Computer-implemented method for cross-account model deployment, computer program element and computer readable medium

Patent metadata

Field	Value
Publication number	US-2025252399-A1
Application number	US-202318855154-A
Country	US
Kind code	A1
Filing date	Apr 6, 2023
Priority date	Apr 8, 2022
Publication date	Aug 7, 2025
Grant date	—

Abstract

A computer-implemented method for cross-account model deployment is provided. According to the method, at least one artifact identifier of at least one to-be-deployed model artifact is provided. Further, at least one account tuple, the account tuple comprising a source account identifier identifying a source account and a target account identifier identifying a target account, is provided. Finally, the at least one to-be-deployed model artifact is moved from the source account to the target account. Further, a computer program element and a computer readable medium are provided.

First claim

1 . A computer-implemented method for cross-account model deployment, comprising:
providing at least one artifact identifier of at least one to-be-deployed model artifact; providing at least one account tuple, the account tuple comprising a source account identifier identifying a source account and a target account identifier identifying a target account; and moving, the at least one to-be-deployed model artifact from the source account to the target account.

2 . The method according to claim 1 , wherein the model is a machine learning model.

3 . The method according to claim 1 , wherein the model is an agricultural management model.

4 . The method according to claim 1 , wherein the at least one to-be-deployed model artifact is at least one out of model files, sources files, scripts, binary executable files, database tables, development deliverables, word-processing documents and/or mail messages.

5 . The method according to claim 1 , further comprising: logging the at least one artifact identifier along with the at least one account tuple.

6 . The method according to claim 1 , wherein a list of account tuples is provided, the list comprising at least two account tuples.

7 . The method according to claim 1 , wherein at least one of the source accounts is a development account, at least one of the accounts is a testing account and/or at least one of the target accounts is a production account.

8 . The method according to claim 1 , wherein at least one of the accounts is a cloud-based account.

9 . The method according to claim 1 , wherein the at least one artifact identifier and/or the at least one account tuple are provided by operator input and/or by a user interface.

10 . The method according to claim 1 , wherein the at least one artifact identifier and/or the at least one account tuple are provided automatically by a deployment script and, optionally, the deployment script further performs automated model training, automated model validation and/or quality assurance testing.

11 . The method according to claim 1 , wherein the method further comprises initializing the at least one account tuple, and the initialization of the account tuple is, optionally, performed upon being provided with the account tuple or right before moving the at least one to-be-deployed model artifact.

12 . The method according to claim 1 , wherein initializing the at least one account tuple comprises:
obtaining an authorization for the source account to share the at least one to-be-deployed model artifact; and obtaining an authorization for the target account to receive the at least one to-be-deployed model artifact, wherein moving the at least one to-be-deployed model artifact is performed from the source account to an intermediary and from the intermediary to the target account, and, optionally, wherein access resources required to obtain the authorizations are provided in a set-up step.

13 . The method according to claim 1 ,
wherein initializing the at least one account tuple comprises obtaining an authorization for the source account to access resources of the target account and moving the at least one to-be-deployed model artifact is performed by the source account by pushing the model artifact to the target account; and/or wherein initializing the at least one account tuple comprises obtaining an authorization for the target account to access resources of the source account and moving the at least one to-be-deployed model artifact is performed by the target account by pulling the model artifact from the source account; and, optionally, wherein access resources required to obtain the authorizations are provided in a set-up step.

14 . A computer program element which when executed by a computing unit is configured to carry out the method according to claim 1 .

15 . A computer readable medium that generates data to control a computing unit according to the method according to claim 1 .

16 . The method according to claim 1 , wherein the moving comprises copying.

17 . The method according to claim 3 , wherein the agricultural management model provides agronomic recommendations and/or agronomic control data.

18 . The method according to claim 6 , wherein the target account of one account tuple equals the source account of the next account tuple in the list.

19 . The method according to claim 6 , wherein the account tuples in the list of account tuples are processed one after the other.

20 . The method according claim 9 , wherein the user interface is a representational state transfer application programming interface, REST API, and/or a graphical user interface.

Assignees

• Basf Agro Trademarks Gmbh

Inventors

• Levin Daniel
• Haase Frederic
• Kerkhoff Christian

Classifications

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• G06F8/60

  Software deployment · CPC title

• G06Q10/101 Primary

  Collaborative creation, e.g. joint development of products or services · CPC title

• G06F8/71 Primary

  Version control (security arrangements therefor G06F21/57); Configuration management · CPC title