US 12,265,548 B2
Method and system for restoring consistency of a digital twin database
Mark Buckley, Munich (DE); Rakebul Hasan, Munich (DE); Martin Ringsquandl, Raubling (DE); and Johannes Maderspacher, Garmisch-Partenkirchen (DE)
Assigned to Siemens Aktiengesellschaft, Munich (DE)
Filed by Siemens Aktiengesellschaft, Munich (DE)
Filed on Oct. 25, 2023, as Appl. No. 18/494,627.
Claims priority of application No. 22204712 (EP), filed on Oct. 31, 2022.
Prior Publication US 2024/0143623 A1, May 2, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 16/215 (2019.01); G06F 16/27 (2019.01)
CPC G06F 16/273 (2019.01) [G06F 16/215 (2019.01)] 11 Claims
OG exemplary drawing
 
1. A computer implemented method for restoring consistency of a digital twin database of an industrial system, wherein the following operations are performed by components, and wherein the components are software components executed by one or more processors and/or hardware components:
storing, by a digital twin database, the digital twin of the industrial system, wherein the digital twin database is inconsistent because a first identifier imported from a first data source and a second identifier imported from a second data source are stored independently from each other in the digital twin database, even though both identifiers identify a first entity of the industrial system,
computing, by an encoder, latent representations of the first identifier and the second identifier,
comparing, by a similarity metric, the latent representations, and computing a similarity score, and
updating the digital twin database by aligning the first identifier and the second identifier if the similarity score is above a threshold.