Legacy Control Retrofit Panel With ML-Based Actuation Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The mass adoption of smart home technologies is hindered by consumer concerns over price sensitivity and perceived installation complexity, particularly due to the need for professional installation and the inefficiency of replacing legacy devices like light switches, which require knowledge of residential wiring and pose safety risks.

Innovation Solution

A cognitive retrofit system that retrofits existing legacy control devices with a multi-layered automation panel, enabling manual actuation while automatically adjusting based on machine-learning predictions, using a touch sensor to sense manual inputs and an actuator to respond to control signals, thereby integrating these devices into a smart home network without requiring removal of existing components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If legacy control devices are replaced with smart devices, then automation capability and network connectivity are improved, but installation complexity and safety risks increase

Engineering Contradiction:
Improveautomation capabilityVSAvoidinstallation complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent applies nesting by placing a smart automation panel inside or behind an existing legacy control device. The automation panel is a self-contained unit that includes its own electronics, sensors, and actuators, which can be installed within the existing device housing or mounted adjacent to it. This nested structure allows the legacy device to remain visible and functional while the smart panel provides automated control capabilities, eliminating the need to replace the entire device and reducing installation complexity.

Inventive Principle:
Principle #7Nested doll (Nesting)

2Extent of automation

If legacy control devices are replaced with smart devices, then automation capability is improved, but installation costs increase

Engineering Contradiction:
Improveautomation capabilityVSAvoidinstallation cost
Core Design Contradiction:
Extent of automationVSEase of manufacture

Solution Approach 1:

The patent applies segmentation by dividing the smart home control system into two separate components: the existing legacy control device and a new automation panel. The automation panel is a modular unit that can be independently manufactured and installed. This segmentation allows consumers to keep their existing devices and only purchase/install the automation panel, significantly reducing costs compared to replacing entire devices. The modular approach also enables easier installation without requiring professional electricians.

Inventive Principle:
Principle #1Segmentation

3Extent of automation

If multi-layered automation panel is added to legacy device, then automated control is enabled, but device complexity increases

Engineering Contradiction:
Improveautomated controlVSAvoiddevice complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent applies the intermediary principle by introducing a machine learning classifier as a mediator between the automation panel's sensors and the control element. The classifier processes sensor data, learns user behavior patterns, and makes intelligent decisions about when to activate the control element. This intermediary layer enables sophisticated automated control while keeping the overall system architecture simple and manageable, as the complex AI processing is encapsulated within the automation panel rather than requiring changes to the legacy device.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS12130604B2Cognitive retrofit for legacy control devices
Publication Date: 2024.10.29 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US12130604B2 patent drawing
  • US12130604B2 patent drawing
  • US12130604B2 patent drawing

AI summary

An embodiment includes retrofitting an existing control device with an automation panel that senses manual actuation of a control element of the control device, and automatically actuates the control element in response to a specified control signal. The embodiment collects state data indicative of an actuation state of the control element and context data of conditions at a time that the state data is collected, and generates a training dataset comprising collected state data and sensor data. It then uses this data to train a classification model to predict a control element actuation state based on sensor data. The embodiment deploys the trained classification model to process sensor data and upon detecting a mismatch between a predicted actuation state output from the trained classification model and an actual actuation state of the control element, the embodiment transmits the specified control signal to the automation panel to actuate the control element.