AI-Generated Data Objects for Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data visualization tools require users to have knowledge of chart options and styles, making it time-consuming for users to generate optimal visualizations, and often lead to underutilization of alternative visualization types that could provide more insight.
Innovation Solution
An AI-generated data object system that uses a large language model (LLM) to interpret natural language inputs from users and generate visualizations by selecting appropriate data columns and visualization types, thereby eliminating the need for users to navigate complex charting options.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users navigate menu choices and chart options to generate visualizations, then they can create customized charts, but the process becomes time-consuming and complex
Solution Approach 1:
The patent introduces an AI model as an intermediary between the user and the complex charting system. The user provides natural language input, and the AI model translates this into appropriate visualization parameters and chart type selections, eliminating the need for users to navigate complex menus and options directly
Solution Approach 2:
The system enables self-service by allowing the AI model to automatically select chart types, data columns, and visualization parameters based on user input and data characteristics, without requiring user expertise in data visualization principles or manual configuration of each parameter
2Loss of information
If users explore alternative visualization types, then they may gain more insight, but the learning curve and complexity increase
Solution Approach 1:
The AI model acts as an intermediary that understands various visualization types and their appropriate use cases, translating user needs into suitable chart selections without requiring users to understand the underlying complexity of different visualization approaches
Solution Approach 2:
The system dynamically changes visualization parameters based on AI analysis of the data characteristics and user intent, automatically selecting appropriate chart types and configurations that optimize insight extraction without requiring user intervention in parameter selection
3Productivity
If users gain proficiency through experience, then they can generate visualizations faster, but this requires repeated practice and time investment
Solution Approach 1:
The AI model provides automated expertise that would otherwise require users to develop through years of practice, enabling immediate high-level productivity without the time investment needed to become proficient in data visualization techniques
Solution Approach 2:
The AI intermediary encapsulates expert knowledge about data visualization best practices, chart type selection, and data analysis principles, making this expertise immediately accessible to users without requiring them to acquire it through experience
Data Source
AI summary
Technology is disclosed herein for generating a visualization of data based on an AI-generated data object. In an implementation, an application, such as a data analytics application, receives a natural language input from a user which relates to a table of data in the application. The table includes data organized according to table columns. The application generates a prompt for a large language model (LLM) service which includes the names of the table columns. The prompt tasks the LLM service with selecting columns for the visualization based on the natural language input and the names of the table columns. The prompt tasks the LLM service with generating a response in a JSON format. The application populates the JSON object, which describes the visualization, according to the response. The application then creates visualization based on the JSON object.