AI Data Broker Channel for Topic-Based Industrial Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial data analysis systems face inefficiencies in deriving value from large datasets due to the need to process unstructured and uncorrelated data, leading to high storage and processing costs, and often produce spurious correlations that require human verification.
Innovation Solution
The implementation of a smart gateway platform that leverages domain expertise to selectively stream relevant industrial data subsets, pre-defining correlations and causalities, and using smart tags to label data items based on analytic topics, thereby reducing the data space for AI analytics and enhancing data contextualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all industrial data is processed and stored for AI analytics, then comprehensive analysis coverage is achieved, but storage costs and processing time increase significantly
Solution Approach 1:
The patent segments industrial data into multiple data channels based on different analytic topics (e.g., predictive maintenance, quality control, energy optimization). Each data channel contains data items labeled with specific analytic topics, allowing the system to process only relevant data subsets for each analysis task rather than processing all industrial data comprehensively.
Solution Approach 2:
The patent applies preliminary action by labeling data items with analytic topics during data collection and organization phases. This pre-categorization enables the system to quickly retrieve and process only the relevant data subsets when specific analytic tasks are initiated, avoiding the need to process all industrial data from scratch.
2Measurement precision
If domain expertise is integrated into the data broker system, then data relevance and analysis accuracy improve, but system complexity increases
Solution Approach 1:
The patent introduces an intermediary layer (the data broker system with topic labels) between raw industrial data and AI analytics applications. This intermediary organizes data by analytic topics using domain expertise, making data retrieval more efficient and relevant without requiring complex processing logic in the AI analytics systems themselves.
Solution Approach 2:
The patent changes the organizational parameter of industrial data from generic storage to topic-based classification. By adding analytic topic labels as a new parameter dimension, the system enables efficient filtering and retrieval of relevant data subsets without fundamentally altering the underlying data structure or requiring complex processing algorithms.
3Productivity
If data is pre-labeled with analytic topics, then data retrieval efficiency improves, but data processing overhead increases
Solution Approach 1:
The patent applies partial action by labeling only the necessary data items with analytic topics based on their relevance to specific business objectives. Rather than labeling all possible attributes of every data item, the system selectively applies labels to enable efficient retrieval for targeted analytics tasks, reducing unnecessary processing overhead.
Data Source
Figure 1
Figure 2a
Figure 2b
AI summary
An industrial data broker system receives contextualized industrial data from one or more industrial devices that support data modeling at the device level. The received industrial data is augmented with contextualization metadata that defines correlations between the data relevant to an analytical objective, and labels specifying analytic topics to which each data item is relevant. The broker system allows external systems, such as analytic systems, to subscribe to topics of interest, and streams a subset of contextualized device data relevant to the topic of interest to the external system for analysis.