Voice Interaction Device Speaker Condition Inquiry Mechanism

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice interaction devices struggle to accurately monitor the conditions of speakers during voice interaction, as image and voice recognition technologies fail to effectively understand the physical and situational conditions of the speaker.

Innovation Solution

A voice interaction device equipped with a processor that recognizes utterance content from speaker voice data, generates and outputs utterance sentences to inquire about speaker conditions, allowing for separate monitoring of speaker conditions during interaction, and can identify and notify secondary interaction partners of primary speaker conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If image recognition or voice recognition is used to detect speaker characteristics, then voice interaction can be performed with an agent image, but the physical conditions of the speaker cannot be accurately monitored

Engineering Contradiction:
Improvevoice interaction capabilityVSAvoidspeaker condition monitoring accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces a condition inquiry mechanism as an intermediary between the voice interaction system and the speaker. The system generates utterance sentences that specifically inquire about speaker conditions (such as fatigue, hunger, thirst) and uses the speaker's responses to monitor their state. This intermediary approach allows the system to obtain condition information that cannot be directly measured by traditional image or voice recognition.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the system continuously monitors speaker conditions during voice interaction, then speaker conditions can be tracked, but the interaction burden on the speaker increases

Engineering Contradiction:
Improvespeaker condition monitoringVSAvoidinteraction process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements periodic condition inquiry during voice interaction, where the system asks about speaker conditions at predetermined intervals rather than continuously. This periodic approach allows condition monitoring to be performed systematically without creating excessive interaction burden, as the inquiries are spaced out during the natural flow of voice interaction.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The condition inquiry process is integrated into the ongoing voice interaction, making the monitoring continuous without interrupting the primary interaction flow. The system maintains the useful action of voice interaction while embedding condition monitoring within it, ensuring that monitoring occurs naturally as part of the interaction rather than as a separate burden.

Inventive Principle:
Principle #20Continuity of useful action

3Measurement precision

If the system inquires about speaker conditions at frequent intervals, then condition monitoring accuracy improves, but the interaction time increases

Engineering Contradiction:
Improvecondition monitoring accuracyVSAvoidinteraction time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by selecting specific, key conditions to inquire about rather than asking about all possible speaker states. The system focuses on monitoring critical conditions (fatigue, hunger, thirst) that are most relevant to speaker safety and interaction quality, rather than attempting to monitor every possible condition, thus reducing time consumption while maintaining effective monitoring accuracy.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS11074915B2Voice interaction device, control method for voice interaction device, and non-transitory recording medium storing program
Publication Date: 2021.07.27 TOYOTA JIDOSHA KK
  • US11074915B2 patent drawing
  • US11074915B2 patent drawing
  • US11074915B2 patent drawing

AI summary

A voice interaction device includes a processor configured to recognize an utterance content from data of voice of a speaker. The processor is configured to perform voice interaction with the speaker by repeating a process of generating data of an utterance sentence based on the utterance content of the speaker and outputting the data of an utterance sentence by voice. The processor is configured to generate the data of the utterance sentence for inquiring about conditions of the speaker and to output the data of the utterance sentence by voice during execution of the voice interaction with the speaker.