US 12,436,845 B1
Multi-database query model in a database backup system
Benjamin Gruenbaum, Herzliya (IL); Ron Kimchi, Tel Aviv (IL); Amir Yonatan, Tel Aviv-Jaffa (IL); Assaf Natanzon, Tel Aviv (IL); and Erez Reuven, Raanana (IL)
Assigned to Eon IO, Ltd., Tel Aviv (IL)
Filed by Eon IO, Ltd., Tel Aviv (IL)
Filed on Feb. 12, 2025, as Appl. No. 19/051,930.
Int. Cl. G06F 16/00 (2019.01); G06F 11/14 (2006.01); G06F 16/248 (2019.01); G06F 16/28 (2019.01)
CPC G06F 11/1458 (2013.01) [G06F 16/248 (2019.01); G06F 16/285 (2019.01); G06F 2201/80 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for querying multiple database tables in a database backup, comprising:
receiving identification of database tables to query, wherein the database tables are stored in the database backup in a column-based format, and wherein the database backup includes for each database table classification data for at least classifying its respective column names, wherein the database tables to query are database tables of different database applications, wherein the classification data is generated by prompting a language model based on a set of values of columns in the respective database table;
generating a prompt for a first language model that, when executed by a generative AI system, provides a set of queries targeting the database tables, wherein the generated prompt is based on at least a received input query and the classification data for the database tables;
executing the set of queries on the database tables, wherein each query of the set of queries is executed on a respective database table; and
aggregating and displaying results returned in response to the execution of the set of queries.