Distributed Computational Graph for Predictive Data Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems for analyzing very large data sets are limited in their ability to combine real-time data streaming with stored data for predictive analysis, requiring rigid programming and linear configurations that cannot handle complex or changing data scenarios, and lack self-assessment and optimization capabilities.

Innovation Solution

A distributed computational graph system that allows users to construct modular streaming analytic workflows using a graphical interface, processing data streams through a directed computational graph with nodes representing workflow stages and edges representing message outputs, enabling flexible, non-linear transformations and self-modification for optimal operation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If rigid programming and linear configurations are used for data analysis, then system stability is maintained, but adaptability to complex or changing data scenarios deteriorates

Engineering Contradiction:

Improvesystem stabilityVSAvoidadaptability to complex data scenarios

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic configuration of processing components where the system can adapt its structure and behavior based on incoming data characteristics. The processing pipeline transitions from static linear configurations to dynamic graphs that can reconfigure themselves, allowing the system to maintain stability through standardized interfaces while adapting to complex data scenarios through flexible component arrangements and routing logic.

Inventive Principle:

Principle #15Dynamics

2Adaptability or versatility

If modular processing components are used, then adaptability improves, but device complexity increases

Engineering Contradiction:

Improveflexibility in data processingVSAvoidsystem configuration complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the data processing system into modular processing components that can be independently configured and deployed. Each component handles specific data transformation tasks, and they are orchestrated through a graph-based framework that manages the complexity by defining clear input-output interfaces and data flow relationships between segments.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent creates universal processing components that can perform multiple functions through configurable parameters and routing logic. A single processing component can handle different data types and transformations by adjusting its configuration, reducing the need for numerous specialized components and simplifying the overall system architecture.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Productivity

If self-assessment and optimization capabilities are added, then productivity improves, but device complexity increases

Engineering Contradiction:

Improvedata analysis speedVSAvoidsystem monitoring complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent implements feedback mechanisms where processing components monitor their own performance metrics and system state. This feedback is used to dynamically adjust processing parameters, optimize data flow routing, and trigger reconfiguration of the processing graph to improve analysis speed while maintaining manageable complexity through automated control loops.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent enables processing components to perform self-assessment and self-optimization by monitoring their own operational status and performance. Components can automatically adjust their processing logic, trigger reconfigurations, or alert system operators when optimization is needed, reducing the burden of external monitoring while improving productivity.

Inventive Principle:

Principle #25Self-service

4Measurement precision

If real-time data streaming is combined with stored data, then measurement precision improves, but loss of time in data processing increases

Engineering Contradiction:

Improvepredictive analysis accuracyVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent pre-processes and stores historical data in optimized formats and structures before real-time analysis is needed. During real-time processing, the system combines streaming data with pre-prepared stored data, avoiding the need to process entire historical datasets in real-time. This preliminary preparation maintains measurement precision by ensuring data quality while reducing processing time by eliminating redundant computation.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11507858B2Rapid predictive analysis of very large data sets using the distributed computational graph using configurable arrangement of processing components

Publication Date: 2022.11.22 QOMPLX INC

AI summary

A system for predictive analysis of very large data sets using a distributed computational graph that intelligently combines processing of a current data stream with the ability to retrieve relevant stored data in such a way that conclusions or actions may be drawn in a predictive manner. The system has a pipeline construction module that allows a user to construct a streaming analytic workflow using modular building blocks, each of which represents either an environmental orchestration stage or a data processing stage of a streaming analytic workflow, and has a pipeline processing module that receives a data stream and constructs a directed computational graph by processing the data stream through the streaming analytic workflow. The directed computational graph is used to analyze the data stream.