# US 2026/0064744 A1 · System and method for providing high-query ai for use with a data analytics environment

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

- Number: US 2026/0064744 A1
- Document ID: US20260064744A1
- Status: Published application
- Kind: A1
- Application number: 19/257,889
- Filed: 2025-07-02
- Published: 2026-03-05
- Earliest claimed: 2024-09-04
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Nicholas Papano; Zachary Brown; Madhvi Sharma; Suraj Bhat; Sandip Ghoshal; Santosh Kalki
- Web page: https://patentgrep.com/patent/US20260064744A1

## CPC

- G06F 16/3344: {using natural language analysis}
- G06F 16/243: {Natural language query formulation}
- G06F 16/24522: {Translation of natural language queries to structured queries}
- G06F 16/3347: {using vector based model}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments described herein are generally related to data analytics environments, and are particularly directed to systems and methods for use with a data analytics environment to provide hi-query AI for use with the data analytics environment. Systems and methods disclosed can provide for query processing and semantic analysis. The system can take a user's natural language question and run a semantic search to discern the query's intent and find tables relevant to the question, and generate a query to run against a data store or data warehouse.

## Claims

### Claim 1

A system for use with a data analytics environment for providing hi-query AI for use with a data analytics environment, comprising:
a computer including one or more processors, that provides access to a data analytics environment; and
an application running at the data analytics environment, wherein the application is configured to receive a natural language query from a client device;
wherein the application, upon receiving the natural language query, communicates a translation of the natural language query to a vector database;
wherein the vector database provides to the application one or more determined data tables or data columns as context for the query;
wherein the application queries a determined large language model with the translation of the natural language query and the context provided by the vector database to receive a generated query;
wherein the generated query is run, by the application, against a data warehouse; and
wherein results of the generated query run against the data warehouse are provided by the application to the client device.

### Claim 2 (depends on 1)

The system of claim 1,
wherein the application comprises a natural language processor which translates the received natural language query to generate the translation of the natural language query.

### Claim 3 (depends on 1)

The system of claim 1,
wherein a filter is provided which filters the results of the generated query run against the data warehouse prior to returning the results to the application.

### Claim 4 (depends on 3)

The system of claim 3,
wherein the filter is configured by the application to filter personal identifying information and/or medical information.

### Claim 5 (depends on 1)

The system of claim 1,
wherein the data warehouse comprises an autonomous data warehouse associated.

### Claim 6 (depends on 1)

The system of claim 1,
wherein the natural language query comprises an instruction to generate a measure.

### Claim 7 (depends on 6)

The system of claim 6,
wherein the results returned from the query run against the data warehouse comprise a generated measure.

### Claim 8

A method for use with a data analytics environment for providing hi-query AI for use with a data analytics environment, comprising:
providing a computer including one or more processors, the computer provides access to a data analytics environment;
providing an application running at the data analytics environment, wherein the application is configured to receive a natural language query from a client device;
upon receiving the natural language query, communicating, by the application, a translation of the natural language query to a vector database;
providing, by the vector database to the application, one or more determined data tables or data columns as context for the query;
querying, by the application, a determined large language model with the translation of the natural language query and the context provided by the vector database to receive a generated query;
running the generated query, by the application, against a data warehouse; and
providing results of the generated query run against the data warehouse by the application to the client device.

### Claim 9 (depends on 8)

The method of claim 8,
wherein the application comprises a natural language processor which translates the received natural language query to generate the translation of the natural language query.

### Claim 10 (depends on 8)

The method of claim 8,
wherein a filter is provided which filters the results of the generated query run against the data warehouse prior to returning the results to the application.

### Claim 11 (depends on 10)

The method of claim 10,
wherein the filter is configured by the application to filter personal identifying information and/or medical information.

### Claim 12 (depends on 8)

The method of claim 8,
wherein the data warehouse comprises an autonomous data warehouse associated.

### Claim 13 (depends on 8)

The method of claim 8,
wherein the natural language query comprises an instruction to generate a measure.

### Claim 14 (depends on 13)

The method of claim 13,
wherein the results returned from the query run against the data warehouse comprise a generated measure.

### Claim 15

A non-transitory computer readable storage medium having instructions thereon for use with a data analytics environment for providing hi-query AI for use with a data analytics environment, which when run and executed cause a computer to perform steps comprising:
providing, by the computer including one or more processors, access to a data analytics environment;
providing an application running at the data analytics environment, wherein the application is configured to receive a natural language query from a client device;
upon receiving the natural language query, communicating, by the application, a translation of the natural language query to a vector database;
providing, by the vector database to the application, one or more determined data tables or data columns as context for the query;
querying, by the application, a determined large language model with the translation of the natural language query and the context provided by the vector database to receive a generated query;
running the generated query, by the application, against a data warehouse; and
providing results of the generated query run against the data warehouse by the application to the client device.

### Claim 16 (depends on 15)

The non-transitory computer readable storage medium of claim 15,
wherein the application comprises a natural language processor which translates the received natural language query to generate the translation of the natural language query.

### Claim 17 (depends on 15)

The non-transitory computer readable storage medium of claim 15,
wherein a filter is provided which filters the results of the generated query run against the data warehouse prior to returning the results to the application.

### Claim 18 (depends on 17)

The non-transitory computer readable storage medium of claim 17,
wherein the filter is configured by the application to filter personal identifying information and/or medical information.

### Claim 19 (depends on 15)

The non-transitory computer readable storage medium of claim 15,
wherein the data warehouse comprises an autonomous data warehouse associated.

### Claim 20 (depends on 15)

The non-transitory computer readable storage medium of claim 15,
wherein the natural language query comprises an instruction to generate a measure; and
wherein the results returned from the query run against the data warehouse comprise a generated measure.
