Semantic Question Recommendations for Survey Response Quality

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional survey creation systems lack efficiency, accuracy, and flexibility, leading to incomplete responses, wasted computing resources, and inability to optimize surveys based on individual user needs.

Innovation Solution

A question recommendation system that provides customized suggestions for survey creation, optimizing question type, order, and phrasing by using semantic labels and survey graphs to suggest additional questions, reorder questions, and remove inefficient ones.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If conventional survey creation systems provide basic survey building tools, then individuals can create surveys, but the surveys are not optimized for response quality and completeness

Engineering Contradiction:

Improveease of survey creationVSAvoidresponse quality

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The system analyzes survey questions using natural language processing to generate semantic labels and identifies related questions from a knowledge base, providing feedback recommendations to survey creators for improving question quality, ordering, and phrasing to enhance response completion rates

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system pre-processes survey questions by generating semantic labels and identifying related questions before the survey is deployed, allowing optimization of survey structure and content in advance to improve response quality

Inventive Principle:

Principle #10Preliminary action

2Quantity of substance

If conventional survey systems send surveys to multiple respondents, then more responses are collected, but computing resources are wasted on incomplete surveys

Engineering Contradiction:

Improvenumber of responsesVSAvoidcomputing resource waste

Core Design Contradiction:

Quantity of substanceVSLoss of energy

Solution Approach 1:

The system performs preliminary optimization of survey questions using semantic analysis and knowledge base matching before deployment, improving survey quality in advance to reduce the number of incomplete responses and wasted computing resources on re-sending surveys

Inventive Principle:

Principle #10Preliminary action

3Quantity of substance

If conventional survey systems use basic question storage, then questions can be stored, but questions cannot be organized in a meaningful way across different topics and wordings

Engineering Contradiction:

Improvequestion storage capacityVSAvoidquestion organization

Core Design Contradiction:

Quantity of substanceVSLoss of information

Solution Approach 1:

The system replaces basic keyword-based storage with semantic labeling using natural language processing and vector space models, enabling meaningful organization and retrieval of survey questions based on their semantic content rather than just exact matches

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms questions into semantic representations by generating labels and computing vector embeddings, changing the organizational parameter from raw text to structured semantic data that enables meaningful categorization and retrieval

Inventive Principle:

Principle #35Parameter changes

4Ease of operation

If conventional survey systems provide fixed survey creation tools, then the system is simple to operate, but the system cannot provide customized suggestions based on user needs

Engineering Contradiction:

Improvesystem simplicityVSAvoidcustomization capability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system automatically performs semantic analysis and generates optimization suggestions without requiring manual configuration, allowing survey creators to receive personalized recommendations based on their specific survey content while maintaining system simplicity

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12380460B2Digital survey creation by providing optimized suggested content

Publication Date: 2025.08.05 QUALTRICS LLC

AI summary

The present disclosure relates to a question recommendation system that intelligently optimizes a survey being created by a user by providing customized suggestions. For example, in one or more embodiments, the question recommendation system provides a suggested question based on questions previous added by a user while creating a survey. In particular, the question recommendation system provides various recommendations to the user to further optimize a survey being created. For instance, the question recommendation system provides recommendations with respect to improving question ordering, question phrasing, and question type as well as recommends removing potentially inefficient questions.