Handwriting Evaluation Using Time-Series Pen Dynamics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing content evaluation systems fail to assess factors related to the creation and execution of handwritten content, such as learning motivation and artistic style, beyond the finished product.
Innovation Solution
A content evaluation system that utilizes an electronic pen to capture writing operations, generating data which is analyzed to calculate time-series feature amounts, integrating these to evaluate characteristics like learning motivation and artistic style through neural networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If content evaluation focuses on scoring completed answers, then evaluation simplicity is improved, but evaluation comprehensiveness deteriorates
Solution Approach 1:
The evaluation process is segmented into multiple stages: data collection during writing, feature extraction from writing dynamics, integration of temporal features, and comprehensive evaluation. This segmentation allows the system to capture both the simplicity of final scoring and the comprehensiveness of process analysis by breaking down the evaluation into manageable components that can be processed sequentially.
Solution Approach 2:
The system performs preliminary data collection and feature extraction during the writing process itself, before final evaluation. By capturing writing dynamics, pressure variations, and temporal patterns in advance, the system prepares comprehensive evaluation data that enables both simple scoring and detailed process analysis without requiring additional data collection steps.
2Loss of time
If only finished product is evaluated, then evaluation time is reduced, but learning motivation assessment is lost
Solution Approach 1:
The evaluation system operates continuously during the writing process rather than only after completion. Data collection, feature extraction, and preliminary analysis occur throughout the writing duration, enabling the system to assess learning motivation and effort in real-time while the student is actively engaged in the task, thus capturing process information without requiring separate post-completion analysis.
Solution Approach 2:
The system performs preliminary analysis of writing dynamics and temporal patterns during the writing process itself. By extracting features such as writing speed variations, pressure changes, and pauses in advance, the system prepares motivation assessment data before the writing concludes, enabling comprehensive evaluation without extending the total time required after completion.
3Loss of information
If writing operation data is collected and analyzed, then evaluation comprehensiveness is improved, but system complexity increases
Solution Approach 1:
The system extracts and isolates specific meaningful features from the complex writing operation data, such as temporal patterns, pressure variations, and writing dynamics. By separating and analyzing only the relevant features rather than processing all raw data, the system reduces computational complexity while maintaining comprehensive evaluation capability.
Solution Approach 2:
The system transforms raw writing operation data into standardized feature parameters through normalization and feature extraction processes. By converting complex multi-dimensional writing data into a set of standardized temporal and spatial parameters, the system simplifies subsequent analysis while preserving comprehensive evaluation information.
Data Source
AI summary
Provided is a content evaluation system including an electronic pen, a data generation section that generates content data from writing operations performed by the electronic pen, a data acquisition section that acquires the content data, a first calculation section that calculates, from the acquired content data, a plurality of kinds of time-series feature amounts indicating a temporal change in a plurality of kinds of feature amounts related to a creation process of the handwritten content, a second calculation section that calculates an integrated feature amount related to the creation process of the handwritten content by using two or more kinds of time-series feature amounts from among the plurality of kinds of time-series feature amounts, and a content evaluation section that evaluates the handwritten content in reference to the integrated feature amount and outputs evaluation result information indicating the evaluation result of the handwritten content.