Dynamic Chatting Server Matching for Natural Language Input

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional chatting servers are inefficient in processing user utterances as they rely on pre-stored responses and lack the ability to dynamically adjust resources based on the complexity of natural language input, leading to unnecessary resource utilization.

Innovation Solution

An electronic apparatus that evaluates the difficulty level of natural language input using AI technology and dynamically matches the user with an optimal chatting server, reducing resource usage by selecting from a range of servers with varying specifications and response models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all chatting servers are embodied with the same specification, then reliability is improved, but resource utilization deteriorates due to overly used resources even for simple questions

Engineering Contradiction:
Improveservice reliabilityVSAvoidresource utilization
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The patent applies parameter changes by varying the specification parameters of chatting servers (e.g., processing power, memory, response model complexity) to match the difficulty level of user utterances. Simple questions are routed to servers with lower specifications, while complex questions are routed to servers with higher specifications, thereby optimizing resource utilization while maintaining service reliability.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent segments the chatting server pool into multiple groups with different specifications based on their processing capabilities. This segmentation allows the system to selectively assign user queries to appropriate server groups based on the complexity of the natural language input, avoiding the use of high-specification servers for simple tasks and thus reducing overall resource consumption.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If a single chatting server is used for all user inputs, then device complexity is reduced, but productivity deteriorates due to inefficient resource allocation

Engineering Contradiction:
Improvesystem complexityVSAvoidprocessing efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent implements dynamics by making the chatting server assignment dynamic rather than static. The system evaluates the difficulty level of each user utterance in real-time and dynamically selects the most appropriate chatting server from the pool. This dynamic approach improves processing efficiency by matching server capabilities to task requirements, while the underlying server pool structure remains manageable.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent introduces an intermediary component (the difficulty level evaluation module and server matching mechanism) that sits between the user input and the chatting server pool. This intermediary evaluates the natural language input, determines the appropriate difficulty level, and selects the suitable server, thereby improving productivity without significantly increasing overall system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Power

If high-specification chatting servers are used for all queries, then processing capability is improved, but resource consumption increases unnecessarily

Engineering Contradiction:
Improveprocessing capabilityVSAvoidresource consumption
Core Design Contradiction:
PowerVSLoss of energy

Solution Approach 1:

The patent applies local quality by assigning different processing capabilities to different servers in the pool based on their specifications. Instead of uniformly using high-specification servers, the system matches the local quality (processing power) of each server to the local quality (complexity) of the specific query, thereby improving processing capability where needed while reducing resource consumption where not needed.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4125029B1Electronic apparatus, controlling method of thereof and non-transitory computer readable recording medium
Publication Date: 2024.09.04 SAMSUNG ELECTRONICS CO LTD
  • EP4125029B1 patent drawingFigure 1~3
  • EP4125029B1 patent drawingFigure 4~5B
  • EP4125029B1 patent drawingFigure 6~7B

AI summary

An electronic apparatus includes an input unit comprising input circuitry configured to receive a natural language input, a communicator comprising communication circuitry configured to perform communication with a plurality of external chatting servers, and a processor configured to analyze a characteristic of the natural language and a characteristic of the user and to identify a chatting server corresponding to the natural language from among the plurality of chatting servers, and to control the communicator to transmit the natural language to the identified chatting server in order to receive a response with respect to the natural language.