# US 2026/0093923 A1 · System and method for managing capability intent action policies for capabilities associated with artificial intelligence productivity tool responses based on feedback sentiment data

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

- Number: US 2026/0093923 A1
- Document ID: US20260093923A1
- Status: Published application
- Kind: A1
- Application number: 18/904,461
- Filed: 2024-10-02
- Published: 2026-04-02
- Earliest claimed: 2024-10-02
- Assignees: Dell Products L.P.
- Applicants: Dell Products LP
- Inventors: Srikanth Kondapi; Daniel L. Hamlin; Balasingh P. Samuel
- Web page: https://patentgrep.com/patent/US20260093923A1

## CPC

- G06F 40/30: Semantic analysis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An information handling system includes a hardware processor to execute computer-readable program code instructions of an AI productivity tool software module to process an initial user query input received from a user and correlate the user query input to a capability intent action and to initiate the capability intent action to respond to the user query input, and execute a sentiment analysis software application to analyze a subsequent user query input and generate feedback sentiment data describing a positive or negative sentiment of the subsequent user query input in a generated transaction log including the initial user query input, the responsive capability intent action, the subsequent user query input and a feedback sentiment score of the subsequent use query input that is transmitted to a remote policy management server for an intent technology decision maker to generate capability intent action policies based on the feedback sentiment data.

## Claims

### Claim 1

An information handling system executing computer-readable program code instructions of an AI productivity tool software module 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 to execute the computer-readable program code instructions of the AI productivity tool software module to process an initial user query input received from a user and correlate, via semantic or lexical matching, the initial user query input to a responsive capability of an AI productivity tool-enablable software application to execute a responsive capability intent action to the initial user query input;
the hardware processor to execute computer-readable program code instructions of a sentiment analysis software application to analyze a subsequent user query input received after the execution of the responsive capability intent action and determine feedback sentiment data from an inverse correlation or a positive correlation of a query intent value of the subsequent user query input to a capability intent value of the executed responsive capability intent action to determine a positive feedback sentiment score or a negative feedback sentiment score, respectively, from the subsequent user query input;
the hardware processor to execute computer-readable program code instructions of a transaction log generation software application to generate a transaction log with the feedback sentiment data including the initial query input, the responsive capability intent action, the subsequent user query input, and the positive feedback sentiment score or the negative feedback sentiment score; and
the hardware processor executing computer-readable program code instructions of the transaction log generation software application to transmit the transaction log to a remote policy management server for an intent technology decision maker (ITDM) capability management network to generate augmented capability intent action policies based on the feedback sentiment data.

### Claim 2 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing computer-readable program code instructions of the sentiment analysis software application to analyze the subsequent user query input received after the execution of the responsive capability intent action and determine from lexical matching of words in the subsequent user query input to emotional intent values to determine the positive feedback sentiment score or the negative feedback sentiment score from the subsequent user query input.

### Claim 3 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to receive the augmented capability intent action policies from the ITDM capability management network that, based on positive criteria of the positive feedback sentiment score within the feedback sentiment data, provides recommendations to be presented to other users in an enterprise describing what user query input from the user results in a better responsive capability intent action.

### Claim 4 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing computer-readable program code instructions of the AI productivity tool software module to receive the augmented capability intent action policies from the ITDM capability management network that, based on negative criteria of the negative feedback sentiment score within the feedback sentiment data, removes or alters the responsive capability intent action of the AI productivity tool-enablable software application.

### Claim 5 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor to execute computer-readable program code instructions of the sentiment analysis software application to invoke, via an AI productivity tool subagent, a feedback sentiment large learning model (LLM) algorithm to use, as in-input, the subsequent user query input and analyze words therein for lexical or semantic correlation with emotional intent to generate the feedback sentiment data.

### Claim 6 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor to execute computer-readable program code instructions of the sentiment analysis software application to invoke, via an AI productivity tool subagent, a feedback sentiment large learning model (LLM) algorithm to use, as in-input, a subsequent query intent value from the subsequent user query input and conduct a semantic correlation algorithm to determine an inverse correlation with the capability intent value of the executed, responsive capability intent action to generate the feedback sentiment data.

### Claim 7 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing computer-readable program code instructions of the sentiment analysis software application to execute computer readable code instructions of a semantic correlation algorithm to identify an inverse correlation between a subsequent action intent value for a subsequent user-instigated action in software, firmware or hardware occurring after the responsive capability intent action and the capability intent value of the responsive capability intent action to further determine the negative feedback sentiment score in the feedback sentiment data.

### Claim 8 (depends on 1)

The information handling system of claim 1 further comprising:
a system capabilities database to store capabilities associated with each of the AI productivity tool-enablable software applications.

### Claim 9 (depends on 1)

The information handling system of claim 1 further comprising:
the hardware processor executing computer-readable program code instructions of an AI productivity tool subagent to invoke a query input-to-intent machine learning model algorithm to generate a vectorized query intent value for the subsequent user query input.

