Get the newsletter
IBM · AI / ML · Filed Mar 26, 2025 · USPTO published Oct 1, 2026 · Oct 1 release

IBM Patents a System That Trains AI to Answer Questions About Stored Data

Most databases speak a language only developers know. IBM's new patent describes a way to automatically build the training material an AI needs to bridge that gap, so anyone can ask a database a question in plain English and get a real answer.

A computer system connects to a wide area network, end user devices, remote servers, and public and private clouds. Drawing from patent filing US 2026/0300274 A1.
A computer system connects to a wide area network, end user devices, remote servers, and public and private clouds.All 7 drawings ↓
Publication number
US 2026/0300274 A1(US20260300274A1)
Applicant
International Business Machines Corporation
Filed · Published
Mar 26, 2025 · Oct 1, 2026
Inventors
Timothy Rea DINGER, Alfio Massimiliano GLIOZZO, Nhan Huu PHAM, Oktie HASSANZADEH, Dharmashankar SUBRAMANIAN, Lisa AMINI, Gaetano ROSSIELLO, Md Faisal Mahbub CHOWDHURY, Long VU, Tanvi KAPLE, Michael Robert GLASS
Status when we published
Company responded; back with the examiner
Document
21 claims
US classification
707/759
Examiner
TRUONG, DENNIS (Art Unit 2164)

What IBM's natural-language database query tool actually does

A database administrator stares at a screen full of tables, columns, and code. Everyone else at the company just wants answers, but getting them still requires knowing a specialized query language called SQL.

This patent describes a method for automatically generating the training data an AI model needs to understand plain-English questions and convert them into proper database queries. The system reads a database's structure (its layout of tables and fields) and uses that structure to create matched pairs: a question in plain English alongside the correct technical query that would answer it. Those pairs can then train an AI to handle real questions from real people.

The key idea is that IBM's system does this work automatically, tailored to whatever specific database you point it at. Instead of hiring experts to hand-write thousands of example questions for each new database, the system generates them on its own.

From the filing · CLAIM 1
… determining, by the processor set and based on the database schema, a group of database concept sets for the target database, wherein each database concept set, of the group of database concept sets, includes a primary concept and a set of secondary concepts relating to the primary concept; …

Translation: The system figures out main ideas and related topics based on how the database is structured.

How IBM maps database concepts to query-language pairs

The patent describes a pipeline that starts by reading a database schema (the blueprint describing what tables, columns, and relationships a database contains). From that schema, the system identifies database concept sets, each built around a primary concept (say, "customer orders") and a cluster of related secondary concepts (order dates, product IDs, shipping addresses).

Using those concept clusters, the system generates two parallel sets of query fragments:

  • First query parts: fragments written in natural language, like "how many orders were placed last month"
  • Second query parts: the matching technical database commands (SQL statements) that would actually retrieve that information

The output is a structured dataset of matched pairs. That dataset becomes training material for an AI model learning to translate between human language and database language.

The process is meant to be automatic and schema-aware, meaning it adapts to the specific layout of whichever database it reads. That matters because no two enterprise databases are structured the same way, and a model trained on one company's data won't automatically understand another's.

From the filing · THE ABSTRACT
… wherein the group of first query parts includes one or more natural language query parts and wherein the group of second query parts includes one or more corresponding query language query parts.

Translation: It pairs everyday human questions with the technical computer code needed to search the database.

What this means for non-technical database users

Most workers who need data from a company database still have to go through a developer or data analyst to write the actual query. That bottleneck slows decisions and creates backlogs. A well-trained AI that converts plain questions into queries could let any employee get their own answers directly.

The challenge has always been training that AI. Building good training data by hand is expensive and slow, especially when a company swaps databases or restructures its data. IBM's patent is aimed squarely at that cost. IBM's track record in natural-language AI patents goes back years, and this filing extends that work into the specific problem of database access for non-technical users.

IBM's 38th filing in the AI training and infrastructure patents we've tracked since May adds to earlier work like one on industry-based learning and one on live data tracking.

Source: US 2026/0300274 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time IBM patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 7 sheets

7 drawing sheets from US 2026/0300274 A1 · click any drawing to enlarge

Computer system and network connections, drawing sheet 1 from US 2026/0300274 A1
Sheet 1 Computer system and network connections
Query generation system, concept generation, drawing sheet 2 from US 2026/0300274 A1
Sheet 2 Query generation system, concept generation
Query generation system, high-level concepts, drawing sheet 3 from US 2026/0300274 A1
Sheet 3 Query generation system, high-level concepts
Query generation system, question generation, drawing sheet 4 from US 2026/0300274 A1
Sheet 4 Query generation system, question generation
Query generation system, question tuning, drawing sheet 5 from US 2026/0300274 A1
Sheet 5 Query generation system, question tuning
Computer system components, drawing sheet 6 from US 2026/0300274 A1
Sheet 6 Computer system components
Database query generation process, drawing sheet 7 from US 2026/0300274 A1
Sheet 7 Database query generation process
Patent filing page

More in AI training & infrastructure

All 316 AI training & infrastructure patents →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.