US 12,321,252 B2
Generating massive high quality synthetic observability data
Ying Mo, Beijing (CN); Wu Di, Beijing (CN); Xing Tian, Beijing (CN); Qing Zhi Yu, Beijing (CN); Nan Chen, Beijing (CN); and Ju Ling Liu, Beijing (CN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Aug. 24, 2023, as Appl. No. 18/237,828.
Prior Publication US 2025/0068535 A1, Feb. 27, 2025
Int. Cl. G06F 11/30 (2006.01); G06F 11/34 (2006.01)
CPC G06F 11/3075 (2013.01) [G06F 11/3457 (2013.01); G06F 11/3466 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
collecting, by a computing device, traces and logs from a system as a seed dataset;
training, by the computing device, a plurality of conditional variational autoencoder (CVAE) models using the seed dataset for learning association between the traces and the logs; and
generating, by the computing device, synthetic traces and logs using the plurality of CVAE models while retaining the association between the traces and the logs for the synthetic traces and logs.