US 11,836,120 B2
Machine learning techniques for schema mapping
Paul Deepakraj Retinraj, Fremont, CA (US); Sravan Kumar Ananthula, Frisco, TX (US); and Rajan Madhavan, Foster City, CA (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Jul. 23, 2021, as Appl. No. 17/383,909.
Prior Publication US 2023/0023645 A1, Jan. 26, 2023
Int. Cl. G06F 16/21 (2019.01); G06N 3/08 (2023.01); G06N 3/04 (2023.01)
CPC G06F 16/211 (2019.01) [G06N 3/04 (2013.01); G06N 3/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:
generating a first graph representing a source database schema comprising a first set of entities, wherein a first set of nodes in the first graph respectively represent entities in the first set of entities, and wherein a first set of edges in the first graph respectively represent relationships between entities in the first set of entities;
generating a first graphical context data, for a first node in the first set of nodes, representing relationships of the first node to other nodes in the first set of nodes, the first node representing a first entity in the first set of entities;
identifying a second graph representing a target database schema comprising a second set of entities, wherein a second set of nodes in the second graph respectively represent entities in the second set of entities, and wherein a second set of edges in the second graph respectively represent relationships between entities in the second set of entities;
generating a second graphical context data, for a second node in the second set of nodes, representing relationships of the second node to other nodes in the second set of nodes, the second node representing a second entity in the second set of entities;
selecting the first node in the first set of nodes and the second node in the second set of nodes for comparison based on a similarity value between a first set of first attribute data associated with the first entity and a second set of second attribute data associated with the second entity;
comparing the first graphical context data, for the first node, to the second graphical context data for the second node to determine that (a) the first entity in the first set of entities corresponds to (b) the second entity in the second set of entities;
responsive to determining that (a) the first entity in the first set of entities corresponds to (b) the second entity in the second set of entities, generating a mapping that converts an association of a target data item from the first entity to the second entity;
storing the mapping such that the mapping is accessible for converting source data entities into target data entities.