Intelligent Tutor Visual Dialog System

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Intelligent tutor systems have isolated text-based communication interfaces from graphical learning interfaces, limiting seamless interaction and integration between user inputs across different components of the system.

Innovation Solution

A method and system that utilize machine learning classifiers to translate text inputs into visual actions or objects, generating program code statements to modify the visualization interface, and vice versa, enabling dynamic integration and enhanced communication between text-based and graphical components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If text-based communication interface and graphical learning interface are kept isolated, then system simplicity is maintained, but interaction seamlessness and integration are limited

Engineering Contradiction:
Improveinteraction seamlessnessVSAvoidsystem integration complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent merges the text-based communication interface and graphical learning interface into a unified system where both interfaces can interact seamlessly. The natural language processing module bridges these interfaces by translating user intents from text input into graphical actions and vice versa, allowing users to interact with graphical elements through natural language while maintaining system manageability through modular architecture.

Inventive Principle:
Principle #5Merging (Combining)

2Adaptability or versatility

If machine learning classifiers are used to translate text inputs to visual actions, then interaction functionality is enhanced, but processing time and computational resources increase

Engineering Contradiction:
Improveinterface integration capabilityVSAvoidinput processing time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing and understanding user intents before full execution. The natural language processing module analyzes and categorizes user intents in advance, preparing the translation to graphical actions or code statements beforehand, which reduces the actual execution time when users interact with the system.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If text-based interface is integrated with graphical components, then user interaction capability improves, but system complexity increases

Engineering Contradiction:
Improveuser interaction capabilityVSAvoidsystem architecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary natural language processing module that mediates between the text-based communication interface and graphical learning components. This intermediary translates user intents from text into graphical actions and vice versa, enabling seamless integration without directly coupling the text and graphical systems, thus managing complexity through abstraction.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11144810B2Enhanced visual dialog system for intelligent tutors
Publication Date: 2021.10.12 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US11144810B2 patent drawing
  • US11144810B2 patent drawing
  • US11144810B2 patent drawing

AI summary

Systems, methods, and computer program products to perform an operation comprising receiving text input via a chat interface of a tutor application, identifying, by at least one classifier applied to the text input, a concept in the text input, mapping the concept in the text input to at least one of a visual action and a first visual object, generating, based on a first machine learning (ML) model, a first program code statement corresponding to the at least one of the visual action and the first visual object, and executing the first program code statement to modify a visualization interface of the tutor application based on the text input received via the chat interface.