US 12,093,277 B2
Data modeling and database recommendation using machine learning
Dhilip S. Kumar, Bangalore (IN); Jaganathan Subramanian, Bangalore (IN); Raja Sekhar Eega, Krishna District (IN); Astha Malhotra, Noida (IN); Solleti Praveen Kumar, Hyderabad (IN); Ashraf Afzal Syed, Hyderabad (IN); Himesh Chopra, Chandigarh (IN); Smriti Mishra, Bangalore (IN); and Sumanta Pandit, Hyderabad (IN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Feb. 15, 2023, as Appl. No. 18/110,209.
Prior Publication US 2024/0273112 A1, Aug. 15, 2024
Int. Cl. G06F 16/20 (2019.01); G06F 16/21 (2019.01); G06F 16/25 (2019.01)
CPC G06F 16/258 (2019.01) [G06F 16/212 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
reading data of one or more files;
identifying one or more data types corresponding to the one or more files;
recommending at least one destination database for the data based at least in part on the one or more data types; and
generating a data model to use in connection with writing the data to the at least one destination database;
wherein the generation of the data model is based at least in part on the one or more data types corresponding to the one or more files;
wherein at least the generation of the data model is performed using one or more machine learning algorithms;
wherein generating the data model comprises using the one or more machine learning algorithms to:
identify a plurality of attributes to select as candidates for at least one node of the at least one destination database;
compute information gain for respective ones of the one or more attributes, wherein at least one attribute with a highest information gain than remaining ones of the plurality of attributes is selected as the at least one node of the at least one destination database; and
predict one or more partitions for the destination database, the one or more partitions respectively storing portions of the data; and
wherein the method is executed by a processing device operatively coupled to a memory.