Interactive artificial intelligence analytical system

1. A system comprising:

a video analyzer to convert a video signal into a plurality of human morphology features;

an audio analyzer to convert an audio signal into a plurality of human speech features;

a transformation module to transform the human morphology features and the human speech features into performance metrics for passion, content, and engagement in a current multi-feature performance vector;

combinatorial logic to generate an integration of the current multi-feature performance vector and one or more prior multi-feature performance vectors to generate a multi-session rubric;

a plurality of behavioral models each configurable as a scoring control on the combinatorial logic such that scores generated for the integration in the multi-session rubric by the combinatorial logic vary according to the behavioral model configured as a scoring control for the combinatorial logic;

wherein the combinatorial logic comprises a supervised and unsupervised machine learning system;

the multi-session rubric applied to generate visual and auditory behavioral change recommendations for a human operator; and

backpropagation logic to apply the current multi-feature performance vector from the combinatorial logic to the video analyzer and the audio analyzer.

2. The system of claim 1 , wherein the video analyzer comprises one or more models embodied in a neural network.

3. The system of claim 2 , wherein the neural network comprises at least one convolutional neural network.

4. The system of claim 2 , wherein the neural network comprises at least one convolutional neural network coupled to at least one recurrent neural network.

5. The system of claim 1 , further comprising a speech-to-text converter.

6. The system of claim 5 , further comprising a natural language processor coupled to receive text from the speech-to-text converter.

7. The system of claim 1 , the audio analyzer comprising a canny edge detector and a Fast Fourier Transform.

8. The system of claim 1 , wherein the multi-session rubric comprises scores for a plurality of second-level performance features grouped within top-level categories for passion, content, and engagement.

9. A method comprising:

converting a video signal into a plurality of human morphology features with a video analyzer;

converting an audio signal into a plurality of human speech features with an audio analyzer;

utilizing supervised and unsupervised machine learning models to transform the human morphology features and the human speech features into performance metrics for passion, content, and engagement in a current multi-feature performance vector;

generating an integration, by combinatorial logic, of the current multi-feature performance vector and one or more prior multi-feature performance vectors;

configuring one of a plurality of behavioral models as a scoring control on the combinatorial logic such that scores generated for the integration in a multi-session rubric by the combinatorial logic vary according to the behavioral features against model configured as a scoring control for combinatorial logic;

wherein the multi-session rubric comprises a plurality of second-level performance scores grouped within top-level categories of passion, content, and engagement;

applying the multi-session rubric to generate visual and auditory behavioral change recommendations for a human operator; and

applying the current multi-feature performance vector as an adaptive feedback signal to the video analyzer and the audio analyzer.

10. The method of claim 9 , wherein the video analyzer comprises one or more models embodied in a neural network.

11. The method of claim 10 , wherein the neural network comprises at least one convolutional neural network.

12. The method of claim 10 , wherein the neural network comprises at least one convolutional neural network coupled to at least one recurrent neural network.

13. The method of claim 9 , wherein transforming the human speech features is performed with a speech-to-text converter.

14. The method of claim 13 , further comprising the use of a natural language processor coupled to receive text from the speech-to-text converter.

15. The method of claim 9 , wherein the audio analyzer comprises a canny edge detector and a Fast Fourier Transform.

16. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a processor, cause a machine comprising the processor to:

convert a video signal into a plurality of human morphology features with a video analyzer;

convert an audio signal into a plurality of human speech features with an audio analyzer;

utilize supervised and unsupervised machine learning models to transform the human morphology features and the human speech features into performance metrics for passion, content, and engagement in a current multi-feature performance vector;

generate an integration, by combinatorial logic, of the current multi-feature performance vector and one or more prior multi-feature performance vectors;

configure one of a plurality of behavioral models as a scoring control on the combinatorial logic such that scores generated for the integration in a multi-session rubric by the combinatorial logic vary according to the behavioral model configured as a scoring control for combinatorial logic;

wherein the multi-session rubric comprises a plurality of second-level performance scores grouped within top-level categories of passion, content, and engagement;

apply the multi-session rubric to generate visual and auditory behavioral change recommendations for a human operator; and

apply the current multi-feature performance vector as an adaptive feedback signal to the video analyzer and the audio analyzer.

17. The non-transitory computer-readable storage medium of claim 16 , the computer-readable storage medium further including instructions that when executed by the processor, cause the machine comprising the processor to:

convert the video signal into the plurality of human morphology features using the video analyzer, wherein the video analyzer comprises one or more models embodied in a neural network;

transform the human speech features using a speech-to-text converter; and

convert the audio signal into the plurality of human speech features using the audio analyzer, wherein the audio analyzer comprises a canny edge detector and a Fast Fourier Transform.

18. The non-transitory computer-readable storage medium of claim 17 , wherein:

the neural network comprises at least one convolutional neural network; and

the neural network comprises the at least one convolutional neural network coupled to at least one recurrent neural network.