# US 2025/0156574 A1 · Data access control for domain specific large language model services

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

- Number: US 2025/0156574 A1
- Document ID: US20250156574A1
- Status: Published application
- Kind: A1
- Application number: 18/508,695
- Filed: 2023-11-14
- Published: 2025-05-15
- Earliest claimed: 2023-11-14
- Assignees: Sap SE
- Applicants: Sap SE
- Inventors: Peter Eberlein; Volker Driesen
- Web page: https://patentgrep.com/patent/US20250156574A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 21/6227: {where protection concerns the structure of data, e.g. records, types, queries}
- G06F 16/3329: Natural language query formulation
- G06F 16/33295: {in dialogue systems}
- G06F 16/3344: {using natural language analysis}
- G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536)
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 16/9035: Filtering based on additional data, e.g. user or group profiles
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The disclosure generally describes methods, software, and systems for to data access control for applications using large language models (LLM). A request to access attributes of an application object is received from a user. A LLM object access layer defining an access level of the user to each attribute of the application object is determined. The LLM object access layer is queried to determine accessible attributes of the attributes of the application object. A response is provided based on the accessible attributes of the application object to the user.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, by one or more processors from a user, a request to access attributes of an application object;
determining, by the one or more processors, a large language model (LLM) object access layer defining an access level of the user to each attribute of the application object;
querying, by the one or more processors, the LLM object access layer, to determine accessible attributes of the attributes of the application object; and
providing, by the one or more processors, a response based on the accessible attributes of the application object to the user.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the LLM object access layer comprises a filter configured to determine the accessible attributes using a filter configuration.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the LLM object access layer accesses a prompt generator to create a content for prompts sent to an external LLM to retrieve the accessible attributes.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising:
interpreting, by the one or more processors, a question, using an application logic, to determine a context of the question.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein determining a domain of an LLM configured to access the accessible attributes is based on processing the context of the question.

### Claim 6 (depends on 4)

The computer-implemented method of claim 4, further comprising:
applying, by the one or more processors, a filtering configuration corresponding to the context of the question.

### Claim 7 (depends on 4)

The computer-implemented method of claim 4, further comprising:
generating, by the one or more processors, an entry in an access log indicating the accessible attributes determined for the context of the question.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the LLM comprises a lifecycle comprising time varying terms and conditions.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining, by the one or more processors, an action to be executed in response to determining the accessible attributes.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the application object comprises object nodes, each node comprising one or more attributes.

### Claim 11

A computer-implemented system comprising:
memory storing application programming interface (API) information; and
a server performing operations comprising:
receiving, from a user, a request to access attributes of an application object;
determining a large language model (LLM) object access layer defining an access level of the user to each attribute of the application object;
querying the LLM object access layer, to determine accessible attributes of the attributes of the application object; and
providing a response based on the accessible attributes of the application object to the user.

### Claim 12 (depends on 11)

The computer-implemented system of claim 11, wherein the LLM object access layer comprises a filter configured to determine the accessible attributes using a filter configuration, and wherein the application object comprises object nodes, each node comprising one or more attributes.

### Claim 13 (depends on 11)

The computer-implemented system of claim 11, wherein the LLM object access layer accesses a prompt generator to create a content for prompts sent to an external LLM to retrieve the accessible attributes.

### Claim 14 (depends on 13)

The computer-implemented system of claim 13, wherein the operations further comprise:
interpreting a question, using an application logic, to determine a context of the question.

### Claim 15 (depends on 14)

The computer-implemented system of claim 14, wherein determining a domain of an LLM configured to access the accessible attributes is based on processing the context of the question.

### Claim 16 (depends on 14)

The computer-implemented system of claim 14, wherein the operations further comprise:
applying a filtering configuration corresponding to the context of the question.

### Claim 17 (depends on 14)

The computer-implemented system of claim 14, wherein the operations further comprise:
generating an entry in an access log indicating the accessible attributes determined for the context of the question.

### Claim 18 (depends on 11)

The computer-implemented system of claim 11, wherein the LLM comprises a lifecycle comprising time varying terms and conditions.

### Claim 19 (depends on 11)

The computer-implemented system of claim 11, wherein the operations further comprise:
determining an action to be executed in response to determining the accessible attributes.

### Claim 20

A non-transitory computer-readable media encoded with a computer program, the computer program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving, from a user, a request to access attributes of an application object;
determining a large language model (LLM) object access layer defining an access level of the user to each attribute of the application object;
querying the LLM object access layer, to determine accessible attributes of the attributes of the application object; and
providing a response based on the accessible attributes of the application object to the user.
