# US 2025/0156648 A1 · Event normalization and enrichment

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

- Number: US 2025/0156648 A1
- Document ID: US20250156648A1
- Status: Published application
- Kind: A1
- Application number: 18/389,153
- Filed: 2023-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: ServiceNow, Inc.
- Applicants: ServiceNow, Inc.
- Inventors: Jason J. Skowronski
- Web page: https://patentgrep.com/patent/US20250156648A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 8/31: {Programming languages or programming paradigms}
- G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications}
- G06F 16/211: {Schema design and management}
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- 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

An identification of one or more computer-generated records in a first schema is received. A specification of a second schema different from the first schema is received. A prompt associated with mapping one or more fields and values of the first schema to corresponding one or more fields and values of the second schema is automatically generated for a pre-trained large language model. At least the specification of the second schema and the automatically generated prompt are provided to the pre-trained large language model. A result of the pre-trained large language model is automatically analyzed to determine the mapping between the first schema and the second schema. The determined mapping is used to manage in the second schema, a new computer-generated record received in the first schema.

## Claims

### Claim 1

A method, comprising:
receiving an identification of one or more computer-generated records in a first schema;
receiving a specification of a second schema different from the first schema;
automatically generating for a pre-trained large language model, a prompt associated with mapping one or more fields and values of the first schema to corresponding one or more fields and values of the second schema;
providing to the pre-trained large language model, at least the specification of the second schema and the automatically generated prompt;
automatically analyzing a result of the pre-trained large language model to determine the mapping between the first schema and the second schema; and
using the determined mapping to manage in the second schema, a new computer-generated record received in the first schema.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more computer-generated records in the first schema correspond to one or more event alerts.

### Claim 3 (depends on 1)

The method of claim 1, further comprising automatically generating a conversion process prompt associated with generating software programming code to perform the mapping between the first schema and the second schema.

### Claim 4 (depends on 3)

The method of claim 3, wherein the conversion process prompt is automatically generated for a different large language model trained to generate the software programming code.

### Claim 5 (depends on 1)

The method of claim 1, further comprising receiving feedback for improving the result of the pre-trained large language model.

### Claim 6 (depends on 5)

The method of claim 5, wherein the received feedback is provided in a natural language format.

### Claim 7 (depends on 5)

The method of claim 5, wherein the received feedback includes one or more requirements associated with the mapping between the first schema and the second schema.

### Claim 8 (depends on 1)

The method of claim 1, wherein the prompt associated with mapping the one or more fields and values of the first schema to the corresponding one or more fields and values of the second schema includes event data of at least one of the one or more computer-generated records in the first schema.

### Claim 9 (depends on 1)

The method of claim 1, further comprising receiving an identification of one or more computer-generated records in a third schema.

### Claim 10 (depends on 9)

The method of claim 9, wherein the received identification of the one or more computer-generated records in the first schema is provided by a first event monitoring service and the received identification of the one or more computer-generated records in the third schema is provided by a second event monitoring service different from the first event monitoring service.

### Claim 11

A system comprising:
one or more processors; and
a memory coupled to the one or more processors, wherein the memory is configured to provide the one or more processors with instructions which when executed cause the one or more processors to:
receive an identification of one or more computer-generated records in a first schema;
receive a specification of a second schema different from the first schema;
automatically generate for a pre-trained large language model, a prompt associated with mapping one or more fields and values of the first schema to corresponding one or more fields and values of the second schema;
provide to the pre-trained large language model, at least the specification of the second schema and the automatically generated prompt;
automatically analyze a result of the pre-trained large language model to determine the mapping between the first schema and the second schema; and
using the determined mapping, manage in the second schema, a new computer-generated record received in the first schema.

### Claim 12 (depends on 11)

The system of claim 11, wherein the one or more computer-generated records in the first schema correspond to one or more event alerts.

### Claim 13 (depends on 11)

The system of claim 11, wherein the memory is further configured to provide the one or more processors with the instructions which when executed cause the one or more processors to automatically generate a conversion process prompt associated with generating software programming code to perform the mapping between the first schema and the second schema.

### Claim 14 (depends on 13)

The system of claim 13, wherein the conversion process prompt is automatically generated for a different large language model trained to generate the software programming code.

### Claim 15 (depends on 11)

The system of claim 11, wherein the memory is further configured to provide the one or more processors with the instructions which when executed cause the one or more processors to receive feedback for improving the result of the pre-trained large language model.

### Claim 16 (depends on 15)

The system of claim 15, wherein the received feedback is provided in a natural language format.

### Claim 17 (depends on 15)

The system of claim 15, wherein the received feedback includes one or more requirements associated with the mapping between the first schema and the second schema.

### Claim 18 (depends on 11)

The system of claim 11, wherein the memory is further configured to provide the one or more processors with the instructions which when executed cause the one or more processors to receive an identification of one or more computer-generated records in a third schema.

### Claim 19 (depends on 18)

The system of claim 18, wherein the received identification of the one or more computer-generated records in the first schema is provided by a first event monitoring service and the received identification of the one or more computer-generated records in the third schema is provided by a second event monitoring service different from the first event monitoring service.

### Claim 20

A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving an identification of one or more computer-generated records in a first schema;
receiving a specification of a second schema different from the first schema;
automatically generating for a pre-trained large language model, a prompt associated with mapping one or more fields and values of the first schema to corresponding one or more fields and values of the second schema;
providing to the pre-trained large language model, at least the specification of the second schema and the automatically generated prompt;
automatically analyzing a result of the pre-trained large language model to determine the mapping between the first schema and the second schema; and
using the determined mapping to manage in the second schema, a new computer-generated record received in the first schema.
