公开(公告)号：US11755896B2

公开(公告)日：2023-09-12

申请号：US17964490

申请日：2022-10-12

Applicant: SAP SE

Inventor： Marco Antonio Carniel Furlanetto ,  Alessandro Parolin ,  Cristiano Ruschel Marques Dias ,  Alejandro Salinger

IPC: G06N5/04 ,  G06N20/00 ,  G06N3/063 ,  G06F18/214 ,  G06F18/243 ,  G06F16/2458

CPC classification number: G06N3/063 ,  G06F18/214 ,  G06F18/24323 ,  G06N5/04 ,  G06N20/00 ,  G06F16/2458

Abstract: In some example embodiments, a computer-implemented method may include training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

公开(公告)号：US20230334303A1

公开(公告)日：2023-10-19

申请号：US18213071

申请日：2023-06-22

Applicant: SAP SE

Inventor： Marco Antonio Carniel Furlanetto ,  Alessandro Parolin ,  Cristiano Ruschel Marques Dias ,  Alejandro Salinger

IPC: G06F18/214 ,  G06N5/04 ,  G06F18/243 ,  G06N3/063 ,  G06N20/00

CPC classification number: G06N3/063 ,  G06F18/214 ,  G06F18/24323 ,  G06N5/04 ,  G06N20/00 ,  G06F16/2458

Abstract: Techniques for implementing cross in-database machine learning are disclosed. In some example embodiments, a computer-implemented method comprises training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

公开(公告)号：US11995535B2

公开(公告)日：2024-05-28

申请号：US18213071

申请日：2023-06-22

Applicant: SAP SE

Inventor： Marco Antonio Carniel Furlanetto ,  Alessandro Parolin ,  Cristiano Ruschel Marques Dias ,  Alejandro Salinger

IPC: G06N5/04 ,  G06F18/214 ,  G06F18/243 ,  G06N3/063 ,  G06N20/00 ,  G06F16/2458

CPC classification number: G06N3/063 ,  G06F18/214 ,  G06F18/24323 ,  G06N5/04 ,  G06N20/00 ,  G06F16/2458

Abstract: In some example embodiments, a computer-implemented method may include training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

公开(公告)号：US20210350254A1

公开(公告)日：2021-11-11

申请号：US16870672

申请日：2020-05-08

Applicant: SAP SE

Inventor： Marco Antonio Carniel Furlanetto ,  Alessandro Parolin ,  Cristiano Ruschel Marques Dias ,  Alejandro Salinger

IPC: G06N5/04 ,  G06K9/62 ,  G06N20/00

Abstract: Techniques for implementing cross in-database machine learning are disclosed. In some example embodiments, a computer-implemented method comprises training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

公开(公告)号：US20230030608A1

公开(公告)日：2023-02-02

申请号：US17964490

申请日：2022-10-12

Applicant: SAP SE

Inventor： Marco Antonio Carniel Furlanetto ,  Alessandro Parolin ,  Cristiano Ruschel Marques Dias ,  Alejandro Salinger

IPC: G06N5/04 ,  G06N20/00 ,  G06K9/62

Abstract: Techniques for implementing cross in-database machine learning are disclosed. In some example embodiments, a computer-implemented method comprises training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

公开(公告)号：US11494672B2

公开(公告)日：2022-11-08

申请号：US16870672

申请日：2020-05-08

Applicant: SAP SE

Inventor： Marco Antonio Carniel Furlanetto ,  Alessandro Parolin ,  Cristiano Ruschel Marques Dias ,  Alejandro Salinger

IPC: G06N5/04 ,  G06N20/00 ,  G06K9/62 ,  G06F16/2458

Abstract: In some example embodiments, a computer-implemented method may include training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.