Anomaly Detection in Smart Home Accessories via Resident Device

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Home automation systems face complexity in controlling smart devices due to the varied feature sets of smart accessories, making it difficult for users to manage and maintain optimal accessory states, and there is a lack of efficient methods to detect anomalous states that could be harmful.

Innovation Solution

A system that automatically generates scene suggestions and trigger suggestions based on historical patterns of use, allowing users to recreate environments with minimal input, and notifies users of anomalous accessory states, using a resident device to aggregate data from multiple user devices and determine normal and abnormal states.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users manually control each smart accessory individually, then precise control over accessory states is achieved, but the complexity of operation increases significantly due to the varied feature sets of multiple devices

Engineering Contradiction:

Improveease of controlVSAvoidsystem complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent combines multiple accessory controls into unified scenes that group related accessories together. Users can control multiple accessories simultaneously through a single scene invocation rather than individually controlling each accessory, thereby reducing operational complexity while maintaining control precision.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system creates universal scene configurations that can apply to multiple different accessory combinations. A single scene can encompass various accessories with different feature sets, providing a multi-functional control mechanism that simplifies operation across diverse device types.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If the system monitors all accessory states continuously, then anomalous states can be detected early, but the energy consumption and processing load increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidenergy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system implements feedback mechanisms where accessories report their states to the controller, which then compares current states against historical patterns and scene configurations. This selective feedback approach allows reliable anomaly detection without requiring continuous monitoring of all parameters, thereby reducing energy consumption while maintaining detection accuracy.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system pre-establishes scene configurations and normal state patterns before monitoring begins. By having baseline expectations of normal accessory behavior pre-configured, the system can quickly compare current states against these pre-set patterns without requiring intensive real-time analysis, reducing processing load and energy consumption.

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If scene suggestions are generated automatically based on historical data, then user convenience is improved, but the time required to analyze historical patterns and generate suggestions increases

Engineering Contradiction:

Improveuser convenienceVSAvoidprocessing time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system pre-processes historical accessory state data and identifies usage patterns in advance. By analyzing historical data and establishing baseline patterns beforehand, the system can quickly generate scene suggestions when needed without performing intensive real-time analysis, thereby reducing the time loss while maintaining user convenience.

Inventive Principle:

Principle #10Preliminary action

4Reliability

If the resident device aggregates data from multiple user devices, then the accuracy of anomaly detection is improved, but the data transmission and processing requirements increase

Engineering Contradiction:

Improvedetection reliabilityVSAvoiddata volume

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system extracts only the essential and relevant data elements from multiple user devices that are necessary for anomaly detection. Rather than aggregating all possible data, the system identifies and extracts key state information, contextual data, and usage patterns, thereby reducing the overall data volume while maintaining detection reliability through focused data collection.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS10938593B2Anomaly detection by resident device

Publication Date: 2021.03.02 APPLE INC

AI summary

In some implementations, a user device (or resident device) can notify the user of anomalous accessory states. For example, the user device can determine which accessory states and contexts represent normal accessory states in the respective contexts. Similarly to scene suggestions, the user device can analyze historical accessory state data and context data to determine an accessory state pattern that indicates a normal state of an accessory for a given context. The user device can compare the current state and/or context of an accessory to historical accessory state data to determine when the current state of the accessory is abnormal for the current context. If the current accessory state is abnormal for the current context, the user device can present a notification to the user informing the user of the anomalous accessory state.