| 摘要 |
The present invention comprises an adaptive temporal correlation network (ATCN) that correlates data patterns, or events, over time. More specifically, the ATCN comprises a plurality of time slices wherein each time slice represents one or more data streams that have occurred at the same time. The ATCN assigns each data stream to a module in the time slice. The ATCN analyzes each data stream and identifies and classifies a data pattern/event found within the data stream. Once an event is found, the ATCN flags that event as active within the module and creates temporal connections between the active event and all other events within the network. The present invention also has a prediction phase in which the probability of the occurrence of future events is predicted. When predicting the occurrence of future events, the ATCN receiving an event, locates that event within the network, and traverses the temporal connections of that event to identify other events in the current time slice and other time slices that are most likely to occur.
|
