Visual Analytics Intent Inference for Natural Language Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data visualization systems struggle to accurately infer user intent from natural language queries, leading to limited and restrictive visualizations that require expert modeling or simple closed-ended questions, failing to support intuitive and effective analytical workflows for non-experts.
Innovation Solution
A natural language interface within data visualization applications that uses context and intent to model transitions in visual analytical conversations, inferring user intent through cue words or phrases to generate interactive graphical responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expert modeling is required to create effective queries, then measurement precision of user intent is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs self-service by automatically inferring user intent from natural language queries without requiring expert modeling. The intent inference engine autonomously analyzes query patterns, extracts analytical goals, and generates appropriate visualizations, eliminating the need for users to possess expert knowledge while maintaining accurate intent understanding.
Solution Approach 2:
The patent replaces the mechanical expert modeling process with an automated computational intent inference system. Instead of requiring users to manually construct complex queries using expert knowledge, the system uses natural language processing and machine learning algorithms to automatically interpret user intent and generate visualizations from simple natural language inputs.
2Ease of operation
If simple closed-ended questions are used, then ease of operation is improved, but adaptability deteriorates
Solution Approach 1:
The natural language interface achieves universality by handling multiple types of analytical queries within a single unified system. It can process everything from simple closed-ended questions to complex open-ended analytical explorations, adapting its intent inference capabilities to match the complexity of each query while maintaining a consistent user experience.
Solution Approach 2:
The system dynamically adjusts its intent inference depth and visualization generation complexity based on the query characteristics. For simple closed-ended questions, it provides quick straightforward answers, while for complex analytical queries, it engages more sophisticated intent inference mechanisms to uncover deeper analytical goals and generate comprehensive visualizations.
3Ease of operation
If basic interactive visualizations are returned, then ease of operation is improved, but loss of information deteriorates
Solution Approach 1:
The system implements feedback by continuously monitoring user interactions with generated visualizations and using this information to refine subsequent intent inference. When users explore visualizations, the system observes their behavior patterns and uses this feedback to better understand their analytical goals, adjusting the depth and complexity of future visualizations to provide more complete information while maintaining ease of use.
Data Source
AI summary
A method uses natural language processing for visual analysis of a dataset by a computer. The computer displays a data visualization based on a dataset retrieved from a database. The computer computes an initial visualization state that includes elements corresponding to data attributes of the data visualization. The computer receives user input to specify a natural language command related to the displayed data visualization. The computer extracts cue phrases from the natural language command. The computer also determines a transitional goal, to transform the data visualization, based on the cue phrases. The computer derives an updated visualization state based on the transitional goal, by applying transitional rules to each element of the initial visualization state. The computer subsequently computes analytical functions associated with the visualization states, thereby creating functional phrases. The computer then updates the data visualization based on the functional phrases.