ML-Determined Query Results Visualizations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users, especially novice ones, face difficulties in selecting appropriate query results visualizations for large volumes of data, making it hard to glean insights, and even experienced users spend significant time and effort creating ineffective visualizations.

Innovation Solution

A supervised machine learning model is used to determine query results visualizations by converting queries into structured query tokenizations, specifically trained for visualization prediction, rather than query execution, to provide relevant visualizations for query results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users manually select query results visualizations, then they can choose appropriate visualizations for data analysis, but novice users face difficulties and experienced users spend significant time and effort

Engineering Contradiction:

Improveease of visualization selectionVSAvoidtime spent creating visualizations

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-service by automatically selecting appropriate query results visualizations using a supervised machine learning model. The model analyzes the query and data characteristics to autonomously determine the most suitable visualization type, eliminating the need for user intervention in visualization selection and thereby resolving both the ease of operation and time loss issues.

Inventive Principle:

Principle #25Self-service

2Reliability

If appropriate visualizations are selected manually, then insights can be gleaned from data, but users require expertise and extensive effort to create effective visualizations

Engineering Contradiction:

Improveeffectiveness of visualizationVSAvoiduser expertise required

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

A supervised machine learning model serves as an intermediary between the query/data and the visualization selection process. The model has been trained on structured query tokenizations and visualization preferences to automatically determine appropriate visualizations, thereby maintaining reliability of visualization effectiveness while eliminating the need for user expertise in visualization creation.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Extent of automation

If a supervised machine learning model is used to determine visualizations, then automatic visualization selection is achieved, but the model requires training data and processing time

Engineering Contradiction:

Improveautomation of visualization selectionVSAvoidmodel training and processing

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The supervised machine learning model is trained in advance using structured query tokenizations and corresponding visualization preferences. This preliminary action of training the model beforehand allows it to automatically select appropriate visualizations during query execution without requiring complex real-time processing, thereby achieving high automation while managing system complexity through pre-computed knowledge.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11941020B2Displaying query results using machine learning model-determined query results visualizations

Publication Date: 2024.03.26 MICRO FOCUS LLC

AI summary

A query is converted into a structured query tokenization. One or more query results visualizations for the query are determined by applying a supervised machine learning model to the structured query tokenization into which the query has been converted. Query results of the query are displayed using the determined query results visualizations.