# US 2026/0099486 A1 · Enhancing interactions with applications using generative ai

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

- Number: US 2026/0099486 A1
- Document ID: US20260099486A1
- Status: Published application
- Kind: A1
- Application number: 18/910,518
- Filed: 2024-10-09
- Published: 2026-04-09
- Earliest claimed: 2024-10-09
- Assignees: Sap SE
- Applicants: Sap SE
- Inventors: Jinchi Lu; Ulrich Miller
- Web page: https://patentgrep.com/patent/US20260099486A1

## CPC

- G06F 16/243: {Natural language query formulation}
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/56: Natural language generation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

As discussed herein, users provide natural language requests that are translated into application-specific events. An operations mapping table defines the operations that are provided by the application. A system prompt for a large language model (LLM) is generated based on the operations mapping table. A user prompt for the LLM is generated based on natural language input from a user. The system prompt and the user prompt are provided to the LLM. In response, the LLM generates structured data that is used to invoke one or more operations of the application. By using the systems and methods herein, a computing system providing a user interface for an application is improved by allowing users to interact with the application using natural language inputs.

## Claims

### Claim 1

A system for recommending data assets, the system comprising:
a memory that stores instructions; and
one or more processors coupled to the memory and configured to execute the instructions to perform operations comprising:
accessing a natural language request;
generating, based on the natural language request and metadata for an application operation, a prompt for a large language model (LLM);
receiving, from the LLM and in response to the prompt, a structured list of parameter values;
executing the application operation based on the structured list of parameter values; and
providing, based on the executing of the application operation, a response to the natural language request.

### Claim 2 (depends on 1)

The system of claim 1, wherein the generating of the LLM prompt is further based on a user-selected scenario.

### Claim 3 (depends on 1)

The system of claim 1, wherein the operations further comprise:
storing data for the application operation into a database table; and
based on the structured list of parameter values, invoking the application operation.

### Claim 4 (depends on 3)

The system of claim 3, wherein the storing of the data for the application operation comprises storing a parameter name and a parameter type.

### Claim 5 (depends on 3)

The system of claim 3, wherein the storing of the data for the application operation comprises storing a parameter description and a parameter default value.

### Claim 6 (depends on 1)

The system of claim 1, wherein the response from the LLM comprises a set of parameter values in extended markup language (XML) format.

### Claim 7 (depends on 1)

The system of claim 1, wherein the operations further comprise:
receiving, via a user interface, the natural language request.

### Claim 8

A non-transitory computer-readable medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
accessing a natural language request;
generating, based on the natural language request and metadata for an application operation, a prompt for a large language model (LLM);
receiving, from the LLM and in response to the prompt, a structured list of parameter values;
executing the application operation based on the structured list of parameter values; and
providing, based on the executing of the application operation, a response to the natural language request.

### Claim 9 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the generating of the LLM prompt is further based on a user-selected scenario.

### Claim 10 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the operations further comprise:
storing data for the application operation into a database table; and
based on the structured list of parameter values, invoking the application operation.

### Claim 11 (depends on 10)

The non-transitory computer-readable medium of claim 10, wherein the storing of the data for the application operation comprises storing a parameter name and a parameter type.

### Claim 12 (depends on 10)

The non-transitory computer-readable medium of claim 10, wherein the storing of the data for the application operation comprises storing a parameter description and a parameter default value.

### Claim 13 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the response from the LLM comprises a set of parameter values in extended markup language (XML) format.

### Claim 14 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the operations further comprise:
receiving, via a user interface, the natural language request.

### Claim 15

A method comprising:
accessing, by one or more processors, a natural language request;
generating, based on the natural language request and metadata for an application operation, a prompt for a large language model (LLM);
receiving, from the LLM and in response to the prompt, a structured list of parameter values;
executing the application operation based on the structured list of parameter values; and
providing, based on the executing of the application operation, a response to the natural language request.

### Claim 16 (depends on 15)

The method of claim 15, wherein the generating of the LLM prompt is further based on a user-selected scenario.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
storing data for the application operation into a database table; and
based on the structured list of parameter values, invoking the application operation.

### Claim 18 (depends on 17)

The method of claim 17, wherein the storing of the data for the application operation comprises storing a parameter name and a parameter type.

### Claim 19 (depends on 17)

The method of claim 17, wherein the storing of the data for the application operation comprises storing a parameter description and a parameter default value.

### Claim 20 (depends on 15)

The method of claim 15, wherein the response from the LLM comprises a set of parameter values in extended markup language (XML) format.
