Voice Analysis for Adaptive Message Timing Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing information notification systems fail to appropriately control the timing of message output, often causing interruptions during conversations due to overlapping voices, as they do not accurately determine when a user is able to listen to messages.

Innovation Solution

An information notification supporting device that analyzes voice input to identify speech patterns and determines the user's state, using this information to control the timing of message output, ensuring messages are delivered when the user is not engaged in conversation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If the system outputs messages immediately after processing user requests, then the response speed is improved, but the messages may overlap with ongoing conversations causing interruptions

Engineering Contradiction:
Improvemessage response speedVSAvoidconversation interruption
Core Design Contradiction:
SpeedVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary analysis of the user's state by analyzing voice input history and speech patterns before determining message output timing. This preliminary action allows the system to predict when the user will be available to receive messages without waiting for the conversation to fully conclude, thus maintaining fast response while avoiding interruptions.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors voice input to detect ongoing speech and uses this feedback to dynamically adjust message output timing. By detecting speech patterns and conversation state in real-time, the system can delay message output until an appropriate moment while still maintaining efficient response overall.

Inventive Principle:
Principle #23Feedback

2Object-affected harmful factors

If the system waits for a fixed waiting time before outputting messages, then conversation overlap is reduced, but the message output timing becomes inappropriate when the user is actually available to listen

Engineering Contradiction:
Improvevoice overlapVSAvoidmessage delivery delay
Core Design Contradiction:
Object-affected harmful factorsVSLoss of time

Solution Approach 1:

The system dynamically adjusts the waiting time before message output based on real-time analysis of voice input patterns and user speech behavior. Instead of using a fixed waiting time, the system adapts the delay period to match the actual conversation flow and user availability, optimizing both the avoidance of voice overlap and the timeliness of message delivery.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If the system analyzes voice input in real-time to determine user state, then message timing accuracy is improved, but the system complexity increases

Engineering Contradiction:
Improveuser state detection accuracyVSAvoidvoice analysis system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces a voice analysis component that acts as an intermediary between the voice input and the message output control. This intermediary analyzes voice patterns and determines user state, providing precise timing information to the message output mechanism while keeping the overall system architecture modular and manageable.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10068575B2Information notification supporting device, information notification supporting method, and computer program product
Publication Date: 2018.09.04 KK TOSHIBA
  • US10068575B2 patent drawing
  • US10068575B2 patent drawing
  • US10068575B2 patent drawing

AI summary

According to an embodiment, an information notification supporting device includes an analyzer configured to analyze an input voice so as to identify voice information indicating information related to speech; a storage unit configured to store therein a history of the voice information; an output controller configured to determine, using the history of the voice information, whether a user is able to listen to a message of which the user should be notified; and an output unit configured to output the message when it is determined that the user is in a state in which the user is able to listen to the message.