Abstract: According to one embodiment of the present disclosure, an approach is provided in which a processor receives a media stream that includes media content. The processor selects a media stream segment included in the media stream, and generates annotated data based upon a portion of the media content included in the selected media stream segment. The processor, in turn, compares the annotated data with obfuscation preferences that correspond to prohibited content, and modifies the media stream segment in response to the comparison.

Abstract: A conveyed set of recipient email messages can be identified. An event triggering the conveyed set of email message to be prioritized relative to each other can be detected. Responsive to the detected event, a priority score for each of the emails in the conveyed set can be determined based upon recipient specific criteria. The recipient specific criteria can be based upon recipient behavior regarding a set of previous email messages. The priority score can be calculated base upon prioritizing factors determined from patterns discovered in the recipient behavior regarding the set of previous email messages. At least one programmatic action can be performed based upon the determined priority scores of the email messages.

Abstract: A plurality of stochastic models is built that predict the probabilities of state transitions for components in a complex system. The models are trained using output observations from the system at runtime. The overall state and health of the system can be determined at runtime by analyzing the distribution of current component states among the possible states. Subsequent to a low level component failure, the state transition probability stochastic model for the failed component can be analyzed by uncovering the previous states at N time intervals prior to the failure. The resulting state transition path for the component can be analyzed for the causes of the failure. Additionally, component failures resulting from the failure, or worsening state transition, in other components can be diagnosed by uncovering the previous states at the N times prior to the failure for multiple components in the system and then analyzing the state transition paths for correlations to the failed component.

Abstract: A conveyed set of recipient email messages can be identified. An event triggering the conveyed set of email message to be prioritized relative to each other can be detected. Responsive to the detected event, a priority score for each of the emails in the conveyed set can be determined based upon recipient specific criteria. The recipient specific criteria can be based upon recipient behavior regarding a set of previous email messages. The priority score can be calculated base upon prioritizing factors determined from patterns discovered in the recipient behavior regarding the set of previous email messages. At least one programmatic action can be performed based upon the determined priority scores of the email messages.

Abstract: A plurality of causal ladder is assembled in advance from component system events taken from previous system failures. The ladders classify the various transitions the system goes through from one set of observed states to another in multiple stages representing issues of differing urgency, importance and need for remediation. These stages are used at runtime to determine the criticality of any abnormal system activity and to accurately predict the component failure prior to the system crashing. Each ladder comprises a plurality of elevated stages representing criticality of the problem. At runtime, the causal ladder engine correlates real-time events received from the system to stages of one or more pre-constructed causal ladders and identifies a probable problem (and/or the faulty component) from the corresponding causal ladder. The causal ladder engine also determines the stage of the problem from event occurrences. At each stage, a different potential solution is identified for the problem.

Abstract: A plurality of causal ladder is assembled in advance from component system events taken from previous system failures. The ladders classify the various transitions the system goes through from one set of observed states to another in multiple stages representing issues of differing urgency, importance and need for remediation. These stages are used at runtime determine the criticality of any abnormal system activity and to accurately predict the component failure prior to the system crashing. Each ladder comprises a plurality of elevated stages representing criticality of the problem. At runtime, the causal ladder engine correlates real-time events received from the system to stages of one or more pre-constructed causal ladders and identifies a probable problem (and/or the faulty component) from the corresponding causal ladder. The causal ladder engine also determines the stage of the problem from event occurrences. At each stage, a different potential solution is identified for the problem.

Abstract: A plurality of causal ladder is assembled in advance from component system events taken from previous system failures. The ladders classify the various transitions the system goes through from one set of observed states to another in multiple stages representing issues of differing urgency, importance and need for remediation. These stages are used at runtime to determine the criticality of any abnormal system activity and to accurately predict the component failure prior to the system crashing. Each ladder comprises a plurality of elevated stages representing criticality of the problem. At runtime, the causal ladder engine correlates real-time events received from the system to stages of one or more pre-constructed causal ladders and identifies a probable problem (and/or the faulty component) from the corresponding causal ladder. The causal ladder engine also determines the stage of the problem from event occurrences. At each stage, a different potential solution is identified for the problem.

Abstract: A plurality of stochastic models is built that predict the probabilities of state transitions for components in a complex system. The models are trained using output observations from the system at runtime. The overall state and health of the system can be determined at runtime by analyzing the distribution of current component states among the possible states. Subsequent to a low level component failure, the state transition probability stochastic model for the failed component can be analyzed by uncovering the previous states at N time intervals prior to the failure. The resulting state transition path for the component can be analyzed for the causes of the failure. Additionally, component failures resulting from the failure, or worsening state transition, in other components can be diagnosed by uncovering the previous states at the N times prior to the failure for multiple components in the system and then analyzing the state transition paths for correlations to the failed component.