Pseudo-genetic meta-knowledge artificial intelligence systems and methods

• US 9,286,572 B2
• Filed: 05/20/2013
• Issued: 03/15/2016
• Est. Priority Date: 05/02/2012
• Status: Active Grant

• Current Assignee: Ether Dynamics Corporation
• Original Assignee: Ether Dynamics Corporation
• Inventors: de Anda Fast, Dominic
• Primary Examiner(s): Fennema, Robert
• Assistant Examiner(s): Sivanesan, Sivalingam
• Application Number:
  US13/897,664
• Publication Number:
  US 20140032456A1
• Time in Patent Office: 1,030 Days
• Field of Search: 700/83
• US Class Current: 1/1
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Abstract

Systems and methods for artificially intelligent physical and virtual actors including pseudo-genetic information and configured to retain meta-knowledge are described. The actors are adapted with unique behavioral and physical attributes which may independently evolve over time. The attributes may include reproduction based attributes which direct how, when, and with whom the actor reproduces and may be subject to mutation and reproductive forces. The attributes may include evaluation attributes which dictate when and how each actor evaluates their performance. The evaluation attributes may also be subject to mutation and reproductive forces. The attributes may consider meta-knowledge which is a reflection of information gathered by an actor. What and how much meta-knowledge is collected may also be expressed as one or more evolvable attributes.

Claims

1. A system for managing an autonomous actor network, the system comprising:

a metadata collector configured to obtain metadata information associated with the autonomous actor network and autonomous actors included therein;

an autonomous actor, said autonomous actor including a self-assessment identifier indicative of;

metadata elements stored by the autonomous actor,

a quantity of metadata information for each metadata element stored by the autonomous actor, and

a relationship between the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element, wherein the relationship includes a threshold result; and

a processor configured to generate an assessment value for the autonomous actor based on the obtained metadata information and the self-assessment identifier, wherein the processor is configured to generate the assessment value at least in part by comparing the threshold result to a combination of the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element in accordance with an identified process.

2. The system of claim 1, wherein the metadata information associated with the autonomous actor network comprises at least one of network size, time, physical parameter, or boundary condition for the autonomous actor network.

3. The system of claim 1, wherein metadata information associated with autonomous actors comprises one or more of:

a measurement of a height, a width, a weight, a total surface area, a speed, an armor thickness, an engine output, a battery life, color, and a property indicating how the actor interacts with the autonomous actor network;

a classification based at least in part on the measurement;

or

a calculation based at least in part on the measurement.

4. The system of claim 1, wherein the self-assessment identifier comprises a pseudo-gene.

5. The system of claim 1, wherein the relationship identifies the process for combining the indicated metadata elements.

6. The system of claim 1, further comprising a genetic processor configured to alter the self-assessment identifier for said autonomous actor based in part on the assessment value.

7. The system of claim 6, wherein altering said self-assessment identifier comprises at least one of changing the metadata elements for the autonomous actor, the quantity of metadata information stored by the autonomous actor, or the relationship between the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element.

8. The system of claim 6, wherein said altering is based on a control-sequence including one or more values indicating which actors of the plurality of autonomous actors will contribute to the self-assessment identifier and a contribution from each of the indicated actors.

9. The system of claim 1, wherein the autonomous actor comprises a physical device having a memory configured to store the self-assessment identifier.

10. The system of claim 1, wherein the autonomous actor comprises a virtual actor instantiated by an electronic device, the virtual actor configured to store the self-assessment identifier in a portion of a memory in communication with the electronic device.

11. The system of claim 1, wherein the assessment value identifies a quantity of an overall goal achieved by the associated autonomous actor.

12. A method of managing an autonomous actor network, the method comprising:

obtaining, by a network management computing system comprising computer hardware, metadata information associated with the autonomous actor network and autonomous actors included therein;

associating, by the network management computing system, a self-assessment identifier with an autonomous actor, the self-assessment identifier indicative of;

metadata elements stored by the autonomous actor,

a quantity of metadata information for each metadata element stored by the autonomous actor, and

a relationship between the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element, wherein the relationship includes a threshold result; and

generating, by the network management computing system, an assessment value for the autonomous actor based on the obtained information and the self-assessment identifier, wherein generating the assessment value includes comparing the threshold result to a combination of the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element in accordance with an identified process.

13. The method of claim 12, wherein the self-assessment identifier comprises a pseudo-gene.

14. The method of claim 12, wherein the relationship identifies the process for combining the indicated metadata elements.

15. The method of claim 12, further comprising altering the self-assessment identifier for said autonomous actor based in part on the assessment value.

16. The method of claim 15, wherein altering said self-assessment identifier comprises at least one of changing the metadata elements for the autonomous actor, the quantity of metadata information stored by the autonomous actor, or the relationship between the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element.

17. The method of claim 15, wherein the altering is based on a control-sequence including one or more values indicating which actors of the plurality of autonomous actors will contribute to the self-assessment identifier and a contribution from each of the indicated actors.

18. A non-transitory computer-readable storage medium comprising instructions executable by a processor of an apparatus to cause the apparatus to:

obtain metadata information associated with an actor network and autonomous actors included therein;

associate a self-assessment identifier with an autonomous actor, the self-assessment identifier indicative of;

metadata elements stored by the autonomous actor,

a quantity of metadata information for each metadata element stored by the autonomous actor, and

a relationship between the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element, wherein the relationship includes a threshold result; and

generate an assessment value for the autonomous actor based on the obtained information and the self-assessment identifier, wherein generating the assessment value includes comparing the threshold result to a combination of the metadata elements for the autonomous actor and the quantity of metadata information stored for each metadata element in accordance with an identified process.