# US 2026/0093924 A1 · System and method for contextual adaptation of capability intent actions responsive to a user query input by an artificial intelligence productivity tool software module executing on an information handling system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0093924 A1
- Document ID: US20260093924A1
- Status: Published application
- Kind: A1
- Application number: 18/904,585
- Filed: 2024-10-02
- Published: 2026-04-02
- Earliest claimed: 2024-10-02
- Assignees: Dell Products L.P.
- Applicants: Dell Products LP
- Inventors: Chih-Chien Hsiao; Jacob Mink; Srikanth Kondapi
- Web page: https://patentgrep.com/patent/US20260093924A1

## CPC

- G06F 40/30: Semantic analysis
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

An information handling system includes a hardware processor executing computer-readable program code instructions of a system component and user context discovery software application to gather system component context telemetry data describing operating hardware, hardware modes, and hardware resource consumption and user operating context telemetry data describing current and historic software application use and executing an artificial intelligence (AI) productivity tool software module to receive user-query input, and to identify a responsive capability of an AI productivity tool enablable software application to select and execute at least one capability intent action responsive to the user-query input using, as input, the system/component context telemetry data and user operating context telemetry data to select and adapt the responsive capability intent action for execution in context of the information handling system and the user making the user-query input.

## Claims

### Claim 1

An information handling system comprising:
a hardware processor, a memory device, and a power management unit to provide power to the hardware processor and memory device;
the hardware processor executing computer-readable program code instructions of a system component and user context discovery software application to gather:
system/component context telemetry data describing operating hardware, hardware modes, and hardware resource consumption; and
user operating context telemetry data describing a user operating the information handling system and current and historic software application use by that user;
the hardware processor executing computer-readable program code instructions of an artificial intelligence (AI) productivity tool software module to receive user-query input from a user of the information handling system via an input/output device;
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to invoke a machine learning (ML) model algorithm to identify a plurality of responsive capabilities of AI productivity-tool enablable software applications responsive to the user-query input and select at least one responsive capability intent action based on input of the system/component context telemetry data and the user operating context telemetry data to select the at least one responsive capability intent action; and
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to invoke a contextual capability modification machine learning (ML) model algorithm to adjust the at least one responsive capability intent action selected to operate based on the detected system/component context telemetry data and the user operating context telemetry data in response to the user query input.

### Claim 2 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing code instructions of the ML model algorithm including a speech-to-text ML model algorithm to convert audio user-query input received at the AI productivity tool software module from a user via a microphone into text.

### Claim 3 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing code instructions of the ML model algorithm including a query input-to-intent ML model algorithm to identify a query intent value of the user-query input using, as input, the user-query input, system/component context telemetry data, and user operating context telemetry data to identify the query intent value to include system/component context and user context on the information handling.

### Claim 4 (depends on 1)

The information handling system of claim 1, further comprising:
the hardware processor executing code instructions of the ML model algorithm including a query intent-to-capability ML algorithm to identify, via similarity matching to a plurality of capability intent values for the plurality of capabilities and to select the at least one responsive capability intent action based on the system/component context telemetry data, and user operating context telemetry data.

### Claim 5 (depends on 1)

The information handling system of claim 1 further comprising:
a plurality of hardware drivers operatively coupled to the system component and user context discovery software application to gather the system/component context telemetry data and the user operating context telemetry data and send the system/component context telemetry data and the user operating context telemetry data to the AI productivity tool software module for input into the ML model algorithm to identify the plurality of responsive capabilities of AI productivity-tool enablable software applications responsive to the user-query input and select the at least one responsive capability intent action.

### Claim 6 (depends on 1)

The information handling system of claim 1 further comprising:
a plurality of sensors operatively coupled to the system component and user context discovery software application to gather the system/component context telemetry data and send the system/component context telemetry data and the user operating context telemetry data to the AI productivity tool software module for input into the ML model algorithm to identify the plurality of responsive capabilities of AI productivity-tool enablable software applications responsive to the user-query input and select the at least one responsive capability intent action.

### Claim 7 (depends on 1)

The information handling system of claim 1 further comprising:
a plurality of hardware drivers operatively coupled to the system component and user context discovery software application to gather the system/component context telemetry data and the user operating context telemetry data and send the system/component context telemetry data and the user operating context telemetry data to the contextual capability modification machine learning (ML) model algorithm to adjust the selected at least one responsive capability intent actions to operate based on the detected system/component context telemetry data and the user operating context telemetry data in response to the user query.

### Claim 8 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing code instructions of a plurality of AI productivity tool-enablable software applications operatively coupled to the system component and user context discovery software application; and
the hardware processor executing computer-readable program code instructions of the system component and user context discovery software application to request and register capabilities and capability modification dependency metrics of each of the capabilities of the AI productivity tool-enablable software applications that define the capabilities and how each capability can be modified based on the system/component context telemetry data and the user operating context telemetry data to execute the at least one responsive capability intent action.

### Claim 9 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing computer-readable program code instructions of the system component and user context discovery software application to request and register capabilities of each of the capabilities of the AI productivity tool-enablable software applications to include a natural language descriptor that defines the capabilities and a current system or user context for each capability in a contextual capability intent value based on the system/component context telemetry data and the user operating context telemetry data; and
the hardware processor executing computer-readable program code instructions of the processor executing code instructions of the AI productivity tool software module including a query intent-to-capability ML algorithm to identify a similarity-matched contextual capability intent value to select the at least one responsive capability intent action.

