Method for determining relationships through use of an ordered list between processing nodes in an emulated human brain

• US 9,064,211 B2
• Filed: 04/12/2011
• Issued: 06/23/2015
• Est. Priority Date: 01/06/2004
• Status: Expired due to Fees

• Current Assignee: Neuric Technologies, LLC
• Original Assignee: Neuric Technologies, LLC
• Inventors: Visel, Thomas A.
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Gonzales, Vincent
• Application Number:
  US13/085,289
• Publication Number:
  US 20120185234A1
• Time in Patent Office: 1,533 Days
• Field of Search: 703 2- 3, 703/27, 706/41, 706/46
• US Class Current: 1/1
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 3/10 Interfaces, programming languages or software development kits, e.g. for simulating neural networks

Abstract

A method for emulating human cognition in electronic form is disclosed. Information is received in the form of a textual or voice input in a natural language. This is parsed into pre-determined phrases based on a stored set of language rules for the natural language. Then, the parsed phrases are determined as to whether they define aspects of an environment and, if so, then creating weighting factors to the natural language that are adaptive, the created weighting factors operable to create a weighted decision based upon the natural language. Then it is determined if the parsed phrases constitute a query and, if so, then using the weighted factors to make a decision to the query.

Claims

1. A method for emulating human cognition in electronic form, comprising:

receiving information in a form of a textual or voice input in a natural language;

parsing the received input into pre-determined semantic phrases based on a stored set of language rules for the natural language;

defining a plurality of concept neurons that each represent a unique concept and stored in a database of concept neurons, each of the concept neurons having relational associations with other of the concept neurons through unique weighting factors, the relational associations defining the concept associated with the concept neuron, certain of the concept neurons associated with phrases representing idioms that are associated with a unique idiom concept;

determining if the parsed semantic phrases define one of the unique idiom concepts associated with phrases representing that idiom and their associated concept neurons and, if so;

then creating a plurality of weighted relational associations to other concept neurons stored in the database that represent in the natural language a body of concepts in an ordered list of the weighted relational associations for each item in the ordered list, the created weighted relational associations operable to create a weighted relationship as the related associations to the other concept neurons from the determined defined one of the associated concept neurons and associating the ordered list with the determined defined one of the associated concept neurons associated with one or more of the concepts associated with the parsed semantic phrases determined to define the concept; and

determining if the parsed phrases determined to define the unique idiom concept associated with the phrase constitute a query and, if so, then using the weighted relational associations to make a decision to the query.

2. The method of claim 1, wherein the stored set of language rules includes fundamental concepts that underlie human personality.

3. The method of claim 1, wherein the weighting factors imply experiences.

4. The method of claim 3, wherein new experiences are associated with new weighting factors to other concept neurons.

5. The method of claim 1, wherein the step of if the parsed phrases define a concept comprises determining if the parsed phrase includes a triad of a speaker, the person/object spoken to, and the person, object or subject spoken of.