Generating event definitions based on spatial and relational relationships
Data from one or more sensors are used to detect an event corresponding to an activity by a person. The detection of the event is then used to loosely model the event to produce an initial event definition. The initial event definition is used in searching historical sensor data to detect other prospective occurrences of the event. Based on the detection of these additional occurrences, the event definition is refined to produce a more accurate event definition. The resulting refined event definition can then be used with current sensor data to accurately detect when the activity is being carried out. For example, the activity may be the use of a video imaging device for cheating, and a casino can use the refined event definition with video imaging to detect when people are using the video imaging device for such purposes.
1. A method for generating event definitions to identify an event corresponding to an activity, comprising:
(a) defining a dynamic event detection architecture;
(b) generally specifying an event that may correspond to the activity;
(c) processing historical sensor data to detect at least one instance of the event that was generally specified;
(d) using modeling language derived from the historical sensor data for the at least one instance to create an initial event definition for the event;
(e) using the initial event definition to search the historical sensor data for additional occurrences of the event;
(f) based on the additional occurrences of the event that were identified in the search of the historical sensor data, creating a refined event definition; and
(g) using the refined event definition to detect an activity corresponding to the event.