Automated Assistant Response Adaptation via Dynamic Familiarity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated assistants lack dynamic adaptation of responses based on user familiarity, leading to inefficient interactions and resource utilization, as they do not account for changing user familiarity over time or the specific intents and historical interactions.

Innovation Solution

A system that generates a dynamic familiarity measure based on historical interactions and intent-specific parameters, adapting responses to be more abbreviated and resource-efficient as user familiarity increases, using techniques such as response abridgment, pronoun substitution, and non-speech sounds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the automated assistant provides detailed and robust responses to all users, then user guidance and comprehension are improved, but network resource usage and interaction duration increase

Engineering Contradiction:
Improveuser guidanceVSAvoidnetwork resource usage
Core Design Contradiction:
Ease of operationVSLoss of energy

Solution Approach 1:

The system dynamically adapts response characteristics based on the calculated familiarity measure between user and assistant. When familiarity is high, responses are abbreviated; when familiarity is low, responses are more detailed and robust. This dynamic adjustment optimizes the balance between providing adequate guidance and conserving network resources.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system applies different response qualities to different users based on their individual familiarity measures. Instead of using a uniform response strategy for all users, the assistant tailors the level of detail and robustness locally to each user's needs, ensuring efficient resource usage while maintaining appropriate guidance levels.

Inventive Principle:
Principle #3Local quality

2Ease of operation

If the automated assistant provides detailed responses to all users, then user comprehension is improved, but interaction duration increases

Engineering Contradiction:
Improveuser comprehensionVSAvoidinteraction duration
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system dynamically adjusts response length and detail based on the familiarity measure. For users with high familiarity, abbreviated responses reduce interaction duration while maintaining comprehension. For users with low familiarity, more detailed responses ensure understanding without unnecessarily extending interactions for experienced users.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of response detail level based on the calculated familiarity measure. By adjusting this parameter dynamically, the system optimizes interaction duration while preserving user comprehension through appropriately tailored response lengths and complexities.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If the automated assistant uses standardized responses for all users, then system complexity is reduced, but adaptability to user needs deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidresponse adaptability
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The system automatically calculates the familiarity measure and selects appropriate response characteristics without requiring manual intervention or complex configuration. This self-service approach enables adaptability while keeping system complexity manageable through automated decision-making based on interaction history.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses historical interaction data as feedback to continuously refine the familiarity measure and adjust response characteristics accordingly. This feedback mechanism enables the system to adapt to user needs dynamically while maintaining relatively simple architecture through data-driven decision-making.

Inventive Principle:
Principle #23Feedback

4Loss of information

If the automated assistant provides comprehensive responses to all users, then information completeness is improved, but network resource usage increases

Engineering Contradiction:
Improveinformation completenessVSAvoidnetwork resource usage
Core Design Contradiction:
Loss of informationVSLoss of energy

Solution Approach 1:

The system dynamically adjusts the level of information provided in responses based on the familiarity measure. For familiar users, abbreviated responses convey essential information with reduced network resource usage. For unfamiliar users, comprehensive responses ensure information completeness while using more network resources, optimizing the balance between these competing requirements.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system applies different information completeness levels locally to different users based on their familiarity. This localized approach ensures that each user receives appropriately tailored information without unnecessarily transmitting excessive data to users who already have high familiarity with the system.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3724874B1Dynamically adapting assistant responses
Publication Date: 2024.07.17 GOOGLE LLC
  • EP3724874B1 patent drawingFigure 1
  • EP3724874B1 patent drawingFigure 2
  • EP3724874B1 patent drawingFigure 3

AI summary

Techniques are disclosed that enable dynamically adapting an automated assistant response using a dynamic familiarity measure. Various implementations process received user input to determine at least one intent, and generate a familiarity measure by processing intent specific parameters and intent agnostic parameters using a machine learning model. An automated assistant response is then determined that is based on the intent and that is based on the familiarity measure. The assistant response is responsive to the user input, and is adapted to the familiarity measure. For example, the assistant response can be more abbreviated and/or more resource efficient as the familiarity measure becomes more indicative of familiarity.