Conversational Agent Handoff via Speech Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing computer-implemented conversational agents struggle to efficiently hand off user conversations between different agents, especially when users cannot or do not wish to interact physically with a device.

Innovation Solution

A method where a computer-implemented agent on a user device receives a digital representation of speech, determines if an utterance requires communication with another agent, and establishes this communication, enabling seamless handoffs between agents.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a computer-implemented agent manually transfers information between agents, then communication between agents is possible, but the process is inefficient and time-consuming

Engineering Contradiction:

Improveconversation handoff efficiencyVSAvoidtime for manual information transfer

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of copying and transferring information with an automated electronic system. The first computer-implemented agent automatically transmits the representation of the utterance to the second agent, eliminating the need for manual intervention and significantly reducing the time required for conversation handoff.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces a communication channel or intermediary system that facilitates automatic information transfer between agents. This intermediary mechanism enables the first agent to send the utterance representation to the second agent without manual copying, improving efficiency while maintaining information integrity.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If users can physically interact with the device, then conversation control is straightforward, but users who cannot physically interact lack access

Engineering Contradiction:

Improveaccessibility for users with physical limitationsVSAvoidphysical interaction requirement

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent replaces physical interaction mechanisms with voice-based interaction. Users can initiate and control conversations through speech rather than physical actions, making the system accessible to users with physical limitations while maintaining ease of operation through natural language processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If multiple agents handle different applications, then service coverage is expanded, but coordination between agents becomes complex

Engineering Contradiction:

Improvecross-application service coverageVSAvoidagent coordination mechanism

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal communication protocol that enables different agents serving various applications to interact through a standardized interface. This allows the first agent to transmit utterance representations to the second agent regardless of which applications they serve, expanding service coverage while managing coordination complexity through standardization.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12243529B2Conversational agent response determined using a sentiment

Publication Date: 2025.03.04 GOOGLE LLC

AI summary

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for handing off a user conversation between computer-implemented agents. One of the methods includes receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance, determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent, and establishing, by the computer-implemented agent, a communication between the other computer-implemented agent and the user device.