Survey System with Mixed Response Mediums
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing feedback mechanisms, such as surveys and usability tests, struggle to gather high-quality insights due to their structured nature, which limits the extraction of less obvious insights, and unstructured methods are costly and rely heavily on manual analysis.
Innovation Solution
A system that combines qualitative and quantitative responses to identify top-level insights through multi-modal data synthesis, using complex computing systems and machine learning to analyze mixed response mediums, enabling conversational querying and real-time follow-up questions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If structured feedback mechanisms (surveys with pre-defined questions) are used, then the scale and cost-effectiveness are improved, but the ability to gather data for less obvious insights deteriorates
Solution Approach 1:
The patent combines structured survey questions with unstructured free-response fields, merging the advantages of both approaches. The structured portion maintains scalability while the unstructured portion captures nuanced insights that predefined options might miss, resolving the contradiction between scale and information quality.
Solution Approach 2:
The system introduces an AI-powered natural language processing intermediary that automatically analyzes unstructured free-response text. This intermediary transforms qualitative feedback into quantifiable data, enabling the system to maintain both large scale collection and deep insight extraction without manual review of each response.
2Loss of information
If unstructured feedback methods (usability tests, focus groups, interviews) are used, then the quality of less obvious insights is improved, but the expense and manual analysis requirements increase significantly
Solution Approach 1:
The patent replaces the mechanical system of manual human analysis with an automated AI-based natural language processing system. This substitution maintains the ability to extract high-quality insights from unstructured data while eliminating the proportional scaling of manual labor costs, resolving the contradiction between insight quality and analysis complexity.
Solution Approach 2:
The system enables self-service analysis where the AI automatically processes and interprets unstructured feedback without requiring human reviewers. The system serves itself by automatically categorizing, analyzing, and extracting insights from free-response text, transforming a previously labor-intensive process into an automated workflow.
3Loss of information
If unstructured free-response fields are added to surveys, then the extraction of less obvious insights is improved, but the time and resources required for manual review increase
Solution Approach 1:
The system performs preliminary action by pre-processing and categorizing free-response text using AI algorithms before human review. This preliminary automated analysis filters and organizes the data, so that when human reviewers do examine the data, they are looking at pre-sorted, pre-analyzed information rather than raw unstructured text, significantly reducing the time required for deep analysis.
Data Source
AI summary
A system is configured to provide a survey interface that collects response data, including both quantitative and qualitative response data, using multiple capture mediums. Mediums used to capture response data include input forms that collect structured response data on particular questions, as well as multimedia input forms that capture and collect free form multimedia response data in video form. This mix of quantitative and qualitative response data is analyzed across multiple modalities and used to develop an indexed response dataset, which may be queried to determine a set of pre-configured insights. An insight interface visualizes these pre-configured insights and accepts additional queries to provide a query interface that draws from the static indexed response dataset to allow for dynamic, conversational querying for additional insights.