International Business Machines Corporation

Marco Selig

Qais Noorshams

Pradeep Parameshwaran

Norman Christopher Böwing

Elpida Tzortzatos

Eric Kass

Dieter Wellerdiek

Simon Spinner

Karin Genther

Tobias Huschle

Anastasiia Didkovska

Toni Pohl

Dave Willoughby

Juri Dragoun

Pavel Kravetskiy

A computer-implemented method, system, and computer program product for classifying a sequence of log entries of a computing system may be provided. The method may include pre-processing the log entries. The method may also include predicting, as a first output of a first trained machine-learning system, a likelihood of a particular next log entry after the window. The method may also include, predicting, as a second output of a second trained machine-learning system, whether the next log entry is unprecedented. The method may also include combining the first output and the second output for determining a classification of the sequence of log entries.

Revealing rare and anomalous events in system automation logs

Aspects of the invention include determining, by a machine learning model, a predicted workload for a system and a current system state of the system, determining an action to be enacted for the system based at least in part on the predicted workload and the current system state, enacting the action for the system, evaluating a state of the system after the action has been enacted, determining a reward for the machine learning model based at least in part on the state of the system after the action has been enacted, and updating the machine learning model based on the reward.

Workload management using reinforcement learning

A method for selectively generating suggested default values for I/O configurations is provided. The method identifies a first selection including a first input value for an I/O configuration. The method determines a set of remaining input options based on the first selection. The method accesses a set of decision trees based on the set of remaining input options and selects a decision tree of the set of decision trees based on the first input value. The method generates a suggested value for a subsequent selection for the I/O configuration and causes presentation of the suggested value and a user interface element representing the subsequent selection.

Selective enhancement of interactive configuration interfaces

Proactively performing tasks based on estimating hardware reconfiguration times. A determination is made, prior to performing one or more reconfiguration actions to reconfigure a configuration of the computing environment, at least one estimated reconfiguration time to perform the one or more reconfiguration actions. At least one reconfiguration action of the one or more reconfiguration actions is performed, and one or more tasks are initiated prior to completing the one or more reconfiguration actions. The initiating is based on the at least one estimated reconfiguration time.

Proactively performing tasks based on estimating hardware reconfiguration times

A computer-implemented method for metadata-based retention of personal data may be provided. The method comprises recording data by a recording system. The data comprise payload data and metadata comprising information about the payload data and an event type; and a rule is associated with the event type, wherein the rule is indicative whether the data shall be stored persistently or temporary. The method comprises further segmenting the recorded data into a plurality of non-overlapping data segments, encrypting each data segment of the plurality of non-overlapping data segments with a unique key each, transmitting the encrypted data segments wirelessly, and storing, using a secure service container, selected ones of the plurality of non-overlapping data segments as a function of the rule.

Access control of specific encrypted data segment

Growing community of inventors

Boeblingen, Germany

Marco Selig