Digital Assistant Session Window With Variable Speech Threshold

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional digital assistant systems require triggering inputs to initiate and continue interactions, leading to cumbersome and repetitive exchanges between users and devices, lacking seamless and effective continuous dialog capabilities.

Innovation Solution

A system and process for continuous dialog with a digital assistant that allows for the initiation of a session window based on speech inputs, with adjustable thresholds to enable dynamic user interaction without the need for additional triggers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional digital assistant systems require triggering inputs to initiate and continue interactions, then the system can maintain clear interaction boundaries and avoid false activations, but the interaction becomes cumbersome and repetitive, reducing ease of operation

Engineering Contradiction:
Improveease of interactionVSAvoidinteraction flow complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system performs preliminary action by initiating a session window in advance after detecting the first speech input. This session window remains open for a predetermined duration, allowing the user to provide additional speech inputs without needing to repeat trigger words. The session window is prepared and maintained ready to receive further inputs, eliminating the need for repetitive triggering.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The interaction model transitions from static (requiring trigger words for every input) to dynamic (session-based continuous listening). The system adapts its behavior by entering a special session state where the speech threshold is lowered and trigger word requirements are relaxed, allowing more natural and fluid conversation flow.

Inventive Principle:
Principle #15Dynamics

2Ease of operation

If the system lowers the speech threshold to enable continuous dialog without triggers, then ease of interaction improves, but the risk of false activations and noise interference increases

Engineering Contradiction:
Improvecontinuity of dialogVSAvoidspeech input accuracy
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system uses periodic action by implementing a session window with a predetermined duration. During this time-limited period, the lowered speech threshold is active, allowing continuous dialog without triggers. After the period expires, the system returns to the normal state with higher threshold requirements, thus limiting false activations to a controlled time window.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The session window is initiated in advance after the first speech input is detected. This preliminary action sets up a controlled environment where the lowered threshold is temporarily active only for legitimate follow-up inputs within the session, rather than being permanently active and causing false activations.

Inventive Principle:
Principle #10Preliminary action

3Duration of action of moving object

If the session window duration is extended to allow more continuous interaction, then user experience improves, but the system consumes more energy and occupies the assistant state longer

Engineering Contradiction:
Improvesession window durationVSAvoidenergy consumption
Core Design Contradiction:
Duration of action of moving objectVSUse of energy by moving object

Solution Approach 1:

The system applies parameter changes by adjusting the speech threshold parameter dynamically based on the session state. During the session window, the speech threshold is lowered to enable continuous dialog without triggers. The session window duration is set to a predetermined value that balances interaction needs with energy consumption constraints.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4057128B1Continuous dialog with a digital assistant
Publication Date: 2025.11.12 APPLE INC
  • EP4057128B1 patent drawingFigure 1
  • EP4057128B1 patent drawingFigure 2A
  • EP4057128B1 patent drawingFigure 2B

AI summary

Systems and processes for operating an intelligent automated assistant are provided. For example, a first speech input directed to a digital assistant is received from a user. A first response is provided based on the first speech input. A session window is initiated, wherein the session window is associated with a variable speech threshold. A second speech input is received during the session window. In accordance with a determination that the second speech input includes speech directed to the digital assistant, a duration associated with the session window is increased. In accordance with a determination that the variable speech threshold does not exceed a predetermined speech threshold, the session window is ended.