Abstract: A method and system for detecting fraud in a telecommunications network matches information on individual calls to a series of rules (18). For each rule r, a threshold Tr is defined, and if the fit of an individual call to that rule is exceeds Tr, an alarm is generated. All call records resulting in alarms are stored within a positive matching file. Likewise, calls which just fail to meet the criteria, within a given tolerance level &THgr;, are stored in a separate negative matching file. The entries in the positive and negative matching files are then checked by skilled operators to determine which in fact represent true fraud. On the basis of those validations, a decision module within the system automatically calculates and implements the necessary changes to the thresholds Tr by means of a feedback loop.

Abstract: A services management system can provide services to a mobile user, via a combination of network platforms. The system uses "Co-operating Intelligent Software Agent" technology in a heterogeneous agent architecture to provide enough flexibility to deal with changing network constraints, for instance as the user moves. In an example, a fixed broadband network might be used in combination with radio transmitters of a mobile network. The agent architecture, involving autonomous agents working co-operatively, forms a layered system using the underlying fixed network for inter-agent communication. In an application, a mobile user might move from a cell of the mobile network which can provide relatively wide bandwidth to one which can only provide limited bandwidth. The service management system can advise the user what services are available in either cell, at what price, based on current bandwidth usage at the two locations.