Dialogue System Input Priority Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing dialogue systems require users to input additional options after providing an answer or instruction, complicating operations, and struggle with recognition processing when there is no information on the number of inputs, leading to inefficient user interaction.

Innovation Solution

A dialogue system with a control unit that integrates sensor information, input content analysis, usage situation analysis, priority calculation, and scenario control to automatically prioritize and manage multiple inputs within a fixed period, preventing unnecessary user input and simplifying operations by adjusting the execution order of scenarios based on input priority.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the system presents options for multiple inputs to the user, then recognition accuracy is improved, but operation complexity increases

Engineering Contradiction:
Improverecognition accuracyVSAvoidoperation complexity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically determines the user's intended input by analyzing temporal relationships and patterns in multiple inputs, eliminating the need for users to manually select from presented options. The system serves itself by autonomously resolving ambiguity through intelligent analysis rather than requiring user intervention.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system utilizes feedback from the timing and sequence of multiple inputs to automatically disambiguate user intention. By analyzing the temporal patterns and providing automatic interpretation based on this feedback, the system resolves recognition ambiguity without requiring additional user input or selection steps.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If the system requires additional input selection after user input, then input accuracy is improved, but user interaction efficiency deteriorates

Engineering Contradiction:
Improveinput accuracyVSAvoiduser interaction efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary analysis of multiple inputs and their temporal relationships before requiring any user selection. By pre-processing and intelligently interpreting the sequence of inputs in advance, the system determines user intention proactively, eliminating the need for subsequent selection steps and maintaining both accuracy and efficiency.

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If the system processes multiple inputs without input count information, then system simplicity is maintained, but recognition processing capability deteriorates

Engineering Contradiction:
Improvesystem simplicityVSAvoidrecognition processing capability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system replaces traditional mechanical counting methods with temporal analysis and pattern recognition. Instead of relying on explicit input count information, the system uses the timing intervals and sequences of inputs to infer the number and nature of user intentions, achieving reliable recognition processing through intelligent analysis rather than simple counting mechanisms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3588267B1Method of controlling dialogue system, dialogue system, and data storage medium
Publication Date: 2022.08.03 HITACHI LTD
  • EP3588267B1 patent drawingFigure 1
  • EP3588267B1 patent drawingFigure 2
  • EP3588267B1 patent drawingFigure 3

AI summary

A dialogue system including a processor, a memory, an audio input apparatus, an audio output apparatus, a touch input apparatus, and a display unit. The processor receives an input from the voice or a touch input apparatus, analyzes the content of the input, and selects a scenario corresponding to the input data from preset scenario information. The processor generates the output data specified in the scenario, calculates the priority of the input data, and determines the presence or absence of the scenario being prepared for the output data. When there is the scenario under generating the output data, the processor changes the output method of the scenario to be executed based on the priority.