Abstract: The present disclosure provides a generative modeling framework for generating highly realistic and privacy preserving synthetic records for heterogenous time-series data, such as electronic health record data, financial data, etc. The generative modeling framework is based on a two-stage model that includes sequential encoder-decoder networks and generative adversarial networks (GANs).

Abstract: Lease transfer between master and slave replicas is described. A master replicator determines that an initial master replica lease takes effect. On determining that a master replica transfer needs to be performed, sending a transfer preparation message to a target replicator prior to expiration of a current master replica lease. The target replicator locally starts and calculates a new master replica lease and returns a readiness response to the master replicator. The master replicator sends a lease extension message to remaining slave replicators to extend local corresponding leases. After receiving lease extension success responses of a majority of the slave replicators, the master replicator terminates the local master replica lease of the master replicator in advance, and sends a transfer confirmation message to the target replicator. The target replicator validates the new master replica lease to make the target replicator a new master replicator.

Abstract: This specification discloses example distributed table lock application methods and apparatuses, storage media, and electronic devices. In an example method, a master node receives a data processing request and determines a data table that to-be-processed data corresponding to the data processing request are located in. The master node generates a table lock for the data table; performs a lock operation on the data table and generates lock status information corresponding to the data table; writes the lock status information into a local log of the master node and synchronizes the log to a slave node such that the slave node stores the log. After the master node restarts, determines whether the master node stores the log; and in response to that the master node stores the log, restores the lock operation on the data table based on the lock status information recorded in the log.

Abstract: A method includes obtaining a dataset that includes health data in a Fast Healthcare Interoperability Resources (FHIR) standard. The health data includes a plurality of healthcare events. The method includes generating, using the dataset, an events table that includes the plurality of healthcare events and is indexed by time and a unique identifier per patient encounter. The method also includes generating, using the dataset, a traits table that includes static data and is indexed by the unique identifier per patient encounter. The method includes training a machine learning model using the events table and the traits table and predicting, using the trained machine learning model and one or more additional healthcare events associated with a patient, a health outcome for the patient.