AI Dialogue Flow Configuration for Easier Business Customization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The complexity of business logic in AI dialogue systems leads to inefficient customized development and maintenance, requiring repeated code modifications, which is not beneficial for post-maintenance.

Innovation Solution

A dialogue management engine that utilizes a dialogue business customization file to determine reply sentences, allowing for simpler and more efficient development and maintenance by replacing the file iteratively without modifying code logic.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If code logic is modified to customize dialogue business flow, then the dialogue system can be adapted to different providers' requirements, but the development complexity and maintenance difficulty increase

Engineering Contradiction:
Improvedialogue business customizationVSAvoiddevelopment complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the dialogue business logic from the core code by using a separate dialogue flow configuration file (e.g., JSON format). This file contains dialogue nodes, edges, and business logic that can be independently customized without modifying the underlying code. The configuration file is divided into modular components such as dialogue nodes, edges, and parameters, allowing providers to customize their dialogue business flow by simply editing the configuration file rather than modifying complex code logic.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If code logic is repeatedly modified for maintenance, then the business flow can be updated, but the maintenance efficiency decreases

Engineering Contradiction:
Improvebusiness flow updateVSAvoidmaintenance efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent extracts the business flow logic from the code and places it into a separate dialogue flow configuration file. This extraction allows maintenance personnel to update business flows by simply editing the configuration file without touching the code, significantly improving maintenance efficiency. The configuration file can be iteratively replaced to update business logic, avoiding the need for repeated code modifications and compilation.

Inventive Principle:
Principle #2Taking out (Extraction)

3Ease of operation

If graphical interface is used for dialogue flow design, then the customization process becomes simpler, but the system requires additional interface components

Engineering Contradiction:
Improvedialogue flow designVSAvoidsystem components
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a graphical interface as an intermediary between the user and the dialogue flow configuration. The graphical interface allows users to design dialogue flows through visual elements such as dragging and dropping dialogue nodes and connecting them with edges, making the customization process intuitive and simple. The graphical interface automatically generates or updates the underlying configuration file based on user actions, eliminating the need for users to manually edit complex configuration syntax while still providing the benefits of structured configuration.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4016330B1Speech dialog processing method and apparatus
Publication Date: 2026.04.22 AISPEECH CO LTD
  • EP4016330B1 patent drawingFigure 1
  • EP4016330B1 patent drawingFigure 2~3
  • EP4016330B1 patent drawingFigure 4~5

AI summary

The present application discloses a voice dialogue processing method and apparatus. The voice dialogue processing method includes: determining a voice semantics corresponding to a user voice to be processed; determining a reply sentence for the voice semantics based on a dialogue management engine, a training sample set of which is constructed from a dialogue business customization file including at least one dialogue flow, and the dialogue flow includes a plurality of dialogue nodes in a set order; and generating a customer service voice for replying to the user voice according to the determined reply sentence.