公开(公告)号：US20210083855A1

公开(公告)日：2021-03-18

申请号：US17019256

申请日：2020-09-12

Applicant: Oracle International Corporation

Inventor： Alberto Polleri ,  Sergio Aldea Lopez ,  Marc Michiel Bron ,  Dan David Golding ,  Alexander Ioannides ,  Maria del Rosario Mestre ,  Hugo Alexandre Pereira Monteiro ,  Oleg Gennadievich Shevelev ,  Larissa Cristina Dos Santos Romualdo Suzuki ,  Xiaoxue Zhao ,  Matthew Charles Rowe

IPC: H04L9/08 ,  G06N20/00 ,  H04L9/32

Abstract: The present disclosure relates to systems and methods for a machine-learning platform for the safe serialization of a machine-learning application. Individual library components (e.g., a pipeline, a microservice routine, a software module, and an infrastructure model) can be encrypted using one or more keys. The keys can be stored in a location different from the storage location of the machine-learning application. Prior to incorporation of the library component into a machine-learning model, one or more keys can be retrieved from the remote storage location to authenticate that the one or more encrypted library components are authentic. The process can reject any of the one or more component, when the encrypted library component fails authentication. If a component is rejected, the system can roll back to a previous, authenticated version of the library component. The authenticated library components can be compiled into machine-learning software.

公开(公告)号：US20210081196A1

公开(公告)日：2021-03-18

申请号：US17019255

申请日：2020-09-12

Applicant: Oracle International Corporation

Inventor： Alberto Polleri ,  Sergio Aldea Lopez ,  Marc Michiel Bron ,  Dan David Golding ,  Alexander Ioannides ,  Maria del Rosario Mestre ,  Hugo Alexandre Pereira Monteiro ,  Oleg Gennadievich Shevelev ,  Larissa Cristina Dos Santos Romualdo Suzuki ,  Xiaoxue Zhao ,  Matthew Charles Rowe

IPC: G06F8/75 ,  G06F8/77 ,  G06N5/02 ,  G06N20/00 ,  G06F16/907 ,  G06F16/9035

Abstract: A server system may match a segment of code for a code integration request to metadata about similar segments of code, wherein the metadata qualifies one or more outcomes of previous integration requests. The server may determine usage rights and rules based on the metadata, wherein some of the usage rights and rules have previously have been approved by a multi-approval workflow that enforces a predetermined process to authorize use of the segment of code for code segment integrations. The server may analyze the metadata to predict an integration score based at least in part on the usage rights and rules of the segments of code. If the integration score of the segment of code exceeds a threshold, the system may automatically generate a data structure for deploying the segment of code, wherein the automatically generating the data structure is performed without the multi-approval workflow.