# US 2021/0241131 A1 · Machine Learning Predictions for Database Migrations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241131 A1 - Document ID: US20210241131A1 - Status: Published application - Kind: A1 - Application number: 16/778,370 - Filed: 2020-01-31 - Published: 2021-08-05 - Earliest claimed: 2020-01-31 - Assignees: Oracle International Corporation - Applicants: Oracle International Corporation - Inventors: Malay K. KHAWAS; Saumika SARANGI; Sudipto BASU; Ranajoy BOSE; Padma Priya Rajan NATARAJAN; Bogapurapu L. K. RAO; Parul YAMINI - Web page: https://patentgrep.com/patent/US20210241131A1 ## CPC - G06N 5/04: Inference or reasoning models - G06F 16/214: {Database migration support} - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/20: Ensemble learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Embodiments generate machine learning predictions for database migrations. For example, a trained machine learning model that has been trained using training data can be stored, where the training data includes migration information for database migrations and migration methods for the database migrations, and the training data migration information includes a source database type and a target database infrastructure. Migration information can be received for a candidate database migration that includes a source database type and a target database infrastructure. Using the trained machine learning model, migration methods based on the migration information for the candidate database migration can be predicted. ## Claims ### Claim 1 A method for generating machine learning predictions for database migrations, the method comprising: storing a trained machine learning model that has been trained using training data, wherein the training data comprises migration information for a plurality of database migrations and migration methods for the plurality of database migrations, and the training data migration information includes a source database type and a target database infrastructure; receiving migration information for a candidate database migration that includes a source database type and a target database infrastructure; and predicting, using the trained machine learning model, migration methods based on the migration information for the candidate database migration. ### Claim 2 (depends on 1) The method of claim 1, wherein the training data comprises instances of migration information for a given database migration and migration methods for the given database migration, the migration methods comprising labels for the training data. ### Claim 3 (depends on 2) The method of claim 2, wherein the migration methods include one or more of database replication, pluggable database implementation, disaster recovery switchover, database cloning, and data pump conventional export and import. ### Claim 4 (depends on 1) The method of claim 1, wherein the candidate database migration information is generated by a script that is executed on a computing device that implements the source database. ### Claim 5 (depends on 1) The method of claim 1, wherein the migration information for the plurality of database migrations and the migration information for the candidate database migration comprise source database size, bandwidth criteria, and downtime criteria. ### Claim 6 (depends on 1) The method of claim 1, further comprising: receiving feedback information comprising migration results associated with the predicted migration methods for the candidate database migration; processing the feedback information to generate an instance of training data; generating updated training data comprising the processed feedback information and a plurality of additional processed feedback information based on database migrations, migration methods for the database migrations, and feedback information comprising results associated with the migration methods for the database migrations; and retraining the machine learning model using the updating training data. ### Claim 7 (depends on 1) The method of claim 1, wherein the machine learning model comprises an ensemble machine learning model that aggregates a plurality of predictions from a set trained machine learning models. ### Claim 8 (depends on 7) The method of claim 7, wherein the migration information for the training data comprises a set of migration features, the set of migration features is split into a plurality of subsets of migration features, and the set of trained machine learning models are configured to receive the subsets of migration features and generate the plurality of predictions. ### Claim 9 (depends on 8) The method of claim 8, wherein the set of machine learning models are configured to receive different sets of the migration features to generate predictions. ### Claim 10 (depends on 1) The method of claim 1, further comprising: translating the candidate database migration information to a machine readable format, wherein the candidate database migration information is mapped to machine readable format data using predetermined mappings based on closed lists of data values for the candidate database migration information; and predicting, using the trained machine learning model, migration methods for the candidate database migration based on the translated migration information. ### Claim 11 A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, cause the processor to generate machine learning predictions for database migrations, wherein, when executed, the instructions cause the processor to: store a trained machine learning model that has been trained using training data, wherein the training data comprises migration information for a plurality of database migrations and migration methods for the plurality of database migrations, and the migration information for the training data includes a source database type and a target database infrastructure; receive migration information for a candidate database migration that includes a source database type and a target database infrastructure; and predict, using the trained machine learning model, migration methods based on the migration information for the candidate database migration. ### Claim 12 (depends on 11) The computer readable medium of claim 11, wherein the training data comprises instances of migration information for a given database migration and migration methods for the given database migration, the migration methods comprising labels for the training data. ### Claim 13 (depends on 12) The computer readable medium of claim 12, wherein the migration methods include one or more of database replication, pluggable database implementation, disaster recovery switchover, database cloning, and data pump conventional export and import. ### Claim 14 (depends on 11) The computer readable medium of claim 11, wherein the candidate database migration information is generated by a script that is executed on a computing device that implements the source database. ### Claim 15 (depends on 11) The computer readable medium of claim 11, wherein when executed, the instructions cause the processor to: receive feedback information comprising migration results associated with the predicted migration methods for the candidate database migration; process the feedback information to generate an instance of training data; generate updated training data comprising the processed feedback information and a plurality of additional processed feedback information based on database migrations, migration methods for the database migrations, and feedback information comprising results associated with the migration methods for the database migrations; and retrain the machine learning model using the updating training data. ### Claim 16 (depends on 11) The computer readable medium of claim 11, wherein the machine learning model comprises an ensemble machine learning model that aggregates a plurality of predictions from a set trained machine learning models. ### Claim 17 (depends on 16) The computer readable medium of claim 16, wherein the training data migration information comprises a set of migration features, the set of migration features is split into a plurality of subsets of migration features, and the set of trained machine learning models are configured to receive the subsets of migration features and generate the plurality of predictions. ### Claim 18 (depends on 17) The computer readable medium of claim 17, wherein the set of machine learning models are configured to receive different sets of the migration features to generate predictions. ### Claim 19 (depends on 11) The computer readable medium of claim 11, further comprising: translating the candidate database migration information to a machine readable format, wherein the candidate database migration information is mapped to machine readable format data using predetermined mappings based on closed lists of data values for the candidate database migration information; and predicting, using the trained machine learning model, migration methods for the candidate database migration based on the translated migration information. ### Claim 20 A system for generating machine learning predictions for database migrations, the system comprising: a processor; and a memory storing instructions for execution by the processor, the instructions configuring the processor to: store a trained machine learning model that has been trained using training data, wherein the training data comprises migration information for a plurality of database migrations and migration methods for the plurality of database migrations, and the training data migration information includes a source database type and a target database infrastructure; receive migration information for a candidate database migration that includes a source database type and a target database infrastructure; and predict, using the trained machine learning model, migration methods based on the migration information for the candidate database migration.