Systems and methods for semantic concept definition and semantic concept relationship synthesis utilizing existing domain definitions

Patent metadata

Field	Value
Publication number	US-12596741-B2
Application number	US-202418743449-A
Country	US
Kind code	B2
Filing date	Jun 14, 2024
Priority date	Aug 29, 2008
Publication date	Apr 7, 2026
Grant date	Apr 7, 2026

Abstract

A method for assessing the coherence of an input with a data processing system using synthesized concepts is provided. The method includes obtaining an active concept definition from the input of a cognitive agent, extracting real concept definitions composed of a set of attributes from an analyzed domain, matching the active concept definition to the extracted definitions, deriving virtual concept definitions from the real concept definitions using a semantic processing protocol such that the derived virtual concept definitions form a tree-structure graph of concepts and concept relationships, and measuring the attribute set coherence of the virtual concept definitions using a confidence gradient. The confidence gradient is based on at least one metric of relative proximity and co-occurrence. The method further includes assessing the probability of coherence, of the input with the data processing system, based on the measure of coherence within the confidence gradient.

First claim

The invention claimed is:

1 . A method for assessing the coherence of an input with a data processing system using synthesized concepts, the method comprising:
obtaining an active concept definition from the input of a cognitive agent; extracting a plurality of real concept definitions composed of a set of attributes from an analyzed domain; matching the active concept definition to the extracted real concept definitions; deriving a plurality of virtual concept definitions from the real concept definitions using a semantic processing protocol, such that the derived virtual concept definitions form a tree-structure graph of concepts and concept relationships; measuring an attribute set coherence of the virtual concept definitions using a confidence gradient, wherein the confidence gradient is based on at least one metric of relative proximity and co-occurrence; and assessing the probability of coherence, of the input with the data processing system, based on the measure of coherence within the confidence gradient.

2 . The method of claim 1 , wherein the cognitive agent is one of a human, multiple humans, an expert system, a neural network, and an evolutionary system.

3 . The method of claim 1 , further comprising synthesizing additional possible virtual concept definitions using the virtual concept definitions.

4 . The method of claim 1 , wherein the synthesized concepts and concept definitions are generated by the data processing system.

5 . The method of claim 1 , wherein a depth of a hierarchy of virtual concept definitions is selectable.

6 . The method of claim 5 , wherein the selection of the depth of the hierarchy is based upon the confidence gradient.

7 . The method of claim 1 , further comprising searching a plurality of domains to build a selectable quantity of virtual concept definitions.

8 . The method of claim 1 , wherein the virtual concept definitions are in a poly-hierarchal relationship with the real concept definitions.

9 . The method of claim 1 , wherein a scope of the virtual concept definitions is variable with respect to a change in a relative proximity measure between attributes in the set of attributes.

10 . The method of claim 1 , wherein the semantic processing protocol is based upon one of formal concept analysis, faceted classification synthesis, and concept inferencing.

11 . A system for assessing the coherence of an input with a data processing system using synthesized concepts, the system comprising:
at least one processor, operable to execute executable instructions stored in at least one tangible memory, to: obtain an active concept definition from the input of a cognitive agent; extract a plurality of real concept definitions composed of a set of attributes from an analyzed domain; match the active concept definition to the extracted real concept definitions; derive a plurality of virtual concept definitions from the real concept definitions using a semantic processing protocol, such that the derived virtual concept definitions form a tree-structure graph of concepts and concept relationships; measure an attribute set coherence of the virtual concept definitions using a confidence gradient, wherein the confidence gradient is based on at least one metric of relative proximity and co-occurrence; and assess the probability of coherence of the input with the data processing system based on the measure of coherence within the confidence gradient.

12 . The system of claim 11 , wherein the cognitive agent is one of a human, multiple humans, an expert system, a neural network, and an evolutionary system.

13 . The system of claim 11 , wherein the at least one processor further executes the instructions to synthesize additional possible virtual concept definitions using the virtual concept definitions.

14 . The system of claim 11 , wherein the synthesized concepts and concept definitions are generated by the data processing system.

15 . The system of claim 11 , wherein a depth of a hierarchy of virtual concept definitions is selectable.

16 . The system of claim 15 , wherein the selection of the depth of the hierarchy is based upon the confidence gradient.

17 . The system of claim 11 , wherein the at least one processor further executes the instructions to search a plurality of domains to build a selectable quantity of virtual concept definitions.

18 . The system of claim 11 , wherein the virtual concept definitions are in a poly-hierarchal relationship with the real concept definitions.

19 . The system of claim 11 , wherein a scope of the virtual concept definitions is variable with respect to a change in a relative proximity measure between attributes in the set of attributes.

20 . The system of claim 11 , wherein the semantic processing protocol is based upon one of formal concept analysis, faceted classification synthesis, and concept inferencing.

Assignees

• Primal Fusion Inc

Inventors

• Sweeney Peter
• Black Alexander David

Classifications

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F16/36 Primary

  Creation of semantic tools, e.g. ontology or thesauri · CPC title