US 10,706,356 B1Granted

System and method for understanding human level meaning using a 9-dimensional hypercube of cognitive frames

OwnerWilliam P Doyleinventor

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present invention provides for a computerized method for generation an action instruction based on cognitive learning. The present method and apparatus provides for accessing at least one neural network having a data set stored therein. The present method and apparatus determines at least one meaning data map of the data set. The meaning data map includes a plurality of cognitive frames that are embedded within a nine dimensional hypercube. For example, one embodiment may include a four frames making up a four dimensional cognitive dimension grammar that is embedded within the nine dimensional hypercube. The method and apparatus calculates a data meaning based on the at least one meaning data map. From this data meaning, the method and system then generates an action instruction.

Claims10

Dependent claims

A computerized method for generating an action instruction based on cognitive learning, the computerized method comprising:

electronically accessing at least one neural network having a data set stored therein;
retrieving the data set via a networked connection for processing by at least one processing device;
determining, via the at least one processing device, at least one meaning data map of the data set, wherein the meaning data map is a collection of data including four cognitive frames, the cognitive frames being data structures representing cognitive structures of the data therein, the four cognitive frames including at least three meaning frames and at least one fact frame, wherein the cognitive frames are stored using a nine dimensional hypercube that comprises a plurality of three dimensional hypercubes, each of the three dimensional hypercubes representing a different level of knowledge data simulating human knowledge including:
an entity multidimensional hypercube, a transform multidimensional hypercube, and a story multidimensional hypercube, and wherein the transform multidimensional hypercube is composed by applying production rule grammar to the entity multidimensional hypercube, and wherein the story multidimensional hypercube is composed by applying production rule grammar to the transform multidimensional hypercube;
for each of the cognitive frames, associating a neural network with a corresponding training data set, wherein different cognitive frames are associated with different neural networks;
training each neural network using the associated training data set;
executing the neural networks of the at least one meaning data map to calculate a data meaning wherein the at least one meaning data map includes measurements of constituent concept properties associated with words;
and
generating the action instruction based on the data meaning of the data set.

6 more elements

A system for generating an action instruction based on cognitive learning, the system comprising:

a data store having four-dimensional cognitive meaning grammar and a knowledge library stored therein;
and
at least one processor programmed with executable instructions which, when executed, cause the processor to perform a method comprising:
access the data store to retrieve the data set;
determine at least one meaning data map of the data set, wherein the at least one meaning data map is a collection of data including four cognitive frames, the cognitive frames being data structures representing cognitive structures of the data therein, the four cognitive frames including at least three meaning frames and at least one fact frame, wherein the cognitive frames are stored using a nine dimensional hypercube that comprises a plurality of three dimensional hypercubes, each of the three dimensional hypercubes representing a different level of knowledge data simulating human knowledge including:
an entity multidimensional hypercube, a transform multidimensional hypercube and a story multidimensional hypercube, and wherein the transform multidimensional hypercube is composed by applying production rule grammar to the entity multidimensional hypercube, and wherein the story multidimensional hypercube is composed by applying production rule grammar to the transform multidimensional hypercube;
for each of the cognitive frames, associate a neural network with a corresponding training data set, wherein different cognitive frames are associated with different neural networks;
train each neural network using the associated training data set
execute the neural networks of the at least one meaning data map to calculate a data meaning, wherein the at least one meaning data map includes measurements of constituent concept properties associated with words;
and
generating the action instruction based on the data meaning of the data set.

8 more elements

Dependencies are inferred from the claim text.