METHODS AND SYSTEMS THAT PREDICT FUTURE ACTIONS FROM INSTRUMENTATION-GENERATED EVENTS

• US 20170300966A1
• Filed: 03/24/2015
• Published: 10/19/2017
• Est. Priority Date: 12/26/2013
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Dereszynski, Ethan, Brayman, Vladimir, Wong, Weng-Keen
• Granted Patent: US 9,928,526 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 9/45504 Abstract machines for programme code execution, e.g. Java virtual machine [JVM], interpreters, emulators
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

The current document is directed to methods and systems that receive instrumentation-generated events and that employ statistical inference to discover event topics and to assign an action to each of a number of events and that use the actions to predict future events and actions. In a described implementation, accumulated action messages are used to build a predictive model for each monitored website and the predictive model is used, in turn, to predict future actions based on already received actions.

Claims

1. A prediction subsystem within an event-collection-and-event-processing system that includes one or more computer systems, each having one or more processors, one or more memories, and one or more mass-storage devices, the prediction subsystem executing on the one or more processors to:

receive a stream of action messages, each action message comprising a set of key/value pairs and an action assigned to the action message by an abstraction layer, the stream stored in one or more memories and/or mass-storage devices; and

for each action message received in the stream of action messages,

store the action for subsequent evaluation of predictions,

use the action to generate one or more predictions by input of the action to a predictive model,

store the one or more predictions, and

output an enhanced action message that includes the one or more predictions.