AI Reasoning Problem Generator for Automated Assessment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In formal educational settings, students can easily find solutions to reasoning problems online, leading to cheating, and manual grading of submissions is time-consuming and inefficient, especially in large classes.

Innovation Solution

An AI platform that automatically generates unique reasoning problems and assesses solutions using the HyperGrader and HyperSlate modules, which include a problem generator and solution analyzer, respectively, to create and evaluate logic-based challenges without pre-existing templates, ensuring each problem has a unique solution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If problem sets are updated and mixed to reduce cheating, then reliability of assessment is improved, but loss of time for creating problems increases

Engineering Contradiction:
Improveassessment reliabilityVSAvoidtime for creating problems
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system pre-generates large pools of reasoning problems using AI before they are needed for assessment. This preliminary creation of problem banks allows instructors to quickly select and assign problems without spending time creating them at the moment of need, thus maintaining assessment reliability while reducing time loss.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The AI system generates multiple variations and instances of reasoning problems by copying and transforming logical structures. Instead of manually creating unique problems, the system automatically produces numerous problem variants that maintain the same logical validity, enabling frequent problem updates without proportional time investment.

Inventive Principle:
Principle #26Copying

2Measurement precision

If manual grading is performed to assess student solutions, then measurement precision of student understanding is improved, but loss of time for grading increases

Engineering Contradiction:
Improvestudent understanding assessmentVSAvoidtime for grading
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system implements automated grading that allows solutions to be assessed without human intervention. The AI-powered grader independently evaluates student submissions against the generated problems, providing immediate feedback on logical correctness. This self-service assessment maintains measurement precision while eliminating the time loss associated with manual grading.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual human grading with an automated computational system. The AI grader uses algorithmic logic to evaluate student solutions, substituting human manual review with automated computational assessment that achieves comparable precision without the time cost of human involvement.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If large class sizes are accommodated, then productivity of educational delivery is improved, but device complexity for monitoring and grading increases

Engineering Contradiction:
Improveeducational delivery efficiencyVSAvoidsystem complexity for assessment
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The AI-powered assessment system serves multiple functions simultaneously: it generates problems, grades solutions, provides feedback, and tracks student progress. This universal system handles all assessment tasks for large classes through a single integrated platform, improving educational delivery efficiency without proportionally increasing system complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses automated copying and transformation of logical problem structures to generate unlimited problem variants and assess corresponding solutions. This approach allows the system to scale to large class sizes without requiring proportional increases in human resources or system complexity, as the AI automatically handles the replication and evaluation of numerous student submissions.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS11526779B2Artificial intelligence platform for auto-generating reasoning problems and assessing solutions
Publication Date: 2022.12.13 MOTALEN LLC
  • US11526779B2 patent drawing
  • US11526779B2 patent drawing
  • US11526779B2 patent drawing

AI summary

An artificial intelligence (AI) logic problem platform. A disclosed system includes a first AI module having: a problem generator for automatically generating unique reasoning problems; and a solution analyzer for automatically analyzing a logic solution submitted in response to an automatically generated reasoning problem; and a second AI module includes a user interface for allowing a user to create the logic solution and output a solution file.