Sensor Metadata Mapping Using Physical Simulation and Time-Series Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for estimating the correspondence between sensors and physical quantities in facility management systems (FMS) lack accuracy, particularly when dealing with multiple sensors of the same type, as they fail to distinguish between them effectively.
Innovation Solution
An information processing device that performs physical simulations using a physical model to estimate metadata by analyzing sensor time-series data, employing a learning model to determine the matching degree between sensor data and simulation data, thereby accurately mapping sensors to their corresponding physical quantities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If text mining method is used to generate metadata by analyzing sensor time-series data, then metadata can be generated automatically, but the accuracy of estimating correspondence between sensors and physical quantities deteriorates when there are multiple sensors of the same type
Solution Approach 1:
The patent segments the sensor data analysis by introducing unique identification information for each sensor. Even when sensors are of the same type, each sensor is treated as a separate entity with its own ID, allowing the system to distinguish between multiple sensors of the same type and accurately map each sensor's data to its corresponding physical quantity without confusion.
2Productivity
If conventional text mining methods are used for metadata estimation, then the process is simple and fast, but the ability to distinguish between multiple sensors of the same type is lost
Solution Approach 1:
The patent performs preliminary action by assigning unique identification information to each sensor before the metadata generation process. This pre-identification ensures that when sensor time-series data is analyzed, the system can trace and attribute each data point to the specific sensor that generated it, preserving sensor individuality throughout the automated metadata generation process without adding significant complexity.
Data Source
AI summary
An information processing device includes one or more processors. The one or more processors are configured to: perform, by using a physical model for performing a simulation of operations of a plurality of electronic devices, the simulation, and output a plurality of pieces of first data representing outputs by the plurality of electronic devices; and estimate, based on the first data and a plurality of pieces of second data representing outputs obtained by operating the plurality of electronic devices, mapping data representing a correspondence between the plurality of electronic devices that output the first data and the plurality of electronic devices that output the second data.