Alert Qualification via Multi-System Activity Drift Comparison

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing home monitoring systems for elderly individuals often trigger false alarms due to external factors such as time changes or seasonal variations, leading to unnecessary mobilization of resources and concern for relatives, as they struggle to differentiate between normal and abnormal behavior.

Innovation Solution

A method that compares the activity index drift of a monitored individual with the average drift of multiple interconnected systems, grouping them by similar domestic contexts and weighting data by the commissioning date of each system, to qualify alerts as 'confirmed' or 'invalidated' based on overall trends, thereby reducing false alarms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the monitoring system compares activity readings with reference data from the initial setup period, then it can detect significant deviations in individual behavior, but it triggers false alarms when external factors like time changes or seasonal variations affect behavior

Engineering Contradiction:
Improvealert accuracyVSAvoidfalse alarms
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent combines data from multiple monitoring systems into a pooled dataset, comparing individual system deviations against the aggregate pattern. This merging approach allows the system to distinguish between individual anomalies and widespread behavioral changes caused by external factors, thereby reducing false alarms while maintaining reliable detection of genuine concerns.

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If the system triggers an alert for every significant deviation in activity index, then it ensures thorough monitoring of individual behavior changes, but it unnecessarily ties up technical and human resources

Engineering Contradiction:
Improvebehavior change detectionVSAvoidresource mobilization time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent introduces a pooled dataset from multiple monitoring systems as an intermediary layer between individual system alerts and resource mobilization. This intermediary allows for preliminary filtering and contextuation of alerts, enabling the system to distinguish between genuine concerns requiring intervention and routine variations, thereby reducing unnecessary resource mobilization while maintaining thorough monitoring.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If the system resets when significant changes occur to adapt to new routines, then it maintains tracking accuracy for new behaviors, but activity tracking becomes less reliable during the new initialization period

Engineering Contradiction:
Improveactivity tracking accuracyVSAvoidinitialization period
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent makes the pooled dataset from multiple systems a universal reference that serves both as individual baseline data and as contextual comparison data. This multi-functional approach allows the system to maintain accurate tracking during initialization periods by comparing against the broader pooled data, eliminating the need for lengthy individual re-initialization when behaviors change.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3026647B1Method for qualifying an alert among alerts from an activity supervision system
Publication Date: 2022.08.31 ORANGE SA
  • EP3026647B1 patent drawingFigure 1
  • EP3026647B1 patent drawingFigure 2
  • EP3026647B1 patent drawingFigure 3

AI summary

The invention relates to a method for qualifying an alert among alerts from a first monitoring system overseeing the activity of an individual, the system being adapted to calculate an activity index representative of the individual's activity, alerts being triggered by the monitoring system when there is a drift in the activity index, a drift corresponding to a deviation of the index value from a reference value, the method being implemented in a management server connected to at least one second monitoring system, and comprising, upon receiving an alert triggered by the first monitoring system, steps for obtaining a drift in the activity index from at least one second monitoring system, comparing the drift in the activity index of the first monitoring system with a value representative of the drift in the activity index of at least one second system.and the qualification of the alert based on the comparison result. The invention also relates to a device and a server implementing the method. According to another aspect, the invention relates to a method for requesting alert qualification and a terminal implementing this method.