Real-time interactive AI-based training ecosystem

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected April 1st, 2026

Summary

USPTO granted Patent US12592161B1 to inventor Otito Ruth Umoren-Udom for a real-time interactive AI-based testing system that uses machine learning and artificial neural networks to generate adaptive test questions based on user response analysis. The patent (16 claims) covers systems and methods for automated assessment with predictive question generation.

View original document View source feed page

What changed

USPTO issued Patent No. US12592161B1 on March 31, 2026, covering a system for automated real-time interactive testing using machine learning. The system comprises a testing support server with a processor hosting an ML module connected to user-entity and test-entity nodes over a network. The processor provides test questions, receives and parses user responses to extract classifying features, queries a local testing database for historical data, generates feature vectors, and feeds them to an ML module with an artificial neural network to produce question update parameters for adaptive test generation.

Companies developing AI-based educational or assessment platforms should review this patent for freedom-to-operate considerations. While patents grant exclusive rights rather than imposing compliance obligations, entities creating similar adaptive testing technologies may need to seek licensing or design around these claims to avoid infringement risk.

Source document (simplified)

← USPTO Patent Grants

Real-time interactive AI-based training ecosystem

Grant US12592161B1 Kind: B1 Mar 31, 2026

Inventors

Otito Ruth Umoren-Udom

Abstract

A system for an automated real-time interactive testing based on user-response data including a processor of a testing support server (TSS) node configured to host a machine learning (ML) module and connected to at least one user-entity node and to at least one test-entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: provide test question data including a plurality of key elements to the at least one user-entity node; receive user response data from the at least one user-entity node; parse the user response data to extract a plurality of classifying features based on the plurality of key elements; query a local testing database to retrieve local historical tests-related data based on the plurality of classifying features; generate at least one feature vector based on the plurality of classifying features and the local historical tests-related data; provide the at least one feature vector to the ML module coupled to an Artificial Neural Network (ANN); receive a plurality of question update parameters from a test predictive model generated by the ML module using outputs of the ANN based on the feature vector; and generate an updated question based on the plurality of question update parameters.