 , wherein the mood comprises at least one of: focused, frustrated, stressed, excited, curious, distracted, bored, scared, or satisfied.

8 . The IHS of claim 1 , wherein to identify the mood, the program instructions, upon execution, cause the AI model to process the sensor data.

9 . The IHS of claim 8 , wherein the AI model is further configured to process eye tracking data, facial expression data, gesture data, movement data, heart rate data, blood pressure data, or speech data to identify the mood.

10 . The IHS of claim 1 , wherein to modify the performance setting, the program instructions, upon execution, further cause the IHS to change a clock speed of the processor in response to the mood.

11 . The IHS of claim 1 , wherein to modify the processor performance setting, the program instructions, upon execution, further cause the IHS to change a voltage of the processor in response to the mood.

12 . The IHS of claim 1 , wherein to modify the processor performance setting, the program instructions, upon execution, further cause the IHS to enable or disable a Dynamic Voltage and Frequency Scaling (DVFS) feature in response to the mood.

13 . The IHS of claim 1 , wherein to modify the processor performance setting, the program instructions, upon execution, further cause the IHS to change one or more power (PLx) limit settings of the processor in response to the mood.

14 . The IHS of claim 1 , wherein to modify the processor performance setting, the program instructions, upon execution, further cause the IHS to switch a workload from a first processor core to a second processor core in response to the mood.

15 . The IHS of claim 1 , wherein to modify the processor performance setting, the program instructions, upon execution, further cause the IHS to follow a policy comprising one or more rules that associate each of a plurality of moods with a respective modification of a selected performance setting.

16 . The IHS of claim 1 , wherein the program instructions, upon execution, further cause the IHS to:

identify a change in the mood of the user; and

change the modified processor performance setting based, at least in part, upon the change.

17 . A hardware memory device configured with program instructions stored thereon that, upon execution by a processor of a Human Interface Device (HID), cause the HID to perform operations that comprise:

receive an indication of a selected Artificial Intelligence (AI) model determined at least in part by an AI model selector configured in the HID, wherein the AI model selector has a plurality of discrete positions that correspond to respective AI models stored in the HIDD;

select, based at least in part on one or more predefined policies and rules derived from context information received from an Information Handling System (IHS), a primary data path and an alternative data path for communication between the HID and the IHS, wherein the primary data path and the alternative data path each comprise one of: (i) an enhanced data path that provides the data to a processor of the IHS without involvement by an embedded controller (EC) of the IHS; or (ii) an EC data path configured to involve the EC;

monitor communication performance of the primary data path;

in response to a determination that the primary data path experienced high latency or packet loss, based at least in part on the monitored communication performance, switch from the primary data path to the alternative data path;

in response to a determination of a match between sensor data received by the HID and a stored biometric profile, load the selected AI model;

in response to a determination that the sensor data received by the HID did not match the stored biometric profile, block at least one raw user input received at the HID and notify the IHS of the blocked at least one raw user input;

identify a mood of a user based, at least in part, upon sensor data processed by the selected AI model, wherein the sensor data is indicative of at least one of: a keystroke frequency, a keystroke velocity, a pressure, a button click frequency, a button click velocity, a mouse pressure, a button pressure, or an after touch; and

issue an instruction via the primary data path or the alternative data path to modify a processor performance setting of the IHS based, at least in part, upon the identification.

18 . The hardware memory device of claim 17 , wherein the program instructions, upon execution, cause the HID to issue the instruction over the enhanced data path without any involvement by the EC.

19 . The hardware memory device of claim 17 , wherein the program instructions, upon execution, cause the HID to issue the instruction over the EC data path.

20 . A method, comprising:

receiving an indication of a selected Artificial Intelligence (AI) model based at least in part upon an AI model selector configured in a Human Interface Device (HID), wherein the AI model selector has a plurality of discrete positions corresponding to respective AI models stored in the HID;

selecting, based on one or more predefined policies and rules derived from context information, a primary data path between the HID and an Information Handling System (IHS), the primary data path comprising one of: (i) an enhanced data path that provides data to a processor of the IHS without involvement by an embedded controller (EC) of the IHS; or (ii) an EC data path involving the EC;

monitoring communications performance of the primary data path;

in response to determining that the primary data path experiences high latency or packet loss, switching from the primary data path to an alternative data path comprising the other of the enhanced data path or the EC data path;

in response to determining a match between sensor data captured by the HID and a stored biometric profile, load the selected AI model;

identifying a mood of a user based, at least in part, upon sensor data obtained from the HID and processed by the selected AI model, wherein the HID is coupled to the IHS, and wherein the sensor data is indicative of at least one of an input: speed, rhythm, pressure, or error;

at least one of: (a) in response to a first mood, reducing a power consumption of the IHS;

or (b) in response to a second mood, increasing the power consumption of the IHS; and

in response to determining that the sensor data does not match the stored biometric profile, blocking at least one raw user input received at the HID and notifying the IHS of the blocked at least one raw user input.