Virtual Agent Question Generation for Adaptive Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer-enabled learning systems lack the ability to converse with users and automatically generate questions tailored to specific subjects or users' histories, requiring significant manual effort from knowledge experts to create assessments.
Innovation Solution
A system and method that preprocesses input documents to detect sections, processes them through machine learning models to select and generate grammatically correct questions, and calculates answer scores, allowing for the arrangement of questions in a conversational format using a virtual agent, tailored to subjects and users' histories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual question creation by knowledge experts is used, then question quality and relevance are improved, but time consumption and manual effort increase significantly
Solution Approach 1:
The system enables self-service by allowing the virtual agent to automatically generate, select, and arrange test questions without requiring manual intervention from knowledge experts. The machine learning models process learning materials and autonomously create personalized question sets, eliminating the need for human experts to manually create assessments while maintaining question quality through AI-driven generation and selection processes
2Loss of time
If automated question generation is implemented, then time consumption is reduced, but the ability to tailor questions to specific users or subjects is worsened
Solution Approach 1:
The system applies local quality by customizing question generation to match specific user characteristics, learning histories, and subject requirements. The machine learning models analyze individual user profiles and learning materials to generate locally optimized questions tailored to each user's needs, ensuring that automated generation maintains high adaptability and personalization rather than producing generic questions
Solution Approach 2:
The system utilizes parameter changes by dynamically adjusting question characteristics based on user performance data, learning histories, and subject matter requirements. The machine learning models modify question parameters such as difficulty level, question type, and topic focus to create personalized assessments that adapt to individual user needs while maintaining automated generation efficiency
3Adaptability or versatility
If questions are arranged based on user history, then personalization is improved, but system complexity increases
Solution Approach 1:
The system replaces complex manual curation processes with machine learning-based automated selection and arrangement mechanisms. Instead of requiring complex manual systems to personalize questions, the patent uses AI models that automatically analyze user history and learning materials to generate personalized question sequences, substituting mechanical complexity with intelligent automation
Data Source
AI summary
The disclosed system and method focus on automatically generating questions from input of written text and/or audio transcripts (e.g., learning materials) to aid in teaching people through testing their knowledge about information they have previously been presented with. These questions may be presented to an end user via a conversational system (e.g., virtual agent or chatbot). The user can iterate through each question, provide feedback for the question, attempt to answer the question, and/or get an answer score for each answer. The disclosed system and method can generate questions tailored to a particular subject by using teaching materials as input. The disclosed system and method can further curate the questions based on various conditions to ensure that the questions are automatically selected and arranged in an order that best suits the subject taught and the learner answering the questions.