US 2022/0019448 A1Published application

Affect-focused gamified portal builder

AssigneeBank of America Corporation

InventorsMadhusudhanan Krishnamoorthy, Ganesan Vijayan, Gurubaran Vt

Life of this patent

Estimating the term…

Loading patent…

Abstract

An adaptive gamified portal builder is provided. The portal builder may include a camera that captures video input and a microphone that captures audio input. The portal builder may identify affective features from the captured audio and video inputs. Using generative adversarial networks (GAN), the portal builder may generate a user interface (UI) output based on the affective features. Using a generator neural network, the portal builder may generate an image. Using a discriminator neural network, the portal builder may access a repository of gamified portal features associated with the cluster of affective vectors and validate the image. The portal builder may iterate through the generator network and the discriminator network to enhance the image. The portal builder may generate a UI image output comprising the enhanced image. Using a UI encoder, the portal builder may generate source code for the UI image output.

Claims15

Dependent claims

A system for building an affect-focused gamified portal, the system comprising:

a camera, configured to capture a video input from a user;
a microphone, configured to capture an audio input from a user;
machine-readable memory configured to store the video input and the audio input;
and
a processor configured to:
identify a plurality of affective features from the captured audio and video inputs;
generate, based on the plurality of affective features, a plurality of affective vectors corresponding to a user engagement level and store the affective vectors in the machine-readable memory in association with a user identifier;
cluster the set of affective vectors into clusters based at least in part on the user engagement level;
using a generative adversarial network (GAN), generate a first layer user interface (UI), the generating comprising:
receiving a cluster of affective vectors;
using a first generator neural network, generating a first image, the first image based at least in part on the affective vectors;
using a first discriminator neural network, accessing a repository of gamified portal features associated with the cluster of affective vectors and validating the first image;
iterating through the first generator network and the first discriminator network to enhance the first image;
and
generating a first layer UI output comprising the enhanced first image;
using the GAN, generate a second layer UI, the generating comprising:
receiving the first layer UI output and a first base portal feature;
using a second generator neural network, generating a second image, the second image based at least in part on the first layer UI output and the first base portal feature;
using a second discriminator neural network, accessing the repository of gamified portal features associated with the cluster of affective vectors and validating the second image;
iterating through the second generator network and the second discriminator network to enhance the second image;
and
generating a second layer UI output comprising the enhanced second image;
using the GAN, generate a third layer UI, the generating comprising:
receiving the second layer UI output and a second base portal feature;
using a third generator neural network, generating a third image, the third image based at least in part on the second layer UI output and the second base portal feature;
using a third discriminator neural network, accessing the repository of gamified portal features associated with the cluster of affective vectors and validating the third image;
iterating through the generator network and the discriminator network to enhance the third image;
and generating the third layer UI output comprising the third enhanced image;
and
using a UI encoder, receive the third layer UI output and generate corresponding source code for the portal.

27 more elements

A method for building an affect-focused gamified portal, the method executed via computer-executable instructions run on a processor, the method comprising:

receiving captured video input from a camera;
receiving captured audio input from a microphone;
storing the video input and audio input in machine-readable memory;
identifying a plurality of affective features from the captured audio and video inputs;
generating a plurality of affective vectors corresponding to a user engagement level;
storing the affective vectors in the machine-readable memory in association with a user identifier;
clustering the plurality of affective vectors into clusters based at least in part on the user engagement level;
using a generative adversarial network (GAN), generating a first layer user interface (UI), the generating comprising:
receiving a cluster of affective vectors;
using a first generator neural network, generating a first image, the first image based at least in part on the affective vectors;
using a first discriminator neural network, accessing a repository of gamified portal features associated with the cluster of affective vectors and validating the first image;
iterating through the first generator network and the first discriminator network to enhance the first image;
and
generating a first layer UI output comprising the enhanced first image;
using the GAN, generating a second layer UI, the generating comprising:
receiving the first layer UI output and a first base portal feature;
using a second generator neural network, generating a second image, the second image based at least in part on the first layer UI output and the first base portal feature;
using a second discriminator neural network, accessing the repository of gamified portal features associated with the cluster of affective vectors and validating the second image using;
iterating through the second generator network and the second discriminator network to enhance the second image;
and
generating a second layer UI output comprising the enhanced second image;
using the GAN, generate a third layer UI, the generating comprising:
receiving the second layer UI output and a second base portal feature;
using a third generator neural network, generating a third image, the third image based at least in part on the second layer UI output and the second base portal feature;
using a third discriminator neural network, accessing the repository of gamified portal features associated with the cluster of affective vectors and validating the third image;
and
iterating through the generator network and the discriminator network to enhance the third image;
and
generating the third layer UI output comprising the third enhanced image;
using a UI encoder, receiving the third layer UI output and generating corresponding source code for the portal.

27 more elements

One or more non-transitory computer-readable media storing computer-executable instructions which, when executed by a processor on a computer system, perform a method for building an affect-focused gamified portal, the method comprising:

receiving captured video input from a camera;
receiving captured audio input from a microphone;
storing the video input and audio input in machine-readable memory;
identifying a plurality of affective features from the captured audio and video inputs;
generating a plurality of affective vectors corresponding to a user engagement level;
storing the affective vectors in the machine-readable memory in association with a user identifier;
clustering the plurality of affective vectors into clusters based at least in part on the user engagement level;
using a generative adversarial network (GAN), generating a first layer user interface (UI), the generating comprising:
receiving a cluster of affective vectors;
using a first generator neural network, generating a first image, the first image based at least in part on the affective vectors;
using a first discriminator neural network, accessing a repository of gamified portal features associated with the cluster of affective vectors and validating the first image;
iterating through the first generator network and the first discriminator network to enhance the first image;
and
generating a first layer UI output comprising the enhanced first image;
using the GAN, generating a second layer UI, the generating comprising:
receiving the first layer UI output and a first base portal feature;
using a second generator neural network, generating a second image, the second image based at least in part on the first layer UI output and the first base portal feature;
using a second discriminator neural network, accessing the repository of gamified portal features associated with the cluster of affective vectors and validating the second image using;
iterating through the second generator network and the second discriminator network to enhance the second image;
and
generating a second layer UI output comprising the enhanced second image;
using the GAN, generate a third layer UI, the generating comprising:
receiving the second layer UI output and a second base portal feature;
using a third generator neural network, generating a third image, the third image based at least in part on the second layer UI output and the second base portal feature;
using a third discriminator neural network, accessing the repository of gamified portal features associated with the cluster of affective vectors and validating the third image;
and
iterating through the generator network and the discriminator network to enhance the third image;
and
generating the third layer UI output comprising the third enhanced image;
using a UI encoder, receiving the third layer UI output and generating corresponding source code for the portal.

27 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/933,061Filed 20 Jul 2020
Published: 20 Jan 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification15 codes

G06F 3/011
Input arrangements or combined input and output arrangements for interaction between user and computer: arrangements for interaction with the…
G06F 9/451
Arrangements for executing specific programs: execution arrangements for user interfaces
G06F 3/005
Specific input/output arrangements not covered by G06F3/01 - G06F3/16: input arrangements through a video camera
G06N 3/044
Architecture, e.g. interconnection topology: recurrent networks, e.g. Hopfield networks