Motor Vehicle Function Control Using Semantic Condition Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for controlling motor vehicle functions through voice assistants are laborious and prone to errors due to the complexity of linguistic descriptions and conditions, leading to incorrect or missed executions.

Innovation Solution

A method utilizing a large language model (LLM) to convert linguistic conditions into embeddings, determining vehicle parameters, and executing functions when embeddings show a predetermined similarity, incorporating external information sources for accurate condition fulfillment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice assistant control is used to simplify function control, then ease of operation is improved, but complexity of linguistic control increases making it laborious

Engineering Contradiction:

Improveease of function controlVSAvoidcomplexity of linguistic control

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary system that translates natural language conditions into structured representations and matches them against sensor data. This intermediary layer (comprising embedding models and matching logic) mediates between the user's simple voice input and the complex control system, resolving the contradiction by hiding complexity while preserving ease of use.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical/manual control interfaces with a cognitive system based on natural language processing and semantic matching. Instead of requiring users to navigate complex menus or use precise commands, the system substitutes a more intuitive language-based interface that automatically interprets intent, reducing operational effort.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automatic control based on predetermined conditions is implemented, then productivity is improved, but reliability deteriorates due to errors in condition definition

Engineering Contradiction:

Improveautomation of function executionVSAvoidaccuracy of condition interpretation

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements feedback mechanisms where the system continuously monitors sensor data and compares it against the interpreted condition state. When the condition is met, the system executes the function and can provide feedback to the user about what triggered the execution. This feedback loop improves reliability by ensuring accurate condition detection and allowing for correction of misinterpretations.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary action by pre-processing and storing the semantic meaning of user-defined conditions in an embedded representation. Before actual condition checking occurs, the system has already prepared the condition model, including handling ambiguities and vagueness in advance. This preliminary preparation improves reliability by ensuring conditions are correctly interpreted before execution decisions are made.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If linguistic descriptions are made more flexible to capture vagueness, then adaptability is improved, but measurement precision deteriorates

Engineering Contradiction:

Improveflexibility of condition descriptionVSAvoidprecision of condition matching

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent applies parameter changes by transforming the condition description from discrete, precise parameters into continuous embedded representations that capture semantic meaning. Instead of requiring exact threshold values, the system uses vector embeddings where similarity distances provide a continuous measure of condition fulfillment, allowing flexible interpretation while maintaining measurable precision through similarity thresholds.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent transitions from one-dimensional binary condition checking (met/not met) to multi-dimensional semantic space comparison. By representing conditions and sensor states as vectors in high-dimensional embedding spaces, the system gains another dimension for measuring similarity, enabling precise matching even when linguistic descriptions are vague or flexible.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS20260088028A1Automatic Control of a Function of a Motor Vehicle

Publication Date: 2026.03.26 BAYERISCHE MOTOREN WERKE AG

AI summary

A method for controlling a function of a motor vehicle comprises steps of recording a linguistic description of conditional function execution; wherein the description includes a condition and a function of the motor vehicle to be executed when the condition is met; determining a first embedding on the basis of the condition by means of an LLM; determining parameters of a situation of the motor vehicle; determining a second embedding on the basis of the parameters; and automatically executing the function when the first embedding has a predetermined similarity to the second embedding.