17974853. DATA CONFIDENTIALITY-PRESERVING MACHINE LEARNING ON REMOTE DATASETS simplified abstract (SAP SE)
Contents
- 1 DATA CONFIDENTIALITY-PRESERVING MACHINE LEARNING ON REMOTE DATASETS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DATA CONFIDENTIALITY-PRESERVING MACHINE LEARNING ON REMOTE DATASETS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DATA CONFIDENTIALITY-PRESERVING MACHINE LEARNING ON REMOTE DATASETS
Organization Name
Inventor(s)
Philipp Knuesel of Nussloch (DE)
DATA CONFIDENTIALITY-PRESERVING MACHINE LEARNING ON REMOTE DATASETS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17974853 titled 'DATA CONFIDENTIALITY-PRESERVING MACHINE LEARNING ON REMOTE DATASETS
Simplified Explanation
The present disclosure involves systems, software, and computer implemented methods for data confidentiality-preserving machine learning on remote datasets. An example method includes receiving connection information for connecting to a remote customer database and storing the connection information in a machine learning runtime. Workload schedule information for allowable time windows for machine learning pipeline execution on remote customer data of the customer is received from the customer. A determination is made that an execution queue includes a machine learning pipeline during an allowed time window. The connection information is used to connect to the remote customer database during the allowed time window. Execution is triggered by the machine learning runtime of the machine learning pipeline on the remote customer database. Aggregate evaluation data corresponding to the execution of the machine learning pipeline on the remote customer database is received and provided to a user.
- Data confidentiality-preserving machine learning on remote datasets
- Receiving connection information for remote customer database
- Storing connection information in machine learning runtime
- Workload schedule information for allowable time windows received
- Determination of machine learning pipeline execution during allowed time window
- Connection to remote customer database during allowed time window
- Triggering execution by machine learning runtime
- Receiving and providing aggregate evaluation data to user
Potential Applications
This technology can be applied in industries where data confidentiality is crucial, such as healthcare, finance, and government sectors.
Problems Solved
This technology solves the problem of securely accessing and analyzing remote customer data without compromising confidentiality.
Benefits
The benefits of this technology include improved data security, efficient machine learning pipeline execution on remote datasets, and enhanced privacy protection for sensitive information.
Potential Commercial Applications
A potential commercial application of this technology could be in the development of secure data analytics platforms for businesses handling sensitive customer data.
Possible Prior Art
One possible prior art for this technology could be secure data processing methods used in cloud computing environments to protect sensitive information.
Unanswered Questions
== How does this technology ensure data confidentiality during machine learning pipeline execution on remote datasets? This article does not provide specific details on the encryption or security measures used to protect data during the execution process.
== What are the potential limitations or challenges of implementing this technology in real-world scenarios? This article does not address potential obstacles such as compatibility issues with existing databases, scalability concerns, or regulatory compliance requirements that may arise when deploying this technology.
Original Abstract Submitted
The present disclosure involves systems, software, and computer implemented methods for data confidentiality-preserving machine learning on remote datasets. An example method includes receiving connection information for connecting to a remote customer database and storing the connection information in a machine learning runtime. Workload schedule information for allowable time windows for machine learning pipeline execution on remote customer data of the customer is received from the customer. A determination is made that an execution queue includes a machine learning pipeline during an allowed time window. The connection information is used to connect to the remote customer database during the allowed time window. Execution is triggered by the machine learning runtime of the machine learning pipeline on the remote customer database. Aggregate evaluation data corresponding to the execution of the machine learning pipeline on the remote customer database is received and provided to a user.
