Methods and systems for self-improving reasoning tools
AssigneeSchlumberger Technology Corporation
InventorsMichael Stundner, Gustavo Nunez, Georg Zangl, Andreas Al-Kinani
Life of this patent
Estimating the term…
Abstract
Implementations that integrate data-driven modeling and knowledge into self-improving reasoning systems and processes are described. For example, an implementation of a method may include determining at least one recommended action using a reasoning component having a data-driven modeling portion and a knowledge-based portion. Such determining includes integrating one or more determination aspects determined by the data-driven modeling portion, and one or more additional determination aspects determined by the knowledge-based portion.
Claims20
A method, comprising:
- determining at least one recommended action using a reasoning component having a data-driven modeling portion and a knowledge-based portion, wherein determining includes integrating one or more determination aspects determined by the data-driven modeling portion and one or more additional determination aspects determined by the knowledge-based portion.
A system, comprising:
- at least one processing component;
- a memory component operatively coupled to the at least one processing component;
- and
- one or more computer-readable instructions stored on the memory component that, when executed by the at least one processing component, configure the system to:
- determine one or more determination aspects using a data-driven modeling component;
- determine one or more additional determination aspects using a knowledge-based component;
- and
- provide a recommended action at least partially based on integrating the one or more determination aspects determined by the data-driven modeling component and the one or more additional determination aspects determined by the knowledge-based component.
A method of determining a recommended action, comprising:
- capturing a plurality of events based on one or more of key performance indicators and knowledge;
- identifying one or more possible actions using a prediction process that includes integrating a data-driven model and a knowledge-based logic;
- selecting a recommended action from the one or more identified actions;
- implementing the recommended action, including managing one or more constraints in an optimized way and to meet at least one defined objective function;
- and
- capturing an effectiveness of the implemented action into the plurality of events based on one or more of key performance indicators and knowledge.
Dependencies are inferred from the claim text.