# US 2025/0053560 A1 · Method and system for providing real-time assistance to users using generative artificial intelligence (ai) models

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

- Number: US 2025/0053560 A1
- Document ID: US20250053560A1
- Status: Published application
- Kind: A1
- Application number: 18/437,658
- Filed: 2024-02-09
- Published: 2025-02-13
- Earliest claimed: 2023-08-10
- Assignees: Infosys Limited
- Applicants: Infosys Limited
- Inventors: Syed AHMED; Ritarshi CHAKRABORTY
- Web page: https://patentgrep.com/patent/US20250053560A1

## CPC

- G06F 16/2423: {Interactive query statement specification based on a database schema}
- G06F 16/2365: {Ensuring data consistency and integrity}
- G06N 3/0475: Generative networks
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/205: {involving negotiation or determination of the one or more network security mechanisms to be used, e.g. by negotiation between the client and the server or between peers or by selection according to the capabilities of the entities involved (negotiation of communication capabilities H04L69/24)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

This disclosure relates to a method and a system for providing real-time assistance to a user using a generative AI model. The method includes receiving by the generative AI model, a user query corresponding to an activity. The user query includes one or more multi-modal inputs. The generative AI model is pretrained based on a set of predefined policies associated with an entity. The method further includes processing in real-time, by the generative AI model, the user query to determine a type of the user query based on the activity. The method further includes providing, by the generative AI model, assistance to the user in real-time by generating instructions in response to the processing of the user query.

## Claims

### Claim 1

A method for providing real-time assistance to a user using a generative Artificial Intelligence (AI) model, the method comprising:
receiving, by the generative AI model, a user query corresponding to an activity, wherein the user query comprises one or more multi-modal inputs, and wherein the generative AI model is pretrained based on a set of predefined policies associated with an entity;
processing in real-time, by the generative AI model, the user query to determine a type of the user query based on the activity; and
providing, by the generative AI model, assistance to the user in real-time by generating instructions in response to the processing of the user query.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more multi-modal inputs comprise at least one of a live screen activity, a live screen activity display, a text, an audio, a video, or an image.

### Claim 3 (depends on 1)

The method of claim 1, wherein providing the assistance to the user in the real-time comprises:
generating, by the generative AI model, an instruction based on the user query in response to the processing; and
rendering the instruction to the user.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
receiving, by the generative AI model, a user selection corresponding to the instruction;
processing, by the generative AI model, the user selection to determine an accuracy of the user selection, wherein the accuracy of the user selection is determined based on a pre-defined accuracy threshold;
dynamically generating, by the generative AI model, a subsequent instruction based on the accuracy of the user selection; and
rendering the subsequent instruction to the user.

### Claim 5 (depends on 4)

The method of claim 4, wherein the subsequent instruction is one of a subsequent action or a corrective action.

### Claim 6 (depends on 5)

The method of claim 5, wherein the subsequent instruction is the subsequent action when the accuracy of the user selection is above the pre-defined accuracy threshold, and wherein the subsequent instruction is the corrective action when the accuracy of the user selection is below the pre-defined accuracy threshold.

### Claim 7 (depends on 4)

The method of claim 4, further comprising:
iteratively generating, by the generative AI model, the subsequent instruction based on the accuracy of the user selection received corresponding to a previous instruction until the user query is resolved.

### Claim 8 (depends on 4)

The method of claim 4, wherein each of the instruction and the subsequent instruction is at least one multi-modal instruction, and wherein the at least one multi-modal instruction comprises an on-screen control, an on-screen guided instruction, a textual instruction, and an audio instruction.

### Claim 9

A system for providing real-time assistance to a user using a generative Artificial Intelligence (AI) model, the system comprising:
a processing circuitry; and
a memory communicatively coupled to the processing circuitry, wherein the memory stores processor instructions, which when executed by the processing circuitry, cause the processing circuitry to:
receive, by the generative AI model, a user query corresponding to an activity, wherein the user query comprises one or more multi-modal inputs, and wherein the generative AI model is pretrained based on a set of predefined policies associated with an entity;
process in real-time, by the generative AI model, the user query to determine a type of the user query based on the activity; and
provide, by the generative AI model, assistance to the user in real-time by generating instructions in response to the processing of the user query.

### Claim 10 (depends on 9)

The system of claim 9, wherein the one or more multi-modal inputs comprise at least one of a live screen activity, a live screen activity display, a text, an audio, a video, or an image.

### Claim 11 (depends on 9)

The system of claim 9, wherein, to provide the assistance to the user in the real-time, the processor instructions, on execution, further cause the processing circuitry to:
generate, by the generative AI model, an instruction based on the user query in response to the processing; and
render the instruction to the user.

### Claim 12 (depends on 11)

The system of claim 11, wherein the processor instructions, on execution, further cause the processing circuitry to:
receive, by the generative AI model, a user selection corresponding to the instruction;
process, by the generative AI model, the user selection to determine an accuracy of the user selection, wherein the accuracy of the user selection is determined based on a pre-defined accuracy threshold;
dynamically generate, by the generative AI model, a subsequent instruction based on the accuracy of the user selection; and
render the subsequent instruction to the user.

### Claim 13 (depends on 12)

The system of claim 12, wherein the subsequent instruction is one of a subsequent action or a corrective action.

### Claim 14 (depends on 13)

The system of claim 13, wherein the subsequent instruction is the subsequent action when the accuracy of the user selection is above the pre-defined accuracy threshold, and wherein the subsequent instruction is the corrective action when the accuracy of the user selection is below the pre-defined accuracy threshold.

### Claim 15 (depends on 12)

The system of claim 12, wherein the processor instructions, on execution, further cause the processing circuitry to:
iteratively generate, by the generative AI model, the subsequent instruction based on the accuracy of the user selection received corresponding to a previous instruction until the user query is resolved.

### Claim 16 (depends on 12)

The system of claim 12, wherein each of the instruction and the subsequent instruction is at least one multi-modal instruction, and wherein the at least one multi-modal instruction comprises an on-screen control, an on-screen guided instruction, a textual instruction, and an audio instruction.

### Claim 17

A non-transitory computer-readable medium storing computer-executable instructions providing real-time assistance to a user using a generative Artificial Intelligence (AI) model, the stored instructions, when executed by a processor, cause the processor to perform operations comprises:
receiving, by the generative AI model, a user query corresponding to an activity, wherein the user query comprises one or more multi-modal inputs, and wherein the generative AI model is pretrained based on a set of predefined policies associated with an entity;
processing in real-time, by the generative AI model, the user query to determine a type of the user query based on the activity; and
providing, by the generative AI model, assistance to the user in real-time by generating instructions in response to the processing of the user query.
