AUTONOMOUS BIOLOGICALLY BASED LEARNING TOOL

• US 20110131162A1
• Filed: 03/08/2008
• Published: 06/02/2011
• Est. Priority Date: 03/08/2008
• Status: Active Grant

• Current Assignee: Tokyo Electron Limited
• Original Assignee: Tokyo Electron Limited
• Inventors: Kaushal, Sanjeev, Patel, Sukesh Janubhai, Sugishima, Kenji
• Granted Patent: US 8,190,543 B2
• Time in Patent Office: Days
• US Class Current: 706/13
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

An autonomous biologically based learning tool system and a method that the tool system employs for learning and analysis are provided. The autonomous biologically based learning tool system includes (a) one or more tool systems that perform a set of specific tasks or processes and generate assets and data related to the assets that characterize the various processes and associated tool performance; (b) an interaction manager that receives and formats the data, and (c) an autonomous learning system based on biological principles of learning. The autonomous learning system comprises a memory platform and a processing platform that communicate through a network. The network receives data from the tool system and from an external actor through the interaction manager. Both the memory platform and the processing platform include functional components and memories that can be defined recursively. Similarly, the one or more tools can be deployed recursively, in a bottom-up manner in which an individual autonomous tools is assembled in conjunction with other (disparate or alike) autonomous tools to form an autonomous group tool, which in turn can be assembled with other group tools to form a conglomerated autonomous tool system. Knowledge generated and accumulated in the autonomous learning system(s) associated with individual, group and conglomerated tools can be cast into semantic networks that can be employed for learning and driving tool goals based on context.

Claims

1. An autonomous biologically based semiconductor tool system comprising:

an adaptive inference engine that analyzes data and infers an action to perform based at least in part on a process goal; and

a component that evolves the process goal based at least in part on one of data or a context change.

2. The system of claim 1, the data includes at least one of intrinsic data or extrinsic data, wherein the intrinsic data is generated through a functionality of the component that evolves the process goal and extrinsic data is received by said component.

3. The system of claim 1, further comprising:

a tool system that performs a task, the tool includes a sensor component that generates data that characterizes the task;

an interaction component that receives the generated data, the interaction component includes an adaptor that packages the data and conveys the packaged data; and

an autonomous learning system that receives the packaged data and generates a knowledge that characterizes the received data and the performance of the tool.

4. The system of claim 3, the interaction component further comprises an interaction manager that facilitates data exchange with an external actor.

5. The system of claim 4, at least one of the generated data or the data exchanged with actor includes training data, wherein the training data.

6. The system of claim 5, the training data further includes at least one of an identification of a tool variable associated with the task;

a functional relationship among two or more tool variables associated with the task;

a causal graph that includes a set of a priori probabilities associated with a set of tool variables related to the task and present in the causal graph and a set of conditional probabilities that relate one or more tool variables related to the task and present in the causal graph;

or a set of parameters that describe a behavior of the tool.

7. The system of claim 3, the autonomous learning system comprises a memory platform that stores the knowledge, wherein the memory platform includes a hierarchy of memories.

8. The system of claim 7, the autonomous learning system comprises a platform that processes the received packaged data, wherein the platform includes a set of functional units that operate on the received packaged data.

9. The system of claim 8, wherein a knowledge network facilitates communication among the hierarchy of memories in the memory platform, the set of functional units in the platform that processes the packaged data, or a combination thereof.

10. The system of claim 7, the hierarchy of memories includes a long term memory, a short term memory, and an episodic memory.

11. The system of claim 9, the set of functional units includes a memory platform and a platform that processes data.

12. The system of claim 11, the set of functional units includes at least one unit that identifies a degradation condition of the tool.

13. The system of claim 12, the at least one unit that identifies a degradation condition of the tool further identifies a canonical pattern of data, said unit stores the canonical pattern of data.

14. The system of claim 12, the at least one unit that identifies a canonical pattern of data compares two or more canonical patterns of data.

15. The system of claim 11, the set of functional units includes at least one unit that identifies a set of relationships among the received packaged data.

16. The system of claim 11, the set of functional units includes at least one unit that identifies a performance condition of the tool.

17. The system of claim 16, the at least one unit that identifies a performance condition of the tool ranks a set of points of failure through an assignment and propagation of a failure probability to each point of failure in the set.

18. The system of claim 10, the long term memory stores a set of concepts, wherein the set of concepts includes at least one of an entity, a relationship, or a procedure.

19. The system of claim 18, wherein a concept in the set of concepts includes a first numeric attribute that indicates the relevance of a concept to a current state of the tool, and a second numeric attribute that indicates the degree of difficulty to use the concept.

20. The system of claim 10, a content stored in the short term memory is temporary.

21. A method for learning in an autonomous biologically based semiconductor tool system, the method comprising:

establishing a goal;

receiving data associated with the goal;

generating knowledge from the received data;

storing the generated knowledge;

utilizing the generated or stored knowledge to determine at least one of the goal is accomplished or the goal is to be changed; and

changing the goal according to a context extracted from the generated or stored knowledge.

22. The method of claim 21, generating knowledge from the received data further comprising:

determining a state of a component that pursues the goal;

determining a set of concepts which can be applied to the state of the component that pursued the goal; and

adjusting a situation score for each concept in the set of concepts.

23. The method of claim 22, the situation score for each concept comprising at least a metric that indicates a suitability of the concept and a metric that indicates the complexity to employ the concept to evolve the pursued goal.

24. The method of claim 21, further comprising:

associating a set of concepts to a set of data types;

determining a semantic network for a set of concepts according to a set of priorities determined for each concept in the set of concepts, a priority in the set of priorities defines a situation score; and

propagating the set of priorities over the semantic network to make an inference.

25. The method of claim 22, the semantic network comprises a set of priority-based sub-networks, the sub-networks linked to a determined class of concepts.

26. The method of claim 25, a class of concepts includes at least a functional concept class.

27. The method of claim 23, the metric that indicates the suitability of a concept to evolve a goal is a function of time.

28. The method of claim 23, the metric that indicates the complexity to employ a concept to evolve a goal is a function of time.

29. The method of claim 21, the goal comprises a process that is performed by a tool system.

30. The method of claim 21, utilizing the generated or stored knowledge further comprising optimizing the goal to be accomplished.

31. The method of claim 21, utilizing the generated or stored knowledge further comprising:

devising a plan for maintaining the autonomous biologically based tool system; and

executing the devised plan.

32. The method of claim 31, devising a plan for maintaining the autonomous biologically based system tool system comprising conducting a root cause analysis.

33. The method of claim 32, wherein executing the devised plan entails performing at least one of scheduled or unscheduled preventive maintenance on the autonomous biologically based tool system.

34. The method of claim 33, wherein the at least one of scheduled or unscheduled preventive maintenance is to be conducted at least in one of a periodic interval or an ad hoc instance.

35. The method of claim 21, the data associated with the goal is at least one of a training data set or a production data set.

36. The method of claim 21, wherein the data comprises intrinsic data, the intrinsic data is generated while pursuing the goal.

37. The method of claim 21, wherein the data comprises extrinsic data generated or received while conducting a process ancillary to pursuing the goal.

38. A computer program product including a computer-readable storage medium comprising a set of instructions that when executed by a computer cause the computer to perform the following acts:

learning in an autonomous biologically based tool system, the method comprising;

receiving data, the data includes training data and production data;

generating knowledge from the received data;

storing the generated knowledge; and

utilizing the generated or stored knowledge.