Predictive In-Vehicle Interface Control for One-Tap Action Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current in-vehicle user interfaces present users with complex menus requiring multiple interactions to select interface control actions, leading to decreased usability.
Innovation Solution
A method that predicts the most likely interface control action by collecting and storing vehicle and user data, assigning likelihoods using a classifier, and presenting the most likely action for single-user interaction selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a vast amount of interface control actions are provided in the user interface, then the functionality and versatility of the system is improved, but the complexity of the menu structure increases and multiple user interactions are required
Solution Approach 1:
The system performs preliminary actions by collecting and storing vehicle data and user interaction data before the user needs to select an interface control action. This pre-processing of data enables the prediction of the user's intended action, allowing the system to present only the most likely control actions in advance, thereby reducing menu complexity and the number of interactions required.
Solution Approach 2:
The patent replaces the traditional mechanical menu navigation system with a predictive information processing system. Instead of relying on hierarchical menu structures that require multiple manual selections, the system uses machine learning classifiers to predict user intent and automatically present the most likely control actions, substituting computational prediction for manual navigation.
2Adaptability or versatility
If multiple sub-menus and options are required to select an interface control action, then comprehensive control is achieved, but the time required for selection increases
Solution Approach 1:
The system performs preliminary data collection and analysis to predict user intent before the selection process begins. By continuously collecting vehicle data and user interaction patterns, the system prepares prediction models in advance that can quickly suggest the most likely control actions, reducing the time needed for selection while maintaining comprehensive control options.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring user interactions with the interface and using this information to refine predictions. The classifier is trained on user interaction data, creating a feedback loop where past selections improve future predictions, thereby reducing selection time while preserving access to all control functions.
3Loss of information
If all interface control actions are presented to the user at once, then complete information availability is achieved, but user distraction and cognitive load increase
Solution Approach 1:
The system extracts and separates the most relevant interface control actions from the complete set of available actions. By using predictive algorithms to identify and extract only the most likely control actions based on current context and user patterns, the system presents a filtered subset that maintains information availability while reducing user distraction and cognitive load.
Solution Approach 2:
The system applies local quality by making the interface presentation context-specific rather than uniformly comprehensive. Different sets of control actions are presented based on the predicted user intent and current vehicle context, ensuring that the most relevant information is prominently displayed while less relevant options remain accessible but less prominent, thereby reducing distraction.
4Adaptability or versatility
If traditional menu navigation is used, then all control actions are accessible, but the number of user interactions required increases
Solution Approach 1:
The system performs preliminary predictions of user intent before the navigation process begins. By pre-analyzing vehicle data and user interaction patterns, the system prepares a ranked list of predicted control actions, allowing users to select their intended action with fewer interactions while ensuring all control actions remain accessible through the prediction hierarchy.
Solution Approach 2:
The patent substitutes traditional mechanical menu navigation with an intelligent prediction-based selection system. Instead of requiring users to manually traverse menu hierarchies, the system uses machine learning classifiers to predict and present the most likely control actions directly, replacing manual navigation mechanics with intelligent prediction while maintaining full accessibility to all controls.
Data Source
Figure 1~3
AI summary
The invention relates to a method for predicting an interface control action of a user (5) with an in-vehicle user interface (1), comprising the steps of collecting and storing data (10), at least vehicle data about the vehicle and its environment from at least one sensor (3, 4) of the vehicle and user data about user interactions (5) with the user interface (1) and/or different applications inside the vehicle; assigning likelihoods (11) to at least two possible interface control actions by the user based on the collected and stored data; determining (12) at least one most likely interface control action from the likelihoods (11); and making available (13) to the user (5) the at least one most likely interface control action so that it is selectable and performable with one single user interaction with the user interface (1).