Probabilistic event networks based on distributed time-stamped data

摘要

Techniques for producing probabilistic event networks (Bayesian network based representation of node dependencies, whereas nodes comprise event occurrences, explicit times of occurrences, and the context of event occurrences) based on distributed time-stamped data are disclosed. An aspect provides a method for predicting events from event log data via constructing a probabilistic event net and using the probabilistic event net to infer a probabilistic statement regarding a future event using a network inference mechanism. Other embodiments are disclosed.

主权项

1. A method for predicting events from event log data, comprising:
constructing at least one probabilistic event network using training data, the training data being multivariate point process data, said constructing comprising:
receiving the training data;generating co-occurrence scores for pairs of event classes represented in the training data;the co-occurrence scores indicating a correlation between two variables included in the pairs of event classes;wherein a co-occurrence score for at least one of the pairs of event classes is based upon a correlation of time between the two variables included in the at least one of the pairs of event classes;wherein the co-occurrence score for at least one of the pairs of event classes is based upon an order of events between the two variables included in the at least one of the pairs of event classes;generating at least one case set comprising correlated events for at least a portion of the pairs of event classes using the co-occurrence scores; andconstructing the at least one probabilistic event network from the at least one case set; receiving a query regarding at least one future event; and upon receiving the query, using the at least one probabilistic event network to infer a probabilistic statement regarding said at least one future event using a network inference mechanism.