### Claim 10

A method of executing computer-readable program code instructions of an AI productivity tool software module comprising:
executing, via a hardware processor, computer-readable program code instructions of the AI productivity tool software module to invoke a machine learning (ML) model algorithm to process an initial user query input received from a user and correlate, via semantic or lexical matching, the initial user query input to a responsive capability of an AI productivity tool-enablable software application to execute a responsive capability intent action to the initial user query input;
executing computer-readable program code instructions of a sentiment analysis software application to analyze a subsequent user query input received after the execution of the responsive capability intent action and determine feedback sentiment data including a negative feedback sentiment score from an inverse correlation of a query intent value of the subsequent user query input to a capability intent value of the executed responsive capability intent action;
executing computer-readable program code instructions of a transaction log generation software application to generate a transaction log with the feedback sentiment data including the initial query input, the responsive capability intent action, the subsequent user query input, and the negative feedback sentiment score; and
transmitting, via a network interface device, the transaction log to a remote policy management server for an intent technology decision maker (ITDM) capability management network to generate augmented capability intent action policies based on the feedback sentiment data.

### Claim 11 (depends on 10)

The method of claim 10 further comprising:
executing computer-readable program code instructions of the sentiment analysis software application to analyze the subsequent user query input received after the execution of the responsive capability intent action; and
determining from lexical matching of words in the subsequent user query input to emotional intent values to further determine the negative feedback sentiment score from the subsequent user query input.

### Claim 12 (depends on 10)

The method of claim 10 further comprising:
executing computer-readable program code instructions of the sentiment analysis software application to analyze the subsequent user query input received after the execution of the responsive capability intent action; and
determining from a positive matching correlation of a query intent value of the subsequent user query input to a capability intent value of the executed responsive capability intent action, and from lexical matching of words in the subsequent user query input to emotional intent values, a positive feedback sentiment score from the subsequent user query input when the negative feedback sentiment score has not been determined for the subsequent use query input.

### Claim 13 (depends on 10)

The method of claim 10 further comprising:
executing computer-readable program code instructions of the AI productivity tool software module to receive the augmented capability intent action policies from the ITDM capability management network; and
based on negative criteria of the negative feedback sentiment score within the feedback sentiment data, removing or altering the responsive capability intent action of the AI productivity tool-enablable software application.

### Claim 14 (depends on 10)

The method of claim 10 further comprising:
executing computer-readable program code instructions of the sentiment analysis software application to invoke, via an AI productivity tool subagent, a feedback sentiment large learning model (LLM) algorithm to use, as in-input, a subsequent query intent value from the subsequent user query input and conduct a semantic correlation algorithm to determine an inverse correlation with the capability intent value of the executed, responsive capability intent action to generate the feedback sentiment data.

### Claim 15 (depends on 10)

The method of claim 10 further comprising:
executing computer-readable program code instructions of the sentiment analysis software application to execute computer readable code instructions of a semantic correlation algorithm to identify an inverse correlation between a subsequent action intent value for a subsequent user-instigated action in software, firmware or hardware occurring after the responsive capability intent action and the capability intent value of the responsive capability intent action to further determine the negative feedback sentiment score in the feedback sentiment data from the subsequent user-instigated action.

### Claim 16

An information handling system executing computer-readable program code instructions of an AI productivity tool software module 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 to execute the computer-readable program code instructions of the AI productivity tool software module to invoke a machine learning (ML) model algorithm to process an initial user query input received from a user and correlate, via semantic or lexical matching, the initial user query input to a responsive capability of an AI productivity tool-enablable software application to execute a responsive capability intent action to the initial user query input;
the hardware processor to execute computer-readable program code instructions of a sentiment analysis software application to execute computer readable code instructions of a semantic correlation algorithm to identify an inverse correlation between a subsequent action intent value for a subsequent user-instigated action in software, firmware or hardware and a capability intent value of the responsive capability intent action to determine a negative feedback sentiment score for the subsequent user-instigated action for feedback sentiment data;
the hardware processor to execute computer-readable program code instructions of a transaction log generation software application to generate a transaction log with the feedback sentiment data including the initial query input, the responsive capability intent action, the subsequent user-instigated action, and the negative feedback sentiment score; and
the hardware processor executing computer-readable program code instructions of the transaction log generation software application to transmit the transaction log to a remote policy management server for an intent technology decision maker (ITDM) capability management network to generate augmented capability intent action policies based on the feedback sentiment data.

### Claim 17 (depends on 16)

The information handling system of claim 16 further comprising:
the hardware processor to execute computer-readable program code instructions of the sentiment analysis software application to analyze a subsequent user query input received after the execution of the responsive capability intent action and further determine in the feedback sentiment data the negative feedback sentiment score from an inverse correlation of a query intent value of the subsequent user query input to the capability intent value of the executed responsive capability intent action.

### Claim 18 (depends on 16)

The information handling system of claim 16 further comprising:
the hardware processor executing computer-readable program code instructions of the sentiment analysis software application to analyze a subsequent user query input received after the execution of the responsive capability intent action and determine from lexical matching of words in the subsequent user query input to emotional intent values to further determine the negative feedback sentiment score in the feedback sentiment data from the subsequent user query input.

### 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 AI productivity tool software module to receive the augmented capability intent action policies from the ITDM capability management network that, based on negative criteria of the negative feedback sentiment score within the feedback sentiment data, removes or alters the responsive capability intent action of the AI productivity tool-enablable software application.

### Claim 20 (depends on 16)

The information handling system of claim 16 further comprising:
the hardware processor to execute computer-readable program code instructions of the sentiment analysis software application to invoke, via an AI productivity tool subagent, a feedback sentiment large learning model (LLM) algorithm to use, as input, the subsequent action intent value from the user instigated action query input and conduct a semantic correlation algorithm to determine an inverse correlation with the capability intent value of the executed, responsive capability intent action to generate the feedback sentiment data.
