Automated Taxonomy System for Real-Time Data Stream Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current real-time systems in the petroleum industry lack the ability to automatically differentiate between various data streams from sensors and IoT devices, making manual differentiation increasingly challenging due to the growing number of signals and decreasing subtleties between them, which hinders effective business intelligence analysis.
Innovation Solution
An automatable signal discovery and taxonomy system that identifies the source of incoming data streams and associates them with descriptive taxonomies, allowing for automatic mapping and storage as facts and dimensions in a business intelligence data repository, reducing human intervention and errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If manual differentiation of data streams is used, then initial system setup can be performed, but human effort and errors increase significantly as the number of signals grows
Solution Approach 1:
The patent segments the complex task of data stream identification into multiple hierarchical taxonomic levels (e.g., asset type, equipment category, sensor type). This segmentation allows the system to break down the overwhelming complexity of differentiating hundreds of data streams into manageable classification stages, reducing both human effort and error rates while maintaining systematic organization.
Solution Approach 2:
The patent creates a universal taxonomy framework that can automatically classify data streams from multiple sources (different rigs, platforms, sensor types) using a single standardized system. This multi-functional taxonomy serves as a universal language for organizing diverse data streams, eliminating the need for source-specific manual classification approaches.
2Quantity of substance
If the number of sensors and IoT devices increases, then more comprehensive data collection is achieved, but manual differentiation becomes increasingly challenging
Solution Approach 1:
The patent implements a self-service automated classification system that independently identifies and categorizes data streams without requiring manual intervention. The system uses embedded logic and algorithms to automatically differentiate incoming data streams, allowing the system to serve itself in organizing increasingly large volumes of data from expanding sensor and IoT device networks.
Solution Approach 2:
The patent replaces the mechanical manual process of data stream differentiation with an automated computational system. Instead of engineers manually examining and categorizing each data stream, the system uses automated algorithms, pattern recognition, and taxonomy matching to substitute human manual operations with machine-based classification, significantly improving ease of operation as data volume increases.
3Productivity
If automated identification techniques are implemented, then human effort is reduced, but system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-establishing comprehensive taxonomic frameworks and classification rules before data streams arrive. The system prepares the classification structure in advance, so when data streams come in, they can be automatically matched against pre-defined categories using straightforward comparison logic. This preliminary preparation reduces the computational complexity required during actual data processing while maintaining high productivity.
Solution Approach 2:
The patent introduces a taxonomy framework as an intermediary layer between raw data streams and analysis processes. This intermediary structure acts as a mediator that translates diverse data streams into a standardized format, simplifying the automated identification process. The taxonomy serves as a buffer that reduces the direct complexity of matching and differentiating raw data while enabling efficient automated processing.
Data Source
AI summary
Introduced herein are techniques that can create descriptive taxonomies of expected data streams and identify and associate each incoming data stream with the taxonomies automatically. The introduced techniques can significantly reduce the human intervention and efforts and hence the number of human errors in identifying and mapping signals. The introduced techniques can also automatically store values of the data streams and their corresponding taxonomies as facts and dimensions in a business intelligence (BI) data repository/warehouse. Doing so, the techniques create a BI data repository with various sets of logically nested dimensions and facts that can be used to analyze performances of various assets in petroleum service environment. Leveraging their similar hierarchical structures and elements, the techniques can expand and combine taxonomies and allow an end user to, not only analyze performances of assets in a specific rig, but across multiple rigs and projects, which were not possible before.