Dialog System Local Unit Connection Interruption Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Spoken dialog systems in vehicles face reliability issues due to connection interruptions and inadequate network availability, leading to potential driver distraction and limitations in system optimization and updates.
Innovation Solution
A method for operating a dialog system with a local unit for detecting and outputting dialog inputs and outputs, and an external unit for analyzing these inputs and determining outputs, where a probable future course of dialog is calculated and saved for retrieval during connection interruptions, allowing seamless continuation of dialog without requiring coordination between local and external managers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If speech processing is carried out entirely locally in the motor vehicle, then system availability is maintained, but speech recognition quality deteriorates and software updates become complicated
Solution Approach 1:
The system is divided into local and external processing components. The local dialog unit handles basic speech detection and dialog management, while the external dialog unit performs sophisticated speech recognition and system optimization. This segmentation allows each component to operate independently, maintaining availability locally while improving recognition quality externally.
Solution Approach 2:
A communication interface acts as an intermediary between the local and external dialog units. This intermediary enables the transfer of dialog inputs and outputs, allowing the system to leverage external processing capabilities while maintaining local operation and availability.
2Measurement precision
If speech processing is carried out entirely online externally, then speech recognition quality improves, but connection interruptions and inadequate network availability occur
Solution Approach 1:
The local dialog unit performs preliminary actions by detecting speech inputs and managing the dialog flow locally. This preliminary processing ensures that even when external connection is interrupted, the system can continue operating with previously processed information, maintaining reliability while enjoying the benefits of external speech recognition when connected.
3Reliability
If hybrid speech processing is implemented with local and external units, then system reliability improves, but coordination complexity between local and external managers increases
Solution Approach 1:
The complex coordination logic is extracted from the local unit and placed in the external unit. The local unit simply detects speech and outputs dialog information, while the external unit handles all coordination tasks including generating future dialog courses and managing communication. This extraction simplifies the local unit while maintaining system reliability.
Solution Approach 2:
The external dialog unit provides feedback to the local unit by calculating probable future courses of dialog based on current speech inputs. This feedback mechanism enables the local unit to operate autonomously with guidance from the external unit, reducing coordination complexity while maintaining high reliability through continuous external oversight.
4Reliability
If embedded dialog systems are used in vehicles, then system availability is maintained, but opportunities to optimize and learn from multiple systems are limited
Solution Approach 1:
The external dialog unit serves multiple functions: it performs speech recognition, optimizes system behavior, learns from multiple systems simultaneously, and provides guidance to the local unit. This multi-functionality enables the system to maintain local availability while gaining access to external optimization and learning opportunities that would be impossible in a purely embedded system.
Data Source
AI summary
The invention relates to a method for operating and a method for controlling a dialog system, wherein the dialog system comprises a local dialog unit for detecting dialog inputs and for outputting dialog outputs as well as an external dialog unit having a data connection to the local dialog unit for analyzing detected dialog inputs and determining dialog outputs based thereon. At least one probable future course of dialog consisting of dialog inputs and/or dialog outputs is calculated and transmitted to the local dialog unit by the external dialog unit. Said course of dialog is received and saved by the local dialog unit. The saved course of dialog is called up in the event of an interruption to the data connection between the local dialog unit and the external dialog unit. Dialog inputs are detected and/or dialog outputs are output based on the called-up course of dialog.