Multi-Device Coordination Control Using Service-Achievement Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing IoT systems require manual and labor-intensive adjustments to control multiple devices in physical spaces, as environmental factors and device-specific characteristics complicate the creation of optimal control logic, leading to inefficiencies and increased costs.

Innovation Solution

A multi-device coordination control system that uses sensor information to calculate a 'degree of service achievement' and applies machine learning to determine actuator control amounts, automatically adjusting these amounts using an evolution strategy algorithm to achieve targeted service levels, thereby simplifying the control of various actuator devices in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual designing and adjustment of control logic is performed for each device, then the control precision can be optimized for specific environments, but the development time and labor cost increase significantly

Engineering Contradiction:

Improvecontrol logic optimizationVSAvoiddevelopment time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary machine learning training to pre-compute optimal control logic for various device configurations and environmental conditions. This pre-computed control logic is then applied automatically without requiring manual adjustment for each specific deployment scenario, resolving the contradiction between optimization precision and development time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The control system automatically adapts to specific environments and device configurations through machine learning algorithms that self-optimize control parameters. The system serves itself by learning from sensor data and automatically adjusting control logic, eliminating the need for manual designing and adjustment while maintaining optimal control precision.

Inventive Principle:

Principle #25Self-service

2Reliability

If comprehensive examination of all possible situations is conducted to create optimum control logic, then the service quality improves, but the labor hours required increase dramatically

Engineering Contradiction:

Improveservice qualityVSAvoidlabor efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system continuously collects sensor data from the physical environment and uses this feedback to automatically refine control logic through machine learning. This closed-loop feedback mechanism enables the system to improve service quality by learning from actual operating conditions without requiring manual examination of all possible situations, thereby maintaining high productivity.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The machine learning model dynamically adjusts control parameters based on learned patterns from sensor data, automatically adapting to different situations and environmental conditions. This parameter optimization is performed computationally rather than through manual examination, improving service quality while maintaining labor efficiency.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If the system adapts to different device installations and environmental conditions, then the control accuracy improves, but the system complexity increases

Engineering Contradiction:

Improvecontrol accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system employs a universal machine learning framework that can handle various device types, installation configurations, and environmental conditions through a single adaptable model. This universal approach maintains control accuracy across diverse scenarios without increasing system complexity, as the same core learning architecture serves multiple functions and adapts to different contexts.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11874634B2Multi-device coordination control device, multi-device coordinaton control method, and multi-device coordination control program, and learning device, learning method, and learning program

Publication Date: 2024.01.16 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

A multi device coordination control device includes: a degree-of-service-achievement calculator configured to acquire sensor information from one or more sensor devices disposed on the same physical space, and convert the acquired sensor information to a degree of service achievement; a target control amount calculation part configured to make a learning device allow an input of the degree of service achievement and compute therefrom an actuator control amount for each of the actuator devices, to thereby obtain the actuator control amount as an output value; and an actuator controller configured to convert the actuator control amount obtained as the output value to a control instruction in accordance with each of the actuator devices, and transmit the control instruction to each of the actuator devices, to thereby make the each of the actuator devices execute the control instruction.