AI Robot User Behavior Adaptation via Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional robots lack the ability to analyze user behavior and provide appropriate reactions, leading to repetitive and unresponsive interactions with users.

Innovation Solution

A robotic system that collects user data through various sensors and machine learning algorithms to cluster and analyze user behavior, determining a representative state and reaction to output an appropriate response.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional robots perform predetermined operations under predetermined conditions, then the robot operations are simple and controllable, but the robot reactions become repetitive and users quickly get tired

Engineering Contradiction:
Improverobot reaction adaptabilityVSAvoidrobot control system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The robot control system transitions from static predetermined operations to dynamic adaptive reactions. The processor continuously learns user behavior patterns through machine learning algorithms and dynamically adjusts robot reactions based on real-time user state analysis, making the system both adaptable and dynamically responsive to user needs.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The robot performs self-learning and self-adjustment through automated machine learning processes. The system automatically analyzes user behavior data, updates its internal models, and generates appropriate reactions without requiring external programming or manual intervention, enabling continuous improvement of adaptability while maintaining operational simplicity.

Inventive Principle:
Principle #25Self-service

2Loss of information

If the robot analyzes user behavior and outputs appropriate reactions, then user interaction quality improves, but the processing complexity and computational requirements increase

Engineering Contradiction:
Improveuser behavior understanding accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system extracts only the most relevant features from raw user behavior data such as voice tone, facial expressions, and body language. By focusing on key indicators of user state rather than processing all available data, the system achieves accurate behavior understanding while reducing computational complexity and processing requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces an intermediary layer of behavior analysis models that translate complex raw user data into simplified user state representations. This intermediary processing stage bridges the gap between raw data collection and reaction generation, reducing the complexity of subsequent decision-making processes while preserving essential behavioral information.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If the robot learns and adapts to user behavior, then personalized reactions are provided, but the learning time and data requirements increase

Engineering Contradiction:
Improveuser personalization capabilityVSAvoidlearning adaptation time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The robot performs preliminary learning during manufacturing and initial setup phases, establishing baseline user behavior models before actual deployment. This preliminary action reduces the learning time required during normal operation, allowing the system to provide personalized reactions more quickly while still adapting to individual user preferences over time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements partial personalization by focusing on the most impactful behavioral patterns and user preferences rather than attempting to learn all aspects of user behavior. This selective approach enables the robot to provide meaningful personalized reactions with reduced learning time and data requirements, balancing personalization quality with adaptation speed.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3725470B1Robot reacting on basis of user behavior and control method therefor
Publication Date: 2025.04.23 SAMSUNG ELECTRONICS CO LTD
  • EP3725470B1 patent drawingFigure 1
  • EP3725470B1 patent drawingFigure 2
  • EP3725470B1 patent drawingFigure 3A

AI summary

A robot for outputting various reactions according to user behaviors is disclosed. A control method for a robot using an artificial intelligence model, according to the present disclosure, comprises the steps of: acquiring data related to at least one user; inputting the data related to the at least one user into the artificial intelligence model as learning data so as to learn a user state for each user of which there is at least one; determining representative reactions corresponding to the user states learned on the basis of the data related to the at least one user; and inputting the input data into the artificial intelligence model so as to determine a user state of a first user and controlling the robot on the basis of a representative reaction corresponding to the determined user state, when input data related to the first user among the users, of which there is a least one, is acquired.