/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents platform to mix human feedback with AI training

Patent drawing
Patent drawing from the official filing.

Google has filed a patent for a computer platform that helps developers combine human input with reinforcement learning, a method where AI improves by trial and error. The system offers pre-written code blocks that users can select to create a framework for gathering human feedback on how well an AI model performs.

Why it mattersThis could make it easier for companies to build AI systems that learn from human corrections, potentially leading to more accurate and reliable software tools.

In the filing’s own words

A computer-implemented method includes receiving information associated with one or more machine-learned models provided by an external computing system, providing predefined code segments for obtaining human-in-the-loop reinforcement learning (HITL RL) feedback with respect to the one or more machine-learned models, identifying a selection of one or more of the predefined code segments, and generating a HITL RL framework configured to be applied to the one or more machine-learned models to obtain feedback associated with performance of the one or more machine-learned models, based on the selection of the one or more of the predefined code segments.

What exactly they claim (claim 1)

1. A computer-implemented method, comprising: receiving, by a computing system, information associated with one or more machine-learned models provided by an external computing system; providing, by the computing system, predefined code segments for obtaining human-in-the-loop reinforcement learning (HITL RL) feedback with respect to the one or more machine-learned models; identifying, by the computing system, a selection of one or more of the predefined code segments; and generating, by the computing system, a HITL RL framework configured to be applied to the one or more machine-learned models to obtain feedback associated with performance of the one or more machine-learned models, based on the selection of the one or more of the predefined code segments.

Facts

Company
Google (Google LLC)
Official title
Computer Platform for Human-in-the-Loop Reinforcement Learning
Publication number
US20260310983A1
Application number
19483166
Filed
May 1, 2024
Published
Oct 8, 2026
Inventors
3
Claims
20

Classified under

G06N 3/092 Physics & computingG06N 3/0475 Physics & computingG06N 3/091 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.