Natural Language Interface Refinement Widgets for Data Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data visualization systems require significant user effort and training to interact with and analyze complex data sets, and they lack efficient methods for updating visualizations using natural language inputs, which can be cumbersome and inefficient, especially for battery-operated devices.
Innovation Solution
A method that enables users to interact with data visualizations using natural language commands, allowing for conversational operations such as sorting, removing, and replacing data fields, with automatic updates and incremental changes displayed in a graphical user interface, utilizing a computing device with processors and memory to process and display updated visualizations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional data visualization interfaces are used, then data analysis functionality is provided, but user effort and training requirements are significant
Solution Approach 1:
The patent replaces traditional mechanical interaction methods (drag-and-drop, menu navigation, parameter configuration) with a natural language processing system. Users speak or type conversational commands like 'show me sales by region' instead of manually configuring visualization parameters, substituting complex mechanical interface operations with speech-to-text and natural language interpretation systems.
Solution Approach 2:
The system performs automatic refinement of natural language commands by displaying proposed actions and their effects before execution. The interface shows what the command will do (e.g., 'This will create a bar chart showing sales by region') and allows users to review and modify the interpretation, making the system self-correcting and reducing the need for users to understand complex underlying processes.
2Ease of operation
If natural language processing is implemented, then ease of operation improves, but processing time and energy consumption increase
Solution Approach 1:
The system implements incremental refinement where natural language commands are processed in stages. First, the system parses the basic intent and shows proposed actions. If the command is simple and unambiguous, execution follows quickly. If refinement is needed, the system iteratively presents options and updates, allowing users to intervene only when necessary. This partial processing approach reduces average energy consumption compared to full formal processing of every command.
3Loss of information
If detailed proposed actions are displayed, then user understanding improves, but interface complexity increases
Solution Approach 1:
The interface segments the proposed action information into distinct, manageable components: the action type (e.g., 'create visualization'), the visualization type (e.g., 'bar chart'), the data fields involved (e.g., 'sales', 'region'), and the expected outcome description. Each segment is presented separately and can be independently reviewed or modified by the user, making complex information processing easier without overwhelming the user.
Data Source
AI summary
A method executes at a computing device that includes a display, one or more processors, and memory. The device displays a data visualization based on a dataset retrieved from a database. The device also displays one or more first phrases in a first region. The first phrases define the data visualization. The device receives a first user input in a second region to specify a natural language command related to the displayed data visualization. In response to the first user input, the device displays one or more proposed actions. The device receives user selection of a first proposed action of the proposed actions. In response to the user selection, the device generates an updated data visualization. The device displays the updated data visualization and displays a plurality of second phrases in the first region. The second phrases define the updated data visualization.