Conversational Data Story Recommendations Through Adaptive User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data visualization tools are difficult for users with limited data science knowledge or graphical design skills to use effectively, requiring tedious manual workflows and extensive computing resources for generating meaningful data stories.
Innovation Solution
A conversational approach that elicits user feedback through iterative inquiries to automatically generate data story recommendations, reducing the number of candidate stories based on user preferences and optimizing inquiries to minimize computing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If automated data story generation is implemented, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The patent introduces an automated data story generation system that acts as an intermediary between the user and the extensive data/visualization tools. This intermediary automatically generates data stories based on user feedback and inquiries, shielding users from the complexity of underlying data processing and visualization technologies while delivering meaningful insights.
2Adaptability or versatility
If extensive data and visualization options are provided, then adaptability is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs self-service by automatically generating data stories without requiring users to manually select from extensive data options or configure visualization parameters. The automated generation process independently navigates the vast solution space, adapting to user needs through feedback while eliminating the operational burden of exploring extensive options.
3Manufacturing precision
If manual data story creation is required, then manufacturing precision is improved, but productivity deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-generating multiple candidate data stories automatically before presenting them to the user. This preliminary automated generation maintains high data story quality through rigorous processing while significantly improving productivity by eliminating the need for users to manually create each story from scratch.
4Measurement precision
If user feedback is elicited through multiple inquiries, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system applies partial action by selectively eliciting only the necessary user feedback required to generate high-quality data stories, rather than collecting exhaustive information. The automated generation process intelligently determines the minimum viable feedback needed, maintaining measurement precision of user preferences while minimizing time loss through efficient, targeted inquiries.
Data Source
AI summary
Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating generation of data story recommendations. In one implementation, a set of candidate data stories is generated. Each candidate data story can include various data visualizations. From the set of candidate data stories, a data story recommendation is determined based on an adaptive elicitation of user feedback via a set of inquiries selected in accordance with at least one potential reduction of the set of candidate data stories. Thereafter, the data story recommendation, including a set of data visualizations is provided for display.