# US 2026/0094013 A1 · Dynamic attribute split for NLP-oriented AI data analytics

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

- Number: US 2026/0094013 A1
- Document ID: US20260094013A1
- Status: Published application
- Kind: A1
- Application number: 18/903,098
- Filed: 2024-10-01
- Published: 2026-04-02
- Earliest claimed: 2024-10-01
- Inventors: Maxim Chuprunov
- Web page: https://patentgrep.com/patent/US20260094013A1

## CPC

- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06F 16/258: {Data format conversion from or to a database}
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems, methods, and computer algorithms disclosed herein enable dynamic adjustment of data structures in data sources used for Artificial Intelligence (AI) assisted data analytics, especially when Natural Language Processing (NLP) is used. This method includes a dynamic creation of attribute fields, definition of their names, and content based on existing datasets. Such transformation of the underlying data aims to enhance performance of NLP-based data processing by making it better match human language.

## Claims

### Claim 1

A method for attribute splitting to enhance the data analysis capabilities of AI models, comprising techniques for identifying and transforming distinct attribute data within datasets.

### Claim 2

A system for attribute splitting integrated with AI models that facilitates improved efficiency and accuracy in data analysis tasks, particularly in applications involving Natural Language Processing (NLP).

### Claim 3

A novel algorithm for increasing the success rate of deriving correct SQL logic from natural language input, utilizing an attribute splitting technique in AI models.
