Vehicle Controller Topic Selection via Syntax Moniker Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle query systems require explicit invocation and struggle to distinguish between forward and reverse cadences, leading to inefficient conversation processing and unclear desired answer topics.

Innovation Solution

A vehicle controller selects topics for generating answers based on vehicle operating parameters and syntax analysis of utterances, using an always-listening algorithm to identify tag questions and provide context-based responses, allowing for seamless conversation processing without explicit invocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If explicit invocation is required before questions (forward cadence), then the system can clearly identify when to answer, but it requires more statements and ignores conversations prior to invocation

Engineering Contradiction:

Improvequestion identification accuracyVSAvoidconversation processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by continuously analyzing conversations before invocation occurs. It identifies potential questions and prepares answers in advance, so when a moniker is detected, the system can immediately provide context-aware responses without ignoring prior conversation context.

Inventive Principle:

Principle #10Preliminary action

2Ease of operation

If the system supports reverse cadence (answering without explicit invocation), then it can provide more natural conversation flow, but it cannot distinguish between forward and reverse cadences

Engineering Contradiction:

Improveconversation naturalnessVSAvoidcadence distinction accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system applies local quality by detecting the position of the moniker within the utterance structure. It analyzes whether the moniker appears at the beginning (indicating forward cadence with explicit invocation) or follows a statement (indicating reverse cadence), thereby accurately distinguishing between the two cadence types and providing appropriate responses.

Inventive Principle:

Principle #3Local quality

3Quantity of substance

If the system processes all conversations without selection, then it can capture all potential questions, but it cannot identify which topic the user wants answered

Engineering Contradiction:

Improveconversation context capturedVSAvoiddesired topic identification

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The system uses the moniker as an intermediary element that bridges the captured conversation context and the desired topic identification. When the moniker is detected, it serves as a signal to select and answer the specific topic that follows or precedes it, enabling precise topic identification from the captured conversation context.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11704533B2Always listening and active voice assistant and vehicle operation

Publication Date: 2023.07.18 FORD GLOBAL TECH LLC

AI summary

A vehicle includes a controller configured to select one of a group of topics for generating an answer to a question embedded within the group based on an operating parameter of the vehicle and a syntax of a phrase. The selection is responsive to input originating from utterances including a preceding topic and a following topic having a moniker therebetween that is associated with only one of the topics through the syntax. The vehicle may operate an interface to output the answer.