Amazon patents SQL queries that call on machine learning models
Amazon has been granted a patent for a system that allows users to write standard database queries that directly reference machine learning models. When a query is run, the system uses the model to fill in missing or inferred data values in the database table before returning the final results to the user.
In the filing’s own words
Querying databases may be performed with references to machine learning models. A database query may be received that references a machine learning model and database. In response to the query, the machine learning model may provide information which may be returned as part of a result of the query or may be used to generate a result of the query. The machine learning model may be generated in response to a request to generate a machine learning model that includes a database query that identifies the data upon which a machine learning technique may be applied to generate the machine learning model.
What exactly they claim (claim 1)
1. A system, comprising: a plurality of computing devices, respectively implement a processor and a memory, configured to implement a provider network service, the provider network service configured to: receive, via an interface of the provider network service, a query statement that is stated in Structured Query Language (SQL), wherein the interface supports queries stated in the query language, and wherein the query statement specifies a column in a table of a data warehouse and a machine learning model; cause an evaluation of respective data in the specified column to determine one or more records in the table of the data warehouse to add inferred data values determined from the machine learning model referenced in the query; cause the evaluation of the machine learning model referenced in the query to determine the inferred data values for the one or more records in the table; return, via the interface of the provider network service, a result of the query statement based on the inferred data values from the evaluation of the machine learning model determined for the one or more records.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- Querying databases with machine learning model references
- Patent number
- US12755192B2
- Application number
- 18054837
- Filed
- Nov 11, 2022
- Granted
- Oct 6, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06N 20/00 Physics & computingG06F 16/90335 Physics & computingG06N 5/022 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.