Get the newsletter
IBM · AI / ML · Filed May 16, 2025 · USPTO published Nov 19, 2026 · This week's release

IBM Files Patent for Training AI on Made-Up Business Planning Problems

How do you train an AI on problems that come with no answer key? IBM's patent application says to mash real problems together, let the AI solve each one several ways, and keep only the answers that agree.

An example problem about packing holiday gift baskets gets turned step by step into math and computer code to find the best business plan. Drawing from patent filing US 2026/0368627 A1.
An example problem about packing holiday gift baskets gets turned step by step into math and computer code to find the best business plan.All 9 drawings ↓
Publication number
US 2026/0368627 A1(US20260368627A1)
Applicant
International Business Machines Corporation
Filed · Published
May 16, 2025 · Nov 19, 2026
Inventors
Dzung Tien Phan, Vinicius Lima Silva, Dhavalkumar C. Patel, Ali Koc, Nianjun Zhou, Pavan Kapanipathi Bangalore, Luis A. Lastras-Montano, Jayant R. Kalagnanam
Status when we published
Waiting for an examiner
Document
20 claims
US classification
706/12

What IBM's made-up practice problems actually do

Every time a business asks an AI to find the cheapest delivery route or the best staff schedule, the request has to be turned from plain English into strict math code that a separate solver program can run. If the AI forgets a rule along the way, you get an answer that looks fine but breaks a requirement.

IBM's patent is about training that translator. Learning takes huge piles of examples, and real ones with checked answers are scarce. So the system takes a collection of real problems, randomly blends a handful of them into one new made-up problem, and has the AI write solver code for it in several programming languages.

Then every version gets run. When most of them reach the same answer, that answer is treated as correct and the example joins the training pile. By the filing's own math, 145 real problems mixed five at a time yield about 500 million practice problems.

From the filing · CLAIM 1
… generating a synthetic natural language description defining a synthetic optimization problem from the natural language descriptions for the optimization problems in a subset of the subsets; …

Translation: The system invents entirely fictional business planning problems by mixing pieces of real ones together.

How IBM blends real problems into new ones

The claims cover a pipeline for building training data. It starts with a set of optimization problems (puzzles where you maximize or minimize something, like profit or cost, while obeying limits) written in plain English. The system picks random subsets of k problems out of n, then writes one synthetic description that merges each subset. The filing says the merged problems can come from different fields.

Next, a generative AI model reads that description and writes optimization models, which are code versions of the problem in different modeling languages (the filing names Pyomo, DOcplex and AMPL). A solver, meaning a separate program that calculates the best answer, runs each one. Training examples are made for models that reach the same answer, and one dependent claim requires a majority to agree.

Each example pairs the made-up description (input) with the code (output). The filing also covers training on the steps in between:

  • Pulling out the decision variables (the things you can change) and the constraints (the rules you must follow)
  • Writing a mathematical formulation from the description and those pieces
  • Writing the final code in each language
From the filing · THE ABSTRACT
The generative AI model processes the synthetic natural language description to generate optimization models in different optimization modelling languages implementing the synthetic optimization problem.

Translation: The artificial intelligence then translates those fake problems into multiple computer programming languages.

What this could mean for business planning tools

The practical payoff is for anyone who has a planning problem but no math degree. Today, turning a plain-English request into solver code often takes a specialist, and an AI doing the same job can miss a rule. A model trained on huge numbers of checked practice problems could get better at catching the rules you actually care about, though the filing gives no accuracy numbers.

For IBM, the interesting part is the shortcut. Training examples normally need people to supply the right answers. Here, several versions of the code vote, and the winner becomes the answer key. The filing says the trained model could run in the cloud or on a customer's own computer, which points to a back-office tool for companies rather than a phone feature.

That makes this IBM's 80th filing we've tracked in our AI guardrails race since May, alongside earlier work like plain-English security rules and AI judges for chatbot answers.

Source: US 2026/0368627 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 · 9 sheets

9 drawing sheets from US 2026/0368627 A1 · click any drawing to enlarge

How the system converts business questions into math solutions, drawing sheet 1 from US 2026/0368627 A1
Sheet 1 How the system converts business questions into math solutions
Checking whether rules match the original request, drawing sheet 2 from US 2026/0368627 A1
Sheet 2 Checking whether rules match the original request
Resolving errors and voting on the best answer across solvers, drawing sheet 3 from US 2026/0368627 A1
Sheet 3 Resolving errors and voting on the best answer across solvers
Building artificial planning problems to train an AI model, drawing sheet 4 from US 2026/0368627 A1
Sheet 4 Building artificial planning problems to train an AI model
Three record formats used to store synthetic practice questions, drawing sheet 5 from US 2026/0368627 A1
Sheet 5 Three record formats used to store synthetic practice questions
Steps for creating synthetic challenges from real sample problems, drawing sheet 6 from US 2026/0368627 A1
Sheet 6 Steps for creating synthetic challenges from real sample problems
Tuning the model on synthetic challenges before rolling it out, drawing sheet 7 from US 2026/0368627 A1
Sheet 7 Tuning the model on synthetic challenges before rolling it out
Transforming an everyday inventory puzzle into executable code, drawing sheet 8 from US 2026/0368627 A1
Sheet 8 Transforming an everyday inventory puzzle into executable code
Show the other 1 sheets
Hardware and cloud networks that run the planning AI, drawing sheet 9 from US 2026/0368627 A1
Sheet 9 Hardware and cloud networks that run the planning AI
Patent filing page

More in AI training & infrastructure

All 323 AI training & infrastructure patents →

Watchlists this filing belongs to

All watchlists →
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.