Amazon patents tool that builds and tests AI models from a data file
This patent describes a system that lets users upload a data file and select a column to predict. The system automatically tests different AI algorithms to find the best model and shows the results to the user.
In the filing’s own words
Techniques for automated machine learning (ML) pipeline exploration and deployment are described. An automated ML pipeline generation system allows users to easily construct optimized ML pipelines by providing a dataset, identifying a target column in the dataset, and providing an exploration budget. Multiple candidate ML pipelines can be identified and evaluated through an exploration process, and a best ML pipeline can be provided to the requesting user or deployed for production inference. Users can configure, monitor, and adapt the exploration at multiple points in time throughout.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: receiving, at an automated machine learning system of a cloud provider network via use of one or more graphical user interfaces (GUIs) presented by a computing device: a comma-separated values (CSV) file or an identifier of the CSV file, wherein the CSV file provides a tabular dataset including data values arranged via a plurality of columns to be used for automated machine learning pipeline generation, and a user-selected column from the plurality of columns of the CSV file, wherein the user-selected column indicates which column is to be predicted; determining, by the automated machine learning system based on at least some of the data values and the user-selected column, a prediction type; selecting, by the automated machine learning system, one or more ML algorithms based at least in part on use of the determined prediction type; generating, by the automated machine learning system, a plurality of candidate ML model pipelines based at least in part on use of the tabular dataset, the generating comprising training multiple candidate ML models based on the selected one or more ML algorithms; and causing results associated with the training of the multiple candidate ML model pipelines to be presented via the one or more GUIs, the results including values of an objective metric for the multiple candidate ML model pipelines.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- Automated machine learning pipeline exploration and deployment
- Patent number
- US12749026B1
- Application number
- 18757148
- Filed
- Jun 27, 2024
- Granted
- Sep 29, 2026
- Inventors
- 12
- Claims
- 20
Classified under
G06N 20/20 Physics & computingG06F 9/5066 Physics & computingG06F 9/546 Physics & computingMore from Amazon in AI & software
- Amazon patents system that cites sources for AI answers Sep 29, 2026
- Amazon patents tech to swap words in movies using actor's voice Sep 8, 2026
- Amazon patents ML tool to add graphics to live sports from moving cameras Sep 15, 2026
- Amazon patents shopping assistant that remembers your search filters Oct 6, 2026
- Amazon patents system where AI agents split tasks and talk to each other Oct 20, 2026
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.