Vehicle Conversational Agent Selection and Personalization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current vehicle conversational agents are preconfigured and not modifiable, limiting user choice and personalization, as they are adapted to an average user profile and rely on a limited set of criteria, which can lead to dissatisfaction among users with varying preferences.

Innovation Solution

An assistance device with voice recognition and control means that allows users to select from various conversational agents, each with predefined criteria for intervention modes and rights, enabling customization based on user needs, including options like coach, benefactor, butler, and friend types, and allowing modification of preconfigured criteria in an expert mode.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single pre-configured conversational agent is used, then the system complexity is reduced and ease of manufacture is improved, but user satisfaction and adaptability deteriorate because the agent cannot be modified to suit individual user preferences

Engineering Contradiction:
Improveuser personalizationVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the single conversational agent into multiple independent agents, each with its own pre-configured personality and intervention style. Users can select from different agents (e.g., authoritative, supportive, neutral) to match their preferences. This segmentation resolves the contradiction by providing adaptability through multiple specialized agents rather than one general agent, while each agent remains independently configured to manage system complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces dynamic configurability where users can adjust intervention parameters such as authority level, supportiveness, and information provision in real-time. The system transitions from static pre-configuration to dynamic adaptation, allowing users to modify agent behavior based on their needs. This dynamic approach enables personalization without requiring complete system redesign, balancing adaptability with manageable complexity.

Inventive Principle:
Principle #15Dynamics

2Adaptability or versatility

If intervention parameters are made modifiable, then user personalization is improved, but the ease of operation deteriorates due to the increased complexity of configuration

Engineering Contradiction:
Improvepersonalization capabilityVSAvoidconfiguration simplicity
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent applies preliminary action by providing pre-configured conversational agents with default personality profiles and intervention styles before user interaction. Users start with ready-to-use agents that require minimal configuration, and can later adjust parameters if needed. This approach resolves the contradiction by offering personalization through pre-configured options that are easy to select, while detailed configuration remains available but not mandatory.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent enables parameter changes by allowing users to modify specific intervention parameters (authority, supportiveness, information provision) without changing the entire agent configuration. Users can adjust individual parameters independently, making personalization simpler and more manageable. This selective parameter modification resolves the contradiction by providing customization capability while maintaining operational simplicity through incremental adjustments.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If multiple conversational agents with different personalities are provided, then user satisfaction is improved, but the device complexity increases due to multiple configuration sets

Engineering Contradiction:
Improveagent varietyVSAvoidconfiguration management
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the conversational agent system into multiple independent agents, each with its own pre-configured personality and intervention style. This segmentation allows the system to manage complexity by treating each agent as a separate, self-contained unit with its own configuration, rather than one complex configurable system. Users can select from pre-defined agent types, reducing the burden of configuration management while maintaining high adaptability.

Inventive Principle:
Principle #1Segmentation

4Ease of operation

If pre-configuration is made fixed, then system stability is improved, but user satisfaction deteriorates due to lack of customization options

Engineering Contradiction:
Improvesystem stabilityVSAvoidcustomization flexibility
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent introduces dynamic configurability that allows users to adjust intervention parameters in real-time while maintaining stable agent identities. The system transitions from static pre-configuration to dynamic adaptation, where agents can modify their behavior based on user preferences without changing their core personality. This dynamic approach resolves the contradiction by providing both stability (through defined agent personalities) and flexibility (through adjustable parameters).

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3571693B1User assistance device for a vehicle, having multiple conversational agents
Publication Date: 2021.01.06 PSA AUTOMOBILES SA
  • EP3571693B1 patent drawingFigure 1~3
  • EP3571693B1 patent drawing

AI summary

A device (DA) for assisting a user of a vehicle (V) comprising equipment suitable for performing tasks. This device (DA) comprises: - voice recognition means (MR) for recognising words and expressions uttered by the user, and - control means (MC) suitable both for proposing to the user a list of conversational agents in order that he selects one of these, each conversational agent being suitable for conversing with the user, at least for proposing the performing of a task or tasks, and/or for automatically triggering the performance of a task or tasks, according to a predefined associated set of preconfigured criteria each defining at least one mode or right of action, as well as for operating the conversational agent selected by the user, automatically or when a word or an expression uttered by the user has been recognised.