Natural Language Interface for Multi-Dimensional Data Analytics

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Natural language processing in data analytics systems often results in cluttered user interfaces that distract users from understanding results, requiring complex phrasings and additional interactions, which can lead to inefficient data analytics and resource consumption.

Innovation Solution

A user interface design that integrates natural language processing with a seamless layout, featuring an interactive text box for intent expression, a historical log for previous inputs and responses, and a graphical representation of results, allowing separate scrolling and synchronization to accommodate different user preferences, thereby reducing clutter and interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If natural language processing is used to facilitate user interactions with data analytics systems, then ease of operation is improved, but the user interface becomes cluttered and difficult to understand

Engineering Contradiction:
Improveease of operationVSAvoiduser interface complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The user interface is divided into three distinct non-overlapping portions: a first portion for natural language input, a second portion for conversational history, and a third portion for graphical results. This segmentation allows each portion to serve its specific function without cluttering the overall interface, resolving the contradiction between ease of operation and interface complexity.

Inventive Principle:
Principle #1Segmentation

2Ease of operation

If conversational interactions are used to elicit user inputs, then ease of operation is improved, but users are distracted from the underlying data analytics results

Engineering Contradiction:
Improveease of operationVSAvoidfocus on data analytics results
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The interface transitions from a single-dimensional conversational view to a three-dimensional layout where natural language input, conversational history, and graphical results exist in separate spatial dimensions (portions). This allows users to access conversational features without being distracted from the analytical results, as both are visible but separated in the interface space.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Measurement precision

If complicated phrasings are required for natural language processing, then measurement precision is improved, but ease of operation deteriorates

Engineering Contradiction:
Improveprecision of data analyticsVSAvoidease of operation
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system provides autocomplete functionality that automatically suggests appropriate phrasings based on the user's partial input. This self-service feature allows users to obtain precise data analytics results without needing to master complicated phrasings, as the system assists in formulating the correct queries.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4310692A1User interface for data analytics systems
Publication Date: 2024.01.24 DATACHAT AI
  • EP4310692A1 patent drawingFigure 1
  • EP4310692A1 patent drawingFigure 2A
  • EP4310692A1 patent drawingFigure 2B

AI summary

A device configured to perform data analytics comprising a memory and a processor may be configured to perform the techniques described in this disclosure. The memory may store multi-dimensional data. The processor may present, via a user interface, a graphical representation of a format for visually representing the multi-dimensional data. The processor may also receive, via the user interface, a selection of an aspect of one or more aspects of the graphical representation of the format. The processor may further receive, via the user interface and for the aspect of the one or more aspects of the graphical representation of the format for visually representing the multi-dimensional data, an indication of a dimension of the multi-dimensional data, and associate the dimension to the aspect to generate a visual representation of the multi-dimensional data. The processor may then present, via the user interface, the visual representation of the multi-dimensional data.