In-Call Virtual Assistant Task Execution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current voice-communication systems lack integrated assistance capabilities that allow users to perform tasks during voice communications, such as retrieving information or scheduling meetings, without manual intervention or separate channels.

Innovation Solution

Implementing a virtual assistant module that can be invoked during voice communications to identify voice commands, perform tasks, and provide outputs through speech recognition, authentication, and interaction with communication networks or user profiles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a virtual assistant module is integrated into voice communication systems to enable task execution during calls, then user productivity and convenience are improved, but system complexity increases

Engineering Contradiction:
Improvetask execution capability during voice callsVSAvoidsystem architecture complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The virtual assistant system is divided into separate functional modules including speech recognition components, task execution engines, and communication interfaces. Each module operates independently but coordinates through standardized protocols, allowing the system to provide enhanced functionality while maintaining manageable complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary components such as speech-to-text conversion services and task interpretation layers that bridge the gap between voice input and system actions. These intermediaries handle the complexity of processing and translation, allowing the core communication system to remain relatively simple while still enabling sophisticated task execution capabilities.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If speech recognition and authentication mechanisms are implemented during voice calls, then task execution accuracy is improved, but processing time and computational resources increase

Engineering Contradiction:
Improvevoice command recognition accuracyVSAvoidprocessing time for voice commands
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing and caching speech patterns, authentication credentials, and task templates before they are needed during actual voice calls. Speech recognition models are pre-trained and stored, allowing rapid matching during interactions. Authentication data is verified against pre-established criteria, reducing real-time processing requirements and minimizing delays during task execution.

Inventive Principle:
Principle #10Preliminary action

3Speed

If the virtual assistant monitors and processes audio signals in real-time during communications, then task responsiveness is improved, but energy consumption increases

Engineering Contradiction:
Improvetask execution responsivenessVSAvoidenergy consumption for audio processing
Core Design Contradiction:
SpeedVSUse of energy by moving object

Solution Approach 1:

Instead of continuous monitoring, the virtual assistant employs periodic sampling of audio signals at strategically determined intervals. The system activates speech recognition processing only when triggered by specific events such as detection of wake words, pause periods in conversation, or explicit user requests. This periodic operation maintains task responsiveness while dramatically reducing energy consumption compared to continuous real-time processing.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3050051B1In-call virtual assistants
Publication Date: 2022.05.25 AMAZON TECH INC
  • EP3050051B1 patent drawingFigure 1
  • EP3050051B1 patent drawingFigure 2A
  • EP3050051B1 patent drawingFigure 2B

AI summary

Techniques for providing virtual assistants to assist users during a voice communication between the users. For instance, a first user operating a device may establish a voice communication with respective devices of one or more additional users, such as with a device of a second user. For instance, the first user may utilize her device to place a telephone call to the device of the second user. A virtual assistant may also join the call and, upon invocation by a user on the call, may identify voice commands from the call and may perform corresponding tasks for the users in response.