Abstract: A method and apparatus for executing a service of a server computer system for a client system are described. The method may include defining a client system descriptor file that includes a set of signals suitable for input into a large language machine learning model (LLM), and collecting data associated with a first client system that is representative of the set of signals. The data can then be compressed into the set of signals for a first client system descriptor file allocated for the client system. A query is executed using at least the first client system descriptor file as input into the LLM, and in response to an output obtained by the LLM, at least an action is executed by the service of the server computer system.

Abstract: A method and apparatus for executing a service of a server computer system for a client system are described. The method may include defining a client system descriptor file that includes a set of signals suitable for input into a large language machine learning model (LLM), and collecting data associated with a first client system that is representative of the set of signals. The data can then be compressed into the set of signals for a first client system descriptor file allocated for the client system. A query is executed using at least the first client system descriptor file as input into the LLM, and in response to an output obtained by the LLM, at least an action is executed by the service of the server computer system.

Abstract: One method includes detecting a condition associated with an event stream of a first plurality of event streams associated with a first system; determining that the event stream is associated with a second system; identifying a second plurality of event streams associated with the second system; generating, based on the condition, an event data structure comprising a first set of events identified from the first plurality of event streams and a second set of events identified from the second plurality of event streams; converting the event data structure into at least two feature vectors corresponding to the first system and the second system for one or more machine-learning models; and executing the one or more machine-learning models using the at least two feature vectors as input and outputting a likelihood of fraud for the first system or the second system.