No-Code Machine Learning UI for In-Platform Model Deployment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data visualization applications require users to build custom machine learning models outside of the data visualization environment, creating a disjointed experience that segregates predictive model builders from decision-making teams, leading to slow results delivery, errors, and irrelevance due to misunderstood requirements.

Innovation Solution

Integrating visual analytics with predictive analytics by allowing users to create and deploy no-code machine learning models directly within the data visualization platform, enabling collaboration among team members with varying backgrounds to train, understand, and operationalize models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If users build custom ML models outside the data visualization application, then model customization and flexibility are improved, but system complexity and operational difficulty increase

Engineering Contradiction:

Improvemodel customizationVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges the ML model building capability with the data visualization application by integrating a model builder that allows users to create, train, and deploy ML models directly within the visualization environment. This consolidation eliminates the need for separate external tools while maintaining model customization flexibility, thereby reducing system complexity and operational difficulty.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The data visualization application is enhanced with multi-functionality by incorporating ML model building, training, and deployment capabilities alongside existing visualization features. This universal platform allows users to perform both data visualization and predictive analytics within a single system, reducing the need to learn and switch between multiple specialized tools.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If users build custom ML models outside the data visualization application, then model building flexibility is improved, but delivery speed decreases

Engineering Contradiction:

Improvemodel building flexibilityVSAvoiddelivery speed

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

By combining model building and visualization functions in one application, the patent enables seamless integration of predictive models with visual analytics workflows. This eliminates time-consuming data extraction and model integration steps, significantly accelerating delivery speed while preserving model building flexibility through the integrated model builder.

Inventive Principle:

Principle #5Merging (Combining)

3Adaptability or versatility

If users build custom ML models outside the data visualization application, then model customization is improved, but collaboration effectiveness worsens

Engineering Contradiction:

Improvemodel customizationVSAvoidcollaboration effectiveness

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The integration of model building capabilities within the data visualization application creates a unified collaborative environment where data analysts, domain experts, and stakeholders can work together on the same platform. This eliminates silos between model builders and decision-makers, improving communication and collaboration effectiveness while maintaining full model customization capabilities.

Inventive Principle:

Principle #5Merging (Combining)

4Adaptability or versatility

If users build custom ML models outside the data visualization application, then model flexibility is improved, but error rate increases

Engineering Contradiction:

Improvemodel flexibilityVSAvoiderror rate

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

By consolidating model building within the trusted data visualization environment, the patent ensures that models are developed using the same data quality controls, validation processes, and best practices that govern the visualization workflows. This integrated approach reduces errors from data misinterpretation and requirement misunderstandings while preserving model flexibility.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS12411665B1User interface for machine learning model generation

Publication Date: 2025.09.09 TABLEAU SOFTWARE INC

AI summary

A computing device displays, in a user interface, a workflow that includes a plurality of steps. In response to user selection of a first step of the plurality of steps, the computing device displays a list of data sources. The device receives user selection of a first data source of the data sources. The device receives user input specifying a target data field from the first data source and a modeling objective for the target data field. In response to the user input, the device automatically executes a model to predict a first outcome for the target data field based on the modeling objective. The device displays results of the model. The device receives user input to deploy the model. In accordance with the user input, the device deploys the model.