Living Activity Inference Using Energy Consumption and Operational States
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for inferring living activities based on electric appliance energy consumption have low accuracy due to reliance on conditions related to appliance types, locations, and operational states, leading to inconsistent results.
Innovation Solution
A living activity inference device that uses an obtainer to monitor energy consumption, an appliance operation detector to identify operational states, and an activity inferrer to perform inference processes by selecting and applying rules based on past activities and operational states, with prioritization and seasonal adjustments, to determine current living activities with improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If living situation is inferred by measuring energy consumption of electric appliances, then living safety can be improved, but the accuracy of inference results is not always high
Solution Approach 1:
The patent segments the inference process into multiple independent components: energy consumption measurement, operational state identification, and living activity inference. Each component processes specific data independently before integrating results, allowing for more precise and reliable inference of living situations while maintaining high living safety monitoring capability
Solution Approach 2:
The patent adds temporal dimension by incorporating timing information of detected operation situations alongside energy consumption data. This multi-dimensional approach (energy + timing + operational state) significantly improves inference accuracy while maintaining the reliability needed for living safety monitoring
2Ease of operation
If appliance types and installation locations are registered and associated with activity categories, then activity inference can be performed, but the accuracy remains insufficient due to reliance on predetermined conditions
Solution Approach 1:
The patent transitions from static predetermined associations to dynamic inference by continuously analyzing operational states and timing patterns. The system adapts to actual usage patterns rather than relying solely on pre-configured appliance-category mappings, significantly improving accuracy while maintaining ease of operation
Solution Approach 2:
The patent implements feedback mechanisms where inferred living activities are used to refine future inferences. The system learns from past operation patterns and adjusts its inference logic, creating a continuous improvement cycle that enhances accuracy without complicating the operational interface
Data Source
AI summary
The living activity inference device according to the present invention includes: an obtainer configured to obtain an energy consumption of an electric appliance; an appliance operation detector configured to identify an operational state of the electric appliance based on the energy consumption obtained by the obtainer; and an activity inferrer configured to perform an inference process of determining which one of a plurality of living activities predetermined a current living activity corresponds to, based on existing information including the operational state of the electric appliance identified by the appliance operation detector and a past living activity.