Intelligent Server Voice Assistant Auto-Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face reduced convenience and increased operational burden when selecting voice assistant apps on portable digital communication devices, as existing systems require manual selection and re-selection due to inadequate context-based app identification and functionality matching.

Innovation Solution

An intelligent server and electronic device system that uses context information to automatically select the appropriate voice assistant app based on user utterances, transmitting relevant information to perform designated functions without the need for repeated user intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple voice assistant apps are included in one category, then the system can provide more functionality options, but user convenience deteriorates due to the need for manual selection and re-selection

Engineering Contradiction:
Improvefunctionality optionsVSAvoiduser convenience
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system automatically selects the appropriate voice assistant app by analyzing the user's utterance and matching it with the most suitable app based on pre-set conditions and context information, eliminating the need for manual user selection and enabling the system to serve itself in the selection process

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses context information from the electronic device (such as currently running applications or recent user interactions) as feedback to dynamically determine which voice assistant app should be activated, creating a closed-loop selection mechanism that adapts to the current operational state

Inventive Principle:
Principle #23Feedback

2Ease of operation

If voice assistant app selection is automated, then user convenience is improved, but system complexity increases due to context-based identification requirements

Engineering Contradiction:
Improveuser convenienceVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-configuring conditions and context parameters for each voice assistant app before runtime, so that during operation the selection process simply needs to evaluate pre-defined criteria rather than performing complex real-time analysis, thereby reducing operational complexity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system manages complexity by changing parameters such as context information thresholds and matching criteria dynamically, allowing the selection mechanism to adapt to different situations without requiring a complete redesign of the selection architecture

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11978449B2Electronic device for processing user utterance and operation method therefor
Publication Date: 2024.05.07 SAMSUNG ELECTRONICS CO LTD
  • US11978449B2 patent drawing
  • US11978449B2 patent drawing
  • US11978449B2 patent drawing

AI summary

An intelligent server is provided. The intelligent server includes a communication circuit; and at least one processor configured to receive a user utterance from an electronic device via the communication circuit, identify a first category associated with the user utterance, among a plurality of categories stored in the intelligent server, identify a plurality of voice assistant applications included in the first category, transmit information on the plurality of voice assistant applications to the electronic device, receive, from the electronic device, information about a first application, identified to satisfy a designated condition based on at least one parameter associated with a function corresponding to the user utterance, identify a first voice assistant application corresponding to the first application by using the information about the first application, generate result information for performing the function by using the first voice assistant application, and transmit the result information to the electronic device.