Modular, hierarchically organized artificial intelligence entity

• US 6,738,753 B1
• Filed: 08/21/2000
• Issued: 05/18/2004
• Est. Priority Date: 08/21/2000
• Status: Expired due to Fees

• Current Assignee: Michael Andrew Hogan
• Original Assignee: Michael Andrew Hogan
• Inventors: Hogan, Michael Andrew
• Primary Examiner(s): Starks, Jr., Wilbert L.
• Assistant Examiner(s): Booker, Kelvin
• Application Number:
  US09/642,356
• Time in Patent Office: 1,366 Days
• Field of Search: 706/48, 706/47, 706/12, 706/13, 706/15, 706/16, 706/25, 706/26, 706/27
• US Class Current: 706/12
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards

Abstract

A modular artificial intelligence learning entity (a “golem”) which is replicated many times to form a super-entity that shows intelligent behavior transcending that of its individual constituents. Within the group of golems, individual golems may occupy roles, and are role differentiated, in that structurally identical entities perform different functions and exhibit different behavior depending on their personas and the learning they have completed as driven by other entities. The group of golems is hierarchically organized, in the sense that ‘superior’ entities issue policies to ‘subordinate’ entities. In addition to responding to ‘sense’ input from its environment, the golem responds to policy requirements set by other entities, including its superiors, and in turn sets policy requirements for its subordinates. Actions of the golem are measured for successful compliance with that golem'"'"'s policies by its superior, who directs the golem'"'"'s learning process. The super-entity thus gains intelligence through the policy reinforcement occurring in each superior-subordinate relationship. This scheme is well adapted to working over a network with logically separated but communicating golems. Its flexibility allows its application both to single complex problems and to repetitively occurring simple problems. Opportunities for its use arise in operating environments, in simulation and gaming, and in research.

Claims

1. An artificial intelligence system for creating actual multi-entity situations and solving complex problems, comprising:

(a) a computer apparatus comprising;

(i) interface means of accepting computer-readable data input,

(ii) memory means for storing computer-readable data;

(iii) processor means for manipulating computer-readable data; and

(iv) interface means for communicating computer-readable data output,

(b) a plurality of modular artificial intelligence learning entities, similar in structure, each comprising;

(i) means of accepting sense data,

(ii) means of accepting policy instructions,

(iii) algorithmic artificial intelligence means of evaluating and making decisions, and

(iv) means of implementing actions; and

(c) a means of hierarchically arranging said modular artificial intelligence learning entities into superior-subordinate relationships, each of said superior-subordinate relationships comprising;

(i) a means for issuance of policy instructions by said superior modular artificial intelligence learning entity for said subordinate modular artificial intelligence learning entity, and

(ii) a means for evaluation of success and reinforcement of the algorithmic artificial intelligence process of said subordinate modular artificial intelligence learning entity by said superior modular artificial intelligence learning entity.

2. The artificial intelligence system of claim 1, wherein the hierarchical arrangement of said modular artificial intelligence learning entities is at any moment organized in a superior-subordinate form, and these superior-subordinate relationships may be changed by policy as time passes.

3. The artificial intelligence system of claim 1, further including at least one foreign artificially-intelligent entity.

4. The artificial intelligence system of claim 3, further including a means whereby each of said foreign artificially-intelligent entities can interface with said modular artificial intelligence learning entities.

5. The artificial intelligence system of claim 1, further including at least one human being.

6. The artificial intelligence system of claim 5, further including a means whereby each of said human beings can interface with said modular artificial intelligence learning entities.

7. The artificial intelligence system of claim 1, further including a means of role differentiation of said modular artificial intelligence learning entities, comprising:

(a) a means for assigning to each modular artificial intelligence learning entity a collection of policies,

(b) a means for assigning to each modular artificial intelligence learning entity a collection of action types, and

(c) a means for assigning a unique role to each unique collection of policies and action types,

whereby said modular artificial intelligence learning entities having different roles are role differentiated.

8. The artificial intelligence system of claim 7, further including a means of behavior differentiation among said modular artificial intelligence learning entities having a same role, comprising:

(a) a means for assigning to each modular artificial intelligence learning entity a collection of meaningful sense statements,

(b) a means for assigning to each modular artificial intelligence learning entity a set of decision-making weights, and

(c) a means for assigning a unique persona to each unique collection of role, sense statements, and weights;

whereby two of said modular artificial intelligence learning entities having identical roles and different weights or collections of sense statements thereby exhibit variation of behavior.

9. The artificial intelligence system of claim 8, further including a means for introducing new sense statements and policies to said modular artificial intelligence learning entities.

10. An individual artificially intelligent entity, comprising:

(a) A means for evaluating and making decisions,

(b) A means for formally separating the evaluation means into three categories of information, comprising;

(i) senses,

(ii) policies, and

(iii) actions,

(c) A means for transforming said actions into policies for other individual artificially intelligent entities,

(d) A means for enabling said policies of said individual artificially intelligent entity to comply with reinforcement directives set by other individual artificially intelligent entities, and

(e) A means for defining said artificially intelligent entity as superior to subordinate entities selected from the group consisting of foreign artificially intelligent entities, foreign non-intelligent entities, human beings, and other instances of the individual artificially intelligent entity.

11. The individual artificially intelligent entity of claim 10, further including a means for organizing said senses into sense statements.

12. The individual artificially intelligent entity of claim 11, wherein said means for organizing senses into sense statements includes a means for building complex statements from combinations of said sense statements.

13. The individual artificially intelligent entity of claim 12, further including a means for generating additional complex statements for use by said evaluation means of said individual artificially intelligence entity.

14. The individual artificially intelligent entity of claim 10, further including a means for determining success of said subordinate entity'"'"'s actions in complying with policies set by said individual artificially intelligent entity.

15. The individual artificially intelligent entity of claim 14, wherein said means for determining success is receipt of said reinforcement directives from said superior entities.

16. The individual artificially intelligent entity of claim 14, wherein the actions of said individual artificially intelligent entity are transformed into a policy for said subordinate entities directing compliance with a reinforcement directive.