Automated Question Validation via Collective Intelligence

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current knowledge validation methods using questions and answers are manual, slow, and biased towards specific individuals or groups, lacking uniformity and reliability due to limited expertise and manual effort.

Innovation Solution

A computer-implemented method combining machine learning algorithms with collective intelligence techniques to automate the generation, filtering, classification, and validation of questions and answers, utilizing two sources of user input and supervised learning for objective evaluation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual methods are used to generate and validate questions and answers, then expertise and knowledge accuracy can be ensured, but the process becomes slow and biased towards specific individuals or groups

Engineering Contradiction:
Improveknowledge validation reliabilityVSAvoidquestion generation speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent combines machine learning algorithms with collective intelligence methods to merge automated processing capabilities with human validation expertise. The system automatically generates questions and answers using ML, then validates them through a community of validators, achieving both speed and reliability simultaneously.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intermediary validation layer where multiple human validators review and approve automatically generated questions and answers. This intermediary step ensures quality control while allowing the bulk of question generation to be automated, resolving the contradiction between automation speed and validation reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If a small group of experts manually creates questions and answers, then knowledge accuracy is maintained, but the process is slow and lacks uniformity across different subjects

Engineering Contradiction:
Improveknowledge evaluation uniformityVSAvoidtest development time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent creates a universal system that can generate and validate questions across multiple subjects and domains using the same ML algorithms and collective intelligence framework. This universal approach ensures uniformity in evaluation standards while dramatically reducing the time required for test development compared to manual expert creation.

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

Solution Approach 2:

The system performs preliminary automated generation of questions and answers using machine learning before human validation. This preliminary action handles the time-consuming generation phase automatically, allowing human validators to focus only on reviewing and approving the pre-generated content, thus reducing overall development time while maintaining uniformity.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If manual expert validation is used for questions and answers, then quality control is achieved, but the process remains biased towards the knowledge of specific individuals

Engineering Contradiction:
Improvevalidation accuracyVSAvoidknowledge diversity
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent enables the system to serve itself by using machine learning to automatically generate questions and answers without relying on a specific group of experts. The collective intelligence of multiple validators then ensures quality control, eliminating bias towards any single individual's knowledge while maintaining validation accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent changes the parameter of validation from a small group of experts to a larger community of validators with diverse backgrounds. This parameter change increases knowledge diversity and reduces individual bias while maintaining or improving validation accuracy through the aggregation of multiple perspectives.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4099262A1Method for assessing subject knowledge using collective intelligence in combination with machine learning algorithms
Publication Date: 2022.12.07 THE WISE SEEKER SL
  • EP4099262A1 patent drawingFigure 1~2
  • EP4099262A1 patent drawingFigure 3
  • EP4099262A1 patent drawingFigure 4

AI summary

Method for the evaluation of subjects knowledge using collective intelligence in combination with machine learning algorithms that comprises: • Obtain, filter and classify questions, with their corresponding answers, of a knowledge of a given subject by means of artificial intelligence, • Validate the questions and the answers generated, filtered and classified in the previous stage, using collective intelligence for the correct classification and ordering • Review the questions validated in the previous stage for their use or discard.