Display Device AI Agent Identification via Dynamic UI

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face difficulties in distinguishing between different AI agents providing voice recognition services, especially when the AI agent for the starting command differs from the one performing the operation, and there is a lack of language support for multiple languages, leading to confusion in using voice recognition services.

Innovation Solution

A display device with a network interface and control unit that identifies the AI agent matched to the starting command, displays a corresponding UI, and changes it when an AI agent for the operating command is different, while a natural language process server converts voice data into text to analyze intent fulfillment results, providing support for multiple languages through a menu.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple AI agents are deployed to provide voice recognition services, then the capability to support multiple languages and functions is improved, but the user's ability to distinguish which AI agent is processing their command deteriorates

Engineering Contradiction:
Improvemulti-language support capabilityVSAvoiduser recognition of active AI agent
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent applies visual differentiation through UI changes to indicate which AI agent is currently active. Different AI agents are represented by distinct UI elements or visual indicators on the display device, allowing users to easily recognize which agent is processing their command without confusion, thus resolving the contradiction between having multiple agents and maintaining user clarity

Inventive Principle:
Principle #32Color changes

Solution Approach 2:

The display device acts as an intermediary between the user and multiple AI agents. It visually presents which AI agent is currently active through UI elements, serving as a mediator that translates the complex multi-agent system into simple, recognizable visual feedback for the user, thereby maintaining ease of operation while supporting multiple agents

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If the UI is changed to represent different AI agents, then the clarity of agent identification is improved, but the system complexity increases

Engineering Contradiction:
Improveinformation about active AI agentVSAvoidUI management complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The UI dynamically changes to reflect which AI agent is currently active. The system automatically updates the visual representation based on the active agent state, providing clear information about which agent is processing commands without requiring complex manual UI management. This dynamic adaptation resolves the contradiction by automating the UI update process

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system automatically manages UI updates based on the active AI agent state without requiring external intervention. The display device autonomously determines which agent is active and updates the corresponding UI elements, reducing the complexity of manual UI management while maintaining clear agent identification for users

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS12190876B2Display device and artificial intelligence system
Publication Date: 2025.01.07 LG ELECTRONICS INC
  • US12190876B2 patent drawing
  • US12190876B2 patent drawing
  • US12190876B2 patent drawing

AI summary

A display device according to an embodiment of the present invention may include: a display unit which displays a content image; a microphone which receives a voice command of a user; a network interface unit for communicating with a natural language processing server and a search server; and a control unit which transmits the received voice command to the natural language processing server, receives intent analysis result information that indicates the intent of the user, which corresponds to the voice command, from the natural language processing server, and performs a function of the display device according to the received intent analysis result information.