Method and device for monitoring a process of generating metric data for predicting anomalies

A device for monitoring a process using at least one electronic device in operation and generating first data of a metric, the device further comprising at least one processor, at least one memory operatively coupled to the at least one processor, the at least one memory including a set of instructions configured to, when executed by the at least one processor, cause an execution by the device of steps of a method including:

• a learning process, including:
• analysing automatically second data, representative of events that have occurred during the process, in order to determine anomalies of a chosen type, and
• automatically determining an indicator representative of the metric, then a correlation between the determined anomalies and the indicator, and then at least one rule defining the correlation, and
• a monitoring process, including:
• automatically analysing, periodically and group after group, newly generated first data, by checking whether at least one value of the indicator, determined on the basis of the afore the data, satisfies the determined rule, in order to predict the occurrence of the anomaly in a future group of first data when the at least one value satisfies the rule.