Driver Assistance Re-Recommendation Using Adaptive Pacing Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems fail to effectively re-recommend the use of functions refused by drivers, lacking methods to encourage the use of unutilized driver assistance systems.
Innovation Solution
A use recommendation apparatus and vehicle system that acquires sensor, traffic, and non-traffic data to generate a degree of necessity for using a driver assistance system, selects a pacing model, and outputs tailored recommendation sentences to encourage the use of the system based on driver-specific data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If driver assistance systems provide recommendations via HMI, then drivers receive useful information, but drivers may refuse to use the recommended functions and the system lacks capability to re-recommend
Solution Approach 1:
The system monitors driver responses to recommendations (acceptance or refusal) and uses this feedback to determine subsequent actions. When a driver refuses a recommendation, the system evaluates whether to re-recommend based on changing driving conditions, creating a closed-loop feedback mechanism that enables adaptive re-recommendation without requiring complex system restructuring
Solution Approach 2:
The recommendation system dynamically adjusts its behavior based on real-time driving conditions and driver responses. The system can transition between different recommendation strategies (initial recommendation, re-recommendation, or cessation) based on the degree of necessity calculated from current sensor data, traffic data, and non-traffic data, making the system adaptable without increasing structural complexity
2Productivity
If the system provides personalized recommendations based on driver data, then recommendation effectiveness improves, but data processing requirements and system complexity increase
Solution Approach 1:
The system segments data processing into distinct categories: sensor data from vehicle sensors, traffic data from external sources, and non-traffic data from user terminals. Each data type is processed independently to calculate the degree of necessity, allowing the system to handle complex multi-source data through modular segmentation rather than monolithic processing
Solution Approach 2:
The system uses multiple thresholds (first threshold and second threshold) to transform continuous data into discrete recommendation decisions. By changing parameters such as threshold values and data weighting, the system can personalize recommendations for different drivers and conditions without requiring fundamentally different processing architectures
Data Source
AI summary
A use recommendation apparatus includes acquiring circuitry and processing circuitry. The processing circuitry generates a degree of necessity of a recommendation of a use of a predetermined operation device, based on sensor data, traffic data, and non-traffic data acquired by the acquiring circuitry; selects, when the degree of necessity is greater than or equal to a first threshold and less than or equal to a second threshold, a predetermined pacing model from a plurality of pacing models, based on the sensor data, the traffic data, and the non-traffic data; acquires, from the predetermined pacing model, a first recommendation sentence having undergone predetermined pacing processing as a recommendation sentence that recommends the use of the predetermined operation device by inputting the sensor data, the traffic data, and the non-traffic data to the predetermined pacing model; and outputs the first recommendation sentence.