Bias-Free Big Data Analysis via Hyper-Dimensional Cubes

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current technologies lack a holistic approach for understanding and analyzing large-scale, heterogeneous big data sets, failing to provide reliable insights into both current trends and future dynamics due to their atomistic and criterion-based methods, which are not suitable for real-time, theoretically sound data collection and processing.

Innovation Solution

A computer-implemented method that imports raw data, parses it into subject-verb-object format, extracts causality relations, identifies properties and behaviors, creates associative networks, performs statistical calculations to detect asymmetric shifts, and extracts patterns to predict future scenarios, allowing for bias-free and self-predictive smart data analysis without human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional statistical analysis methods are used to process big data, then data processing can be performed with existing tools, but the analysis remains atomistic and criterion-based, failing to provide holistic insights into current trends and future dynamics

Engineering Contradiction:
Improveholistic analysis capabilityVSAvoiddata processing system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments big data into multiple data cubes organized in a hierarchical structure (hyper-dimensioned data cubes), where each cube represents a specific dimension of analysis. This segmentation allows holistic analysis by examining relationships across multiple segmented views simultaneously, rather than treating data as a single undifferentiated mass.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces hyper-dimensional data cubes that add multiple dimensions to traditional data analysis. By organizing data in multi-dimensional cubes with various hierarchical levels, the system enables holistic insights through dimensional exploration, allowing users to analyze data from different perspectives and identify patterns that single-dimensional analysis would miss.

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

2Productivity

If manual data processing and analysis is performed, then human expertise can guide the analysis process, but human bias is introduced and large quantities of data cannot be processed efficiently

Engineering Contradiction:
Improvedata processing throughputVSAvoidbias-free analysis
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements automated systems that perform data processing, analysis, and pattern recognition without human intervention. The hyper-dimensional data cube structure and associated algorithms enable the system to self-analyze big data, automatically identifying trends and generating insights. This self-service capability eliminates human bias while maintaining high processing throughput through automated computational methods.

Inventive Principle:
Principle #25Self-service

3Quantity of substance

If extensive big data sets are processed using traditional methods, then large volumes of data can be handled, but the processing lacks theoretical soundness and methodological validity for real-time analysis

Engineering Contradiction:
Improvedata volume processingVSAvoidanalysis accuracy
Core Design Contradiction:
Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent performs preliminary organization of big data into structured hyper-dimensional cubes before analysis. By pre-processing and structuring data into standardized multi-dimensional formats with defined hierarchies and relationships, the system ensures methodological soundness is established before actual analysis occurs. This preliminary structuring enables both large-scale processing and analytically rigorous results.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent transforms raw big data into structured hyper-dimensional data cubes by changing the organizational parameters from flat, unstructured formats to multi-dimensional hierarchical structures. This parameter transformation enables both efficient processing of large volumes and analytically valid results by imposing mathematically sound organizational structures on the data.

Inventive Principle:
Principle #35Parameter changes

4Reliability

If current forecasting techniques analyze single-dimensional measurements, then simple trends can be identified, but reliable insights into future dynamics and complex patterns cannot be obtained

Engineering Contradiction:
Improveprediction reliabilityVSAvoidanalysis system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a universal hyper-dimensional data cube framework that can analyze multiple dimensions simultaneously. This multi-functional structure enables the system to perform various types of analysis (trend identification, pattern recognition, predictive modeling) within a single unified framework, improving prediction reliability by considering multiple factors together rather than in isolation.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4006753A1Creating bias-free and self-predictive parameters
Publication Date: 2022.06.01 PRISMA ANALYTICS GMBH
  • EP4006753A1 patent drawingFigure 1
  • EP4006753A1 patent drawingFigure 2
  • EP4006753A1 patent drawingFigure 3

AI summary

The present invention is directed towards a computer-implemented method for creating bias-free and self-predictive smart data and for hardware independent processing of big data applications allowing an enhanced analysis of extracted parameters. The suggested method is able to automatically perform technical processes such that firstly no human ado is required and secondly the resulting data is not prone to errors. The method suggests iterations on evolving data sets and hence a bias is excluded or at least minimized in each iteration. The invention is furthermore directed towards a respectively arranged system along with a computer program product and a computer-readable medium.