Custom Query Engine for Industrial Process Data Visualization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users of industrial process control systems require SQL expertise to create custom queries, leading to reliance on R&D teams for query preparation and manual data consolidation, which is time-consuming and inefficient.

Innovation Solution

A computer-implemented method using a machine learning custom query engine that builds a training dataset from system data, generates domain models, and executes custom queries based on user input, eliminating the need for SQL expertise and automating data access and visualization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users manually create custom queries using SQL or Advanced Query tools, then query functionality is achieved, but user expertise requirement and time consumption increase significantly

Engineering Contradiction:
ImproveQuery creation easeVSAvoidTime for query preparation and data consolidation
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system enables users to create custom queries through natural language input without requiring SQL expertise. The natural language processing engine automatically translates user-friendly queries into executable database queries, allowing users to serve themselves without relying on R&D teams for query preparation.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

A natural language processing intermediary layer is introduced between the user and the database system. This intermediary translates natural language queries into SQL or other database query languages, eliminating the need for users to learn complex query syntax while maintaining full database access capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If R&D teams prepare and validate custom queries for users, then query accuracy is improved, but development complexity and time loss increase

Engineering Contradiction:
ImproveQuery validation reliabilityVSAvoidR&D team dependency complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system includes built-in validation and error handling mechanisms that automatically check query correctness and provide feedback to users. This self-validation capability eliminates the need for R&D teams to manually verify queries while maintaining high reliability through automated testing and correction.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system provides immediate feedback to users about query validity, data availability, and potential errors. This real-time feedback loop allows users to correct issues without R&D intervention, maintaining query reliability while reducing dependency on expert teams.

Inventive Principle:
Principle #23Feedback

3Productivity

If users manually consolidate query results and prepare analytics, then data analysis is achieved, but productivity and time efficiency decrease

Engineering Contradiction:
ImproveData analysis productivityVSAvoidTime for data consolidation and report preparation
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system merges query execution, data consolidation, analytics generation, and report creation into a single automated workflow. When a user submits a natural language query, the system automatically retrieves data, processes it through analytical functions, and generates visualizations or reports without requiring separate manual steps.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system automatically performs data consolidation and analytics preparation without user intervention. Built-in analytical engines process query results and generate insights, allowing users to obtain ready-to-use analytics immediately after submitting their natural language queries.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4187453A1Generating models for use in monitoring an industrial process control system
Publication Date: 2023.05.31 SCHNEIDER ELECTRIC SYSTEMS USA INC
  • EP4187453A1 patent drawingFigure 1
  • EP4187453A1 patent drawingFigure 2
  • EP4187453A1 patent drawingFigure 3

AI summary

Monitoring an industrial process by building a training dataset of system data representative of status of industrial process parameters and training a custom query engine based on the training dataset. Models are generated using the custom query engine for matching query terms to the system data in response to user input representative of the system data that the user intends to access. Executing one of the models based on the input from the user generates an output retrieving the selected system data from the data tables for visualization.