Personalized Chatbot Automation for Telephone Calls

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing chatbots are unable to fully automate telephone calls on behalf of users, requiring user intervention to handle conversations and perform tasks.

Innovation Solution

Implementing a personalized chatbot that can identify entities associated with incoming calls and dynamically determine whether to fully automate, partially automate, or refrain from automating the call, using on-device machine learning models for speech recognition, natural language understanding, and text-to-speech generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If existing chatbots answer incoming telephone calls, then they can engage in conversations with additional users, but they are not capable of performing actions or tasks and require user intervention

Engineering Contradiction:

Improveautomation of telephone callsVSAvoidcapability to perform actions or tasks

Core Design Contradiction:

Extent of automationVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts the level of automation based on the conversation context and entity type. It can operate in fully automated mode for routine tasks, partially automated mode for complex tasks requiring user input, or manual mode for tasks requiring user intervention. This dynamic adaptation resolves the contradiction by making the automation extent flexible rather than fixed.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the automation parameter based on the task complexity and entity characteristics. By modifying the automation level parameter dynamically during conversations, the system can perform actions autonomously when appropriate while maintaining the ability to involve the user when necessary, thus resolving the contradiction between automation extent and task capability.

Inventive Principle:

Principle #35Parameter changes

2Ease of operation

If the chatbot fully automates telephone calls, then user intervention is minimized, but computational resources and processing complexity increase

Engineering Contradiction:

Improveuser intervention requirementVSAvoidcomputational processing complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system applies partial automation rather than complete automation for all calls. It performs automated actions for routine tasks while reserving the option to involve the user for complex situations. This partial action approach reduces the computational burden compared to full automation while still providing significant automation benefits for common scenarios.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The chatbot autonomously determines the appropriate level of automation and executes tasks independently without requiring continuous user input. It self-manages the conversation flow, identifies when automated actions are appropriate, and handles routine tasks autonomously, thereby reducing user intervention requirements while managing computational resources efficiently.

Inventive Principle:

Principle #25Self-service

3Adaptability or versatility

If the chatbot processes all audio data and generates synthesized speech, then conversation capability is improved, but energy consumption and processing time increase

Engineering Contradiction:

Improveconversation capabilityVSAvoidenergy consumption

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system applies different processing qualities to different parts of the conversation. It processes audio data and generates synthesized speech for segments where automated actions are needed, while skipping processing for segments where the user is speaking or where manual intervention is required. This localized quality approach maintains conversation capability where needed while reducing overall energy consumption.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system periodically activates intensive processing (audio data processing and synthesized speech generation) only when necessary for automated actions, rather than continuously processing all audio data. This periodic action pattern maintains conversation capability for automated segments while significantly reducing energy consumption during periods when full processing is not required.

Inventive Principle:

Principle #19Periodic action

Data Source

PatentUS20250150532A1System(s) and method(s) for implementing a personalized chatbot

Publication Date: 2025.05.08 GOOGLE LLC

AI summary

Processor(s) of a client device of a user can receive a telephone call that is initiated by an additional user, and, in response to receiving the telephone call, identify an entity that is associated with the additional user, and determine, based on the entity that is associated with the additional user, whether to (1) fully automate the telephone call, or (2) partially automate the telephone call. In fully automating the telephone call, the processor(s) can cause a chatbot to engage in a corresponding conversation with the additional user and without prompting the user for any input. In partially automating the telephone call, the processor(s) can cause the chatbot to engage in a corresponding conversation with the additional user but with prompting the user for input(s) via suggestion chip(s). In some implementations, the processor(s) can further determine whether to (3) refrain from automating the telephone call entirely.