Representation and processing of information related to real world events

Abstract

Event based analysis plays an important role in reducing the latency of information delivery in an event driven world. Also, the perception of an 'event' by a user is at a higher level (a meta event), and would involve the analysis of several less complex or lower order events (basic events) in order to convey meaningful information. This is especially true of real world events and it is often necessary to completely capture the attributes of events and the relationships between them, so that the process of retrieval of event related information is efficient. In this paper, we discuss a formal system for representing and analyzing real world events. The event representation discussed in this paper accounts for three important event attributes, namely, time, space, and label. We introduce the notion of sequence templates that appears natural for capturing event related semantics; and in semantically analyzing user queries. To harness this potential, we present a formal structure to represent the queries related to real world events as well as an approach to semantically analyze a user query, and collate event related information to be dispatched to the user. Finally, we discuss the design and implementation of the Query-Event Analysis System (QEAS), which is an integrated system to (a) identify a best-matching sequence template(s) given a user query; (b) derive the meta-events based on the selected sequence templates; and (c) and use the meta-event information to answer the user query.