### Claim 10

A method of selecting a capability of an artificial intelligence (AI) productivity tool-enablable software application via execution of computer-readable code instructions of an AI productivity tool software module comprising:
executing, with a hardware processor, computer-readable program code instructions of a system component and user context discovery software application to gather:
system/component context telemetry data describing operating hardware, hardware modes, and hardware resource consumption; and
user operating context telemetry data describing a user operating the information handling system and current and historic software application use of the user;
executing, with the hardware processor, the AI productivity tool software module to receive user-query input from a user of an information handling system;
executing computer-readable program code instructions of the system component and user context discovery software application to request and register capabilities and capability modification dependency metrics of each of the capabilities of plural AI productivity tool-enablable software applications on the information handling system that define the capabilities and how each capability can be modified based on the system/component context telemetry data and the user operating context telemetry data to execute the responsive capability intent action;
executing computer-readable program code instructions of the AI productivity tool software module to invoke a machine learning (ML) model algorithm to identify a responsive capability of the AI productivity tool-enablable software application executable as a capability intent action responsive to the user-query input; and
executing computer-readable program code instructions of the AI productivity tool software module to invoke a contextual capability modification ML model algorithm to adjust the capability intent action to operate based on the detected system/component context telemetry data or user operating context telemetry data triggering at least one capability modification dependency metric for the capability intent action.

### Claim 11 (depends on 10)

The method of claim 10 further comprising:
executing computer readable code instructions of the ML model algorithm including a speech-to-text ML model algorithm to, with the hardware processor executing the computer-readable program code instructions of the speech-to-text ML model algorithm, convert audio user-query input received at the AI productivity tool software module from a user via a microphone into text.

### Claim 12 (depends on 10)

The method of claim 10 further comprising:
executing computer readable code instructions of the ML model algorithm including a query input-to-intent ML model algorithm to identify a query intent value of the user-query input using, as input, the user-query input, system/component context telemetry data, and user operating context telemetry data to identify the query intent value to include system/component context and user context.

### Claim 13 (depends on 12)

The method of claim 12 further comprising:
executing the computer-readable program code instructions of the ML model algorithm including a query intent-to-capability ML algorithm to, with the hardware processor, to select from a plurality of similarity-matched capability intent values to select the responsive capability based on the query intent value including system/component context and user context.

### Claim 14 (depends on 10)

The method of claim 10 further comprising:
executing the computer-readable program code instructions of the ML model algorithm including a query intent-to-capability ML algorithm to identify a similarity-matched capability intent value to select the responsive capability.

### Claim 15 (depends on 10)

The method of claim 10 further comprising:
sending the system/component context telemetry data and user operating context telemetry data to the system component and user context discovery software application via a plurality of hardware drivers operatively coupled to the system component and user context discovery software application.

### Claim 16

An information handling system comprising:
a hardware processor, a memory device, and a power management unit to provide power to the hardware processor and memory device;
the hardware processor executing computer-readable program code instructions of a system component and user context discovery software application to gather:
system/component context telemetry data describing operating hardware, hardware modes, and hardware resource consumption; and
user operating context telemetry data describing a user operating the information handling system and current and historic software application use by that user;
the hardware processor executing an artificial intelligence (AI) productivity tool software module to receive user-query input from a user of the information handling system via an input/output device;
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to identify and select a responsive capability of an AI productivity-tool enablable software application on the information handling system for execution of a capability intent action that is responsive to the user-query input; and
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to invoke a contextual capability modification machine learning (ML) model algorithm to adjust the capability intent action to operate based on the detected system/component context telemetry data and user operating context telemetry data in response to the user query input, wherein the invoked contextual capability modification ML model algorithm uses, as input, the system/component context telemetry data and user operating context telemetry data to adapt the responsive capability intent action execution on the information handling system.

### Claim 17 (depends on 16)

The information handling system of claim 16 further comprising:
the processor executing code instructions of the AI productivity tool software module including a query input-to-intent ML model algorithm to identify a query intent value of the user-query input using, as input, the user-query input, system/component context telemetry data, and user operating context telemetry data to identify the query intent value to include system and user context; and
the processor executing code instructions of the AI productivity tool software module including a query intent-to-capability ML algorithm to identify a similarity-matched capability intent value to select the responsive capability.

### Claim 18 (depends on 16)

The information handling system of claim 16 further comprising:
a plurality of sensors operatively coupled to the system component and user context discovery software application to gather the system/component context telemetry data and the user operating context telemetry data and send the system/component context telemetry data and the user operating context telemetry data to the contextual capability modification ML model algorithm to adjust the responsive capability intent action to operate based on the detected system/component context telemetry data at the information handling system and the user operating context telemetry data of the user in response.

### Claim 19 (depends on 16)

The information handling system of claim 16 further comprising:
the hardware processor executing computer-readable program code instructions of the system component and user context discovery software application to request and register capabilities and capability modification dependency metrics of each of the capabilities of the AI productivity tool-enablable software applications that define the capabilities and how each capability can be modified based on the system/component context telemetry data and the user operating context telemetry data during execution of the responsive capability intent action; and
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to invoke the contextual capability modification machine learning (ML) model algorithm to adjust execution of the capability intent action by a first AI productivity tool-enablable software application in response to the user query input based on the detected system/component context telemetry data or user operating context telemetry data triggering at least one capability modification dependency metric.

### Claim 20 (depends on 16)

The information handling system of claim 16 further comprising:
the hardware processor executing computer-readable program code instructions of the system component and user context discovery software application to request and register capabilities and capability modification dependency metrics of each of the capabilities of the AI productivity tool-enablable software applications to include a natural language descriptor that defines the capabilities and a current system or user context for each capability in a contextual capability intent value based on the system/component context telemetry data and the user operating context telemetry data; and
the hardware processor executing computer-readable program code instructions of the processor executing code instructions of the AI productivity tool software module including a query intent-to-capability ML algorithm to identify a similarity-matched contextual capability intent value to select the responsive capability.
