Abstract
Querying data sources such as databases requires knowledge of querying techniques, such as the structured query language (SQL) as well as an understanding of the databases being queried. Users with inadequate knowledge may struggle to write queries that execute successfully and retrieve the targeted data accurately. Additionally, lack of knowledge of database properties such as table sizes, partitioning, database schema, etc. can cause users to write queries that are computationally inefficient and/or fail at runtime. This disclosure describes the use of artificial intelligence techniques, including models trained on a training dataset that represents various types of successful and failed queries, to provide users with guidance regarding avoiding errors and/or optimizing queries. The AI model can identify the likely factors behind query success and failure, and suggest fixes based on comparing a current query with past examples. The suggestions can include suggestions to refine the query to fix errors and/or to optimize runtime performance.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Wolf, Lois, "Applying Artificial Intelligence to Suggest Operational Optimizations to Data Queries", Technical Disclosure Commons, (November 04, 2025)
https://www.tdcommons.org/dpubs_series/8836