Mental Load Estimation for Vehicle Information Presentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information presentation technologies face challenges in defining and measuring mental workload (WL) across a vast number of situations, as it is influenced by numerous internal and external factors, making it difficult to calculate and manage effectively.
Innovation Solution
An information presentation device that includes a storage unit for task and sub-task information, an information acquisition unit, a situation estimation unit, a load estimation unit, and a presentation information selection unit, which identifies tasks, estimates sub-tasks, calculates load demand, and selects presentation information based on the capacity level to manage mental load comprehensively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If workload correlation data is used to predict user mental workload, then information presentation can be optimized for user safety, but the system becomes difficult to maintain and manage due to the vast number of situations that must be defined
Solution Approach 1:
The patent segments the complex workload prediction system into modular components: a situation definition module that stores situation patterns and associated workload levels, a situation recognition module that identifies current situations, and a workload prediction module that outputs workload estimates. This segmentation allows each module to be independently maintained and updated without affecting the entire system, resolving the maintainability issue while preserving prediction accuracy.
Solution Approach 2:
The patent creates a universal situation definition framework that can handle diverse driving scenarios through a standardized structure. The situation definition module uses a common data format and classification system that can accommodate various situations (traffic conditions, weather, road types) without requiring separate customizations, making the system both comprehensive and easy to manage.
2Measurement precision
If all possible driving situations are defined in advance with their corresponding mental workload levels, then accurate workload prediction can be achieved, but the system becomes extremely complex and difficult to manage
Solution Approach 1:
The patent divides the situation definition into hierarchical segments: general situation categories (e.g., traffic congestion, adverse weather) and specific situation patterns within each category. This hierarchical segmentation allows accurate characterization of workload across all situations while organizing the data in a manageable structure that reduces complexity.
Solution Approach 2:
The patent implements a dynamic situation definition system where situation patterns and workload levels can be easily updated and adapted. The modular architecture allows the situation definition module to be dynamically modified to incorporate new situations or adjust workload levels based on emerging data, maintaining accuracy without permanent system reconfiguration.
3Adaptability or versatility
If the system considers a large number of internal and external factors affecting mental workload, then comprehensive workload assessment is achieved, but the calculation becomes extremely difficult
Solution Approach 1:
The patent segments the numerous workload影响因素 into distinct modules: external factors (traffic, weather, road conditions) and internal factors (driver state, task difficulty). Each factor is processed by dedicated sub-modules that output standardized workload contributions, which are then aggregated. This segmentation makes the comprehensive assessment computationally manageable.
Solution Approach 2:
The patent introduces intermediary situation patterns that mediate between raw sensor data and final workload calculations. These patterns act as intermediate representations that simplify complex factor interactions into standardized workload level assignments, reducing calculation complexity while preserving comprehensiveness.
Data Source
AI summary
An information presentation device includes: a situation estimation unit configured to identify one or more tasks based on input information that has been input and task information indicating one or more tasks indicating a situation; a load estimation unit configured to identify one or more sub-tasks based on each of the identified tasks and sub-task information indicating, for each situation of a task, one or more sub-tasks, which are work elements, having a possibility of being executed by a worker, and to acquire a load demand amount based on the identified sub-tasks and sub-task demand amount information indicating a load demand amount, which is a mental load for each sub-task; a capacity level estimation unit configured to acquire a capacity level based on the acquired load demand amount; and a presentation information selection unit configured to select information to be presented based on the capacity level.